engleski

Adaptive Bidding for Electricity Wholesale Markets in a Smart Grid

One of challenges for researchers in smart grids is to find mechanisms for putting orders on the electricity wholesale market. This paper tackles this problem by proposing adaptive bidding mechanism for trading in the wholesale market. The research challenge lies in the fact that wholesale players simultaneously trade on 24 different wholesale markets determined by the moment of electricity delivery which ranges from 1 to 24 hours ahead. Namely, the variant Roth-Erev reinforcement learning algorithm is used to coordinate wholesale bidding across different markets by choosing among four implemented wholesale strategies. The Power Trading Agent Competition is used to evaluate the performance of different implementations of the adaptive bidding mechanism as well as to benchmark adaptive bidding approach against single strategy approach.

smart grids ; software agents ; electricity wholesale market ; reinforcement learning ; Power Trading Agent Competition

nije evidentirano