1.东南大学电气工程学院,江苏省南京市 210096
2.无锡学院自动化学院,江苏省无锡市 214105
3.国家电网有限公司华东分部,上海市 200120
杨沈生(2001—),男,硕士研究生,主要研究方向:需求侧管理。E-mail:1922273481@qq.com
胥鹏(1994—),男,博士,主要研究方向:数据挖掘、人工智能在电力系统中的应用。E-mail:272223671@qq.com
王蓓蓓(1979—),女,通信作者,博士,研究员,主要研究方向:电力市场、需求侧管理等。E-mail:wangbeibei@seu.edu.cn
收稿:2025-04-05,
修回:2025-07-23,
网络首发:2025-10-31,
纸质出版:2026-01-10
移动端阅览
杨沈生,胥鹏,王蓓蓓等.异源数据下综合需求响应画像建模及响应能力评估[J].电力系统自动化,2026,50(1):178-187.
YANG Shensheng,XU Peng,WANG Beibei,et al.Profiling Modeling and Response Capability Assessment of Integrated Demand Response Based on Heterogeneous Data[J].Automation of Electric Power Systems,2026,50(1):178-187.
杨沈生,胥鹏,王蓓蓓等.异源数据下综合需求响应画像建模及响应能力评估[J].电力系统自动化,2026,50(1):178-187. DOI: 10.7500/AEPS20250405003.
YANG Shensheng,XU Peng,WANG Beibei,et al.Profiling Modeling and Response Capability Assessment of Integrated Demand Response Based on Heterogeneous Data[J].Automation of Electric Power Systems,2026,50(1):178-187. DOI: 10.7500/AEPS20250405003.
综合需求响应(IDR)作为能源互联网发展的重要产物,是需求侧参与电网互动的关键手段之一。其响应方式主要包括能源替代与能源时段转移,具有用户舒适度高、响应积极性强、响应潜力大及不确定性较小等显著优势,展现出广阔的发展潜力。首先
分析IDR的机理及考虑异源数据的IDR画像建模。随后,针对电-气综合能源系统用户,基于纵向联邦学习方法构建气替代模型,并结合消费者心理学模型构建电负荷转移模型,刻画用户需求响应特性。最后,通过耦合电负荷转移模型与气替代模型,建立电-气IDR画像,实现基于价格数据驱动的用户响应潜力精准刻画。算例结果表明,所构建的IDR画像模型充分考虑了异源数据下电-气两种能源的耦合与协调性,能够有效刻画电-气综合能源系统用户的响应能力,为能源系统优化调度提供了科学依据。
As a key outcome of Energy Internet development
integrated demand response (IDR) serves as an essential approach for enabling demand-side participation in interactions with the power grid. Its response methods mainly include energy substitution and energy time-shift
and it has significant advantages such as high user comfort level
strong response enthusiasm
large response potential
and relatively low uncertainty
thereby demonstrating broad development potential. First
the mechanisms of IDR are analyzed and an IDR profiling model that incorporates heterogeneous data is developed. Subsequently
for users in electricity-gas integrated energy systems
a gas substitution model is constructed based on vertical federated learning
while a power load shifting model is developed by integrating consumer psychology models to describe the characteristics of user demand response. Finally
by coupling the power load shifting model with the gas substitution model
an electricity-gas IDR profile is established to realize the precise characterization of user response potential based on price data. Case studies indicate that the proposed profiling model of IDR effectively considers the coupling and coordination between electricity and gas based on heterogeneous data
and can effectively characterize the response capabilities of users in electricity-gas integrated energy system
which provides a scientific basis for the optimal dispatching of energy systems.
ZHANG D D , ZHU H Y , ZHANG H C , et al . Multi-objective optimization for smart integrated energy system considering demand responses and dynamic prices [J]. IEEE Transactions on Smart Grid , 2022 , 13 ( 2 ): 1100 - 1112 .
ZHAO N , WANG B B , BAI L Q , et al . Quantitative model of the electricity-shifting curve in an energy hub based on aggregated utility curve of multi-energy demands [J]. IEEE Transactions on Smart Grid , 2021 , 12 ( 2 ): 1329 - 1345 .
李伊竹林 , 韩肖清 , 李廷钧 , 等 . 基于动态电-碳需求响应的综合能源系统日前多元低碳交易方法 [J]. 电力系统自动化 , 2024 , 48 ( 12 ): 24 - 35 .
LI Yizhulin , HAN Xiaoqing , LI Tingjun , et al . Multi-day low-carbon trading method for integrated energy systems based on dynamic electricity-carbon demand response [J]. Automation of Electric Power Systems , 2024 , 48 ( 12 ): 24 - 35 .
