... A centralised deep learning control system (DeepCS) for preventive security control and a decentralised multiagent control system (MACS) for emergency control. The DeepCS includes two deep neural networks - a deep multilayer perceptron to recognise reactive power injections and a long short-term memory network to predict system state after control actions. The MACS is a decentralised automatic Volt/VAr control that involves determining the time of critical overload and switching to the load shedding ...
Теги: control systems , deep neural networks , man machine systems , multilayer neural networks , current generation , intelligent techniques , learning control systems , multiagent control systems , reactive power... minimizing the real power losses while taking into account the permissible limits of nodes' voltages. Finally, the standard IEEE-33 bus power system is utilized to validate the evolved algorithm, results show that a good enhancement in finding the optimal reactive power flow is well achieved. © 2018 IEEE.
Теги: cuckoo search , differential evolution , radial distribution networks evolutionary algorithms , shunt capacitors , electric load flow , learning algorithms , optimization , reactive power , cuckoo search algorithms , cuckoo searches , evolutionary computation technPanasetsky D., Tomin N., Sidorov D. et al. Decentralized multi-agent algorithm for voltage control // Asia-Pacific Power and Energy Engineering Conference, APPEEC. Vol.Decem. 2016. P.852-856. ISBN 9781509054183. DOI: 10.1109/APPEEC.2016.7779615. In recent years, due to liberalization, power systems are being operated closer and closer to their limits. At the same time, they have increased in size and complexity. Both factors increase the risk of major power outages and blackouts. Most of the existing...
Теги: automatic voltage control , emergency control , multi-agent systems , power system control , reactive power control , fault tolerance , multi agent systems , power control , reactive power , software agents , voltage control , development and testing , multi-agent al