AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY
This paper explores the transformative role of artificial intelligence (AI) in modernizing energy systems to enhance efficiency, sustainability, and resilience in response rising global energy demands and environmental concerns. A comprehensive literature review and systematic analysis highlight how...
Gespeichert in:
| Datum: | 2025 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | Englisch |
| Veröffentlicht: |
General Energy Institute of the National Academy of Sciences of Ukraine
2025
|
| Schlagworte: | |
| Online Zugang: | https://systemre.org/index.php/journal/article/view/905 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Назва журналу: | System Research in Energy |
| Завантажити файл: |  |
Institution
System Research in Energy| _version_ | 1871104414965563392 |
|---|---|
| author | Karpenko, Dmytro Yevtukhova, Tetiana Novoseltsev, Oleksandr |
| author_facet | Karpenko, Dmytro Yevtukhova, Tetiana Novoseltsev, Oleksandr |
| author_institution_txt_mv | [
{
"author": "Dmytro Karpenko",
"institution": null
},
{
"author": "Tetiana Yevtukhova",
"institution": null
},
{
"author": "Oleksandr Novoseltsev",
"institution": null
}
] |
| author_sort | Karpenko, Dmytro |
| baseUrl_str | https://systemre.org/index.php/journal/oai |
| collection | OJS |
| datestamp_date | 2026-07-18T12:57:49Z |
| description | This paper explores the transformative role of artificial intelligence (AI) in modernizing energy systems to enhance efficiency, sustainability, and resilience in response rising global energy demands and environmental concerns. A comprehensive literature review and systematic analysis highlight how AI-driven innovations impact energy generation, distribution, consumption, and system operations. Key AI techniques such as machine learning, deep learning, reinforcement learning, and optimization algorithms play pivotal roles in enhancing renewable energy integration, optimizing smart grid functionalities, improving energy storage solutions, and redefining energy market dynamics. A structured approach was presented for AI-based energy system transformation, emphasizing the importance of setting clear goals, selecting strategic directions, implementing AI applications, and establishing continuous feedback loops for verification and improvement. By segmenting the energy system into functional components, production, transportation, distribution, consumption, and system operations, an in-depth analysis of AI applications was provided relevant to each segment. Specific AI technologies, models, and algorithms suitable for various applications are identified, along with associated challenges and considerations. AI is a transformative force capable of reshaping energy systems to meet contemporary demands for sustainability and efficiency. By thoughtfully integrating AI technologies across the various components of energy systems and addressing associated challenges, the energy sector can unlock new levels of performance and innovation, contributing significantly to global sustainability objectives. |
| doi_str_mv | 10.15407/srenergy2025.03.041 |
| first_indexed | 2026-03-24T02:03:33Z |
| format | Article |
| fulltext |
Системні дослідження в енергетиці. 2025. 3(83) 41
МОДЕЛЮВАННЯ, ОПТИМІЗАЦІЯ
ТА ПРОГНОЗУВАННЯ В ЕНЕРГЕТИЦІ
_____________________________________________________________________________
ISSN 2786-7102 (Online), ISSN 2786-7633 (Print)
https://doi.org/10.15407/srenergy2025.03.041
UDC 004.8; 620.9; 621.3
Dmytro Karpenko*, PhD (Engin.), https://orcid.org/0000-0002-8022-9782
Tetiana Yevtukhova, PhD (Engin.), Associate Professor, https://orcid.org/0000-0003-4778-2479
Oleksandr Novoseltsev, Dr. Sci. (Engin.), Senior Research, https://orcid.org/0000-0001-9272-6789
General Energy Institute of NAS of Ukraine, 172, Antonovycha St., Kyiv, 03150, Ukraine
*Corresponding author: dmytro.qua@gmail.com
_______________________________________________________________________________________
AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY
SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY
Abstract: This paper explores the transformative role of artificial intelligence (AI) in modernizing energy
systems to enhance efficiency, sustainability, and resilience in response rising global energy demands and
environmental concerns. A comprehensive literature review and systematic analysis highlight how AI-
driven innovations impact energy generation, distribution, consumption, and system operations. Key AI
techniques such as machine learning, deep learning, reinforcement learning, and optimization algorithms
play pivotal roles in enhancing renewable energy integration, optimizing smart grid functionalities,
improving energy storage solutions, and redefining energy market dynamics. A structured approach was
presented for AI-based energy system transformation, emphasizing the importance of setting clear goals,
selecting strategic directions, implementing AI applications, and establishing continuous feedback loops
for verification and improvement. By segmenting the energy system into functional components, production,
transportation, distribution, consumption, and system operations, an in-depth analysis of AI applications
was provided relevant to each segment. Specific AI technologies, models, and algorithms suitable for
various applications are identified, along with associated challenges and considerations. AI is a
transformative force capable of reshaping energy systems to meet contemporary demands for sustainability
and efficiency. By thoughtfully integrating AI technologies across the various components of energy systems
and addressing associated challenges, the energy sector can unlock new levels of performance and
innovation, contributing significantly to global sustainability objectives.
Keywords: energy system, energy security, energy transformation, energy market, energy services,
artificial intelligence.
1. Introduction
The energy sector is undergoing a substantial transformation driven by global efforts to achieve
sustainability, efficiency, resilience, and equity. Artificial Intelligence (AI) is playing a crucial role in enabling
these transformative processes across various segments of the energy industry. AI's role in the modernization
of energy systems encompasses several key areas: optimizing renewable energy integration, enhancing smart
grid functionalities, improving energy storage solutions, and redefining energy market dynamics.
The analytical report [1] provides a comprehensive examination of AI applications in Ukraine’s energy
sector, emphasizing its transformative potential for sustainability and efficiency. These insights underscore the
critical need for an integrated AI-based approach to modernize energy systems for transforming Ukraine’s
energy sector in the context of post-conflict reconstruction. It is underscored in [2] that transforming Ukraine’s
energy systems via energy management systems (EMS) is vital for sustainability and efficiency. This
emphasizes the critical role of AI-driven EMS in fostering resilient, sustainable energy systems in Ukraine.
https://orcid.org/0000-0002-8022-9782
https://orcid.org/0000-0003-4778-2479
https://orcid.org/0000-0001-9272-6789
mailto:dmytro.qua@gmail.com
Системні дослідження в енергетиці. 2025. 3(83) 42
One critical area of transformation is the integration of renewable energy sources into the existing power
systems. AI has shown significant potential in addressing challenges such as variability, unpredictability, and
grid integration associated with renewables. Forecasting renewable energy generation with AI, for instance,
helps in optimizing hybrid systems that comprise a mix of renewable energy sources and other technologies,
improving the overall efficiency and reliability of the energy grid [3−5]. AI's predictive capabilities in this
domain are further emphasized in studies focusing on demand forecasting and real-time energy management,
illustrating the importance of integrated data analytics and predictive modeling [6, 7].
The development of smart grids is another transformative direction facilitated by AI. AI technologies
enable real-time monitoring, decentralized control, and provide advanced functionalities such as fault
detection, load balancing, and predictive maintenance. These capabilities contribute to making energy systems
more reliable and adaptable to disruptions [8−10]. By using techniques such as behavior trees, AI can introduce
innovative control strategies to enhance the adaptability and efficiency of smart grid systems [11] and can
enhance the efficiency of renewable energy systems by optimizing energy storage through predictive charge-
discharge cycle management, improving battery performance, and addressing challenges related to storage
capacity and cost-effectiveness in the context of Ukraine's increasing adoption of RES technologies, e.g for
heat supply [12].
In terms of energy market optimization, AI has revolutionized pricing dynamics and demand-response
systems. With AI-powered tools, dynamic pricing models are more accurately tailored to supply and demand
fluctuations, leading to reduced price volatility and enhanced market transparency. This fosters an environment
where smaller players and households can engage in energy trading, thus contributing to a more decentralized
and democratized energy market [13, 14]. Moreover, AI facilitates the integration of intermittent renewable
energy sources, supporting their economic viability and influence on the cost structure of energy production
[15]. AI also plays a pivotal role in enhancing energy efficiency by optimizing operations in generation,
transmission, and distribution. AI and IoT-enabled smart infrastructures, such as buildings, advance energy
efficiency further by real-time adjustments based on usage patterns [16].
