A novel deep learning-based forecasting model optimized by heuristic algorithm for energy management of microgrid

Abstract

Recently, the integration of renewable energy sources (RESs) in microgrids (MGs) has risen significantly owing to extensive promotion of decarbonization and green energy. However, despite the environmental–economic benefits, RESs are intermittent, and increasing penetration of RESs into MG poses operation challenges in handling uncertainties. In this paper, a novel deep learning-based forecasting model is proposed for MG operation considering uncertainties of RESs, load, and day-ahead price (DAP). To handle the intrinsic uncertainties of MGs, a long short-term memory (LSTM) network is employed and a method for increasing prediction accuracy of the LSTM model based on a genetic algorithm–adaptive weight particle swarm optimization (GA-AWPSO) combination along with a global attention mechanism (GAM) is proposed. Herein, the hyperparameters of the LSTM model are optimized by the GA-AWPSO algorithm, and GAM is added to mine important features from input datasets to improve forecasting performance. To handle uncertainties through the demand side, A DM-CIDR program is developed for providing optimal incentive rate strategies to participants, as different customers exhibit diverse attitudes toward remunerated incentives. In this program, ordering points to identify the clustering structure (OPTICS) and k-nearest neighbor algorithms (k-NN) are used for clustering and classification, respectively, to determine reasonable incentive rates for customers according to their bid/offer data. A simulation was implemented on historical PJM datasets, the results of which revealed the performance and superiority of the proposed approach in handling uncertainties.