
1.华南理工大学电力学院,广东省广州市 510640
2.广东省电网智能量测与先进计量企业重点实验室,广东省广州市 510640
Received:04 July 2025,
Revised:2026-01-03,
Online First:06 July 2026,
Published:25 September 2026
移动端阅览
郑焕新,余涛,吴毓峰等.需求响应收益导向的虚拟电厂多时段等效负荷预测方法[J].电力系统自动化,2026,50(18):68-79.
ZHENG Huanxin,YU Tao,WU Yufeng,et al.Demand Response Revenue-oriented Multi-period Equivalent Load Forecasting Method for Virtual Power Plants[J].Automation of Electric Power Systems,2026,50(18):68-79.
郑焕新,余涛,吴毓峰等.需求响应收益导向的虚拟电厂多时段等效负荷预测方法[J].电力系统自动化,2026,50(18):68-79. DOI: 10.7500/AEPS20250704003.
ZHENG Huanxin,YU Tao,WU Yufeng,et al.Demand Response Revenue-oriented Multi-period Equivalent Load Forecasting Method for Virtual Power Plants[J].Automation of Electric Power Systems,2026,50(18):68-79. DOI: 10.7500/AEPS20250704003.
在日前邀约型需求响应中,虚拟电厂等效负荷预测结果直接影响其申报决策与运行收益。然而,传统预测方法致力于实现预测精度的最大化,忽视了预测偏差和决策收益损失的不对称关系,这反而可能造成收益的降低。为此,文中提出一种需求响应收益导向的虚拟电厂多时段等效负荷预测方法。首先,揭示了等效负荷预测精度提升与虚拟电厂收益改善的非一致性,并构建了虚拟电厂需求响应的两阶段决策模型;其次,设计了“精度导向训练+决策导向微调”的框架,利用代理网络实现对决策模型预测偏差收益损失的有效表征;最后,针对多时段耦合决策下代理网络学习困难问题,提出多时段解耦表征的局部决策导向损失函数学习方法,通过单时段局部损失的聚合学习,实现多时段局部决策导向损失函数的近似刻画。算例结果表明,相比于精度导向方法,所得预测结果可显著提升虚拟电厂的需求响应收益。
In the day-ahead invitation-based demand response
the equivalent load forecasting results of virtual power plants (VPPs) directly affect their bidding decisions and operation revenues. However
traditional forecasting methods aim at maximizing forecasting accuracy but neglect the asymmetric relationship between forecasting deviations and decision-induced revenue loss
which may lead to revenue reduction. To address this
this paper proposes a revenue-oriented multi-period equivalent load forecasting method for VPPs participating in demand response. Firstly
this paper reveals the inconsistency between equivalent load forecasting accuracy improvement and VPP revenue enhancement
and constructs a two-stage decision-making model for VPP demand response. Secondly
a framework of “accuracy-oriented training + decision-oriented fine-tuning” is designed
utilizing a surrogate network to effectively characterize the revenue loss caused by forecasting deviations of the decision-making model. Finally
to tackle the learning difficulty for surrogate networks under multi-period coupling decision-making
a local decision-oriented loss function learning method with multi-period decoupling representation is proposed to approximately characterize the multi-period local decision-oriented loss function by the aggregated learning of single-period local losses. Numerical case results demonstrate that
compared with accuracy-oriented methods
the obtained forecasting results can significantly enhance the demand response revenue of VPPs.
田富豪 , 包铭磊 , 惠恒宇 , 等 . 考虑多重不确定性的虚拟电厂可信备用评估 [J]. 电力系统保护与控制 , 2025 , 53 ( 10 ): 45 - 56 .
Tian Fuhao , Bao Minglei , Hui Hengyu , et al . Reserve credit evaluation of virtual power plants considering multiple uncertainties [J]. Power System Protection and Control , 2025 , 53 ( 10 ): 45 - 56 .
