Short-term prediction on integrated energy loads considering temperature-humidity index and coupling characteristics

doi:10.3969/j.issn.2097-0706.2023.07.008

Abstract

Abstract:

To address the vulnerability of integrated energy load prediction to meteorological factors and the complexity and low accuracy of prediction models caused the coupling characteristics of heterogeneous energy， a short-term load forecasting model considering temperature-humidity index and coupling characteristics is proposed. Excavating the coupling characteristics of multiple loads， the input variables considering the influence of temperature-humidity index and multiple factors are constructed. Ensuring that the information is valid，kernel principal component analysis （KPCA） is used to complete the dimensional reduction of prediction input space， and the prediction model is built based on gated recurrent unit （GRU） neural network. Attention mechanism is introduced into the model to extract important differentiated features. Finally， the electric and cooling load data of a practical system are selected for simulation， and the results show that the root mean square errors and mean absolute percentage errors of the electric and cooling load predicted by KPCA-GRU-Attention model are 1 025 kW， 2.7% and 2 167 kW， 2.9 %， respectively. The accuracy has been significantly improved. The proposed model effectively improves the short-term prediction accuracy of integrated energy loads by considering the influence of multiple factors， realizing the accurate perception on energy demand.

Key words: integrated energy system, multiple load, temperature-humidity index, coupling characteristics, kernel principal component analysis, gated recurrent unit neural network, Attention mechanism, short-term load forecasting

CLC Number:

TK01：TM714

JIN Li, ZHANG Li, TANG Yang, TANG Qiao, REN Juguang, YANG Kun, LIU Xiaobing. Short-term prediction on integrated energy loads considering temperature-humidity index and coupling characteristics[J]. Integrated Intelligent Energy, 2023, 45(7): 70-77.

