Short Term Load Forecasting Based on VMD-DNN

• Published in: 2019 IEEE 8th International Conference on Advanced Power System Automation and Protection (APAP) pp. 1045 - 1048
• Main Authors: Wang, Can, Huang, Shaoxiong, Wang, Song, Ma, Yuan, Ma, Jinhui, Ding, Jinjin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21-10-2019
• Subjects: deep neural networks; empirical mode decomposition; Short-term load forecasting; variational mode decomposition
• DOI: 10.1109/APAP47170.2019.9224746

Improving the accuracy of load forecasting is of great significance to economic dispatch and stable operation of power system. A short-term load forecasting model based on variational mode decomposition (VMD) and deep neural network (DNN) is proposed. VMD algorithm is used to decompose load series into different intrinsic mode functions (IMF), and each IMF is combined with DNN for prediction. Finally, the four forecasting results of each part are added together. Through experimental simulation, compared with the forecasting result of DNN and empirical mode decomposition (EMD) methods, the proposed method can effectively improve the load forecasting accuracy.