ANN Based Day-Ahead Load Demand Forecasting for Energy Transactions at Urban Community Level with Interoperable Green Microgrid Cluster

Abstract

Microgrids are formed with the rapid penetration of renewable energy sources (RES) into the distribution grid (DG) network, which increases the complexity of DG system and at the same time the conventional grid is getting overloaded due to the urbanization. So, to reduce the stress on the utility grid and for safe and reliable operation of microgrid (MG), it is necessary to develop proper Energy Management System (EMS) with adequate real time control. With this motivation in this paper Artificial Neural Network (ANN) is used along with EMS in the proposed microgrid cluster for making energy transactions based on the availability of localized green energy sources. Energy management system uses day-ahead load demand forecasted by ANN for scheduling the energy sources and managing the energy transactions between the proposed system and utility grid during surplus/shortage power conditions. The cluster is formed by interconnecting two interoperable areas and each area associated with two microgrids. The proposed system with ANN in this paper is modeled and implemented in MATLAB software with Simulink and NN tool box. The simulated test results showed the accuracy of ANN for forecasting day-ahead load demand of the proposed system when compared with Linear Regression (LR).