面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判

doi:10.11930/j.issn.1004-9649.202307100

中国电力 ›› 2024, Vol. 57 ›› Issue (1): 9-17.DOI: 10.11930/j.issn.1004-9649.202307100

面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判

周颖¹(), 白雪峰²(), 王阳³(), 邱敏¹(), 孙冲⁴(), 武亚杰¹(), 李彬²()

1. 需求侧多能互补优化与供需互动技术北京市重点实验室（中国电力科学研究院有限公司），北京　100192
2. 华北电力大学电气与电子工程学院，北京　102206
3. 国家电网有限公司，北京　100031
4. 国网河北省电力有限公司营销服务中心，河北石家庄　050081

收稿日期:2023-07-26 接受日期:2023-11-20 出版日期:2024-01-28 发布日期:2024-01-23
作者简介:周颖（1993—），女，硕士，工程师，从事电力电量分析预测研究，E-mail：hgzhouying@163.com
白雪峰（1997—），男，硕士研究生，从事电力电量分析预测研究，E-mail：884973072@qq.com
王阳（1985—），女，博士，高级工程师，从事电力电量分析预测研究，E-mail：wang-yang@sgcc.com.cn
邱敏（1992—），男，博士，工程师，从事电力电量分析预测研究，E-mail：qiumin@epri.sgcc.com.cn
孙冲（1983—），男，高级工程师，从事电力电量分析预测研究，E-mail：sunchong@163.com.cn
武亚杰（1993—），男，从事电力电量分析预测研究，E-mail：wuyajie@epri.sgcc.com.cn
李彬（1983—），男，通信作者，博士，副教授，从事需求响应和负荷预测研究，E-mail：direfish@163.com
基金资助:
国家电网有限公司科技项目（支撑重过载台区治理的区域供用电综合预测与智能预警技术研究与应用，5108-202218280A-2-379-XG）。

Analysis and Evolution Trend of Temperature-Sensitive Loads for Virtual Power Plant Operation

Ying ZHOU¹(), Xuefeng BAI²(), Yang WANG³(), Min QIU¹(), Chong SUN⁴(), Yajie WU¹(), Bin LI²()

1. Beijing Key Laboratory of Demand Side Multi-Energy Carriers Optimization and Interaction Technique (China Electric Power Research Institute), Beijing 100192, China
2. Department of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China
3. State Grid Coporation of China, Beijing 100031, China
4. Marketing Service Center of State Grid Hebei Electric Power Co., Ltd., Shijiazhuang 050081, China

Received:2023-07-26 Accepted:2023-11-20 Online:2024-01-28 Published:2024-01-23
Supported by:
This work is supported by Science and Technology Project of SGCC (Regional Power Supply and Consumption Comprehensive Pre-Treatment Supporting Heavy Overload Station Area Governance, No.5108-202218280A-2-379-XG).

摘要/Abstract

摘要：

随着极端天气频发，温度敏感负荷用电逐年攀升，温度敏感负荷作为虚拟电厂优质的调控资源，亟须分析气象变化对于此类负荷的影响，由于叠加极端高温、大规模寒潮等异常天气的影响，温度敏感负荷波动剧烈，常规分析预测方法难以适应极端气象场景。针对寒潮天气下温度敏感负荷样本数据及预测精度不足的问题，提出寒潮天气小样本条件下的温度敏感负荷日最大负荷预测方法。该方法先采用时序对抗生成网络（TimeGAN）扩充寒潮期间小样本数据，再采用卷积-长短时记忆神经网络（CNN-LSTM）对寒潮期间的日最大负荷进行预测。以国内某省近两年迎峰度冬期间数据进行模型验证，结果表明所提模型优于其他模型的预测结果，在验证集上日最大负荷的预测精度为99.5%。

关键词: 温度敏感负荷预测, 寒潮, 时间序列生成对抗网络, 虚拟电厂, 卷积神经网络, 长短时记忆神经网络

Abstract:

With the frequent occurrence of extreme weather, the electricity consumption of temperature-sensitive loads is increasing year by year. As a high-quality regulation resource of virtual power plant (VPP), temperature-sensitive loads urgently need to be analyzed for the impact of meteorological changes on them. Due to the influence of abnormal weather such as extreme high temperature and large-scale cold waves, temperature-sensitive loads fluctuate violently. Conventional analysis and prediction methods are not adaptable to the extreme meteorological scenarios. Aiming at the problem of insufficient sample data and prediction accuracy of temperature-sensitive loads under cold wave weather, this paper proposes a daily maximum load prediction method for temperature-sensitive loads under the condition of small sample in cold wave weather. In this method, the TimeGAN is used to expand the small sample data during the cold wave period, and then the CNN-LSTM network is used to predict the daily maximum load during the cold wave period. Finally, the model is verified by the load data of a province in China during the winter period in the past two years. The results show that the prediction results of the proposed model are better than those of other models, with the prediction accuracy of the daily maximum load on the verification set being 99.5%.

