Short-term household load forecasting based on EMD-SLSTM

被引：0

作者：

Liu J. ^{[1
]}

Li J. ^{[1
]}

Yang L. ^{[1
]}

Yan Y. ^{[1
]}

Liu Y. ^{[1
]}

Zhang Y. ^{[1
]}

机构：

[1] School of Electrical and Power Engineering, China University of Mining and Technology, Xuzhou

来源：

Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control | 2019年 / 47卷 / 06期

关键词：

Deep learning; Empirical mode decomposition; Short-term household load forecasting; Stack long short-term memory network; Time series;

D O I：

10.7667/PSPC180365

中图分类号：

学科分类号：

摘要：

For non-stationary short-term household load data, it is difficult to mine deeper temporal characteristics by directly applying the prediction model. A combination of Empirical Mode Decomposition (EMD) and Stack Long Short-Term Memory (SLSTM) algorithm is proposed for short-term household load forecasting. Firstly, the principle of EMD and SLSTM is analyzed and the EMD-SLSTM combined prediction model is proposed. Then, the load data is decomposed by the EMD algorithm and the decomposed component data is respectively converted into three-dimensional data. By designing the network architecture of SLSTM and its parameters, the normalized component data and original data are separately predicted and reconstructed. In order to show the performance of the algorithm, the performance of the support vector regression, artificial neural network, deep neural network, gradient boosting regression is compared and verified by MAPE and RMSE performance metrics in two scenarios. The results show that EMD-SLSTM can more effectively express the time series relationship of short-term household load and has higher prediction accuracy. © 2019, Power System Protection and Control Press. All right reserved.

引用

页码：40 / 47

页数：7

共 22 条

[1]

Shu Y., Zhang Z., Guo J., Et al., Study on key factors and solution of renewable energy accommodation, Proceedings of the CSEE, 37, 1, pp. 1-8, (2017)

[2]

Kazmerski L., Renewable and sustainable energy reviews, Renewable & Sustainable Energy Reviews, 38, pp. 834-847, (2013)

[3]

Wang S., Sun Z., Liu Z., Household energy collaborative scheduling strategy for smart power utilization, Automation of Electric Power Systems, 39, 17, pp. 108-113, (2015)

[4]

Sun G., Li Y., Wei Z., Et al., Discussion on the architecture of smart power use interaction system, Automation of Electric Power Systems, 39, 17, pp. 68-74, (2015)

[5]

Liu X., Su X., Yan X., Et al., Load forecasting of active distribution system for active response and selling electricity market, Proceedings of the CSU-EPSA, 29, 2, pp. 121-128, (2017)

[6]

Ryu S., Noh J., Kim H., Deep neural network based demand side short term load forecasting, 2016 IEEE International Conference on Smart Grid Communications (SmartGridComm), pp. 308-313, (2016)

[7]

Liao N., Hu Z., Ma Y., Et al., Review of the short-term load forecasting methods of electric power system, Power System Protection and Control, 39, 1, pp. 147-152, (2011)

[8]

Mai H., Xiao J., Wu X., Et al., Research on load forecasting ARIMA model parallelization based on R language, Power System Technology, 39, 11, pp. 3216-3220, (2015)

[9]

Xiong J., Niu K., Zhang C., Et al., LSSVM in short-term load forecasting based on wavelet transform and mutant fruit fly optimization algorithm, Power System Protection and Control, 45, 13, pp. 71-77, (2017)

[10]

Wu X., He J., Zhang P., Et al., Power system short-term load forecasting based on improved random forest with grey relation projection, Automation of Electric Power Systems, 39, 12, pp. 50-55, (2015)

← 1 2 3 →