Environmental sustainability is significantly impacted by AI-driven initiatives, which prioritize low-
emission and renewable sources, consequently reducing carbon footprints. AI aids in the assessment and
optimization of waste management systems, and predictive analytics for waste heat recovery, particularly in
district heating systems [17−19]. AI's integration into the energy market brings about substantial regulatory
and governance challenges and opportunities. AI enables sophisticated modeling of policy effects, aiding
regulators in informed decision-making [20].
AI's transformative capabilities offer substantial benefits across various facets of the energy sector, from
technological advancements in grid management to economic optimization of energy markets. The integration
of AI within energy systems not only leads to operational improvements but also supports the global transition
towards more sustainable energy solutions, aligning with strategic objectives outlined for future developments.
The aim of this paper is to develop a holistic approach to enhancing the transformative role of artificial
intelligence in modernizing energy systems by exploring models and algorithms that facilitate this transition.
To achieve the task, the following objectives were set:
- conduct a review of the existing literature to identify the state-of-the-art advancements and gaps in the
application of AI for energy systems transformation;
- delineate the key stages in the transformation of energy systems, highlighting how AI technologies
enable and enhance each stage;
- segment the energy system into functional components and provide an in-depth analysis of AI-based
applications relevant to each segment and propose a conceptual framework or roadmap for the integration of
AI-driven approaches across energy systems.
According to the defined objectives, the research methodology is structured into four sequential stages,
as illustrated in Fig. 1. This systematic approach ensures a comprehensive exploration of the ways and means
to transform energy systems using AI. Each stage contributes uniquely to achieving the study’s goals by
Системні дослідження в енергетиці. 2025. 3(83) 43
addressing key aspects such as literature analysis, identification of transformation phases, AI applications, and
the development of a conceptual framework.
The proposed research methodology systematically addresses the objectives of the study. Starting with
a thorough literature review to identify current advancements and gaps, the methodology delineates the
transformation stages of energy systems with a focus on AI integration. It further explores AI methods and
applications across system components and concludes with the development of a conceptual framework to
ensure scalability and sustainability. This structured approach provides valuable insights and practical
guidelines for advancing energy system transformations powered by AI.
Figure 1. Methodology of research
2. Methods and materials
Literature review. The literature on transforming energy systems using AI reflects a burgeoning field
that aims to revolutionize how energy is generated, distributed, and consumed. The convergence of AI with
energy systems offers innovative solutions but also poses complex challenges. This review synthesizes insights
across several studies to delineate the core developmental trends, applications, challenges, and future directions
associated with AI in energy transformation.
Advancements in AI applications have led to significant improvements in various domains of the energy
sector. The integration of AI into energy systems has facilitated automation and optimization of power grids.
For instance, AI algorithms have been applied to automate power grid management, perform multidimensional
data analysis, and optimize decision-making processes. Machine learning methods, metaheuristic algorithms,
and intelligent fuzzy inference systems enhance operations such as cybersecurity, smart grid management,
energy saving, power loss minimization, fault diagnosis, and renewable energy integration, as highlighted in
[21]. In distributed smart grids, AI techniques support applications including distributed energy management,
generation forecasting, grid health monitoring, fault detection, and home energy management. The integration
of renewable energy sources and energy storage systems is optimized through AI, enhancing the reliability and
efficiency of the future power system, as discussed in [22].
The digital transformation of microgrids through AI technologies like distributed energy resource
management systems, the Internet of Things (IoT), big data analytics, blockchain, and digital twins improves
performance, efficiency, and resilience. AI enables advanced control and optimization strategies for microgrid
operations [23, 24]. In the domain of electric vehicles, the integration of AI into energy management systems
has led to advancements in energy management optimization, route planning, energy demand forecasting, and
real-time adaptation to driving conditions. This enhances vehicle performance, energy efficiency, and range,
as analyzed in [25]. Expanding the scope to critical infrastructure, AI has been instrumental in optimizing
energy systems within railway transport. An innovative model of deep mutual integration of the architecture
of an intelligent computer environment for managing objects in the power supply system of railway transport
has been proposed in [26]. By integrating AI, the management systems of power supply facilities become more
flexible and adaptive to changes in load and working conditions.
Системні дослідження в енергетиці. 2025. 3(83) 44
Despite these advancements, several gaps and challenges hinder the full potential of AI in energy
systems transformation. The incorporation of AI into existing energy infrastructures faces technical
complexities, interoperability issues, and a lack of standardization, making implementation difficult [27].
Increased reliance on digital technologies introduces vulnerabilities to cyberattacks. AI systems themselves
can be targets of attacks or may inadvertently introduce security loopholes [28, 29]. Policy and regulatory
barriers, such as inadequate policies, regulations, and institutional hindrances, impede the integration of AI
into the energy sector. There is a need for supportive regulatory frameworks that facilitate innovation while
ensuring security and privacy. Additionally, the vast amounts of data required for AI applications raise
concerns about data privacy and ethical use. Strategies for secure data handling and compliance with privacy
laws are essential.
The transformation of energy systems involves several key stages where AI technologies play a crucial
role. Digitalization of energy systems is foundational for integrating AI technologies [30, 31]. Power grid
enterprises are adopting digital transformation management modes based on AI algorithms to improve
management and service levels. For instance, enterprises employing AI-based digital transformation have
shown significant improvements in informatization project management and operation and maintenance
service management indices [32]. In intelligent buildings, AI enhances robustness, reliability, automation, and
flexibility by applying smart controls, fault detection, diagnosis, and optimization techniques, while AI-driven
energy management systems enable better demand response and load management. Moreover, AI can
significantly reduce excess energy generation by accurately predicting energy consumption patterns [33]. By
analyzing data and forecasting energy demand, AI helps optimize energy system operations, ensuring efficient
use of resources and avoiding overproduction. Research indicates that methods like deep learning significantly
enhance the accuracy of electricity demand predictions, a cornerstone for the reliable operation of future power
systems [34]. This aspect is particularly crucial in contexts like Ukraine's recovery, where efficient resource
utilization and reduction of greenhouse gas emissions are paramount [35].
The transition to smart grids represents a prominent area where AI is making a substantial impact. Smart
grids incorporate high levels of renewable energy, which introduces variability due to the intermittent nature
of resources like solar and wind. AI-powered methods, such as machine learning and data-driven approaches,
help manage and predict the behaviors of such systems, improving their efficiency despite these variabilities.
These predictive analyses are propelled by the integration of digital technologies such as the Internet of Things
(IoT), blockchain, and AI itself, collectively referred to as the Internet of Energy [36]. AI is instrumental in
developing smart grids and transitioning towards the Energy Internet, which envisions a decentralized,
efficient, and sustainable energy system. Smart grids utilize real-time data and intelligent algorithms to
optimize operations, enhance energy distribution, and integrate prosumers into the energy market [37−39].
AI enables the transformation of energy markets by optimizing trading, forecasting prices, and
facilitating new market models like local electricity markets. AI-based computational models support the
sustainable transformation of energy markets, improving operations and accelerating the transition to cleaner
energy sources [40, 41]. A significant aspect of the energy sector's transformation involves the integration of
AI, which is facilitating the flow of information and enabling more efficient operations. The use of AI in the
power sector is evidenced by a survey that covered hundreds of companies globally, highlighting a significant
level of adoption and showcasing how these technologies are pivotal in supporting energy supply chains and
digital solutions [42].
Short-term load forecasting is another domain where AI, particularly machine learning, plays a crucial
role in smart grids. Accurate forecasting of load, photovoltaic production, and electricity sales is critical for
grid management and demand-side optimization. Advanced AI models, including LSTMs and ensemble
methods, have been developed to enhance prediction accuracy across these domains [43, 44]. Supporting these
models, Big Data technologies enable the processing of vast real-time data streams, ensuring that forecasts are
based on the most current and comprehensive information available [45]. Furthermore, AI-driven optimization
techniques, such as genetic algorithms for solar panel configuration, contribute to maximizing renewable
energy output, thereby promoting sustainability [46].
Системні дослідження в енергетиці. 2025. 3(83) 45
The integration of AI into energy systems is emerging as a transformative force, poised to reshape the
way energy is generated, distributed, and consumed. This comprehensive literature review reveals that AI
offers numerous opportunities to enhance efficiency, reliability, and sustainability within energy systems, yet
it also brings about complex challenges that need addressing. By deploying AI-driven digital transformation
strategies, power grid enterprises are capable of elevating their operational efficacy significantly. This
transformation is evident in the transition towards smart grids, where AI empowers intelligent networks to
self-optimize and better assimilate renewable sources, thereby fostering improved grid reliability and security.
