Fuzzy Q -- Learning for Uniform Price Wholesale Power Markets

The generators gain more profits through bidding strategies become an important in the open competitive market. In the incomplete information market, the generators are looking for a best bidding strategy according to the changing market structure and their own conditions are a significant. The reinforcement Q - learning combined with fuzzy control are considered to solve this problem. The day - ahead uniform price wholesale power market model is presented. The model is suitable for multi area power system and which simulated throughout IEEE 30 bus power system with six generators in three areas. The resulting simulations demonstrated the Fuzzy Q - learning (FQ - leaning) has convergent more rapidly than the conventional Q - learning and the supplier agents can choose the best bidding strategy according to the changing power market structure.

[1]  Yang Liu,et al.  A new Q-learning algorithm based on the metropolis criterion , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[2]  Mohammad-R. Akbarzadeh-T,et al.  Q-adjusted annealing for Q-learning of bid selection in market-based multisource power systems , 2006 .

[3]  Richard Green,et al.  A Review of the Monitoring of Market Power The Possible Roles of TSOs in Monitoring for Market Power Issues in Congested Transmission Systems , 2005 .

[4]  H. R. Mashhadi,et al.  Modeling the Supplier Agent's Risk Strategy based on Fuzzy Logic Combined with the Q-Learning Algorithm , 2006, 2006 International Conference on Computational Intelligence and Security.

[5]  Donald V. Bourcier,et al.  Locational Market Power Screening and Congestion Management: Experience and Suggestions , 2002, IEEE Power Engineering Review.

[6]  Xiuli Wang,et al.  Generation bidding strategies for marginal price based power market , 2004, IEEE Power Engineering Society General Meeting, 2004..

[7]  Y.-Y. Hong,et al.  Bidding strategy based on artificial intelligence for a competitive electric market , 2001 .

[8]  Haili Song,et al.  Optimal electricity supply bidding by Markov decision process , 2000 .

[9]  Fushuan Wen,et al.  Market power in generation markets , 2000 .

[10]  F. Nogales,et al.  Price-Taker Bidding Strategy under Price Uncertainty , 2002, IEEE Power Engineering Review.

[11]  Chen Qingsong,et al.  Realization of Decision-making Module in Agent-based Simulation of Power Markets , 2008 .

[12]  Craig Boutilier,et al.  The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems , 1998, AAAI/IAAI.

[13]  Gaofeng Xiong,et al.  An electricity supplier bidding strategy through Q-Learning , 2002, IEEE Power Engineering Society Summer Meeting,.

[14]  Leigh Tesfatsion,et al.  Capacity withholding in restructured wholesale power markets: An agent-based test bed study , 2009, 2009 IEEE/PES Power Systems Conference and Exposition.

[15]  A.G. Bakirtzis,et al.  Multi-Agent Reinforcement Learning for Strategic Bidding in Power Markets , 2006, 2006 3rd International IEEE Conference Intelligent Systems.