Key words: temperature sensitive load forecasting, cold wave, time series generative adversarial network, virtual power plant, convolutional neural network, long short-term memory neural network

周颖, 白雪峰, 王阳, 邱敏, 孙冲, 武亚杰, 李彬. 面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判[J]. 中国电力, 2024, 57(1): 9-17.

Ying ZHOU, Xuefeng BAI, Yang WANG, Min QIU, Chong SUN, Yajie WU, Bin LI. Analysis and Evolution Trend of Temperature-Sensitive Loads for Virtual Power Plant Operation[J]. Electric Power, 2024, 57(1): 9-17.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202307100

https://www.electricpower.com.cn/CN/Y2024/V57/I1/9

图/表 8

图 1 TimeGAN架构及本文改进的TimeGAN架构

Fig.1 The TimeGAN architecture and the improved TimeGAN architecture in this paper

图 2 TimeGAN-CNN-LSTM模型流程示意

Fig.2 The TimeGAN-CNN-LSTM model flowchart

表 1 各气象指标与不同负荷相关系数

Table 1 The correlation coefficient between meteorological factors and different loads

项目	相关系数
项目	总负荷	温度敏感负荷	基础负荷
最高温度	–0.69	–0.74	–0.34
平均温度	–0.72	–0.77	–0.20
最低温度	–0.70	–0.74	–0.32
风速	–0.44	–0.23	0.17
湿度	0.15	0.20	–0.16
寒湿指数	0.70	0.67	0.35
体感温度	–0.75	–0.78	–0.28
人体舒适度	–0.74	–0.77	–0.34

图 3 平均温度的合成样本与真实样本分布情况

Fig.3 Distribution of synthetic and real samples of average temperature

图 4 负荷的合成样本与真实样本分布情况

Fig.4 Distribution of synthetic and real samples of load

图 5 不同算法对总负荷的预测结果

Fig.5 The prediction results of each algorithm for total load direct prediction

图 6 对各算法温度敏感负荷预测值+基础负荷的预测结果

Fig.6 The prediction results of each algorithm with the predicted value of temperature sensitive load + basic load

表 2 误差分析

Table 2 Error analysis

模型方法	直接预测总负荷		预测温度敏感负荷+ 基础负荷
模型方法	E_MA/(万kW)	E_MAP/%	E_MA/(万kW)	E_MAP/%
多元线性回归	86.11	0.99	82.68	0.96
BP神经网络	158.88	1.82	150.06	1.74
LSTM	171.19	1.95	78.20	0.91
CNN-LSTM	159.60	1.83	75.10	0.86
TimeGAN-CNN-LSTM	51.20	0.59	39.98	0.46

