Near-Optimal Day-Ahead Scheduling of Energy Storage System in Grid-Connected Microgrid

This paper proposes a near-optimal day-ahead scheduling of energy storage system based on the mismatch between supply and demand, state-of-charge and real-time electricity price when deciding how much to charge and discharge the energy storage system. An artificial neural network, the extreme learning machine is used for the day-ahead forecast of the mismatch between supply and demand and real-time electricity market price. After the day-ahead forecast is obtained, the scheduling problem is formulated into a mixed-integer linear programming and implemented in AMPL and solved using CPLEX. This paper also considers the impact of forecasting errors in the day-ahead scheduling. Empirical evidence shows that the proposed near-optimal day-ahead scheduling of ESS can achieve lower operating cost and life-cycle.