Bidding Strategy on Demand Side Using Eligibility Traces Algorithm

Subject Areas : International Journal of Smart Electrical Engineering

Seyed Mohammad Ali  Naseri Gavareshk ¹ (Department of Electrical and Biomedical Engineering; Sadjad University of Technology, Mashhad, Iran)
Somayeh  Hasanpour Darban ² ()
Amin  Noori ³ ()
Mahdi  Besharatifar ⁴ ()

Received: 2017-12-20 Accepted : 2018-01-15 Published : 2017-12-31

Keywords: Power market, reinforcement learning, bidding strategy, demand side, service provider companies, elgibility traces,

Abstract :

Restructuring in the power industry is followed by splitting different parts and creating a competition between purchasing and selling sections. As a consequence, through an active participation in the energy market, the service provider companies and large consumers create a context for overcoming the problems resulted from lack of demand side participation in the market. The most prominent challenge for customers on demand side, is bidding strategy selection manner for attending in the competitive market. In this regard, they attempt to pay the least expense for purchasing the energy, while tolerating the least risk. In this paper, bidding strategy of service provider companies and the large consumers in the power market is proposed under the eligibility traces algorithm. In this algorithm, the demand side customers are considered as agents of Reinforcement Learning (RL). These agents learn through interaction with environment to bid such that earn the highest benefit.