An ensemble-based enhanced short and medium term load forecasting using optimized missing value imputation

Electricity load forecasting is integral to planning, energy management, and the energy market. Utility companies serve a massive number of customers by supplying electricity. These utility companies require a precise forecast of electricity usage. This paper presents a forecasting model for energy load based on the ensemble voting regressor method. In addition, to enhance the accuracy of forecasting, develop an imputation method for handling missing values in the user's energy consumption data. A real-time data set is used for performance comparison with multiple imputation techniques to validate the imputation approach by generating random missing data for different missing rates of 10-30%. The proposed forecasting model is compared with other state-of-the-art methods to show its effectiveness in terms of MAPE, MAE, and RMSE. The experimental results demonstrate that the proposed methodology significantly improves the accuracy of the predicted load for a day and week ahead of energy consumption.