Moreover, methodological challenges in managing the complex and often stochastic nature of energy systems,
particularly with regards to renewable energy sources, must be mitigated to fully harness the benefits AI can
provide.
Key stages of AI-based energy system transformation. The necessity for transforming energy systems
stems from the pressing challenges of climate change, resource scarcity, and the increasing complexity of
energy demand and supply dynamics. Traditional energy systems, reliant on fossil fuels and centralized
structures, are no longer sustainable or efficient in meeting the needs of a rapidly evolving world. The
integration of renewable energy sources, electrification of sectors, and decarbonization goals require
innovative approaches that go beyond conventional methods. AI provides a pivotal solution by enabling
predictive analytics, real-time decision-making, and system optimization. These advancements address critical
issues such as reducing greenhouse gas emissions, enhancing energy access and equity, and improving the
resilience of energy infrastructure against disruptions.
The fig. 2 outlines key stages in the AI-based energy system transformation cycle, offering a structured
approach to transforming energy systems using AI technologies.
Figure 2. Key stages of a closed-loop energy system transformation based on artificial intelligence
Formulating goals of energy system transformation stage in the transformation cycle involves defining
clear and actionable goals for energy system transformation. Leveraging AI's capabilities in data analysis,
predictive modeling, and optimization, energy systems can identify precise objectives. For instance, goals
might include achieving net-zero emissions, enhancing grid reliability, or improving energy efficiency. Recent
advancements in AI-driven forecasting and scenario analysis provide actionable insights, enabling energy
planners to set realistic and impactful objectives.
Системні дослідження в енергетиці. 2025. 3(83) 46
Selection of transformation directions stage prioritizes areas within energy systems where AI
interventions will yield the most significant impact. AI algorithms can analyze historical data and predict future
trends to identify transformation opportunities in energy production, distribution, or consumption. For
example, AI can guide investments in renewable energy integration or energy storage systems by evaluating
their potential impact on grid stability and cost efficiency.
Verification ensures that the application of AI aligns with the predefined objectives. This involves using
AI tools to continuously monitor progress, identify deviations, and refine strategies. For example, machine
learning models can track energy efficiency improvements over time, providing feedback on whether the
implemented measures meet the intended goals.
Periodic reviews are essential to evaluate the effectiveness of AI applications in addressing energy
system challenges. By integrating feedback loops, energy planners can reassess the relevance of AI-driven
initiatives. This iterative process ensures adaptability to changing circumstances, such as evolving energy
demands or technological advancements.
AI methods, such as deep learning, reinforcement learning, and optimization algorithms, play a pivotal
role in energy system transformation. Applications include load forecasting, predictive maintenance, and smart
grid management. For example, reinforcement learning has been successfully applied to optimize energy
dispatch in microgrids, while deep learning models enhance demand-side management by predicting
consumption patterns.
Identifying and addressing challenges is critical to the success of AI-based energy transformations.
Common barriers include data scarcity, high computational costs, and resistance to change among
stakeholders. AI can also help overcome these barriers by automating data collection, optimizing resource
allocation, and demonstrating clear benefits through pilot projects.
Assessment of future directions involves forecasting emerging trends and identifying opportunities for
AI integration in energy systems. Recent advancements, such as AI-enabled energy trading platforms and
autonomous grid operation technologies, highlight the potential for transformative innovation. By synthesizing
insights from existing literature, future research can focus on scaling these technologies and addressing
implementation challenges.
AI tools facilitate accurate measurement and verification of energy system performance metrics, such
as energy savings, emission reductions, and system reliability. Techniques like digital twins and real-time
analytics enable energy operators to validate the impact of AI-driven interventions and ensure continuous
improvement.
Corrective measures are essential to address any gaps or inefficiencies identified during the
transformation process. AI systems can dynamically adjust operational strategies based on real-time data,
ensuring optimal performance. For instance, adaptive control systems can reconfigure energy flows to mitigate
bottlenecks or balance supply and demand.
The long-term success of AI-based energy transformations depends on maintaining system resilience
and adaptability. AI can support this by enabling predictive maintenance, optimizing resource allocation, and
fostering collaboration across stakeholders. By continuously evolving with advancements in technology and
shifting energy needs, AI ensures the sustainability of transformation efforts.
The final stage synthesizes insights from the entire transformation cycle to establish a sustainability
paradigm. AI plays a central role in fostering sustainable practices, such as maximizing renewable energy
utilization, minimizing waste, and optimizing lifecycle costs. By integrating sustainability considerations at
every stage, the transformation cycle ensures that energy systems contribute to a resilient and low-carbon
future.
The schema of an AI-based energy system transformation cycle provides a comprehensive framework
for addressing the complex challenges of energy transition. By systematically applying AI methods and models
across each stage, energy systems can achieve transformative goals that align with sustainability objectives.
This closed-loop approach ensures continuous improvement and adaptability, paving the way for resilient and
future-ready energy systems.
Системні дослідження в енергетиці. 2025. 3(83) 47
AI-based methods, models, and applications in energy systems. The challenges in leveraging AI for
energy transformation include issues such as data quality and availability, ethical and regulatory concerns,
security and privacy, scalability, and interoperability in legacy systems. Meanwhile, emerging opportunities
focus on adaptability in forecasting, optimization of energy markets, hybrid algorithm development, fault
detection, and operations in smart grids and microgrids, alongside improved interactions with energy storage
systems and enhanced cybersecurity measures. This conceptual framework underscores the potential and
complexity of using AI to address the evolving demands of modern energy systems.
By segmenting the energy system into distinct groups, the unique requirements, inefficiencies, and
opportunities inherent to each component can be identified. Segmentation analysis is provided in Fig. 3 and
highlights the interconnected nature of these components, emphasizing the need for AI-driven approaches that
ensure interoperability and scalability across the entire energy system [47]. It enables the identification of
critical data flow pathways and control mechanisms, which are essential for designing integrated AI solutions
that align with the system's long-term sustainability goals. Additionally, this analytical framework serves as a
foundation for proposing conceptual roadmaps and frameworks, as the segmentation aligns with the
hierarchical and functional structure of energy systems.
Figure 3. Functional segmentation of a local energy system (based on [47])
The “Energy production” group is responsible for generating energy, encompassing both thermal and
electric forms. This group includes several key components. The electricity producer supplies electrical energy
directly to the electricity distribution network, ensuring the availability of power for downstream systems.
Combined Heat and Power (CHP) energy producers play a dual role, generating both electricity and thermal
energy, thereby contributing to the efficiency of the overall energy system. Renewable energy sources (RES)
producers provide electricity derived from sustainable resources, such as solar and wind, thus promoting the
decarbonization of energy systems. Additionally, thermal energy producers generate heat for various
applications, including residential heating and industrial processes, further diversifying the energy portfolio.
The “Energy transportation and distribution” group serves as the intermediary between energy producers
and end-users, focusing on the efficient and reliable delivery of energy. This group includes the electricity
distribution network, which facilitates the transfer of electricity from production units to consumers, ensuring
grid stability. Similarly, the thermal energy distribution network ensures the delivery of heat to consumers for
residential, commercial, and industrial use. Energy storage systems are integral to this group, acting as buffers
to store excess energy during periods of low demand and release it during peak consumption. These systems
enhance the flexibility and resilience of the energy system by mitigating supply-demand imbalances.
Системні дослідження в енергетиці. 2025. 3(83) 48
The “Energy consumption” Group comprises the end-users of the energy system, categorized based on
their level of energy management capability. Consumers equipped EMS actively optimize their energy usage
and, in some cases, interact with other system components, such as storage or demand response programs. In
contrast, consumers without EMS exhibit traditional consumption patterns with limited flexibility in managing
their energy use.
The “System operations” group plays a critical role in coordinating and managing the overall energy
system, ensuring seamless integration of production, distribution, and consumption components. The system
operator oversees the balance and stability of energy flows, maintaining operational reliability. The energy
storage operator manages the charging and discharging of storage systems to optimize their utilization and
enhance system flexibility. The market operator facilitates economic transactions within the energy system,
ensuring the viability of energy trade and market operations. Finally, the demand response coordinator interacts
with consumers to adjust their energy usage patterns dynamically in response to real-time supply conditions,
thereby contributing to system efficiency and demand-side flexibility.
