Based on the EMD and PSO-BP Neural Network of Short-Term Load Forecasting

Abstract:

This paper proposes that based on the EMD and PSO-BP neural network of short-term load forecasting. This method will be automatically historical load sequence into several independent intrinsic mode functions (IMF) by using EMD. As the BP neural network training for a long time and easy to fall into local minimum of the shortcomings, we use genetic algorithm to optimize BP neural network algorithm replaces the traditional BP algorithm. Finally, we use the BP neural network optimized separately for each IMF component for training and prediction. We should add the component to the final prediction forecast. This method has higher precision than the EMD-BP model prediction by Simulation results show.

• Periodical: Advanced Materials Research (Volumes 614-615)
• Pages: 1872-1875
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.614-615.1872
• Online since: December 2012
• Authors: Feng Sha, Feng Zhu, Shun Nan Guo, Jian Tong Gao
• Keywords: BP Neural Network (BPNN), Empirical Mode Decomposition (EMD), Particle Swarm Optimization (PSO), Short-Term Load Forecasting

References

[1] TANG Jun-jie, NIU Huan-na, YANG Ming-hao. Periodic autoregressive short-term forecasting method based on the linear correlation analysis[J]. Power System Protection and Control, 2010, 38（14）: 128-133.

[2] LU Ning, ZHOU Jian-zhong, HE Yao-yao. Particle swarm optimization-based neural network model for short-term load forecasting[J]. Power System Protection and Control, 2010, 38（12): 65-68.

[3] WANG Zhi-yong, GUO Chuang-xin, CAO Yi-jia. A Method for Short Load Forecasting Integrating Fuzzy-Rough Set with Artificial Neural Network[J]. Proceedings of the CSEE, 2005, 25(19):7-11.

DOI: 10.1109/ipec.2005.206900

[4] XIE Jing-xin, CHENG Chun-tian. A New Direct Multi-step Ahead Prediction Model Based on EMD and Chaos Analysis[J]. Journal of Automation, 2008, 34(6): 684-689.

DOI: 10.3724/sp.j.1004.2008.00684

[5] WANG Hong-bo, ZHU Qi-bing. Trend Prediction of Non-stationary Vibration Signals based on Empirical Mode Decomposition and Least Square Support Vector Machin[J]. Computer Engineering and Applications, 2008, 44(16):157-159.

[6] ZHU Zhi-hui, SUN Yun-lian, LI Huang-qiang. Hybrid of EMD and SVMs for Short-Term Load Forecasting[A]. in:IEEE International Conference on Control and Automation[C]. 2007, 1044-1047.

DOI: 10.1109/icca.2007.4376516

[7] ZHENG Lian-qing, ZHENG Yan-qiu. Short-term power load forecasting based on empirical mode decomposition and ANN[J]. Power System Protection and Control, 2009, 37(23):L66-69.

[8] NIU Dong-xiao, LI Yuan-yuan, QI Jian-xun. A Novel Approach for Load Analysis Based on Empirical Mode Decomposition and Influencing Factors[J]. Proceedings of the CSEE, 2008, 28(16): 96-102.

[9] Huang N E, Shen Z, Long S R. The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis[C]. Proceedings of the Royal Society of London, Series A, 1998, 454: 903-995.

DOI: 10.1098/rspa.1998.0193