Pricing scheme based Nash Q-learning load control in smart grids

Calls to improve customer participation as a key element of smart grids have reinvigorated interest in demand-side features such as load control for residential users. For the load control problems, a pricing scheme based Nash Q-learning load controller is proposed. It considers a game with some non-cooperative energy equipments. The energy pricing scheme is introduced to the design of the reward value in the learning process of Q-learning. Because of the uncertainties and highly time-varying, the Nash Q-learning, which is independent of mathematic model, is adopted to deal with the incomplete information for smart grid. By means of learning procedures, the proposed controller can learn to take the best actions to regulate the energy usage for equipments with the features of high comfortable for energy usage and low electric charge meanwhile. Simulation results show that the proposed load controller can promote the performance energy usage in smart grids.