基于小波包分解与循环神经网络的综合能源系统短期负荷预测

doi:10.12204/j.issn.1000-7229.2020.12.013

电力建设 ›› 2020, Vol. 41 ›› Issue (12): 133-140.doi: 10.12204/j.issn.1000-7229.2020.12.013

基于小波包分解与循环神经网络的综合能源系统短期负荷预测

朱刘柱¹, 王绪利¹, 马静¹, 陈庆会², 齐先军²

1.国网安徽省电力有限公司经济技术研究院,合肥市 230071
2.安徽新能源利用与节能省级实验室(合肥工业大学),合肥市 230009

收稿日期:2020-04-17 出版日期:2020-12-01 发布日期:2020-12-04
通讯作者: 齐先军
作者简介:朱刘柱(1972),男,硕士,高级工程师,主要从事电力规划设计与评审工作;|王绪利(1984),男,学士,高级工程师,主要从事电力规划设计与评审工作;|马静(1984),男,硕士,高级工程师,主要从事电力规划设计与评审工作;|陈庆会(1995),男,硕士研究生,主要从事配电网规划、负荷预测研究工作。
基金资助:
中央高校基本科研业务费专项资金资助项目(PA2020GDSK0099)

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

ZHU Liuzhu¹, WANG Xuli¹, MA Jing¹, CHEN Qinghui², QI Xianjun²

1. Institute of Economy and Technology, State Grid Anhui Electric Power Co., Ltd., Hefei 230071, China
2. Anhui Provincial Laboratory of New Energy Utilization and Energy Conservation (Hefei University of Technology), Hefei 230009, China

Received:2020-04-17 Online:2020-12-01 Published:2020-12-04
Contact: QI Xianjun
Supported by:
Fundamental Research Funds for the Central Universities(PA2020GDSK0099)

摘要/Abstract

摘要：

文章提出了基于小波包分解(wavelet packet decomposition,WPD)与循环神经网络的电冷热综合能源短期负荷预测方法。利用能够突出负荷细节特征的小波包对电冷热负荷进行频段分解,分析每一频段中电冷热负荷的互相关性。为体现每一频段中电冷热负荷的互相关性对预测结果的影响,将频段中互相关性较强的负荷类型放入同一处理负荷自相关性的循环神经网络模型中进行预测;频段中互相关性较弱的负荷类型则单独进行预测。与直接将电冷热负荷放入同一个循环神经网络进行预测相比,以及与将电冷热负荷通过同一个反向传播神经网络进行预测相比,所提方法考虑了综合能源在不同频段内电冷热负荷的互相关性和电冷热负荷本身的自相关性,能够有效降低负荷预测的平均绝对百分比误差。

关键词: 综合能源系统, 负荷预测, 相关性分析, 小波包分解(WPD), 循环神经网络

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

中图分类号:

TM 71

朱刘柱, 王绪利, 马静, 陈庆会, 齐先军. 基于小波包分解与循环神经网络的综合能源系统短期负荷预测[J]. 电力建设, 2020, 41(12): 133-140.

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.

图/表 14

图1 WPD-RNN预测方法框图

Fig.1 Block diagram of WPD-RNN forecasting method

图2 3层小波包分解结构

Fig.2 Structure of three-layer wavelet packet decomposition

图3 RNN结构

Fig.3 Structure of RNN

图4 电冷热负荷预测流程

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

表1 各频段内电冷热互相关系数分析

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

表2 各频段电冷热负荷Pearson相关系数

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

表3 各频段内电冷热负荷互相关系数分析结果

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

图5 电负荷预测结果

Fig.5 Results of electric load forecasting

图6 冷负荷预测结果

Fig.6 Results of cooling load forecasting

图7 热负荷预测结果

Fig.7 Results of heating load forecasting

图8 电冷热负荷预测的相对误差

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

表4 3种预测方法所得的预测与实际曲线的拟合程度

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

图9 3种预测方法的MAPE

Fig.9 MAPE by three forecasting methods

表5 不同互相关性标准下WPD-RNN 预测方法的MAPE

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

参考文献 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.

基于小波包分解与循环神经网络的综合能源系统短期负荷预测

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

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 20

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈晓东, 马越, 陈贤邦, 刘洋. 基于数据驱动可调鲁棒的冷热电联供综合能源系统日前调度优化[J]. 电力建设, 2021, 42(1): 28-40.
[2]	朱旭, 杨军, 李高俊杰, 董旭柱, 刘首文. 计及虚拟储能系统的区域综合能源系统优化调度策略[J]. 电力建设, 2020, 41(8): 99-110.
[3]	张浩禹，邱晓燕，周晟锐，赵有林，李凌昊，张楷 . 基于机会约束目标规划的多电-气互联综合能源系统分布式优化模型[J]. 电力建设, 2020, 41(7): 82-91.
[4]	魏震波，任小林，黄宇涵. 考虑综合需求侧响应的区域综合能源系统多目标优化调度[J]. 电力建设, 2020, 41(7): 92-99.
[5]	苏俊妮，张鑫，赵俊炜，张锐，曲明辉，杨艳红. 计及需求响应和储能的电-气综合能源系统优化调度[J]. 电力建设, 2020, 41(5): 1-8.
[6]	林紫菡，蒋晨威，陈明辉，尚慧玉，赵宏伟，阳曾，王一铮，文福拴. 计及柔性负荷的综合能源系统低碳经济运行[J]. 电力建设, 2020, 41(5): 9-18.
[7]	李鹏，杨莘博，李慧璇，田春筝，李锰，谭忠富. 计及多能源多需求响应手段的园区综合能源系统优化调度模型[J]. 电力建设, 2020, 41(5): 45-57.
[8]	宋建，束洪春，董俊，梁雨婷，李雨龙，杨博. 基于GM(1，1)与BP神经网络的综合负荷预测[J]. 电力建设, 2020, 41(5): 75-80.
[9]	郇嘉嘉，肖勇，陆文升，刘洪，彭家颖，潘险险，李吉峰. 基于复杂网络理论的区域综合能源系统可靠性评估[J]. 电力建设, 2020, 41(4): 1-9.
[10]	王李龑，许强，黄开艺，吴健，艾芊，张亚新，贾轩. 计及新能源及负荷不确定性的多能微网系统两阶段随机规划方法[J]. 电力建设, 2020, 41(4): 100-108.
[11]	付建民，杨斌，王小君，孙庆凯，张义志，和敬涵，张放. 考虑建筑储能特性的高铁站综合能源系统规划方法[J]. 电力建设, 2020, 41(3): 13-22.
[12]	潘尔生, 宋毅, 原凯, 郭玥, 程浩忠, 张沈习. 考虑可再生能源接入的综合能源系统规划评述与展望[J]. 电力建设, 2020, 41(12): 3-13.
[13]	王澜灵, 刘俊勇, 许立雄, 贺心达, 唐杰, 房钢. 计及实时需求响应的综合能源信息物理系统可靠性分析[J]. 电力建设, 2020, 41(12): 25-40.
[14]	任海泉, 贾燕冰, 田丰, 白云. 计及可替代负荷的电-气综合能源系统可靠性评估[J]. 电力建设, 2020, 41(12): 41-48.
[15]	吴嘉豪, 曾成碧, 苗虹. 基于机会约束目标规划的综合能源系统经济调度[J]. 电力建设, 2020, 41(12): 49-56.