Short-Term Load Forecast of Integrated Energy System Based on Wavelet Packet Decomposition and Recurrent Neural Network

doi:10.12204/j.issn.1000-7229.2020.12.013

Abstract

Abstract:

This paper proposes a short-term load forecast method for electric, cooling and heating loads on the basis of wavelet packet decomposition(WPD) and recurrent neural network. Wavelet packets that can highlight the detail characteristics of the load are used to decompose electric, cooling and heating loads, and analyze the cross-correlation between the electric, cooling and heating loads in each frequency band. In order to reflect the influence of the cross-correlation of electric, cooling and heating loads in different frequency bands on the forecasting results, those loads with strong cross-correlation in a frequency band are put into the same recurrent neural network model that can handle the autocorrelation of the load; while those with weak cross-correlation in a frequency band are forecasted separately. Compared with directly placing the electric, cooling and heating loads into the same recurrent neural network for forecasting, and compared with placing the electric, cooling and heating loads into the same back propagation neural network for forecasting, the method in this paper considers the cross-correlation of the electric, cooling and heating loads in each frequency band and the autocorrelation of the electric, cooling and heating loads, which effectively reduce the mean absolute percentage error of load forecast.

Key words: integrated energy system, load forecast, correlation analysis, wavelet packet decomposition(WPD), recurrent neural network

CLC Number:

TM 71

ZHU Liuzhu, WANG Xuli, MA Jing, CHEN Qinghui, QI Xianjun. Short-Term Load Forecast of Integrated Energy System Based on Wavelet Packet Decomposition and Recurrent Neural Network[J]. ELECTRIC POWER CONSTRUCTION, 2020, 41(12): 133-140.

Figures/Tables 14

Fig.1 Block diagram of WPD-RNN forecasting method

Fig.2 Structure of three-layer wavelet packet decomposition

Fig.3 Structure of RNN

Fig.4 Flow chart of electric, cooling and heating load forecasting

Table 1 Analysis of correlation coefficients of electric,cooling and heating loads in each frequency band

Table 2 Pearson correlation coefficients of electric,cooling and heating loads in each frequency band

Table 3 Results of correlation coefficient analysis of electric,cooling and heating loads in each frequency band

Fig.5 Results of electric load forecasting

Fig.6 Results of cooling load forecasting

Fig.7 Results of heating load forecasting

Fig.8 Relative error of electric, cooling and heating load forecasting

Table 4 Fitting degrees between forecast curves and real curves by three forecasting methods

Fig.9 MAPE by three forecasting methods

Table 5 MAPE of WPD-RNN forecasting method under different cross-correlation criteria

