香港大学深圳研究院,广东省深圳市 518063
李业辉(2000—),男,博士研究生,主要研究方向:大数据分析、边缘智能。E-mail:yhli@eee.hku.hk
黄明宇(1997—),女,博士研究生,主要研究方向:虚拟电厂、辅助服务。E-mail:myhuang@eee.hku.hk
王毅(1992—),男,通信作者,博士,助理教授,主要研究方向:大数据、能源互联网、负荷预测。E-mail:yiwang@ eee.hku.hk
收稿:2025-04-23,
修回:2025-06-11,
网络首发:2025-08-14,
纸质出版:2025-10-25
移动端阅览
李业辉,黄明宇,王毅.云边协同的虚拟电厂轻量化能量管理策略[J].电力系统自动化,2025,49(20):125-135.
LI Yehui,HUANG Mingyu,WANG Yi.Lightweight Energy Management Strategy for Cloud-Edge Collaborative Virtual Power Plants[J].Automation of Electric Power Systems,2025,49(20):125-135.
李业辉,黄明宇,王毅.云边协同的虚拟电厂轻量化能量管理策略[J].电力系统自动化,2025,49(20):125-135. DOI: 10.7500/AEPS20250423004.
LI Yehui,HUANG Mingyu,WANG Yi.Lightweight Energy Management Strategy for Cloud-Edge Collaborative Virtual Power Plants[J].Automation of Electric Power Systems,2025,49(20):125-135. DOI: 10.7500/AEPS20250423004.
虚拟电厂通过聚合海量分布式资源,形成规模化的市场主体与电网进行互动。然而,大规模分布式资源的能量管理面临全局优化与本地需求之间的矛盾。集中式优化调控难以兼顾用户用电成本和舒适度,而本地用户能量管理缺乏对虚拟电厂整体运行状态的统筹协调。因此,提出云边协同的虚拟电厂轻量化用户能量管理策略。首先,构建虚拟电厂能量管理的分层决策框架,实现虚拟电厂能量管理从单向控制向双向互动的转变。其次,考虑到低成本边缘设备的计算资源有限,提出基于稀疏强化学习的本地决策算法,利用自适应拓扑演化降低神经网络可训练参数量。最后,结合在真实数据集上进行的算例,验证了所提轻量化策略的有效性与高效性。
The virtual power plant (VPP) aggregates massive distributed resources to form a large-scale market entity interacting with the power grid. However
the energy management of large-scale distributed resources faces a contradiction between global optimization and local demands. Centralized optimization and regulation struggle to balance electricity costs and comfort of the users
while local user energy management lacks coordinated control over the overall operational state of the VPP. Therefore
a lightweight user energy management strategy for cloud-edge collaborative VPPs is proposed. Firstly
a hierarchical decision-making framework for energy management of VPPs is constructed to shift unidirectional control to bidirectional interaction. Secondly
considering the limited computational resources of low-cost edge devices
a local decision-making algorithm based on sparse reinforcement learning is proposed
which uses adaptive topology evolution to reduce the number of trainable parameters in neural networks. Finally
case studies conducted on real-world datasets validate the effectiveness and efficiency of the proposed lightweight strategy.
王宣元 , 刘敦楠 , 刘蓁 , 等 . 泛在电力物联网下虚拟电厂运营机制及关键技术 [J]. 电网技术 , 2019 , 43 ( 9 ): 3175 - 3183 .
WANG Xuanyuan , LIU Dunnan , LIU Zhen , et al . Operation mechanism and key technologies of virtual power plant under ubiquitous Internet of Things [J]. Power System Technology , 2019 , 43 ( 9 ): 3175 - 3183 .
卫志农 , 余爽 , 孙国强 , 等 . 虚拟电厂的概念与发展 [J]. 电力系统自动化 , 2013 , 37 ( 13 ): 1 - 9 .
WEI Zhinong , YU Shuang , SUN Guoqiang , et al . Concept and development of virtual power plant [J]. Automation of Electric Power Systems , 2013 , 37 ( 13 ): 1 - 9 .
KAISS M , WAN Y H , GEBBRAN D , et al . Review on virtual power plants/virtual aggregators: concepts, applications, prospects and operation strategies [J]. Renewable and Sustainable Energy Reviews , 2025 , 211 : 115242 .
