Reinforcement learning (RL) to optimal reconfiguration of radial distribution system (RDS)

Vlachogiannis, JG; Hatziargyriou, N

dc.contributor.author	Vlachogiannis, JG	en
dc.contributor.author	Hatziargyriou, N	en
dc.date.accessioned	2014-03-01T02:42:57Z
dc.date.available	2014-03-01T02:42:57Z
dc.date.issued	2004	en
dc.identifier.issn	0302-9743	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31147
dc.subject	Closed Loop Control	en
dc.subject	Decision Problem	en
dc.subject	Distributed System	en
dc.subject	Evolutionary Programming	en
dc.subject	Learning Algorithm	en
dc.subject	Reinforcement Learning	en
dc.subject	Satisfiability	en
dc.subject.classification	Computer Science, Theory & Methods	en
dc.subject.other	Busbars	en
dc.subject.other	Closed loop control systems	en
dc.subject.other	Decision making	en
dc.subject.other	Electric potential	en
dc.subject.other	Energy dissipation	en
dc.subject.other	Learning algorithms	en
dc.subject.other	Mapping	en
dc.subject.other	Optimization	en
dc.subject.other	Radial basis function networks	en
dc.subject.other	Reinforcement	en
dc.subject.other	Evolutionary programming (EP)	en
dc.subject.other	Power loss	en
dc.subject.other	Radial distribution systems (RDS)	en
dc.subject.other	Reinforcement learning (RL)	en
dc.subject.other	Learning systems	en
dc.title	Reinforcement learning (RL) to optimal reconfiguration of radial distribution system (RDS)	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1007/978-3-540-24674-9_46	en
heal.identifier.secondary	http://dx.doi.org/10.1007/978-3-540-24674-9_46	en
heal.language	English	en
heal.publicationDate	2004	en
heal.abstract	This paper presents a Reinforcement Learning (RL) method for optimal reconfiguration of radial distribution system (RDS). Optimal reconfiguration involves selection of the best set of branches to be opened, one from each loop, such that the resulting RDS has the desired performance. Among the several performance criteria considered for optimal network reconfiguration, an important one is real power losses minimization, while satisfying voltage limits. The RL method formulates the reconfiguration of RDS as a multistage decision problem. More specifically, the model-free learning algorithm (Q-learning) learns by experience how to adjust a closed-loop control rule mapping operating states to control actions by means of reward values. Rewards are chosen to express how well control actions cause minimization of power losses. The Q-learning algorithm is applied to the reconfiguration of 33-bus RDS busbar system. The results are compared with those given by other evolutionary programming methods.	en
heal.publisher	SPRINGER-VERLAG BERLIN	en
heal.journalName	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)	en
heal.bookName	LECTURE NOTES IN COMPUTER SCIENCE	en
dc.identifier.doi	10.1007/978-3-540-24674-9_46	en
dc.identifier.isi	ISI:000221610800046	en
dc.identifier.volume	3025	en
dc.identifier.spage	439	en
dc.identifier.epage	446	en