The diagram in Fig. 4 delineates the energy system into functional components where AI can
significantly enhance transformation. In energy production, AI improves efficiency through renewable
forecasting and maintenance strategies. For energy transportation and distribution, AI optimizes grid
management, storage operations, and smart grids. On the consumption side, it enables demand-side
management and efficiency through forecasting and personalized recommendations. System operations benefit
from AI in grid balancing, market optimization, and cybersecurity. The framework underscores the potential
of AI to enhance scalability, interoperability, and sustainability, offering a roadmap for integrating AI into
energy systems transformation.
Figure 4. AI applications in energy system transformation
The energy sector is inherently complex, involving a multitude of interconnected components that range
from production to consumption and system operations. Without a structured segmentation of the energy
system, it becomes challenging to identify and address the specific areas where AI can be most effectively
applied. By segmenting the energy system into functional components, such as production, transportation and
distribution, consumption, and system operations, we create a clear framework that facilitates targeted analysis
and application of AI technologies.
Системні дослідження в енергетиці. 2025. 3(83) 49
In energy production, AI enhances the efficiency of both renewable and traditional sources. For instance,
in solar and wind farms, it predicts generation patterns based on historical weather data, enabling better
maintenance scheduling and reducing reliance on backup fossil fuels. This ensures a more reliable integration
of renewable energy into the grid. In traditional power plants, such as those using coal, AI forecasts energy
demand using consumption and weather data, optimizing fuel usage and cutting operational costs while
maintaining stable output. Additionally, AI monitors equipment health in renewable installations, predicting
failures before they occur and extending the lifespan of critical components like turbine blades.
AI plays a crucial role in managing the transportation and distribution of energy. It forecasts load
distribution across transmission lines, anticipating peak demand to prevent overloads and enhances grid
stability. In distribution networks, AI quickly detects faults in power lines, significantly reducing downtime
and improving service reliability for customers. It also optimizes the management of battery storage systems
connected to the grid, extending battery life and supporting renewable energy integration during off-peak
hours. Furthermore, AI identifies energy losses due to leakage in distribution lines, enabling targeted repairs
that improve overall efficiency and lower operational costs.
On the consumption side, AI helps end-users reduce energy usage and costs across residential,
commercial, and industrial settings. Energy apps leverage AI to analyze consumption patterns and provide
personalized recommendations, such as adjusting thermostat settings, to help users reduce energy usage. In
factories, AI monitors machine schedules in real-time, detecting inefficiencies and minimizing waste, which
enhances operational competitiveness.
AI ensures the overall stability, security, and compliance of the energy system. It predicts system-wide
load across large networks, improving resource allocation and reducing the costs of integrating renewable
energy. In substations, AI localizes faults quickly, minimizing disruptions during peak usage. AI also enhances
cybersecurity by detecting anomalies, such as cyber threats, in real-time, preventing potential outages and
maintaining trust in the system. Additionally, it automates compliance reporting for power plants, ensuring
adherence to environmental regulations while reducing administrative workloads.
This analysis presented in Table 1 allows to delve deeply into each segment and uncover the unique
challenges and opportunities present. By identifying these specific needs and potential solutions within each
group, AI applications can be proposed that are not only innovative but also highly relevant and impactful.
Table 1. AI applications, technologies, challenges and benefits in energy system transformation
AI Application AI technologies, models, and
algorithms
Challenges and considerations Expected benefits and impact
Energy production
Renewable energy
generation
forecasting
Long short-term memory
(LSTM) networks, recurrent
neural networks (RNN), time
series analysis, gradient
boosting machines,
convolutional neural networks
(CNN)
Weather data accuracy, complex
patterns in data, computational
intensity, integration into
operational planning
Improved integration of
renewables, enhanced
scheduling and dispatching,
reduced reliance on fossil fuels
Predictive
maintenance of
production
equipment
Machine learning algorithms,
support vector machines
(SVM), random forests,
anomaly detection algorithms,
autoencoders, multilayer
perceptron (MLP)
Data quality and availability,
sensor integration for real-time
monitoring, need for explainable
AI for regulatory compliance
Reduced downtime and
maintenance costs, extended
equipment lifespan increased
reliability of energy supply
Optimization of
energy production
schedules
Reinforcement learning (RL),
genetic algorithms,
optimization algorithms,
swarm intelligence
High computational requirements,
real-time optimization needs,
balancing multiple objectives,
regulatory and market constraints
Increased operational efficiency,
cost savings, lower emissions,
enhanced response to demand
fluctuations
Системні дослідження в енергетиці. 2025. 3(83) 50
Table 1 continued
AI Application AI technologies, models, and
algorithms
Challenges and considerations Expected benefits and impact
Fault detection and
diagnosis in
production
equipment
CNN, SVM, decision trees,
clustering algorithms,
computer vision (CV)
Need for large labeled datasets,
real-time processing, integration
with monitoring systems, data
privacy concerns
Early fault detection, prevention
of failures, improved safety,
reduced repair costs
Emission reduction
strategies
RL for adaptive control,
support vector regression
(SVR)
Regulatory compliance, accurate
emission measurements, trade-
offs between efficiency and
emissions, adoption barriers
Lower greenhouse gas
emissions, regulatory
compliance, improved public
health outcomes
Energy transportation and distribution
Grid load forecasting
and management
LSTM networks, time series
forecasting models; SVR,
ARIMA models
Accurate demand prediction,
integration of distributed
resources, data latency, scalability
for large grids
Improved grid stability, efficient
load balancing, reduced
operational costs, better
renewable integration
Fault detection and
localization in
distribution networks
Anomaly detection algorithms,
SVM, decision trees, clustering
algorithms, CV
Limited data from sparse sensors,
real-time processing needs, sensor
deployment costs, system
interoperability
Faster fault resolution, reduced
downtime, improved reliability,
customer satisfaction
Optimization of
energy storage
operations
RL, particle swarm
optimization, predictive
modeling, deep learning (DL)
Battery degradation,
charge/discharge balancing,
integration with grid and market
signals, storage technology
constraints
Enhanced storage utilization,
improved grid flexibility, cost
saving, increased renewable
integration
Energy loss detection
and reduction
SVM, anomaly detection,
pattern recognition algorithms,
CV
Measuring losses accurately,
complex network topologies, data
quality issues, real-time analytics
needs
Reduction in losses, cost
savings, improved distribution
efficiency
Demand response
management
RL, agent-based modeling Consumer participation rates,
privacy concerns, communication
infrastructure, regulatory
compliance
Better demand-side flexibility,
reduced need for peaking plants,
improved grid stability, cost
savings
Smartgrids and
microgrids
optimization
RL, multi-agent systems,
predictive analytics,
optimization models
Coordinating multiple DERs, data
interoperability, AI model
scalability, regulatory and market
barriers
Improved DER utilization,
enhanced grid resilience, lower
operational costs, support
renewable targets
Energy consumption
Energy usage
forecasting
Time series analysis, LSTM
networks, ARIMA models,
SVR, CV, DL
Accurate consumption modeling,
external factors (weather,
occupancy), scalability, data
privacy concerns
Better energy planning, cost
savings with optimized tariffs,
market participation, sustainable
consumption
Demand response
participation
optimization
RL, game theory models,
optimization algorithms,
transformers
Incentivizing participation,
communication infrastructure,
real-time data processing,
regulatory constraints
Improved grid flexibility,
financial incentives, enhanced
supply-demand balance, peak
load reduction
Automation of
industrial processes
for energy efficiency
CV, RL, predictive
maintenance algorithms,
optimization algorithms
High initial costs, legacy system
integration, skilled workforce
needs, safety and compliance
regulations
Increased efficiency, significant
energy savings, reduced
operational costs, enhanced
competitiveness
Personalized energy
consumption
recommendations
Data mining, transformers Data privacy and protection, need
for quality user data, ethical
considerations, user engagement
strategies
Increased user engagement,
energy savings, enhanced
customer satisfaction, support
for demand management
System operation and
grid balancing
RL, predictive modeling,
transformers
Real-time data processing, data
source integration, cybersecurity
risks, large-scale system modeling
complexity
Enhanced grid stability, reduced
blackout risks, optimal resource
use, better renewable energy
integration
Системні дослідження в енергетиці. 2025. 3(83) 51
Table 1 continued
AI Application AI technologies, models, and
algorithms
Challenges and considerations Expected benefits and impact
System operations
Market operation and
trading optimization
Algorithmic trading systems,
LSTM, DL, agent-based
modeling, game theory
Market volatility, regulatory
constraints, high-frequency data
needs, ethical considerations in
trading
Increased market efficiency,
optimized trading strategies,
better price discovery, enhanced
market liquidity
Cybersecurity Anomaly detection systems,
ML for intrusion detection,
threat intelligence, blockchain
technology
Evolving cyber threats, legacy
system integration, security vs.
