A low-cost evolutionary algorithm for the unit commitment problem considering probabilistic unit outages

Asouti, VG; Giannakoglou, KC

dc.contributor.author	Asouti, VG	en
dc.contributor.author	Giannakoglou, KC	en
dc.date.accessioned	2014-03-01T02:07:19Z
dc.date.available	2014-03-01T02:07:19Z
dc.date.issued	2012	en
dc.identifier.issn	00207721	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/29542
dc.subject	evolutionary algorithms	en
dc.subject	hierarchical optimisation	en
dc.subject	probabilistic outages	en
dc.subject	unit commitment	en
dc.subject.other	Binary string	en
dc.subject.other	Candidate solution	en
dc.subject.other	Decision variables	en
dc.subject.other	Dispatch problems	en
dc.subject.other	Efficient chromosomes	en
dc.subject.other	External resources	en
dc.subject.other	Hierarchical evaluation	en
dc.subject.other	Monte Carlo Simulation	en
dc.subject.other	Objective functions	en
dc.subject.other	Optimisations	en
dc.subject.other	Solution methods	en
dc.subject.other	Start-ups	en
dc.subject.other	Unit commitment problem	en
dc.subject.other	Unit commitments	en
dc.subject.other	Chromosomes	en
dc.subject.other	Evolutionary algorithms	en
dc.subject.other	Monte Carlo methods	en
dc.subject.other	Costs	en
dc.title	A low-cost evolutionary algorithm for the unit commitment problem considering probabilistic unit outages	en
heal.type	journalArticle	en
heal.identifier.primary	10.1080/00207721.2011.604742	en
heal.identifier.secondary	http://dx.doi.org/10.1080/00207721.2011.604742	en
heal.publicationDate	2012	en
heal.abstract	This article presents a solution method to the unit commitment problem with probabilistic unit failures and repairs, which is based on evolutionary algorithms and Monte Carlo simulations. Regarding the latter, thousands of availability-unavailability trial time patterns along the scheduling horizon are generated. The objective function to be minimised is the expected total operating cost, computed after adapting any candidate solution, i.e. any series of generating/non-generating (ON/OFF) unit states, to the availability- unavailability patterns and performing evaluations by considering fuel, start-up and shutdown costs as well as the cost for buying electricity from external resources, if necessary. The proposed method introduces a new efficient chromosome representation: the decision variables are integer IDs corresponding to the binary-to-decimal converted ON/OFF (1/0) scenarios that cover the demand in each hour. In contrast to previous methods using binary strings as chromosomes, the new chromosome must be penalised only if any of the constraints regarding start-up, shutdown and ramp times cannot be met, chromosome repair is avoided and, consequently, the dispatch problems are solved once in the preparatory phase instead of during the evolution. For all these reasons, with or without probabilistic outages, the proposed algorithm has much lower CPU cost. In addition, if probabilistic outages are taken into account, a hierarchical evaluation scheme offers extra noticeable gain in CPU cost: the population members are approximately pre-evaluated using a small representative set of the Monte Carlo simulations and only a few top population members undergo evaluations through the full Monte Carlo simulations. The hierarchical scheme makes the proposed method about one order of magnitude faster than its conventional counterpart. © 2012 Taylor & Francis.	en
heal.journalName	International Journal of Systems Science	en
dc.identifier.doi	10.1080/00207721.2011.604742	en
dc.identifier.volume	43	en
dc.identifier.issue	7	en
dc.identifier.spage	1322	en
dc.identifier.epage	1335	en