A hybrid optimized grey seasonal variation index model improved by whale optimization algorithm for forecasting the residential electricity consumption

Forecasting the residential electricity consumption can provide an effective and sustainable electricity supply in the rapid development of urbanization and industrialization. However, it is a challenging task to establish an efficient forecasting model for enhancing the forecasting accuracy, accelerating the forecasting speed, minimizing the electricity consumption and reducing the environmental pollution. Most existing works on the residential electricity consumption focus on improving the forecasting accuracy while the improvement is insufficient. And few of them have considered the forecasting speed. To overcome these limitations, this paper firstly proposes a hybrid Improved Whale Optimization Algorithm -Optimized Grey Seasonal Variation Index (IWOA-OGSVI) model for best solutions of satisfactory forecasting results with high accuracy and fast-convergence. Next, for evaluating the forecasting performance, two case studies are carried out to estimate the effectiveness of our proposed model compared with a range of benchmark models. Finally, the empirical results present that the MAPE values in our proposed model are smallest at the Excellent level of the forecasting power and all of them have converged before 30 iterations, which demonstrate the superiority of our proposed model over the others on the forecasting accuracy and speed among the five selected regions. (c) 2021 Elsevier Ltd. All rights reserved.

Automated summary

This study proposes a hybrid optimization algorithm-optimized grey seasonal variation index model for forecasting residential electricity consumption, which is validated through case studies to have high accuracy and fast convergence. The results demonstrate that the model performs best at an excellent level of forecasting power with the smallest MAPE values and convergence before 30 iterations.