efficiency balance, regulatory
compliance
Enhanced cyber protection,
safeguarding infrastructure,
maintaining trust, compliance
with security regulations
Regulatory
compliance and
reporting automation
Transformers, data validation
ML models
Keeping up with regulations,
ensuring data accuracy, reporting
system integration, data privacy
concerns
Reduced administrative burden,
increased reporting accuracy,
timely compliance, adaptability
to changes
This analysis directly supports the objective of proposing a conceptual framework and roadmap for AI
integration. By thoroughly examining each segment and identifying how AI can enhance scalability,
interoperability, and sustainability, a solid foundation is provided upon which a cohesive and strategic plan
can be built. This roadmap is essential for guiding policymakers, industry leaders, and other stakeholders in
making informed decisions about investing in and implementing AI technologies within the energy sector. In
essence, this analysis serves as the bridge between theoretical understanding of AI's capabilities and the
practical steps needed to transform energy systems. It ensures that proposed roadmap is grounded in a thorough
understanding of the energy system's intricacies and is tailored to address the specific challenges and
opportunities within each segment.
3. Discussion
The integration of AI into energy systems represents a significant transformation in how energy is
produced, distributed, and consumed. This study highlights the multifaceted roles AI can play in enhancing
efficiency, sustainability, and resilience within the energy sector.
AI integration has profound implications. It enhances efficiency through improved energy forecasting
and optimized resource utilization, leading to reduced operational costs and better load management. In the
realm of renewable energy, AI manages the intermittent nature of sources like solar and wind power, enhancing
predictability and facilitating seamless integration into the grid. Grid reliability is bolstered by AI-driven
predictive maintenance and fault detection, which reduce downtime and improve stability. Consumers are
empowered by AI applications that enable personalized energy management and participation in demand
response programs, fostering active engagement and energy conservation. Economically, AI optimizes market
operations, improves price discovery, and has the potential to lower energy costs for consumers.
Given the ongoing war and the urgent need to recover Ukraine's energy systems, AI offers
transformative potential to improve the efficiency, reliability, and sustainability of the energy sector. The war
has caused extensive damage to generation facilities and transmission networks, with significant losses
reported by [48]. As Ukraine seeks to rebuild and modernize its energy infrastructure, particularly by
integrating renewable energy sources, AI can play a crucial role in addressing current challenges and shaping
a resilient energy future.
One of the most immediate and impactful applications of AI in Ukraine’s energy sector is forecasting
energy production and consumption, especially as the country plans to massively install renewable energy
sources like solar and wind. Accurate forecasting is essential for balancing the grid, particularly in a post-war
context where energy supply and demand can fluctuate unpredictably. Similarly, AI can predict energy demand
by processing consumption patterns, weather data, and economic indicators. This dual forecasting capability
Системні дослідження в енергетиці. 2025. 3(83) 52
enables grid operators to maintain stability across local and unified energy systems, ensuring reliable power
delivery as Ukraine transitions to a greener energy mix.
As Ukraine reconstructs its energy systems with an emphasis on decentralization and renewable
integration, AI can optimize energy distribution and consumption. Smart grid management powered by AI can
predict load distribution, manage energy storage, and implement demand response programs.
Also, the war has left Ukraine’s energy infrastructure vulnerable, with frequent disruptions due to
damaged equipment and networks. AI-based fault detection and predictive maintenance can significantly
enhance system resilience. This is critical for minimizing downtime in a recovery phase where resources are
stretched thin.
Policymakers have a critical role in creating an enabling environment for AI-driven energy
transformations. Updating regulations to accommodate AI technologies, while ensuring ethical standards and
data security, is essential. Financial incentives and subsidies can promote innovation and support infrastructure
upgrades in the energy sector. Investing in education and training programs will develop a skilled workforce
capable of driving and managing these technological advancements. While AI holds immense promise, its
implementation in Ukraine faces challenges. Data availability and quality are critical, as AI relies on large,
accurate datasets that may be disrupted by the war. Rebuilding data collection infrastructure and training
skilled professionals to develop and maintain AI systems will be essential.
Future research should focus on developing robust data management frameworks to improve data
quality and availability for AI applications. Advancing AI algorithms that are more efficient and require less
computational power will facilitate broader adoption. Creating AI-driven cybersecurity solutions is crucial to
protect energy infrastructure from emerging threats. Encouraging interdisciplinary collaboration among
technologists, energy experts, policymakers, and social scientists can lead to holistic solutions that consider
technical feasibility, regulatory compliance, and societal impact. Implementing pilot projects and case studies
will provide valuable insights into practical challenges and effective strategies for AI integration in real-world
settings.
4. Conclusions
This paper has explored the transformative potential of AI in modernizing energy systems, with a
particular emphasis on addressing Ukraine's pressing challenges of efficiency, sustainability, and resilience
amid post-war recovery and growing demands for renewable energy integration. Through a holistic approach
that encompassed a comprehensive literature review, delineation of transformation stages, functional
segmentation of energy systems, and the proposal of a conceptual framework, we have demonstrated how AI
can drive significant advancements across the energy sector tailored to Ukraine's unique context.
By delineating the key stages of AI-based energy system transformation, this study provided a structured
framework that illustrates how AI enables each phase, particularly in Ukraine's post-war context. These stages
include setting goals for resilient infrastructure reconstruction, strategically prioritizing renewable energy
integration, implementing AI-driven solutions like fault detection and load forecasting, and establishing
feedback loops for continuous improvement. This approach ensures that AI integration is purposeful and
adaptable to Ukraine's evolving energy needs, facilitating a transition from recovery to sustainability.
The functional segmentation of the energy system into production, transportation and distribution,
consumption, and system operations allowed for an in-depth analysis of AI applications relevant to each
segment. This detailed analysis culminated in the development of a conceptual framework that serves as a
roadmap for integrating AI-driven approaches across energy systems. By identifying specific AI technologies,
models, and algorithms suitable for various applications, and by acknowledging the challenges and
considerations associated with each, practical guidelines were provided for stakeholders aiming to implement
AI solutions. The expected benefits and impacts, such as improved efficiency, cost savings, enhanced
reliability, and reduced emissions, highlight the significant potential of AI to contribute to sustainable energy
objectives.
Системні дослідження в енергетиці. 2025. 3(83) 53
AI emerges as a pivotal force in reshaping Ukraine's energy systems to meet modern demands. Future
research should refine AI methodologies for post-conflict settings, improve data management, and develop
regulatory frameworks to ensure secure, equitable, and sustainable energy transformations.
The work funding
This research was supported by General Energy Institute of National Academy of Sciences of Ukraine
within the framework of scientific works (0123U100309, 0122U000177).
Acknowledgments
All figures were created by the authors unless otherwise noted.
