College of Automation, Guangdong University of Technology, Guangzhou, P.R.China

---

Abstract—The modeling of the relationships between the power loads and the variables that influence the power loads especially in the abnormal days is the key point to improve the performance of short-term load forecasting systems. To integrate the advantages of several forecasting models for improving the forecasting accuracy, based on data mining and artificial neural network techniques, an ensemble decision tree and FLANN combining short-term load forecasting system is proposed to mainly settle the weathersensitive factors’ influence on the power load. In the proposed strategy, an ensemble decision tree with abnormal pattern modification algorithm and a FLANN algorithm are used respectively to obtain the initial predicting results of the power loads first, a BP-based combination of the above two results are used to get a better prediction afterwards. Corresponding forecasting system is developed for practical use. The statistical analysis showed that the accuracy of the proposed short time load forecasting of abnormal days has increased greatly. Meanwhile, the actual forecast results of Anhui Province’s electric power load have validated the effectiveness and the superiority of the system.

Index Terms—short-term load forecasting, combining forecasting, abnormal days, ensemble data mining, FLANN

[PDF]

Cite: Ming Li, Junli Gao, "An Ensemble Data Mining and FLANN Combining Short-term Load Forecasting System for Abnormal Days," Journal of Software vol. 6, no. 6, pp. 961-968, 2011.