A Demand and Response Management Model Using Load Forecasting Technique for Smart Grid

Demand and response management plays a vital role in the smart grid for reliability between utility providers and smart meter customers. The demand of customers is predicted by load forecasting algorithms. However, existing load forecasting techniques consume high computation costs and limited forecasting accuracy. In this paper, Long Short-Term Memory (LSTM) is implemented for smart meter prediction of load. The proposed work is simulated on Open Energy Data Initiative (OEDI) dataset and our model outperforms the existing works in performance analysis. Mean Squared Error (MSE) and Mean Absolute Error (MAE) are achieved up to 0.0021 and 0.0332, respectively, by proposed model.