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 .
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 .
孔祥玉 , 马玉莹 , 艾芊 , 等 . 新型电力系统多元用户的用电特征建模与用电负荷预测综述 [J]. 电力系统自动化 , 2023 , 47 ( 13 ): 2 - 17 .
KONG Xiangyu , MA Yuying , AI Qian , et al . Review on electricity consumption characteristic modeling and load forecasting for diverse users in new power system [J]. Automation of Electric Power Systems , 2023 , 47 ( 13 ): 2 - 17 .
SRIVASTAVA A , ZHAO J B , ZHU H , et al . Distribution system behind-the-meter DERs: estimation, uncertainty quantification, and control [J]. IEEE Transactions on Power Systems , 2025 , 40 ( 1 ): 1060 - 1077 .
王海冰 , 王简 , 王承民 , 等 . 计及风险约束的虚拟电厂能量管理建模 [J]. 中国电机工程学报 , 2017 , 37 ( 20 ): 5942 - 5950 .
WANG Haibing , WANG Jian , WANG Chengmin , et al . Risk-constrained energy management modeling of virtual power plant [J]. Proceedings of the CSEE , 2017 , 37 ( 20 ): 5942 - 5950 .
王珑 , 王进 , 龚晓琴 , 等 . 基于用户满意度的家庭能量管理系统协调优化调度 [J]. 电力学报 , 2019 , 34 ( 2 ): 101 - 108 .
WANG Long , WANG Jin , GONG Xiaoqin , et al . The home energy management system coordinated and optimized scheduling based on user’s satisfaction [J]. Journal of Electric Power , 2019 , 34 ( 2 ): 101 - 108 .
LI Q , WEI F C , ZHOU Y C , et al . A scheduling framework for VPP considering multiple uncertainties and flexible resources [J]. Energy , 2023 , 282 : 128385 .
YI Z K , XU Y L , GU W , et al . A multi-time-scale economic scheduling strategy for virtual power plant based on deferrable loads aggregation and disaggregation [J]. IEEE Transactions on Sustainable Energy , 2020 , 11 ( 3 ): 1332 - 1346 .
陈张宇 , 刘东 , 刘浩文 , 等 . 基于精细化需求响应的虚拟电厂优化调度 [J]. 电网技术 , 2021 , 45 ( 7 ): 2542 - 2550 .
CHEN Zhangyu , LIU Dong , LIU Haowen , et al . Optimal dispatching of virtual power plant based on refined demand response [J]. Power System Technology , 2021 , 45 ( 7 ): 2542 - 2550 .
栾文鹏 , 李培琳 , 赵博超 , 等 . 考虑隐私保护的虚拟电厂内部交易决策优化 [J]. 电力系统自动化 , 2024 , 48 ( 18 ): 158 - 166 .
LUAN Wenpeng , LI Peilin , ZHAO Bochao , et al . Optimization of internal transaction decisions in virtual power plant considering privacy preservation [J]. Automation of Electric Power Systems , 2024 , 48 ( 18 ): 158 - 166 .
FIORINI L , AIELLO M . Energy management for user’s thermal and power needs: a survey [J]. Energy Reports , 2019 , 5 : 1048 - 1076 .
杨文轩 , 何光宇 , 王伟 , 等 . 用户侧能量管理原型系统的设计与实现 [J]. 电力系统自动化 , 2012 , 36 ( 20 ): 74 - 79 .
YANG Wenxuan , HE Guangyu , WANG Wei , et al . Design and implementation of user energy management archetype system [J]. Automation of Electric Power Systems , 2012 , 36 ( 20 ): 74 - 79 .
ZHAO Z , LEE W C , SHIN Y , et al . An optimal power scheduling method for demand response in home energy management system [J]. IEEE Transactions on Smart Grid , 2013 , 4 ( 3 ): 1391 - 1400 .
加鹤萍 , 郭宇辰 , 余涛 , 等 . 考虑出力偏差与风险控制的虚拟电厂收益分配策略 [J]. 电力建设 , 2024 , 45 ( 6 ): 27 - 36 .
JIA Heping , GUO Yuchen , YU Tao , et al . Profit distribution strategy of virtual power plants considering output deviation and risk control [J]. Electric Power Construction , 2024 , 45 ( 6 ): 27 - 36 .