LI C Y , YAN Z C , YAO Y M , et al . Coordinated low-carbon dispatching on source-demand side for integrated electricity-gas system based on integrated demand response exchange [J]. IEEE Transactions on Power Systems , 2024 , 39 ( 1 ): 1287 - 1303 .
RUAN J Q , LIANG G Q , ZHAO J H , et al . Graph deep-learning-based retail dynamic pricing for demand response [J]. IEEE Transactions on Smart Grid , 2023 , 14 ( 6 ): 4385 - 4397 .
MASSRUR H R , FOTUHI-FIRUZABAD M , DEHGHANIAN P , et al . Fog-based hierarchical coordination of residential aggregators and household demand response with power distribution grids: Part Ⅰ: solution design [J]. IEEE Transactions on Power Systems , 2025 , 40 ( 1 ): 85 - 98 .
ZHANG Y R , GE X X , LI M Y , et al . Demand response potential day-ahead forecasting approach based on LSSA-BPNN considering the electricity-carbon coupling incentive effects [J]. IEEE Transactions on Industry Applications , 2024 , 60 ( 3 ): 4505 - 4516 .
范宇辉 , 姜婷玉 , 黄奇峰 , 等 . 基于画像的工业园区需求响应潜力评估 [J]. 电力系统自动化 , 2024 , 48 ( 1 ): 41 - 49 .
FAN Yuhui , JIANG Tingyu , HUANG Qifeng , et al . Demand response potential assessment of industrial parks based on profiling [J]. Automation of Electric Power Systems , 2024 , 48 ( 1 ): 41 - 49 .
刘涛 , 王瑞琪 , 刘松 , 等 . 考虑碳-绿证交易与需求响应的综合能源系统合作博弈调度 [J]. 电力需求侧管理 , 2024 , 26 ( 6 ): 8 - 15 .
LIU Tao , WANG Ruiqi , LIU Song , et al . Cooperative game scheduling of integrated energy systems considering carbon-green certificate trading and demand response [J]. Electric Power Demand Side Management , 2024 , 26 ( 6 ): 8 - 15 .
黄奇峰 , 杨世海 , 段梅梅 , 等 . 负荷数据特征分析的用户集群需求响应潜力预测方法 [J]. 电力需求侧管理 , 2024 , 26 ( 1 ): 16 - 22 .
HUANG Qifeng , YANG Shihai , DUAN Meimei , et al . A method for predicting user cluster demand response potential based on load data feature analysis [J]. Power Demand Side Management , 2024 , 26 ( 1 ): 16 - 22 .
王蓓蓓 , 胥鹏 , 王宣元 , 等 . 需求响应分布鲁棒建模及其大规模潜力推演方法 [J]. 电力系统自动化 , 2022 , 46 ( 3 ): 33 - 41 .
WANG Beibei , XU Peng , WANG Xuanyuan , et al . Demand response distributed robust modeling and large-scale potential deduction method [J]. Automation of Electric Power Systems , 2022 , 46 ( 3 ): 33 - 41 .
SHI S , GAO Q , JI Y , et al . A supply-demand optimization strategy for integrated energy system considering integrated demand response and electricity-heat-hydrogen hybrid energy storage [J]. Sustainable Energy, Grids and Networks , 2025 , 42 : 101658 - 101658 ..
魏春晖 , 单林森 , 胡大栋 , 等 . 面向需求响应的园区虚拟电厂优化调度策略 [J]. 中国电力 , 2025 , 58 ( 6 ): 112 - 121 .
WEI Chunhui , SHAN Linsen , HU Dadong , et al . Optimization scheduling strategy for park virtual power plants oriented to demand response [J]. China Electric Power , 2025 , 58 ( 6 ): 112 - 121 .
郭光华 , 亓新宏 , 王瑞琪 , 等 . 基于联邦学习的综合能源系统集成需求响应机制 [J]. 电力自动化设备 , 2023 , 43 ( 8 ): 33 - 39 .
GUO Guanghua , QI Xinhong , WANG Ruiqi , et al . Integrated demand response mechanism of integrated energy system based on federated learning [J]. Electric Power Automation Equipment , 2023 , 43 ( 8 ): 33 - 39 .
杨文伟 , 彭显刚 , 全欢 , 等 . 基于联邦强化学习的主动配电网多主体博弈协同优化策略 [J]. 电力系统自动化 , 2025 , 49 ( 13 ): 70 - 82 .
