Energy management of the energy storage-based micro-grid-connected system: an SOGSNN strategy

In this paper, a novel hybrid algorithm is implemented for the system modelling and the optimal management of the micro-grid (MG)-connected systems with low cost. The increasing number of renewable energy sources and distributed generators requires new strategies for their operations in order to maintain the energy balance between the renewable sources and MG. Therefore, an efficient hybrid technique is proposed in the paper. The main objective of the process was the optimum operation of micro-sources for decreasing the electricity production cost by hourly day-ahead and real-time scheduling. The proposed hybrid technique is to manage the power flows between the energy sources and the grid. To achieve this point, demand response and minimum cost of energy are determined. The proposed hybrid technique is the combined performance of both the gravitational search algorithm (GSA)-based artificial neural network (ANN) and squirrel search algorithm (SSA), and it is named as SOGSNN. This technique is involved with the mathematical optimization problems that necessitate more than one fitness function to be optimized simultaneously. By using the inputs of MG-like wind turbine, photovoltaic array, fuel cell, micro-turbine, diesel generator and battery storage with corresponding cost functions, the GSA-based ANN learning phase is employed to predict the load demand. SSA clarifies the squirrel in optimizing the configuration of MG based on the load demand. The proposed hybrid technique is implemented in MATLAB/Simulink working platform and compared with other solution techniques like ANFASO method. The comparison result reveals that the superiority of the proposed technique confirms its ability to solve the problem.