Figures/Tables 9

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Fig.5

Fig.6

Fig.7

Table 2

References 23

[1]	任炬光, 张力, 金立, 等. 考虑可再生能源消纳的建筑综合能源系统日前经济调度模型[J]. 工程科学与技术, 2023, 55(2):160-170.
	REN Juguang, ZHANG Li, JIN Li, et al. Day-ahead economic dispatch model of building integrated energy systems considering the renewable energy consumption[J]. Advanced Engineering Sciences, 2023, 55(2):160-170.
[2]	刘创. 计及气象参数的区域电-热综合能源系统运行优化研究[D]. 北京: 华北电力大学, 2021.
	LIU Chuang. Research on optimization of regional integrated electric-heat system considering the meteorological parameter[D]. Beijing: North China Electric Power University, 2021.
[3]	张爱平, 赵利兴, 刘静. 楼宇型综合能源服务系统智能优化运行研究[J]. 综合智慧能源, 2022, 44(2):42-48. doi: 10.3969/j.issn.2097-0706.2022.02.007
	ZHANG Aiping, ZHAO Lixing, LIU Jing. Research on optimized operation of building-type integrated energy service systems[J]. Integrated Intelligent Energy, 2022, 44(2):42-48. doi: 10.3969/j.issn.2097-0706.2022.02.007
[4]	王定美, 张睿骁, 赵龙. 基于MMoE-TCN的综合能源系统短期多元负荷预测[J]. 电气传动自动化, 2023, 45(1):39-45,38.
	WANG Dingmei, ZHANG Ruixiao, ZHAO Long. Multivariate load short-term forecasting of integrated energy system based on MMoE-TCN[J]. Electric Drive Automation, 2023, 45(1): 39-45,38.
[5]	马建鹏. 基于智能理论的综合能源系统多元负荷短期预测研究[D]. 青岛: 青岛大学, 2020.
	MA Jianpeng. Study on short-term prediction of multivariate load of integrated energy system based on intelligent theory[D]. Qingdao: Qingdao University, 2020.
[6]	陆普凡. 基于改进神经网络的电力负荷短期预测方法研究[D]. 南京: 南京邮电大学, 2022.
	LU Pufan. Research on short-term forecasting of power load based on improved neural network[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2022.
[7]	RANMAN S, BABA M. Software-design and evaluation of a microcomputer-based automated load forecasting system[J]. IEEE Transactions on Power System, 1989, 4(2):782-788. doi: 10.1109/59.193840
[8]	韩富佳, 王晓辉, 乔骥, 等. 基于人工智能技术的新型电力系统负荷预测研究综述[J/OL]. 中国电机工程学报, 2023:1-24[2023-03-12].https://doi.org/10.13334/j.0258-8013.pcsee.221560.
	HAN Fujia, WANG Xiaohui, QIAO Ji, et al. Review on artificial intelligence based load forecasting research for the new-type power system[J/OL]Proceedings of the CSEE, 2023:1-24[2023-03-12].https://doi.org/10.13334/j.0258-8013.pcsee.221560.
[9]	李华, 陆明璇, 佟永吉, 等. 态势感知技术在新型电力系统运行中的应用[J]. 综合智慧能源, 2023, 45(3):24-33. doi: 10.3969/j.issn.2097-0706.2023.03.004
	LI Hua, LU Mingxuan, TONG Yongji, et al. Application of situational awareness technology in the safe and stable operation of new power systems[J]. Integrated Intelligent Energy, 2023, 45(3):24-33. doi: 10.3969/j.issn.2097-0706.2023.03.004
[10]	田浩含. 区域综合能源系统多元负荷短期预测研究[D]. 青岛: 青岛大学, 2021.
	TIAN Haohan. Short-term load forecasting study of multivariate regional integrated energy system[D]. Qingdao: Qingdao University, 2021.
[11]	罗凤章, 张旭, 杨欣, 等. 基于深度学习的综合能源配电系统负荷分析预测[J]. 高电压技术, 2021, 47(1):23-32.
	LUO Fengzhang, ZHANG Xu, YANG Xin, et al. Load analysis and prediction of integrated energy distribution system based on deep learning[J]. High Voltage Engineering, 2021, 47(1): 23-32.
[12]	CHEN B Y, WANG Y F. Short-term electric load forecasting of integrated energy system considering nonlinear synergy between different loads[J]. IEEE Access, 2021, 9:43562-43573. doi: 10.1109/ACCESS.2021.3066915
[13]	陈锦鹏, 胡志坚, 陈纬楠, 等. 二次模态分解组合 DBiLSTM-MLR的综合能源系统负荷预测[J]. 电力系统自动化, 2021, 45(13):85-94.
	CHEN Jinpeng, HU Zhijian, CHEN Weinan, et al. Load prediction of integrated energy system based on combination of quadratic modal decomposition and deep bidirectional long short-term memory and multiple linear regression[J]. Automation of Electric Power Systems, 2021, 45(13):85-94.
[14]	王永利, 周泯含, 姚苏航, 等. 基于多能耦合机理的综合能源系统多元负荷协同预测模型[J]. 华北电力大学学报(自然科学版), 2022, 49(2):118-126.
	WANG Yongli, ZHOU Minhan, YAO Suhang, et al. Multi-load cooperative prediction model of integrated energ system based on multi-energy coupling mechanism[J]. Journal of North China Electric Power University (Natural Science Edition), 2022, 49(2):118-126.
[15]	吴晨, 姚菁, 薛贵元, 等. 基于MMoE多任务学习和长短时记忆网络的综合能源系统负荷预测[J]. 电力自动化设备, 2022, 42(7):33-39.
	WU Chen, YAO Jing, XUE Guiyuan, et al. Load forecasting of integrated energy system based on MMoE multi-task learning and LSTM[J]. Electric Power Automation Equipment, 2022, 42(7):33-39.
[16]	吕忠麟, 顾洁, 孟璐. 基于耦合特征与多任务学习的综合能源系统短期负荷预测[J]. 电力系统自动化, 2022, 46(11):58-66.
	LYU Zhonglin, GU Jie, MENG Lu. Short-term load forecasting of integrated energy system based on coupling characteristics and multi task learning[J]. Automation of Electric Power Systems, 2022, 46(11):58-66.
[17]	张大海, 孙锴, 倪平浩. 基于耦合关系挖掘及渐进式分层提取多任务学习网络的风-光-荷短期预测[J/OL]. 电网技术, 2022:1-14[2023-03-12].https://doi.org/10.13335/j.1000-3673.pst.2022.1492.
	ZHANG Dahai, SUN Kai, NI Pinghao. Wind-photovoltaic-load short-term forecast based on coupling relation mining and progressive layered extraction of multi-task learning network[J/OL]. Power System Technology, 2022:1-14[2023-03-12].https://doi.org/10.13335/j.1000-3673.pst.2022.1492.
[18]	朱继忠, 董瀚江, 李盛林, 等. 数据驱动的综合能源系统负荷预测综述[J]. 中国电机工程学报, 2021, 41(23): 7905-7924.
	ZHU Jizhong, DONG Hanjiang, LI Shenglin, et al. Review of data-driven load forecasting for integrated energy system[J]. Proceedings of the CSEE, 2021, 41(23):7905-7924.
[19]	SUGIHARA G, MAY R, YE H, et al. Detecting causality in complex ecosystems[J]. Science, 2012, 338(6106): 496-500. doi: 10.1126/science.1227079 pmid: 22997134
[20]	WANG C, SHE Z, CAO L. Coupled attribute analysis on numerical data[C]// 23rd International Joint Conference on Artificial Intelligence. Beijing, 2013:3-9.
[21]	金立, 张力, 任炬光, 等. 针对气象敏感型综合能源负荷的收敛交叉映射因果关系分析[J]. 综合智慧能源, 2023, 45(1):23-30. doi: 10.3969/j.issn.2097-0706.2023.01.003
	JIN Li, ZHANG Li, REN Juguang, et al. Causality analysis of climate sensitive loads in integrated energy system based on convergence cross-mapping method[J]. Integrated Intelligent Energy, 2023, 45(1):23-30. doi: 10.3969/j.issn.2097-0706.2023.01.003
[22]	ASU. Campus metabolism[EB/OL].(2021-05-13)[2023-03-12]. http://cm.asu.edu/.
[23]	NSRDB data viewer[EB/OL].(2021-05-13)[2023-03-12]. https://maps.nrel.gov/nsrdb-viewer/.

项目	参数
核函数	高斯核函数
优化器	Adam
学习率	0.001
隐含层层数	2
隐含层神经元数量	20
epoch	100
训练批次大小	32
学习率下降因子	0.9
交叉验证次数	10

模型	电负荷		冷负荷
模型	δ_RMSE/kW	δ_MAPE/%	δ_RMSE /kW	δ_MAPE/%
1	1 025	2.66	2 167	2.92
2	1 325	3.43	3 425	4.78
3	1 514	4.07	3 820	5.06
4	1 444	3.83	2 493	3.47
均值	1 327	3.50	2 976	4.06