References
1. Sukhodolia, O. (2022). Artificial Intelligence in Energy. Kyiv: National Institute for Strategic Studies (49 p.) [in
Ukrainian]. https://doi.org/10.53679/NISS-analytrep.2022.09
2. Kyrylenko, O., Denysiuk, S., & Blinov, I. (2024). Energy management: New priorities of the 21st century. POWER
ENGINEERING: Economics, Technique, Ecology, 1(75), 7–27 [in Ukrainian]. https://doi.org/10.20535/1813-
5420.1.2024.297508
3. Babiarz, B., Krawczyk, D. A., Siuta-Olcha, A., Manuel, C. D., Jaworski, A., Barnat, E., Cholewa, T., Sadowska, B.,
Bocian, M., Gnieciak, M., Werner-Juszczuk, A., Kłopotowski, M., Gawryluk D., Stachniewicz, R., Święcicki, A.,
& Rynkowski, P. (2024). Energy efficiency in buildings: Toward climate neutrality. Energies, 17(18), 4680.
https://doi.org/10.3390/en17184680
4. Tooki, O. O., & Popoola, O. M. (2024). A comprehensive review on recent advances in transactive energy system:
Concepts, models, metrics, technologies, challenges, policies and future. Renewable Energy Focus, 50, 100596.
https://doi.org/10.1016/j.ref.2024.100596
5. Hotra, O., Kulyk, M., Babak, V., Kovtun, S., Zgurovets, O., Mroczka, J., & Kisała, P. (2023). Organization of the
structure and functioning of self-sufficient distributed power generation. Energies, 17(1), 27.
https://doi.org/10.3390/en17010027
6. Stanytsina, V., Zaporozhets, A., & Artemchuk, V. (2024). Demand forecasting mathematical models for residential
electricity consumption considering ambient temperature. Studies in Systems, Decision and Control. Studies in
Systems, Decision and Control, 559 (pp. 127–145). https://doi.org/10.1007/978-3-031-66764-0_6
7. Kulyk, M., & Zgurovets, O. (2020). Modeling of power systems with wind, solar power plants and energy storage.
Studies in Systems, Decision and Control. Systems, Decision and Control in Energy I, 298 (pp. 231–245).
https://doi.org/10.1007/978-3-030-48583-2_15
8. Nagappan, B., Chaudhary, C., Doda, D. K., & Kumar, S. (2024). Review on smart grids and renewable integration:
An artificial intelligence-powered perspective. Multidisciplinary Reviews, 6, 2023ss070.
https://doi.org/10.31893/multirev.2023ss070
9. Safari, A., Daneshvar, M., & Anvari-Moghaddam, A. (2024). Energy intelligence: A systematic review of artificial
intelligence for energy management. Applied Sciences, 14(23), 11112. https://doi.org/10.3390/app142311112
10. Denysov, V., Kostenko, G., Babak, V., Shulzhenko, S., & Zaporozhets, A. (2023). Accounting the forecasting
stochasticity at the power system modes optimization. Studies in Systems, Decision and Control. Studies in Systems,
Decision and Control, 481 (pp. 43–55). https://doi.org/10.1007/978-3-031-35088-7_3
11. Perger, A. v., Gamper, P., & Witzmann, R. (2022). Behavior trees for smart grid control. IFAC-PapersOnLine,
55(9), 122–127. https://doi.org/10.1016/j.ifacol.2022.07.022
12. Derevianko, D., & Vorobel, V. (2023). Performance efficiency increase of the microgrids with energy storage
systems. POWER ENGINEERING: Economics, Technique, Ecology, 4(74), 22–28 [in Ukrainian].
https://doi.org/10.20535/1813-5420.4.2023.290885
13. Hou, H., Gan, M., Wu, X., Xie, K., Fan, Z., Xie, C., Shi, Y., & Huang, L. (2023). Real-time energy management of
low-carbon ship microgrid based on data-driven stochastic model predictive control. CSEE Journal of Power and
Energy Systems, 9(4), 1482–1492. https://doi.org/10.17775/cseejpes.2021.08950
14. Sułek, A., & Borowski, P. F. (2024). Business models on the energy market in the era of a low-emission economy.
Energies, 17(13), 3235. https://doi.org/10.3390/en17133235
15. Forootan, M. M., Larki, I., Zahedi, R., & Ahmadi, A. (2022). Machine Learning and Deep Learning in energy
systems: A review. Sustainability, 14(8), 4832. https://doi.org/10.3390/su14084832
16. Bilous, I., Biriukov, D., Karpenko, D., Eutukhova, T., Novoseltsev, O., & Voloshchuk, V. (2024). Reinforcement
learning model for energy system management to ensure energy efficiency and comfort in buildings. Energy
Engineering, 121(12), 3617–3634. https://doi.org/10.32604/ee.2024.051684
17. Derii, V., Nechaieva, T., & Leshchenko, I. (2023). Assessment of the effect of structural changes in Ukraine’s district
heating on the greenhouse gas emissions. Science and Innovation, 19(4), 57–65.
https://doi.org/10.15407/scine19.04.057
https://doi.org/10.53679/NISS-analytrep.2022.09
https://doi.org/10.20535/1813-5420.1.2024.297508
https://doi.org/10.20535/1813-5420.1.2024.297508
https://doi.org/10.3390/en17184680
https://doi.org/10.1016/j.ref.2024.100596
https://doi.org/10.3390/en17010027
https://doi.org/10.1007/978-3-031-66764-0_6
https://doi.org/10.1007/978-3-030-48583-2_15
https://doi.org/10.31893/multirev.2023ss070
https://doi.org/10.3390/app142311112
https://doi.org/10.1007/978-3-031-35088-7_3
https://doi.org/10.20535/1813-5420.4.2023.290885
https://doi.org/10.17775/cseejpes.2021.08950
https://doi.org/10.3390/en17133235
https://doi.org/10.3390/su14084832
https://doi.org/10.32604/ee.2024.051684
https://doi.org/10.15407/scine19.04.057
Системні дослідження в енергетиці. 2025. 3(83) 54
18. Derii, V., Teslenko, O., Lenchevsky, E., Denisov, V., & Maistrenko, N. (2023). Prospects and energy-economic
indicators of heat energy production through direct use of electricity from renewable sources in modern heat
generators. Studies in Systems, Decision and Control. Studies in Systems, Decision and Control, 454 (pp. 451–463).
https://doi.org/10.1007/978-3-031-22464-5_27
19. Maliarenko, O., Eutukhova, T., Ivanenko, N., Horskyi, V., & Kobernik, V. (2024). Comparison of the fuel
consumption structure and pollutant emissions for determining their reduction directions. System Research in
Energy, 2а(78), 19–20 [in Ukrainian]. https://doi.org/10.15407/srenergy2024.02a
20. Eutukhova, T., Kovalko, O., Novoseltsev, O., & Woodroof, E. (2020). Energy services: A proposed framework to
improve results. Energy Engineering, 117(3), 99–110. https://doi.org/10.32604/ee.2020.010864
21. Szczepaniuk, H., & Szczepaniuk, E. K. (2022). Applications of artificial intelligence algorithms in the energy sector.
Energies, 16(1), 347. https://doi.org/10.3390/en16010347
22. Ali, S. S., & Choi, B. J. (2020). State-of-the-art artificial intelligence techniques for distributed smart grids: A
review. Electronics, 9(6), 1030. https://doi.org/10.3390/electronics9061030
23. Irmak, E., Kabalci, E., & Kabalci, Y. (2023). Digital transformation of microgrids: A review of design, operation,
optimization, and cybersecurity. Energies, 16(12), 4590. https://doi.org/10.3390/en16124590
24. Denysiuk, S., & Hilevych, K. (2023). Optimization of the use of distributed energy resources in local electrical
power systems according to the criterion of minimum loss of electricity. POWER ENGINEERING: Economics,
Technique, Ecology, 4(74), 7–21 [in Ukrainian]. https://doi.org/10.20535/1813-5420.4.2023.290880
25. Arévalo, P., Ochoa-Correa, D., & Villa-Ávila, E. (2024). A systematic review on the integration of artificial
intelligence into energy management systems for electric vehicles: Recent advances and future perspectives. World
Electric Vehicle Journal, 15(8), 364. https://doi.org/10.3390/wevj15080364
26. Holub, H., Gorobchenko, O., Kulbovskyi, I., Goolak, S., & Haidenko, O. (2023). Development of an innovative
model for the inter-integration of the architecture of the intelligent computer environment of critical infrastructure
facilities of the railway. Technology Audit and Production Reserves, 6(2(74)), 20–27. https://doi.org/10.15587/2706-
5448.2023.291244
27. Danish, M. S. S. (2023). AI in energy: Overcoming unforeseen obstacles. AI, 4(2), 406–425.
https://doi.org/10.3390/ai4020022
28. Bellizio, F., Xu, W., Qiu, D., Ye, Y., Papadaskalopoulos, D., Cremer, J. L., & Strbac, G. (2023). Transition to
digitalized paradigms for security control and decentralized electricity market. Proceedings of the IEEE, 111(7),
744–761. https://doi.org/10.1109/jproc.2022.3161053
29. Dong, F., Zhang, S., Zhu, J., & Sun, J. (2021). The impact of the integrated development of AI and energy industry
on regional energy industry: A case of China. International Journal of Environmental Research and Public Health,
18(17), 8946. https://doi.org/10.3390/ijerph18178946
30. Li, X., & Zhang, S. (2024). Management mode and path of digital transformation of power grid enterprises based
on artificial intelligence algorithm. International Journal of Thermofluids, 21, 100552.