黄宇翔 , 陈皓勇 , 牛振勇 , 等 . 基于“能量-信息-价值”三层网络的虚拟电厂架构及运行关键技术综述 [J]. 电力系统保护与控制 , 2024 , 52 ( 24 ): 169 - 187 .
Huang Yuxiang , Chen Haoyong , Niu Zhenyong , et al . A review of virtual power plant architecture and key operational technologies based on a “energy-information-value” three-layer network [J]. Power System Protection and Control , 2024 , 52 ( 24 ): 169 - 187 .
骆徐 , 程静 , 王李鑫 , 等 . 基于等效负荷实时电价和节点实时电价引导的电动汽车时空优化调度 [J]. 电网技术 , 2025 , 49 ( 11 ): 4670 - 4679 .
Luo Xu , Cheng Jing , Wang Lixin , et al . Spatio-temporal optimal scheduling of electric vehicles based on equivalent load real-time tariff and node real-time tariff guidance [J]. Power System Technology , 2025 , 49 ( 11 ): 4670 - 4679 .
成雨阳 , 高红均 , 王仁浚 , 等 . 虚拟电厂两阶段准线型需求响应优化及收益共享-风险共担决策方法 [J]. 电网技术 , 2024 , 48 ( 2 ): 799 - 808 .
Cheng Yuyang , Gao Hongjun , Wang Renjun , et al . Optimal strategy for two stage customer directrix load based demand response and profit sharing-risk sharing decision-making method for virtual power plant [J]. Power System Technology , 2024 , 48 ( 2 ): 799 - 808 .
曹昕冉 , 刘继春 , 刘可欣 . 基于时变量价特性的多主体参与需求响应市场决策方法 [J]. 电网技术 , 2025 , 49 ( 8 ): 3362 - 3371 .
Cao Xinran , Liu Jichun , Liu Kexin . A decision-making method for multi-agent participation in demand response markets based on time-variable pricing characteristics [J]. Power System Technology , 2025 , 49 ( 8 ): 3362 - 3371 .
龚超 , 张轩 , 赵越 , 等 . 考虑虚拟电厂可调能力的综合需求响应市场出清策略 [J]. 南方电网技术 , 2021 , 15 ( 12 ): 56 - 65 .
Gong Chao , Zhang Xuan , Zhao Yue , et al . Market clearing strategy of integrated demand response considering adjustable capacity of virtual power plant [J]. Southern Power System Technology , 2021 , 15 ( 12 ): 56 - 65 .
罗翼婷 , 杨洪明 , 牛犇 , 等 . 考虑多风能预测场景的虚拟电厂日内滚动柔性优化调度方法 [J]. 电力系统保护与控制 , 2020 , 48 ( 2 ): 51 - 59 .
Luo Yiting , Yang Hongming , Niu Ben , et al . Day-ahead flexible rolling optimization dispatch of virtual power plant based on multi-wind forecasting results [J]. Power System Protection and Control , 2020 , 48 ( 2 ): 51 - 59 .
漆淘懿 , 惠红勋 , 叶承晋 , 等 . 建筑虚拟电厂参与需求响应市场的报量报价机制设计 [J]. 电力系统自动化 , 2024 , 48 ( 18 ): 14 - 24 .
Qi Taoyi , Hui Hongxun , Ye Chengjin , et al . Bidding mechanism design for building virtual power plant to participate in demand response markets [J]. Automation of Electric Power Systems , 2024 , 48 ( 18 ): 14 - 24 .
林毓军 , 苗世洪 , 杨炜晨 , 等 . 面向多重不确定性环境的虚拟电厂日前优化调度策略 [J]. 电力自动化设备 , 2021 , 41 ( 12 ): 143 - 150 .
Lin Yujun , Miao Shihong , Yang Weichen , et al . Day-ahead optimal scheduling strategy of virtual power plant for environment with multiple uncertainties [J]. Electric Power Automation Equipment , 2021 , 41 ( 12 ): 143 - 150 .
