Optimal Energy Management Strategy for ESS with Day Ahead Energy Prediction

Abstract

Incorporating with Hybrid Energy Storage System (HESS) with PV farm to establish PV-Storage integrated generation system is a promising solution to develop power quality of renewable energy. The prediction of very short-term generation and active demand response and dynamic state of charge (SOC) based optimum scheduling of HESS are the key points affecting system reliability and effectiveness of PV power. This paper proposes a short-term prediction and optimal scheduling-based energy management algorithm to coordinate among PV generation, HESS, and active demand response. The proposed algorithm composes of dynamic SOC, predicted PV-generation and power consumption, and real-time state of charge of the ESS. Firstly, based on long short-term memory (LSTM) algorithm, the historic data of PV power output is applied to develop the model to achieve good accuracy. Then, the output from the model are derived from the control algorithm to optimize the power flow in the system. The simulation results exhibit the effectiveness and robustness of the proposal.