https://doi.org/10.1016/j.ijft.2023.100552
31. Giraldo, S., la Rotta, D., Nieto-Londoño, C., Vásquez, R. E., & Escudero-Atehortúa, A. (2021). Digital
transformation of energy companies: A Colombian case study. Energies, 14(9), 2523.
https://doi.org/10.3390/en14092523
32. Zhou, Y. (2022). Artificial intelligence in renewable systems for transformation towards intelligent buildings.
Energy and AI, 10, 100182. https://doi.org/10.1016/j.egyai.2022.100182
33. Izonin, I., Tkachenko, R., Mitoulis, S. A., Faramarzi, A., Tsmots, I., & Mashtalir, D. (2024). Machine learning for
predicting energy efficiency of buildings: a small data approach. Procedia Computer Science, 231, 72–77.
https://doi.org/10.1016/j.procs.2023.12.173
34. Ibrahim, B., Rabelo, L., Gutierrez-Franco, E., & Clavijo-Buritica, N. (2022). Machine learning for short-term load
forecasting in smart grids. Energies, 15(21), 8079. https://doi.org/10.3390/en15218079
35. Kuzmenko, O., Chorna, V., & Kozhura, L. (2024). Implementation of artificial intelligence in energy consumption
calculations to reduce excess generation in the context of Ukraine’s recovery. Baltic Journal of Economic Studies,
10(1), 153–162. https://doi.org/10.30525/2256-0742/2024-10-1-153-162
36. Strielkowski, W., Vlasov, A., Selivanov, K., Muraviev, K., & Shakhnov, V. (2023). Prospects and challenges of the
machine learning and data-driven methods for the predictive analysis of power systems: A review. Energies, 16(10),
4025. https://doi.org/10.3390/en16104025
37. Joseph, A., & Balachandra, P. (2020). Smart grid to energy internet: A systematic review of transitioning electricity
systems. IEEE Access: Practical Innovations, Open Solutions, 8, 215787–215805.
https://doi.org/10.1109/access.2020.3041031
38. Olson, E. (2024). Digital transformation and AI in energy systems: Applications, challenges, and the path forward.
Palgrave Studies in Digital Business & Enabling Technologies (pp. 63–79). https://doi.org/10.1007/978-3-031-
61749-2_4
39. Bielokha, H., & Taraba, M. (2023). Transactive local electrical energy systems: Functioning features and
development prospects. POWER ENGINEERING: Economics, Technique, Ecology, 4(74), 29–37 [Ukrainian].
https://doi.org/10.20535/1813-5420.4.2023.290888
https://doi.org/10.1007/978-3-031-22464-5_27
https://doi.org/10.15407/srenergy2024.02a
https://doi.org/10.32604/ee.2020.010864
https://doi.org/10.3390/en16010347
https://doi.org/10.3390/electronics9061030
https://doi.org/10.3390/en16124590
https://doi.org/10.20535/1813-5420.4.2023.290880
https://doi.org/10.3390/wevj15080364
https://doi.org/10.15587/2706-5448.2023.291244
https://doi.org/10.15587/2706-5448.2023.291244
https://doi.org/10.3390/ai4020022
https://doi.org/10.1109/jproc.2022.3161053
https://doi.org/10.3390/ijerph18178946
https://doi.org/10.1016/j.ijft.2023.100552
https://doi.org/10.3390/en14092523
https://doi.org/10.1016/j.egyai.2022.100182
https://doi.org/10.1016/j.procs.2023.12.173
https://doi.org/10.3390/en15218079
https://doi.org/10.30525/2256-0742/2024-10-1-153-162
https://doi.org/10.3390/en16104025
https://doi.org/10.1109/access.2020.3041031
https://doi.org/10.1007/978-3-031-61749-2_4
https://doi.org/10.1007/978-3-031-61749-2_4
https://doi.org/10.20535/1813-5420.4.2023.290888
Системні дослідження в енергетиці. 2025. 3(83) 55
40. Rojek, I., Mroziński, A., Kotlarz, P., Macko, M., & Mikołajewski, D. (2023). AI-based computational model in
sustainable transformation of energy markets. Energies, 16(24), 8059. https://doi.org/10.3390/en16248059
41. Danish, M. S. S., & Senjyu, T. (2023). Shaping the future of sustainable energy through AI-enabled circular
economy policies. Circular Economy, 2(2), 100040. https://doi.org/10.1016/j.cec.2023.100040
42. Franki, V., Majnarić, D., & Višković, A. (2023). A comprehensive review of Artificial Intelligence (AI) companies
in the power sector. Energies, 16(3), 1077. https://doi.org/10.3390/en16031077
43. Fouad, M., Mali, R., Lmouatassime, A., & Bousmah, M. (2020). Machine Learning and IoT for Smart Grid. ISPRS
– International Archives of the Photogrammetry Remote Sensing and Spatial Information Sciences, XLIV-4/W3-
2020, 233–240. https://doi.org/10.5194/isprs-archives-xliv-4-w3-2020-233-2020
44. Matushkin, D. (2024). Photovoltaic generation forecasting models: Conceptual ensemble architectures. System
Research in Energy, 4(80), 56–64. https://doi.org/10.15407/srenergy2024.04.056
45. Dzyuba, V., & Zaporozhets, A. (2023). Using of big data technologies to improve the quality of the functioning of
production processes in the energy sector. In Studies in Systems, Decision and Control. Studies in Systems, Decision
and Control, 454 (pp. 117–128). https://doi.org/10.1007/978-3-031-22464-5_6
46. Hural, I., Putsenteilo, P., Fayerchuk, V., Kudybyn, M., & Koshparenko, O. (2024). Artificial Intelligence
Application in Renewable Energy Sources. CEUR Workshop Proceedings, 3716, 1–8. Retrieved March 11, 2025,
from https://ceur-ws.org/Vol-3716/short1.pdf
47. Karpenko, D., Yevtukhova, T., Novoseltsev, O., & Khodakivskyi, V. (2025). Improving the competitive structure
of the district heating market through energy storage devices. POWER ENGINEERING: Economics, Technique,
Ecology, 1(79), 126–132. https://doi.org/10.20535/1813-5420.1.2025.324272
48. IEA. (2024). Ukraine's Energy Security and the Coming Winter, IEA, Paris. Retrieved March 11, 2025, from
https://www.iea.org/reports/ukraines-energy-security-and-the-coming-winter, Licence: CC BY 4.0
ІНТЕГРОВАНИЙ ПІДХІД ДО СТАЛОГО РОЗВИТКУ ТА
ЕФЕКТИВНОСТІ ТРАНСФОРМУВАННЯ ЕНЕРГЕТИЧНИХ
СИСТЕМ НА ОСНОВІ ШТУЧНОГО ІНТЕЛЕКТУ
Дмитро Карпенко*, канд. техн. наук, https://orcid.org/0000-0002-8022-9782
Тетяна Євтухова, канд. техн. наук, доцент, https://orcid.org/0000-0003-4778-2479
Олександр Новосельцев, д-р. техн. наук, ст. наук. співр., https://orcid.org/0000-0001-9272-6789
Інститут загальної енергетики НАН України, вул. Антоновича, 172, Київ, 03150, Україна
*Автор-кореспондент: dmytro.qua@gmail.com
Анотація: У статті досліджено трансформаційну роль штучного інтелекту (ШІ) у модернізації
енергетичних систем для підвищення ефективності, стійкості та резильєнтності у відповідь на
зростаючий глобальний попит на енергію та екологічні проблеми. Завдяки комплексному огляду
літератури та систематичному аналізу висвітлено, як інновації, керовані ШІ, впливають на
виробництво, розподіл, споживання та роботу системи енергії. Ключові методи штучного
інтелекту, такі як машинне навчання, глибоке навчання, навчання з підкріпленням і алгоритми
оптимізації, відіграють ключову роль у покращенні інтеграції відновлюваної енергетики,
оптимізації функціональних можливостей інтелектуальної мережі, покращенні рішень для
зберігання енергії та переосмисленні динаміки енергетичного ринку. Було представлено
структурований підхід до трансформації енергетичної системи на основі штучного інтелекту з
наголошенням на важливості встановлення чітких цілей, виборі стратегічних напрямків,
впровадженні програм штучного інтелекту та встановленні постійних циклів зворотного зв’язку
для перевірки та вдосконалення. Завдяки сегментуванню енергетичної системи на функціональні
компоненти: виробництво, транспортування та розподіл, споживання енергії та управління
системою, було забезпечено поглиблений аналіз застосувань ШІ щодо кожного сегмента.