李孟阳 , 李国杰 , 汪可友 , 等 . 考虑需求响应及调频性能变化的虚拟电厂日前投标策略 [J]. 电力系统保护与控制 , 2023 , 51 ( 3 ): 13 - 25 .
Li Mengyang , Li Guojie , Wang Keyou , et al . Day-ahead bidding strategy for virtual power plant considering demand response and frequency regulation performance variation [J]. Power System Protection and Control , 2023 , 51 ( 3 ): 13 - 25 .
Nadimi R , Goto M . A novel decision support system for enhancing long-term forecast accuracy in virtual power plants using bidirectional long short-term memory networks [J]. Applied Energy , 2025 , 382 : 125273 .
Wang Y Q , Fu W J , Wang J L , et al . Ultra-short-term distributed PV power forecasting for virtual power plant considering data-scarce scenarios [J]. Applied Energy , 2024 , 373 : 123890 .
张峻凯 , 胡旭光 , 刘要博 , 等 . 基于动态关联图注意力网络的虚拟电厂居民短期负荷预测 [J]. 电力系统自动化 , 2024 , 48 ( 21 ): 120 - 128 .
Zhang Junkai , Hu Xuguang , Liu Yaobo , et al . Short-term residential load forecasting based on dynamic association graph attention networks for virtual power plant [J]. Automation of Electric Power Systems , 2024 , 48 ( 21 ): 120 - 128 .
Chen X B , Yang Y F , Liu Y K , et al . Feature-driven economic improvement for network-constrained unit commitment: a closed-loop predict-and-optimize framework [J]. IEEE Transactions on Power Systems , 2022 , 37 ( 4 ): 3104 - 3118 .
闫馨月 , 张海鹏 , 李然 , 等 . 综合成本导向的风电短期功率预测 [J]. 中国电机工程学报 , 2024 , 44 ( 增刊1 ): 240 - 252 .
Yan Xinyue , Zhang Haipeng , Li Ran , et al . Comprehensive cost-oriented short-term wind power prediction [J]. Proceedings of the CSEE , 2024 , 44 ( S1 ): 240 - 252 .
Chen X , Liu Y , Wu L . Improving electricity market economy via closed-loop predict-and-optimize [PP/OL]. [ 2025-07-03 ]. https://arxiv.org/abs/2208.13065v1 https://arxiv.org/abs/2208.13065v1 .
Zhao C F , Wan C , Song Y H . Cost-oriented prediction intervals: on bridging the gap between forecasting and decision [J]. IEEE Transactions on Power Systems , 2022 , 37 ( 4 ): 3048 - 3062 .
Wu J R , Wang Y G , Tian Y C , et al . Support vector regression with asymmetric loss for optimal electric load forecasting [J]. Energy , 2021 , 223 : 119969 .
Wahdany D , Schmitt C , Cremer J L . More than accuracy: end-to-end wind power forecasting that optimises the energy system [J]. Electric Power Systems Research , 2023 , 221 : 109384 .
Han J Y , Yan L , Li Z Y . A task-based day-ahead load forecasting model for stochastic economic dispatch [J]. IEEE Transactions on Power Systems , 2021 , 36 ( 6 ): 5294 - 5304 .
Zhang J L , Wang Y , Hug G . Cost-oriented load forecasting [J]. Electric Power Systems Research , 2022 , 205 : 107723 .
Beichter M , Werling D , Heidrich B , et al . Decision-focused retraining of forecast models for optimization problems in smart energy systems [C]// The 15th ACM International Conference on Future and Sustainable Energy Systems , 2024 : 170 - 181 .
Amos B , Dilkina B , Ferber A , et al . Landscape surrogate: learning decision losses for mathematical optimization under partial information [C]// Advances in Neural Information Processing Systems , 2023 : 27332 - 27350 .
Shah S , Wilder B , Perrault A , et al . Leaving the nest: going beyond local loss functions for predict-then-optimize [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2024 : 14902 - 14909 .
