Random-Fuzzy Programming and Its Hybrid Intelligent Algorithm to Building Optimal Bidding Strategies for Generation Companies in Electricity Market

In a competitive electricity market with sealed auction, building the optimal bidding strategies for generation companies (Gencos) could be based on many uncertain information including rival´s bidding behaviors, forecasted load and other market parameters. All the uncertain parameters to be considered in the procedure of bidding strategies have the random and fuzzy character. As a result, two main approaches to build optimal bidding strategies for Gencos were based on probability theory and possibility theory. However, as a limit of mathematical theory, there could not simultaneously deal with both random variable and fuzzy variable in a model developed in the past work. Based on credibility theory that was recently founded, a new framework of random-fuzzy programming was proposed for building optimal bidding strategies with risk management in this paper, and a hybrid intelligent algorithm by integrating simulation, artificial neural network and genetic algorithm were presented to find optimal bidding strategies. A numerical example of a simulated electricity market with six participating Gencos is served to demonstrate the feasibility of the developed model and solution method.