Model-free demand response scheduling strategy for virtual power plant considering risk attitude of consumer

Abstract

Driven by the modern advanced information and communication technologies, distributed energy resources has the great potential for energy supply within the framework of virtual power plant(VPP). Meanwhile, demand response(DR) is becoming increasingly important for enhancing the VPP operation and mitigating the risks associated with the fluctuation of renewable energy resources(RESs). In this paper, we proposed an incentive-based DR program for VPP to minimize the deviation penalty from participating in power market. Markov decision process(MDP) with unknown transition probability is constructed from the VPP's prospective to formulate the incentive-based DR program, in which the randomness of consumer behavior and RES generation are taken into consideration. Furthermore, a value function of prospect theory(PT) is developed to characterize consumer's risk attitude and describe the psychological factors. A model-free deep reinforcement learning(DRL)-based approach is proposed to deal with the randomness existing in the model and adaptively determine the optimal DR pricing strategy for VPP, without requiring any system model information. Finally, the results of cases demonstrate the effectiveness of the proposed approach.