Monthly electricity consumption forecasting by the fruit fly optimization algorithm enhanced Holt-Winters smoothing method
This addresses a practical challenge in electric power system management where insufficient data is common, though it is an incremental improvement over existing methods.
The paper tackled the problem of accurately forecasting monthly electricity consumption with limited sample data by proposing a hybrid model (FOA-MHW) that uses the fruit fly optimization algorithm to select smoothing parameters for the Holt-Winters method, resulting in significantly improved accuracy even with small training datasets.
The electricity consumption forecasting is a critical component of the intelligent power system. And accurate monthly electricity consumption forecasting, as one of the the medium and long term electricity consumption forecasting problems, plays an important role in dispatching and management for electric power systems. Although there are many studies for this problem, large sample data set is generally required to obtain higher prediction accuracy, and the prediction performance become worse when only a little data is available. However, in practical, mostly we experience the problem of insufficient sample data and how to accurately forecast the monthly electricity consumption with limited sample data is a challenge task. The Holt-Winters exponential smoothing method often used to forecast periodic series due to low demand for training data and high accuracy for forecasting. In this paper, based on Holt-Winters exponential smoothing method, we propose a hybrid forecasting model named FOA-MHW. The main idea is that, we use fruit fly optimization algorithm to select smoothing parameters for Holt-Winters exponential smoothing method. Besides, electricity consumption data of a city in China is used to comprehensively evaluate the forecasting performance of the proposed model. The results indicate that our model can significantly improve the accuracy of monthly electricity consumption forecasting even in the case that only a small number of training data is available.