参考文献 29

1	辛保安: 2022年国家电网全年电网投资超5000亿元[EB/OL]. (2023-01-12) [2023-03-12]. http://hn.people.com.cn/GB/n2/2023/0112/c356884-40263848.html.
2	赵建立, 向佳霓, 汤卓凡, 等. 虚拟电厂在上海的实践探索与前景分析[J]. 中国电力, 2023, 56 (2): 1- 13.
	ZHAO Jianli, XIANG Jiani, TANG Zhuofan, et al. Practice exploration and prospect analysis of virtual power plant in Shanghai[J]. Electric Power, 2023, 56 (2): 1- 13.
3	康重庆, 陈启鑫, 苏剑, 等. 新型电力系统规模化灵活资源虚拟电厂科学问题与研究框架[J]. 电力系统自动化, 2022, 46 (18): 3- 14. DOI
	KANG Chongqing, CHEN Qixin, SU Jian, et al. Scientific problems and research framework of virtual power plant with enormous flexible distributed energy resources in new power system[J]. Automation of Electric Power Systems, 2022, 46 (18): 3- 14. DOI
4	谢敏, 邓佳梁, 刘明波, 等. 基于气象信息和熵权理论的降温负荷估算方法[J]. 电力系统自动化, 2016, 40 (3): 135- 139. DOI
	XIE Min, DENG Jialiang, LIU Mingbo, et al. Temperature-lowering load estimation method based on meteorological data and entropy weight theory[J]. Automation of Electric Power Systems, 2016, 40 (3): 135- 139. DOI
5	殷跃. 重庆电网夏季高峰负荷特性分析及优化措施[J]. 宁夏电力, 2021, (5): 28- 33, 43.
	YIN Yue. Characteristic analysis of summer peak load and optimization measures in Chongqing power grid[J]. Ningxia Electric Power, 2021, (5): 28- 33, 43.
6	史静, 周琪, 谈健, 等. 江苏电网夏季空调负荷特性挖掘与温度敏感性辨识[J]. 电力工程技术, 2018, 37 (3): 28- 32.
	SHI Jing, ZHOU Qi, TAN Jian, et al. The load excavation and temperature sensitivity identification of air conditioning in summer of Jiangsu power grid[J]. Electric Power Engineering Technology, 2018, 37 (3): 28- 32.
7	袁斌. 陕西电网夏季降温负荷与温度相关性研究[J]. 电网与清洁能源, 2020, 36 (6): 19- 24, 30.
	YUAN Bin. Correlation analysis of cooling load and temperature in Shaanxi power grid in summer[J]. Power System and Clean Energy, 2020, 36 (6): 19- 24, 30.
8	郭占伍, 张泽亚, 周兴华, 等. 考虑气象因素的电采暖负荷预测研究[J]. 电测与仪表, 2022, 59 (2): 154- 158.
	GUO Zhanwu, ZHANG Zeya, ZHOU Xinghua, et al. Study on forecasting method of electric heating load considering meteorological factors[J]. Electrical Measurement & Instrumentation, 2022, 59 (2): 154- 158.
9	张航, 杨靖, 李昊霖. 基于改进回归模型的电网降温负荷预测[J]. 控制工程, 2023, 30 (3): 513- 519.
	ZHANG Hang, YANG Jing, LI Haolin. Power grid cooling load forecast based on improved regression model[J]. Control Engineering of China, 2023, 30 (3): 513- 519.
10	金丽莉, 谭风雷, 吴志坚, 等. 考虑积温效应的负荷预测研究[J]. 电力需求侧管理, 2013, 15 (1): 7- 10, 14. DOI
	JIN Lili, TAN Fenglei, WU Zhijian, et al. The study of load forecasting accounting accumulated temperature effect[J]. Power Demand Side Management, 2013, 15 (1): 7- 10, 14. DOI
11	董莉娜, 张志劲, 王茂政. 基于历史天气的区域电网负荷预测的研究[J/OL]. 中国测试: 1–7[2023-06-16]. https://kns.cnki.net/kcms/detail/51.1714.TB.20210722.0952.002.html.
	DONG Lina, ZHANG Zhijin, WANG Maozheng. Research on regional power grid load forecasting based on historical weather[J/OL]. China Measurement & Test: 1–7[2023-06-16]. https://kns.cnki.net/kcms/detail/51.1714.TB.20210722.0952.002.html.
12	苏振宇, 龙勇, 赵丽艳. 基于regARIMA模型的月度负荷预测效果研究[J]. 中国电力, 2018, 51 (5): 166- 171.
	SU Zhenyu, LONG Yong, ZHAO Liyan. Study on the monthly power load forecasting performance based on regARIMA model[J]. Electric Power, 2018, 51 (5): 166- 171.
13	成丹, 刘静, 郭淳薇, 等. 基于积温效应的华中电网电力负荷预测[J]. 气象科技, 2018, 46 (4): 814- 821.
	CHENG Dan, LIU Jing, GUO Chunwei, et al. Prediction of electric loads over central China based on accumulated temperature effect[J]. Meteorological Science and Technology, 2018, 46 (4): 814- 821.
14	李晨熙. 基于ARIMA模型的短期电力负荷预测[J]. 吉林电力, 2015, 43 (6): 22- 24.
	LI Chenxi. A short-term load forecasting model based on ARIMA[J]. Jilin Electric Power, 2015, 43 (6): 22- 24.
