|
| A refined load forecasting based on historical data and real-time influencing factors |
| DOI：10.7667/PSPC180050 |
| Key Words:load forecasting data fusion support vector machines (SVM) prediction accuracy |
| Author Name | Affiliation | E-mail | | XI Yawen | School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China | | | WU Junyong | School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China | wujy@bjtu.edu.cn | | SHI Chen | School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China | | | ZHU Xiaowen | School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044, China | | | CAI Rong | ABB China Research Institute, Beijing 100015, China | |
|
| Hits: 3910 |
| Download times: 1401 |
| Abstract:With the rapid development of smart grid technology, increasingly demand on the accuracy of load forecasting is put forward. Integrating load, weather and other multi-sourced data, a refined load forecasting method of Support Vector Machine (SVM) based on data fusion is proposed. Firstly, the historical load data is clustered and the operation days are divided into six categories. Then the weather data such as temperature and humidity are combined with the load data, and the refined load forecasting models of SVM based on data fusion are established respectively for the six clustering results. And the parameters of the model are optimized globally. Different forecasting models are used to predict the load of a prefecture-level city in Zhejiang Province in 2013, the prediction results show that the prediction accuracy of the load forecasting method proposed in this paper is obviously higher than that of the traditional load forecasting method. This work is supported by National Natural Science Foundation of China (No. 51577009) and ABB China Research Institute (No. ABB20171128REU-CTR). |
| View Full Text View/Add Comment Download reader |
|
|
|