Оперативне керування потоками у комп’ютерних мережах з технологією MPLS

The problem of traffic management of different classes of service in MPLS computer networks is considered. This problem is formulated as a rerouting problem of flows of different service classes under failures of channels and nodes while preserving the quality of service (QoS). The mathematical mode...

Повний опис

Збережено в:
Бібліографічні деталі
Дата:2015
Автор: Zaychenko, О. Yu.
Формат: Стаття
Мова:rus
Опубліковано: The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" 2015
Онлайн доступ:http://journal.iasa.kpi.ua/article/view/43458
Теги: Додати тег
Немає тегів, Будьте першим, хто поставить тег для цього запису!
Назва журналу:System research and information technologies

Репозиторії

System research and information technologies
Опис
Резюме:The problem of traffic management of different classes of service in MPLS computer networks is considered. This problem is formulated as a rerouting problem of flows of different service classes under failures of channels and nodes while preserving the quality of service (QoS). The mathematical model of this problem is constructed and the algorithm to solve it is suggested. This algorithm allows to determine new routes for requests which were rejected due to failures and reroute them over new virtual routes so that to maximize the value of transmitted global flow. Experimental studies were conducted to estimate the efficiency of the suggested algorithm of traffic management of different classes of service. The problem of optimal choice of carrying capacities and flows distribution was solved. Further fault states were simulated and flows rerouting was performed using the suggested algorithm, the new flow distribution and the total value of the corrected flow from every service class were determined. The results analysis confirms that application of operative traffic management as a rerouting allows to promote the general capacity of a network and increase the total flow value in a case of faults of network elements.