Short-Term Power Load Forecasting Based on EMD and ESN

Abstract:

With the continuous development of power market, the precision requirement for short-term power load forecasting is constantly being improved. In order to obtain higher prediction accuracy, this paper put forward a method of combining empirical mode decomposition (EMD) with echo state network (ESN) for short-term power load forecasting. First, original data had been decomposed into several independent components, whose features were obvious. A corresponding echo state network was built for each component. Then, each component should be trained and predicted by its corresponding echo state network. The experimental results showed that this method has a better prediction accuracy compared with traditional neural network method.

• Periodical: Advanced Materials Research (Volume 651)
• Pages: 910-916
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.651.910
• Online since: January 2013
• Authors: Yong Luo, Xue Jia, Shu Wei Chen
• Keywords: Echo State Network (ESN), Empirical Mode Decomposition (EMD), Intrinsic Mode Function (IMF), Short-Term Power Load Forecasting

References

[1] Nihuan Liao, Zhihong Hu, etc. Summarize of the short-term load forecasting method in electric power system[J]. Power System Protection and Control, 2011, 39(1): 147-152.

[2] Nima Amjady. Short-Term Hourly Load Forecasting Using Time-Series Modeling with Peak Load Estimation Capability[J]. IEEE transactions of power systems, 2001, 16(3): 498-505.

DOI: 10.1109/59.932287

[3] H.M. Al-Hamadi, S.A. Soliman*. Short-term electric load forecasting based on Kalman filtering algorithm with moving window weather and load model[J]. Electric Power Systems Research, 2004, 68(1): 47-59.

DOI: 10.1016/s0378-7796(03)00150-0

[4] SEIJI KAWAUCHI, HIROAKI SUGIHARA, etc. Development of Very-Short-Term Load Forecasting Based on Chaos Theory[J]. Electrical Engineering in Japan, 2004, 148(2): 55-63.

DOI: 10.1002/eej.10322

[5] M. Beccali, M. Cellura*, etc. Forecasting daily urban electric load profiles using artificial neural networks[J]. Energy Conversion and Management, 2004, 45(18): 2879-2900.

DOI: 10.1016/j.enconman.2004.01.006

[6] Bo-Juen Chen, etc. Load Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001[J]. IEEE transactions on power systems, 2004, 19(4): 1812-1830.

DOI: 10.1109/tpwrs.2004.835679

[7] Dengfu Zhao, Meng Wang, etc. Support vector machine (SVM) based on the short-term load forecasting [J]. Proceedings of the CSEE, 2002, 22(4): 26-30.

[8] Zhihui Zhu, Yunlian Sun, etc. Hybrid of EMD and SVMs for Short-Term Load Forecasting[J]. IEEE International Conference on Control and Automation, 2007: 1044-1047.

DOI: 10.1109/icca.2007.4376516

[9] Xiaowei Lin, Zehong Yang, Yixu Song. esc. Short-term stock price prediction based on echo state networks[J]. Expert Systems with Applications, 2009, 36(3): 7313-7317.

DOI: 10.1016/j.eswa.2008.09.049

[10] Hemen Showkati, Amir H. Hejazi, etc. Short Term Load Forecasting Using Echo State Networks[J]. Neural Networks(IJCNN). 2010: 1-5.

DOI: 10.1109/ijcnn.2010.5596950

[11] Chunyang Sheng, Jun Zhao, Ying Liu. esc. Prediction for noisy nonlinear time series by echo state network based on dual estimation[J]. Neurocomputing, 2012, 82(1): 186-195.

DOI: 10.1016/j.neucom.2011.11.021

[12] Qingsong Song*, Zuren Feng. Effects of connectivity structure of complex echo state network on its prediction performance for nonlinear time series[J]. Neurocomputing, 2012, 73(10): 2177-2185.

DOI: 10.1016/j.neucom.2010.01.015

[13] Huang N E, Shen Z, etc. TheEmpirical Mode Decomposition Method and the Hilbert Spectrum for Nonlinear and Nonstationary Time Series Analysis[A]. in: Proceeding of the Royal Society of London, Series A[C]. 1998, 454: 903-955.

[14] Jaeger H. The Echo State Approach to Analyzing and Training Recurrent Networks. German National Research Center for Information Technology, (2001).

[15] Canbing Li, Xiaohui Li, etc. Application of similar selection algorithm in power short-term load forecasting[J]. Automation of electric power systems, 2008, 3(9): 69-73.