Визначено конкретні технології штучного інтелекту, моделі та алгоритми, придатні для різних
застосувань. ШІ виступає як інтегрований підхід, здатний змінювати енергетичні системи
відповідно до вимог стійкості та ефективності. Системна інтеграція технологій штучного
інтелекту в різні компоненти енергетичних систем і вирішення пов’язаних з цим проблем дасть
змогу енергетичному сектору отримати новий рівень продуктивності та інновацій, зробить
значний внесок у глобальні цілі сталого розвитку.
Ключові слова: енергетична система, енергетична безпека, енергетична трансформація,
енергетичний ринок, енергетичні послуги, штучний інтелект.
Надійшла до редколегії: 24.02.2025
https://doi.org/10.3390/en16248059
https://doi.org/10.1016/j.cec.2023.100040
https://doi.org/10.3390/en16031077
https://doi.org/10.5194/isprs-archives-xliv-4-w3-2020-233-2020
https://doi.org/10.15407/srenergy2024.04.056
https://doi.org/10.1007/978-3-031-22464-5_6
https://ceur-ws.org/Vol-3716/short1.pdf
https://doi.org/10.20535/1813-5420.1.2025.324272
https://www.iea.org/reports/ukraines-energy-security-and-the-coming-winter
https://orcid.org/0000-0002-8022-9782
https://orcid.org/0000-0003-4778-2479
https://orcid.org/0000-0001-9272-6789
|
| id | systemreorg-article-905 |
| institution | System Research in Energy |
| keywords_txt_mv | keywords |
| language | English |
| last_indexed | 2026-07-19T01:23:43Z |
| publishDate | 2025 |
| publisher | General Energy Institute of the National Academy of Sciences of Ukraine |
| record_format | ojs |
| resource_txt_mv | systemreorg/32/c5c3996e88b2bd375dbaedd92a9e7b32.pdf |
| spelling | systemreorg-article-9052026-07-18T12:57:49Z AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY Інтегрований підхід до сталого розвитку та ефективності трансформування енергетичних систем на основі штучного інтелекту Karpenko, Dmytro Yevtukhova, Tetiana Novoseltsev, Oleksandr energy system, energy security, energy transformation, energy market, energy services, artificial intelligence. енергетична система, енергетична безпека, енергетична трансформація, енергетичний ринок, енергетичні послуги, штучний інтелект. This paper explores the transformative role of artificial intelligence (AI) in modernizing energy systems to enhance efficiency, sustainability, and resilience in response rising global energy demands and environmental concerns. A comprehensive literature review and systematic analysis highlight how AI-driven innovations impact energy generation, distribution, consumption, and system operations. Key AI techniques such as machine learning, deep learning, reinforcement learning, and optimization algorithms play pivotal roles in enhancing renewable energy integration, optimizing smart grid functionalities, improving energy storage solutions, and redefining energy market dynamics. A structured approach was presented for AI-based energy system transformation, emphasizing the importance of setting clear goals, selecting strategic directions, implementing AI applications, and establishing continuous feedback loops for verification and improvement. By segmenting the energy system into functional components, production, transportation, distribution, consumption, and system operations, an in-depth analysis of AI applications was provided relevant to each segment. Specific AI technologies, models, and algorithms suitable for various applications are identified, along with associated challenges and considerations. AI is a transformative force capable of reshaping energy systems to meet contemporary demands for sustainability and efficiency. By thoughtfully integrating AI technologies across the various components of energy systems and addressing associated challenges, the energy sector can unlock new levels of performance and innovation, contributing significantly to global sustainability objectives. У статті досліджено трансформаційну роль штучного інтелекту (ШІ) у модернізації енергетичних систем для підвищення ефективності, стійкості та резильєнтності у відповідь на зростаючий глобальний попит на енергію та екологічні проблеми. Завдяки комплексному огляду літератури та систематичному аналізу висвітлено, як інновації, керовані ШІ, впливають на виробництво, розподіл, споживання та роботу системи енергії. Ключові методи штучного інтелекту, такі як машинне навчання, глибоке навчання, навчання з підкріпленням і алгоритми оптимізації, відіграють ключову роль у покращенні інтеграції відновлюваної енергетики, оптимізації функціональних можливостей інтелектуальної мережі, покращенні рішень для зберігання енергії та переосмисленні динаміки енергетичного ринку. Було представлено структурований підхід до трансформації енергетичної системи на основі штучного інтелекту з наголошенням на важливості встановлення чітких цілей, виборі стратегічних напрямків, впровадженні програм штучного інтелекту та встановленні постійних циклів зворотного зв’язку для перевірки та вдосконалення. Завдяки сегментуванню енергетичної системи на функціональні компоненти: виробництво, транспортування та розподіл, споживання енергії та управління системою, було забезпечено поглиблений аналіз застосувань ШІ щодо кожного сегмента. Визначено конкретні технології штучного інтелекту, моделі та алгоритми, придатні для різних застосувань. ШІ виступає як інтегрований підхід, здатний змінювати енергетичні системи відповідно до вимог стійкості та ефективності. Системна інтеграція технологій штучного інтелекту в різні компоненти енергетичних систем і вирішення пов’язаних з цим проблем дасть змогу енергетичному сектору отримати новий рівень продуктивності та інновацій, зробить значний внесок у глобальні цілі сталого розвитку. General Energy Institute of the National Academy of Sciences of Ukraine 2025-08-26 Article Article application/pdf https://systemre.org/index.php/journal/article/view/905 10.15407/srenergy2025.03.041 System Research in Energy; No. 3 (83) (2025): System Research in Energy; 41-55 Системні дослідження в енергетиці; № 3 (83) (2025): Системні дослідження в енергетиці; 41-55 2786-7102 2786-7633 en https://systemre.org/index.php/journal/article/view/905/811 Copyright (c) 2025 Dmytro Karpenko, Tetiana Yevtukhova, Oleksandr Novoseltsev https://creativecommons.org/publicdomain/zero/1.0 |
| spellingShingle | energy system energy security energy transformation energy market energy services artificial intelligence. Karpenko, Dmytro Yevtukhova, Tetiana Novoseltsev, Oleksandr AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY |
| title | AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY |
| title_alt | Інтегрований підхід до сталого розвитку та ефективності трансформування енергетичних систем на основі штучного інтелекту |
| title_full | AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY |
| title_fullStr | AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY |
| title_full_unstemmed | AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY |
| title_short | AN INTEGRATED AI-BASED APPROACH TO TRANSFORMING ENERGY SYSTEMS FOR SUSTAINABILITY AND EFFICIENCY |
| title_sort | integrated ai-based approach to transforming energy systems for sustainability and efficiency |
| topic | energy system energy security energy transformation energy market energy services artificial intelligence. |
| topic_facet | energy system energy security energy transformation energy market energy services artificial intelligence. енергетична система енергетична безпека енергетична трансформація енергетичний ринок енергетичні послуги штучний інтелект. |
| url | https://systemre.org/index.php/journal/article/view/905 |
| work_keys_str_mv | AT karpenkodmytro anintegratedaibasedapproachtotransformingenergysystemsforsustainabilityandefficiency AT yevtukhovatetiana anintegratedaibasedapproachtotransformingenergysystemsforsustainabilityandefficiency AT novoseltsevoleksandr anintegratedaibasedapproachtotransformingenergysystemsforsustainabilityandefficiency AT karpenkodmytro íntegrovanijpídhíddostalogorozvitkutaefektivnostítransformuvannâenergetičnihsistemnaosnovíštučnogoíntelektu AT yevtukhovatetiana íntegrovanijpídhíddostalogorozvitkutaefektivnostítransformuvannâenergetičnihsistemnaosnovíštučnogoíntelektu AT novoseltsevoleksandr íntegrovanijpídhíddostalogorozvitkutaefektivnostítransformuvannâenergetičnihsistemnaosnovíštučnogoíntelektu AT karpenkodmytro integratedaibasedapproachtotransformingenergysystemsforsustainabilityandefficiency AT yevtukhovatetiana integratedaibasedapproachtotransformingenergysystemsforsustainabilityandefficiency AT novoseltsevoleksandr integratedaibasedapproachtotransformingenergysystemsforsustainabilityandefficiency |