YANG Wenwei , PENG Xiangang , QUAN Huan , et al . Multi-agent game collaborative optimization strategy for active distribution networks based on federated reinforcement learning [J]. Automation of Electric Power Systems , 2025 , 49 ( 13 ): 70 - 82 .
陈明昊 , 孙毅 , 胡亚杰 , 等 . 基于纵向联邦强化学习的居民社区综合能源系统协同训练与优化管理方法 [J]. 中国电机工程学报 , 2022 , 42 ( 15 ): 5535 - 5550 .
CHEN Minghao , SUN Yi , HU Yajie , et al . A collaborative training and optimization management method for comprehensive energy systems of residential communities based on vertical federated reinforcement learning [J]. Proceedings of the CSEE , 2022 , 42 ( 15 ): 5535 - 5550 .
仲林林 , 刘柯妤 . 面向电力巡检图像目标检测的联邦学习激励机制 [J]. 电工技术学报 , 2024 , 39 ( 17 ): 5434 - 5449 .
ZHONG Linlin , LIU Keyu . Federated learning incentive mechanism for target detection in power inspection images [J]. Transactions of China Electrotechnical Society , 2024 , 39 ( 17 ): 5434 - 5449 .
GUO X , LUO F , ZHAO Z , et al . Federated personalized home BESS recommender system based on neural collaborative filtering [J]. International Journal of Electrical Power and Energy Systems , 2024 , 159 : 110042 .
冯昌森 , 钱燚飞 , 邵亮 , 等 . 考虑特征缺失的个性化居民短期负荷预测 [J]. 电力系统自动化 , 2025 , 49 ( 16 ): 75 - 84 .
FENG Changsen , QIAN Yifei , SHAO Liang , et al . Personalized short-term residential load forecasting considering missing feature [J]. Automation of Electric Power Systems , 2025 , 49 ( 16 ): 75 - 84 .
陈明亮 , 卢志学 , 谢国强 , 等 . 基于半监督联邦学习的分布式电源调控安全威胁协同检测 [J]. 电力系统自动化 , 2024 , 48 ( 22 ): 199 - 209 .
CHEN Mingliang , LU Zhixue , XIE Guoqiang , et al . Collaborative detection of distributed power supply control security threats based on semi-supervised federated learning [J]. Automation of Electric Power Systems , 2024 , 48 ( 22 ): 199 - 209 .
ZHENG S L , SUN Y , QI B , et al . Incentive-based integrated demand response considering S&C effect in demand side with incomplete information [J]. IEEE Transactions on Smart Grid , 2022 , 13 ( 6 ): 4465 - 4482 .
罗凯鸿 , 徐茹枝 , 夏迪娅 , 等 . 基于匿名性差分隐私联邦学习的负荷预测模型训练方法 [J]. 电力信息与通信技术 , 2024 , 22 ( 11 ): 25 - 33 .
LUO Kaihong , XU Ruzhi , XIA Diya , et al . Load forecasting model training method based on anonymous differential privacy federated learning [J]. Electric Power Information and Communication Technology , 2024 , 22 ( 11 ): 25 - 33 .
吴严杰 , 平健 , 严正 , 等 . 基于差分隐私的多园区综合能源系统分布式调度方法 [J]. 电力系统自动化 , 2025 , 49 ( 5 ): 80 - 88 .
WU Yanjie , PING Jian , YAN Zheng , et al . Distributed scheduling method for multi-park integrated energy systems based on differential privacy [J]. Automation of Electric Power Systems , 2025 , 49 ( 5 ): 80 - 88 .
邢晓萱 , 巩敦卫 , 孙晓燕 , 等 . 基于重构误差和极端模式识别的综合能源系统短期负荷预测 [J]. 中国电机工程学报 , 2024 , 44 ( 9 ): 3476 - 3489 .
XING Xiaoxuan , GONG Dunwei , SUN Xiaoyan , et al . Short-term load forecasting of integrated energy system based on reconstruction error and extreme mode identification [J]. Proceedings of the CSEE , 2024 , 44 ( 9 ): 3476 - 3489 .
罗萍萍 , 盛奥 , 林济铿 , 等 . 基于可解释性条件生成对抗网络的台风气象负荷场景生成方法 [J]. 电力系统自动化 , 2025 , 49 ( 2 ): 186 - 197 .
LUO Pingping , SHENG Ao , LIN Jikeng , et al . Typhoon meteorological load scenario generation method based on explainable conditional generative adversarial networks [J]. Automation of Electric Power Systems , 2025 , 49 ( 2 ): 186 - 197 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621