方燕琼 , 甘霖 , 艾芊 , 等 . 基于主从博弈的虚拟电厂双层竞标策略 [J]. 电力系统自动化 , 2017 , 41 ( 14 ): 61 - 69 .
FANG Yanqiong , GAN Lin , AI Qian , et al . Stackelberg game based bilevel bidding strategy for virtual power plant [J]. Automation of Electric Power Systems , 2017 , 41 ( 14 ): 61 - 69 .
王辉 , 金子蓉 , 方航 , 等 . 基于动态定价的虚拟电厂博弈能源管理模型 [J]. 南方电网技术 , 2023 , 17 ( 4 ): 101 - 108 .
WANG Hui , JIN Zirong , FANG Hang , et al . Game energy management model of virtual power plant based on dynamic pricing [J]. Southern Power System Technology , 2023 , 17 ( 4 ): 101 - 108 .
GAO H , LI Z S . A benders decomposition based algorithm for steady-state dispatch problem in an integrated electricity-gas system [J]. IEEE Transactions on Power Systems , 2021 , 36 ( 4 ): 3817 - 3820 .
吕仁周 , 白晓清 , 李佩杰 , 等 . 基于交替方向乘子法的电动汽车分散式充电控制 [J]. 电力系统自动化 , 2016 , 40 ( 16 ): 56 - 63 .
LYU Renzhou , BAI Xiaoqing , LI Peijie , et al . Decentralized charging control of electric vehicles based on alternate direction method of multiplier [J]. Automation of Electric Power Systems , 2016 , 40 ( 16 ): 56 - 63 .
罗天 , 汪可友 , 李国杰 , 等 . 基于拉格朗日对偶松弛的多区域柔性直流互联电网无功优化 [J]. 电力系统自动化 , 2019 , 43 ( 11 ): 68 - 76 .
LUO Tian , WANG Keyou , LI Guojie , et al . Reactive power optimization in multi-area VSC-HVDC interconnected power grids based on Lagrangian dual relaxation [J]. Automation of Electric Power Systems , 2019 , 43 ( 11 ): 68 - 76 .
RUAN G C , QIU D W , SIVARANJANI S , et al . Data-driven energy management of virtual power plants: a review [J]. Advances in Applied Energy , 2024 , 14 : 100170 .
国家能源局 . 关于印发《山东电力市场规则(试行)》的通知 [EB/OL].[ 2025-01-01 ]. https://sdb.nea.gov.cn/dtyw/tzgg/202404/t20240419_261034.html https://sdb.nea.gov.cn/dtyw/tzgg/202404/t20240419_261034.html .
National Energy Administration . Notice on issuing “Shandong Electricity Market Rules (Trial) ”[EB/OL].[ 2025-01-01 ]. https://sdb.nea.gov.cn/dtyw/tzgg/202404/t20240419_261034.html https://sdb.nea.gov.cn/dtyw/tzgg/202404/t20240419_261034.html .
YU L , XIE W W , XIE D , et al . Deep reinforcement learning for smart home energy management [J]. IEEE Internet of Things Journal , 2020 , 7 ( 4 ): 2751 - 2762 .
张甜 , 赵奇 , 陈中 , 等 . 基于深度强化学习的家庭能量管理分层优化策略 [J]. 电力系统自动化 , 2021 , 45 ( 21 ): 149 - 158 .
ZHANG Tian , ZHAO Qing , CHEN Zhong , et al . Hierarchical optimization strategy for home energy management based on deep reinforcement learning [J]. Automation of Electric Power Systems , 2021 , 45 ( 21 ): 149 - 158 .
AIEN M , HAJEBRAHIMI A , FOTUHI-FIRUZABAD M . A comprehensive review on uncertainty modeling techniques in power system studies [J]. Renewable and Sustainable Energy Reviews , 2016 , 57 : 1077 - 1089 .
MOCANU D C , MOCANU E , STONE P , et al . Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science [J]. Nature Communications , 2018 , 9 : 2383 .
Pecan Street Research Institute . Pecan Street dataport [EB/OL]. [ 2025-01-01 ]. https://www.pecanstreet.org/dataport/ https://www.pecanstreet.org/dataport/ .
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