A Hybrid Short-Term Load Forecasting Model Based on Improved Fuzzy C-Means Clustering, Random Forest and Deep Neural Networks

Short-term load forecasting (STLF) plays an important role in the secure and reliable operation of the electric power system. Grouping similar load profiles by a clustering algorithm is a common method to reduce the uncertainty of electric consumption data. However, due to the uneven distribution of different date types in a historical data set, the tradition fuzzy c-means clustering (FCM) algorithm cannot identify typical load consumption patterns accurately. To solve this problem, a novel STLF model based on the improved FCM (IFCM) algorithm, random forest (RF) and deep neural networks (DNN) is proposed in this paper. First, IFCM is used to partition the load consumption profiles into several groups, and each group represents a typical load consumption pattern. The optimal number of clusters is determined by a recent clustering validity index. Then, a RF model is trained by the meteorological and calendar features of the historical data set. Finally, a DNN model is established for each group, and is trained using the features of the days that are partition into this group by IFCM. The experimental results on two daily load consumption data sets have showed that the proposed STLF model achieves better prediction performance as compared to other methods. In addition, the load consumption pattern of holidays was extracted from the historical data sets by utilizing IFCM, and the prediction performance of holidays in the testing set therefore has been significantly improved.

Automated summary

This paper proposes a novel STLF model based on an improved FCM algorithm, RF, and DNN, which successfully improves the accuracy of load consumption data prediction. Experimental results demonstrate that the model outperforms other methods in terms of prediction performance and significantly enhances the prediction accuracy of load consumption data on holidays.