15	李明节, 梁志峰, 许涛, 等. 基于敏感气温空间分布的度夏度冬日最大负荷预测与应用研究[J]. 电网技术, 2023, 47 (3): 1088- 1098. DOI
	LI Mingjie, LIANG Zhifeng, XU Tao, et al. Prediction and application of maximum daily load in summer and winter based on spatial distribution of sensitive temperatures[J]. Power System Technology, 2023, 47 (3): 1088- 1098. DOI
16	CIECHULSKI T, OSOWSKI S. High precision LSTM model for short-time load forecasting in power systems[J]. Energies, 2021, 14 (11): 2983. DOI
17	贾巍, 黄裕春. 基于小样本数据差分扩容的微电网负荷预测方法[J]. 中国电力, 2023, 56 (8): 151- 156, 165.
	JIA Wei, HUANG Yuchun. Method of load forecasting in microgrid based on differential expansion of small sample data[J]. Electric Power, 2023, 56 (8): 151- 156, 165.
18	STEADMAN R G. A universal scale of apparent temperature[J]. Journal of Climate and Applied Meteorology, 1984, 23 (12): 1674- 1687. DOI
19	王汶, 彭爱珺, 张佳丽, 等. 基于体感温度的中国供暖需求分区[J]. 长江流域资源与环境, 2019, 28 (1): 12- 20.
	WANG Wen, PENG Aijun, ZHANG Jiali, et al. Heating demand zoning in China based on apparent temperature[J]. Resources and Environment in the Yangtze Basin, 2019, 28 (1): 12- 20.
20	王惠中, 刘轲, 周佳. 基于综合气象指数和日期类型的电力系统负荷预测[J]. 电网与清洁能源, 2015, 31 (9): 67- 71. DOI
	WANG Huizhong, LIU Ke, ZHOU Jia. Power system load forecasting based on comprehensive meteorological index and date type[J]. Power System and Clean Energy, 2015, 31 (9): 67- 71. DOI
21	黄佳. 全天候电网特殊日短期负荷预测建模[D]. 南宁: 广西大学, 2017.
	HUANG Jia. Modeling of power system short-term load forecasting for special day in all-weather[D]. Nanning: Guangxi University, 2017.
22	许飞. 基于机器学习的短期负荷预测[D]. 广州: 华南理工大学, 2020.
	XU Fei. Short-term load forecasting based on machine learning[D]. Guangzhou: South China University of Technology, 2020.
23	中国气象局: 寒潮定义和标准[EB/OL]. (2018-11-19) [2023-03-19].https://www.cma.gov.cn/2011xzt/kpbd/ColdWave/2018050901/201811/t20181119_483585.html.
24	YOON J , JARRETT D , SCHAAR M . Time-series generative adversarial networks[C]// Neural Information Processing Systems (NeurIPS). 2019.
25	林珊, 王红, 齐林海, 等. 基于条件生成对抗网络的短期负荷预测[J]. 电力系统自动化, 2021, 45 (11): 52- 60. DOI
	LIN Shan, WANG Hong, QI Linhai, et al. Short-term load forecasting based on conditional generative adversarial network[J]. Automation of Electric Power Systems, 2021, 45 (11): 52- 60. DOI
26	叶林, 李奕霖, 裴铭, 等. 寒潮天气小样本条件下的短期风电功率组合预测[J]. 中国电机工程学报, 2023, 43 (2): 543- 555. DOI
	YE Lin, LI Yilin, PEI Ming, et al. Combined approach for short-term wind power forecasting under cold weather with small sample[J]. Proceedings of the CSEE, 2023, 43 (2): 543- 555. DOI
27	郭威, 史运涛. 基于空间域图像生成和混合卷积神经网络的配电网故障选线方法[J/OL]. 电网技术: 1–14[2023-03-22]. http://kns.cnki.net/kcms/detail/11.2410.tm.20230310.1705.003.html.
	Guo Wei, Shi Yuntao. A Fault Line Selection Method for Distribution Network Based on Spatial Domain Image Generation and Hybrid Convolutional Neural Network [J/OL]. Power System Technology: 1–14 [2023-03-22]. http://kns.cnki.net/kcms/detail/11.2410.tm.20230310.1705.003.html.
28	余昊杨, 武昕. 基于一维卷积神经网络的非侵入工业负荷事件检测方法[J]. 计算机应用, 2022, 42 (S2): 277- 284.
	YU Haoyang, WU Xin. Non-invasive industrial load event detection method based on one-dimensional convolutional neural network[J]. Journal of Computer Applications, 2022, 42 (S2): 277- 284.
29	张未, 余成波, 王士彬, 等. 基于VMD-LSTM-LightGBM的多特征短期电力负荷预测[J]. 南方电网技术, 2023, 17 (2): 74- 81. DOI
	ZHANG Wei, YU Chengbo, WANG Shibin, et al. Multi-featured short-term power load forecasting based on VMD-LSTM-LightGBM[J]. Southern Power System Technology, 2023, 17 (2): 74- 81. DOI