References 20

[1]	SHEN F, JU P, SHAHIDEHPOUR M, et al. Singular perturbation for the dynamic modeling of integrated energy systems[J]. IEEE Transactions on Power Systems, 2020,35(3):1718-1728. doi: 10.1109/TPWRS.59 URL
[2]	肖白, 刘庆永, 牛强, 等. 基于元胞负荷特性分析的RBF神经网络空间负荷预测方法[J]. 电网技术, 2018,42(1):301-307.
	XIAO Bai, LIU Qingyong, NIU Qiang, et al. A spatial load forecasting method based on RBF neural network and cellular load characteristics analysis[J]. Power System Technology, 2018,42(1):301-307.
[3]	熊军华, 牛珂, 张春歌, 等. 基于小波变异果蝇优化支持向量机短期负荷预测方法研究[J]. 电力系统保护与控制, 2017,45(13):71-77.
	XIONG Junhua, NIU Ke, ZHANG Chunge, et al. LSSVM in short-term load forecasting based on wavelet transform and mutant fruit fly optimization algorithm[J]. Power System Protection and Control, 2017,45(13):71-77.
[4]	沈沉, 秦建, 盛万兴, 等. 基于小波聚类的配变短期负荷预测方法研究[J]. 电网技术, 2016,40(2):521-526. doi: 10.13335/j.1000-3673.pst.2016.02.027 URL
	SHEN Chen, QIN Jian, SHENG Wanxing, et al. Study on short-term forecasting of distribution transformer load using wavelet and clustering method[J]. Power System Technology, 2016,40(2):521-526. doi: 10.13335/j.1000-3673.pst.2016.02.027 URL
[5]	KONG X Y, LI C, ZHENG F, et al. Improved deep belief network for short-term load forecasting considering demand-side management[J]. IEEE Transactions on Power Systems, 2020,35(2):1531-1538. doi: 10.1109/TPWRS.59 URL
[6]	ZHANG T Y, LI H N, HUI Q, et al. Integrated load forecasting model of multi-energy system based on Markov chain improved neural network [C]//2019 11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA). Qiqihar, China: IEEE, 2019: 454-457.
[7]	POWELL K M, SRIPRASAD A, COLE W J, et al. Heating, cooling, and electrical load forecasting for a large-scale district energy system[J]. Energy, 2014,74:877-885. doi: 10.1016/j.energy.2014.07.064 URL
[8]	史佳琪, 谭涛, 郭经, 等. 基于深度结构多任务学习的园区型综合能源系统多元负荷预测[J]. 电网技术, 2018,42(3):698-706.
	SHI Jiaqi, TAN Tao, GUO Jing, et al. Multi-task learning based on deep architecture for various types of load forecasting in regional energy system integration[J]. Power System Technology, 2018,42(3):698-706.
[9]	张旭. 基于循环神经网络的时间序列预测方法研究[D]. 南京: 南京大学, 2019.
	ZHANG Xu. Time series forecasting based on recurrent neural networks[D]. Nanjing: Nanjing University, 2019.
[10]	刘剑桥. 基于改进LSTM循环神经网络瓦斯数据时间序列预测研究[D]. 徐州: 中国矿业大学, 2018.
	LIU Jianqiao. Research on time series prediction of recurrent neural network gas data based on improved LSTM model[D]. Xuzhou: China University of Mining and Technology, 2018.
[11]	SHI H, XU M H, LI R. Deep learning for household load forecasting: A novel pooling deep RNN[J]. IEEE Transactions on Smart Grid, 2018,9(5):5271-5280. doi: 10.1109/TSG.5165411 URL
[12]	李守茂, 戚嘉兴, 白星振, 等. 基于IPSO-WNN的综合能源系统短期负荷预测[J]. 电测与仪表, 2020,57(9):103-109.
	LI Shoumao, QI Jiaxing, BAI Xingzhen, et al. A short-term load prediction of integrated energy system based on IPSO-WNN[J]. Electrical Measurement & Instrumentation, 2020,57(9):103-109.
[13]	马建鹏, 龚文杰, 张智晟. 基于Copula理论与KPCA-GRNN结合的区域综合能源系统多元负荷短期预测模型[J]. 电工电能新技术, 2020,39(3):24-31.
	MA Jianpeng, GONG Wenjie, ZHANG Zhisheng. Short-term multiple load prediction model for regional integrated energy system based on Copula theory and KPCA-GRNN[J]. Advanced Technology of Electrical Engineering and Energy, 2020,39(3):24-31.
[14]	王浩. 基于小波包分析的短期负荷预测研究[D]. 南京: 南京理工大学, 2013.
	WANG Hao. Study of short-term load forecasting based on wavelet packet analysis[D]. Nanjing: Nanjing University of Science and Technology, 2013.
[15]	多布. 小波十讲[M]. 李建平, 杨万年, 译. 北京: 国防工业出版社, 2004: 314-318.
[16]	叶瑞丽, 郭志忠, 刘瑞叶, 等. 基于小波包分解和改进Elman神经网络的风电场风速和风电功率预测[J]. 电工技术学报, 2017,32(21):103-111.
	YE Ruili, GUO Zhizhong, LIU Ruiye, et al. Wind speed and wind power forecasting method based on wavelet packet decomposition and improved Elman neural network[J]. Transactions of China Electrotechnical Society, 2017,32(21):103-111.
[17]	董长虹, 高志, 余啸海. Matlab小波分析工具箱原理与应用[M]. 北京: 国防工业出版社, 2004: 71-72.
[18]	陈妮亚, 钱政, 孟晓风, 等. 基于空间相关法的风电场风速多步预测模型[J]. 电工技术学报, 2013,28(5):15-21.
	CHEN Niya, QIAN Zheng, MENG Xiaofeng, et al. Multi-step ahead wind speed forecasting model based on spatial correlation and support vector machine[J]. Transactions of China Electrotechnical Society, 2013,28(5):15-21.
[19]	史文博. 地区电网负荷特性分析及短期负荷预测研究[D]. 广州: 华南理工大学, 2015.
	SHI Wenbo. Analysis of power load characteristic and study on short-term load forecasting in regional power system[D]. Guangzhou: South China University of Technology, 2015.
[20]	党雨. 基于改进鲸鱼算法和循环神经网络的短期电力负荷预测[D]. 成都: 西南交通大学, 2019.
	DANG Yu. Short-term load forecasting based on improved whale algorithm and cyclic neural network[D]. Chengdu: Southwest Jiaotong University, 2019.