A learning-based optimization of active power dispatch for a grid-connected microgrid with uncertain multi-type loads

Abstract

An active power dispatch method for a microgrid (MG) with multi-type loads, renewable energy sources, and distributed energy storage devices (DESDs) is the focus of this paper. The MG operates in a grid-connected model, and distributed power sources contribute to the service for load demands. The outputs of multiple DESDs are controlled to optimize the active power dispatch. Our goal with optimization is to reduce the economic cost under the time-of-use price and to adjust the excessively high or low loading rate of distributed transformers caused by the peak-valley demand and load uncertainties. To simulate a practical environment, stochastic characteristics of multi-type loads are formulated. Then, a finite-horizon Markov decision process model is established to describe the dispatch optimization problem. A learning-based technique is adopted to search the optimal joint control policy of multiple DESDs. Finally, simulation experiments are performed to validate the effectiveness of the proposed method.