Hybrid Experimental Learning on Trading Behavior Analysis in Electricity Markets

A modern electricity market is essentially a complex network, characterized by complicated interactions among cyber communications, physical systems, and social agents. Trading behavior modeling has always been complicated in the physical system-based market. In this paper, trading behavior modeling in the electricity market is solved by a data-driven method combining experimental economics and machine learning, called Hybrid Experimental Learning (HEL). Based on the historical and experiment simulated data, HEL models the trading behavior by a machine learning generative model. Taking a simulated electricity market based on the trial spot market rule in Guangdong, China as an example, a Wasserstein generative adversarial network (WGAN) is employed to generate the bidding strategies of a gas generator. By analyzing the result, some suggestions are given for long and short run decision-making for gas generators.