Jeon H , Bae H , Park M , et al . Locally Convex Global Loss Network for Decision-Focused Learning [C]// Proceedings of the AAAI Conference on Artificial Intelligence , 2025 : 26805 - 26812 .
广东电力交易中心 . 广东省市场化需求响应交易实施方案(试行) [EB/OL].[ 2025-07-03 ]. https://pm.gd.csg.cn/portal/#/home/informationNotice/detail id=8077&noticeTypeId=31 https://pm.gd.csg.cn/portal/#/home/informationNotice/detailid=8077&noticeTypeId=31 .
Guangdong Power Exchange Center . Market-based demand response implementation plan of Guangdong Province (trial) [EB/OL].[ 2025-07-03 ]. https://pm.gd.csg.cn/portal/#/home/informationNotice/detail id=8077&noticeTypeId=31 https://pm.gd.csg.cn/portal/#/home/informationNotice/detailid=8077&noticeTypeId=31 .
刘庆楷 , 刘明波 , 陆文甜 . 考虑退化成本的电池储能参与调频辅助服务市场的控制方法 [J]. 电网技术 , 2021 , 45 ( 8 ): 3043 - 3051 .
Liu Qingkai , Liu Mingbo , Lu Wentian . Control method for battery energy storage participating in frequency regulation market considering degradation cost [J]. Power System Technology , 2021 , 45 ( 8 ): 3043 - 3051 .
刘行 , 黎灿兵 , 刘健哲 , 等 . 机组组合中电池储能调峰调频联合调度方法 [J/OL]. 上海交通大学学报 , 2025-10-01 . https://doi.org/10.16183/j.cnki.jsjtu.2024.404 https://doi.org/10.16183/j.cnki.jsjtu.2024.404 .
Liu Hang , Li Canbing , Liu Jianzhe , et al . Joint scheduling method for peak regulation and frequency regulation in unit commitment using battery energy storage systems [J/OL]. Journal of Shanghai Jiao Tong University , 2025-10-01 . https://doi.org/10.16183/j.cnki.jsjtu.2024.404 https://doi.org/10.16183/j.cnki.jsjtu.2024.404 .
胡晶 , 陈红坤 , 陈磊 , 等 . 考虑多主体利益与需求响应的分布式电源优化配置 [J]. 电力系统保护与控制 , 2021 , 49 ( 15 ): 38 - 46 .
Hu Jing , Chen Hongkun , Chen Lei , et al . Distributed generation planning in an active distribution network considering multi-agent interests and demand response [J]. Power System Protection and Control , 2021 , 49 ( 15 ): 38 - 46 .
杨茂 , 王金鑫 . 考虑可再生能源出力不确定的孤岛型微电网优化调度 [J]. 中国电机工程学报 , 2021 , 41 ( 3 ): 973 - 984 .
Yang Mao , Wang Jinxin . Optimal scheduling of islanded microgrid considering uncertain output of renewable energy [J]. Proceedings of the CSEE , 2021 , 41 ( 3 ): 973 - 984 .
Pistikopoulos E N , Georgiadis M C , Dua V . Multi-parametric programming: volume 1: theory, algorithms, and applications [M]. Chichester : Wiley , 2007 .
Shah S , Wilder B , Perrault A , et al . Learning (local) surrogate loss functions for predict-then-optimize problems [PP/OL]. [ 2025-10-01 ]. https://arxiv.org/abs/2203.16067v1 https://arxiv.org/abs/2203.16067v1 .
李彬 , 张雨蒙 , 周照钒 . 基于LSTM-Transformer的钢铁工业用户调节潜力预测与优化 [J]. 电力系统自动化 , 2026 , 50 ( 5 ): 54 - 62 .
Li Bin , Zhang Yumeng , Zhou Zhaofan . LSTM-Transformer based prediction and optimization for user regulation potential of iron and steel industry [J]. Automation of Electric Power Systems , 2026 , 50 ( 5 ): 54 - 62 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621