Evolutionary learning driven load forecasting and demand response management model for smart grid

The smart meter data generated from the customers' usage help utility providers to manage and control the electricity distribution among the customers for reliable services in the smart grid. Demand response management is one of the important applications of the grid that helps smart meter customers to potentially reduce their consumption and balance the load in the entire grid. For the demand response management in the smart grid, a multi-objective problem (MOP) is formulated considering three objectives, i.e., power scarcity, wastage and load factor. These objectives are computed by the newly proposed load forecasting neural network that precisely predicts upcoming loads on the demand side. The weights of the neural network are optimized by hybrid learning, which comprises evolutionary and Adam optimization algorithms. Furthermore, MOP is efficiently solved by the non-dominated sorting genetic algorithm (NSGA-III). The experimental results show the superiority of the proposed work over the state-of-the-art works in terms of load forecasting and management. The forecasting accuracy of the proposed work is achieved up to 96.30% and root mean squared error up to 0.1367 on the Open Energy Data Initiative dataset provided by the National Renewable Energy Laboratory of the United States.