[1]	李明冰, 李强, 管西洋, 周皓阳, 卢瑞, 冯延坤. 市场环境下考虑多元用户侧资源协同的虚拟电厂低碳优化调度[J]. 中国电力, 2025, 58(2): 66-76.
[2]	杨珂, 王栋, 李达, 张王俊, 向尕, 李军. 虚拟电厂网络安全风险评估指标体系构建及量化计算[J]. 中国电力, 2024, 57(8): 130-137.
[3]	吴军英, 路欣, 刘宏, 张彬, 柴守亮, 刘蕴春, 王佳楠. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140.
[4]	娄奇鹤, 李荣盛, 谭捷, 袁铁江. 基于卷积神经网络的暂稳极限功率计算[J]. 中国电力, 2024, 57(4): 211-219.
[5]	仪忠凯, 侯朗博, 徐英, 吴永峰, 李志民, 吴俊飞, 冯腾, 韩柳. 市场环境下灵活性资源虚拟电厂聚合调控关键技术综述[J]. 中国电力, 2024, 57(12): 82-96.
[6]	宋天琦, 吕志鹏, 宋振浩, 马韵婷, 张智慧, 周珊, 李昊. 虚拟电厂规模化灵活资源聚合调控框架研究与思考[J]. 中国电力, 2024, 57(1): 2-8.
[7]	朱睿, 欧乙丁, 李筱天, 雷星雨, 周宇晴, 张珀扬, 欧睿. 基于外特性等值的虚拟电厂灵活性资源价值评估[J]. 中国电力, 2024, 57(1): 30-39.
[8]	谢蒙飞, 马高权, 刘斌, 潘振宁, 商云峰. 基于信息差距决策理论的虚拟电厂报价策略[J]. 中国电力, 2024, 57(1): 40-50.
[9]	冯云辰, 加鹤萍, 闫敏, 李根柱, 刘乐, 刘敦楠. 基于风电分时电价的虚拟电厂参与清洁供暖运营优化方法[J]. 中国电力, 2024, 57(1): 51-60.
[10]	周挺, 谭玉东, 孙晋, 文明, 廖菁, 李杨, 刘巩, 刘敦楠. 虚拟电厂参与能量与辅助服务市场的协同优化策略[J]. 中国电力, 2024, 57(1): 61-70.
[11]	张书涵, 艾芊, 李晓露, 王帝. 适用于多虚拟电厂交易的改进拜占庭容错算法共识机制[J]. 中国电力, 2024, 57(1): 71-81, 157.
[12]	张颖, 文艳, 季宇, 左娟, 王文博. 基于目标级联法的虚拟电厂日前调频容量计算方法[J]. 中国电力, 2024, 57(1): 82-90.
[13]	张超, 赵冬梅, 季宇, 张颖. 基于改进深度Q网络的虚拟电厂实时优化调度[J]. 中国电力, 2024, 57(1): 91-100.
[14]	王世杰, 冯天波, 孙宁, 何可, 李嘉文, 杨程, 崔昊杨. 考虑电-气-热耦合和需求响应的虚拟电厂优化调度策略[J]. 中国电力, 2024, 57(1): 101-114.
[15]	王大兴, 宁妍, 汪敬培, 徐洋, 毕峻, 周铭标, 王鹏. 构建新型电力系统背景下的微电网鲁棒简化建模[J]. 中国电力, 2024, 57(1): 148-157.

面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判

Analysis and Evolution Trend of Temperature-Sensitive Loads for Virtual Power Plant Operation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 29

相关文章 15

编辑推荐

Metrics

模态框（Modal）标题

面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判

Analysis and Evolution Trend of Temperature-Sensitive Loads for Virtual Power Plant Operation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 29

相关文章 15

编辑推荐

Metrics