哈尔滨工业大学电气工程及自动化学院,黑龙江省哈尔滨市 150001
张洋洋(2001—),男,硕士研究生,主要研究方向:数据中心算力-电力协同调度。E-mail:15286431896@163.com
涂正宏(1993—),男,通信作者,博士,副教授,博士生导师,主要研究方向:智能电网、微电网控制与深度强化学习。E-mail:tuzhenghong@hit.edu.cn
徐英(1980—),男,博士,教授,博士生导师,主要研究方向:大系统建模与仿真分析、能源交易与市场理论、虚拟储能与能源互联网。E-mail:ying.xu@hit.edu.cn
收稿:2025-11-13,
修回:2026-03-26,
网络首发:2026-07-15,
纸质出版:2026-09-10
移动端阅览
张洋洋,涂正宏,徐英等.计及计算资源自适应调整的数据中心算力-电力协同调度[J].电力系统自动化,2026,50(17):85-95.
ZHANG Yangyang,TU Zhenghong,XU Ying,et al.Coordinated Scheduling of Computing Power and Electric Power in Data Centers Considering Adaptive Adjustment of Computing Resources[J].Automation of Electric Power Systems,2026,50(17):85-95.
张洋洋,涂正宏,徐英等.计及计算资源自适应调整的数据中心算力-电力协同调度[J].电力系统自动化,2026,50(17):85-95. DOI: 10.7500/AEPS20251113003.
ZHANG Yangyang,TU Zhenghong,XU Ying,et al.Coordinated Scheduling of Computing Power and Electric Power in Data Centers Considering Adaptive Adjustment of Computing Resources[J].Automation of Electric Power Systems,2026,50(17):85-95. DOI: 10.7500/AEPS20251113003.
当前,利用数据中心计算任务的可迁移特性提升服务质量、降低运行成本已成为数据中心运营的重要发展方向。然而,作为能耗巨擘,数据中心的运行方式深刻影响着配电网的安全运行。为此,文中聚焦于数据中心集群与配电网的协同调度问题,将计算任务迁移与电力系统运行相结合,构建了一个分层强化学习模型。该模型采用一种计算资源自适应调整机制,并建立了包含电力侧经济调度与算力侧任务迁移的分层协同框架。在此基础上,设计了一种基于抽象指令的分层多智能体强化学习算法,用于生成配电网与数据中心的功率交换指令、任务迁移指令及计算资源调控策略。仿真结果表明,所提方法能够有效降低系统经济成本、提升新能源消纳能力,同时显著降低计算任务执行违规率,改善整体服务质量。
Currently
leveraging the transferable features of computation tasks in data centers to enhance quality of service and reduce operating costs has become a significant development direction in data center operations. However
as major energy consumers
the operation modes of data centers significantly impact the safe operation of distribution networks. Therefore
focusing on the coordinated scheduling of data center clusters and distribution networks
the computation task transfer is integrated with power system operation to construct a hierarchical reinforcement learning model. The model adopts an adaptive adjustment mechanism for computing resources and establishes a hierarchical coordinated framework that incorporates economic dispatch on the electric-power side and task transfer on the computing-power side. On this basis
a hierarchical multi-agent reinforcement learning algorithm based on abstract instructions is designed to generate power exchange instructions between the distribution network and data centers
task transfer commands
and computing resource scheduling strategies. Simulation results demonstrate that the proposed method can effectively reduce system economic costs
enhance renewable energy accommodation capability
significantly decrease execution violations of computation tasks
and improve overall quality of service.
刘祎泽 , 向月 . 计及负荷转移需求响应的低碳数据中心光储容量优化配置 [J]. 电力自动化设备 , 2024 , 44 ( 7 ): 149 - 155 .
Liu Yize , Xiang Yue . Optimal allocation of photovoltaic and storage capacity in low carbon data center considering load transfer demand response [J]. Electric Power Automation Equipment , 2024 , 44 ( 7 ): 149 - 155 .
Cao Y J , Cao F , Wang Y J , et al . Managing data center cluster as non-wire alternative: a case in balancing market [J]. Applied Energy , 2024 , 360 : 122769 .
吴舒坦 , 王琦 , 于昌平 , 等 . 计及时空灵活性资源协同的配电信息物理系统规划方法 [J]. 电力系统自动化 , 2025 , 49 ( 15 ): 74 - 88 .
Wu Shutan , Wang Qi , Yu Changping , et al . Planning method for cyber-physical distribution system considering spatial-temporal flexibility resource collaboration [J]. Automation of Electric Power Systems , 2025 , 49 ( 15 ): 74 - 88 .
Li H J , Gao Y , Zhu L S , et al . Cost-aware scheduling for streaming applications in geographically distributed heterogeneous cloud [J]. Future Generation Computer Systems , 2026 , 175 : 108036 .
Kathole A B , Vhatkar K , Lonare S , et al . Optimization-based resource scheduling techniques in cloud computing environment: a review of scientific workflows and future directions [J]. Computers and Electrical Engineering , 2025 , 123 : 110080 .
曹雨洁 . 数据中心和电网“算力-能源”协同优化及综合效益研究 [D]. 北京 : 华北电力大学 , 2024 .
Cao Yujie . Research on coordinated optimization and comprehensive benefits of “computing power-energy” integration between data centers and power grids [D]. Beijing : North China Electric Power University , 2024 .
Jayanetti A , Halgamuge S , Buyya R . Multi-agent deep reinforcement learning framework for renewable energy-aware workflow scheduling on distributed cloud data centers [J]. IEEE Transactions on Parallel and Distributed Systems , 2024 , 35 ( 4 ): 604 - 615 .
陈冬林 , 马一帆 , 邹安琪 . 基于可再生能源消纳的数据中心负荷调度研究综述 [J]. 计算机工程与科学 , 2023 , 45 ( 5 ): 790 - 801 .
Chen Donglin , Ma Yifan , Zou Anqi . A survey of data center load scheduling based on renewable energy consumption [J]. Computer Engineering and Science , 2023 , 45 ( 5 ): 790 - 801 .
可思为 , 董萍 , 马铭宇 , 等 . 考虑风光荷时空互补的多能源绿色数据中心多目标配置方法 [J]. 电力系统保护与控制 , 2024 , 52 ( 22 ): 22 - 33 .
Ke Siwei , Dong Ping , Ma Mingyu , et al . A multi-objective allocation method for multi-energy green data centers considering wind, solar and load spatial-temporal complementarity [J]. Power System Protection and Control , 2024 , 52 ( 22 ): 22 - 33 .
刘琦帆 . 基于动态优先级的数据中心网络流量调度方法研究 [D]. 武汉 : 华中科技大学 , 2021 .
Liu Qifan . Research on a datacenter network traffic scheduler based on dynamic priority [D]. Wuhan : Huazhong University of Science and Technology , 2021 .
曾博 , 刘一贤 , 张卫翔 , 等 . 综合考虑内外生不确定性的绿色数据中心多域资源协同规划方法 [J]. 中国电机工程学报 , 2024 , 44 ( 12 ): 4732 - 4747 .
Zeng Bo , Liu Yixian , Zhang Weixiang , et al . A collaborative optimization approach for green data center multi-domain resource planning considering both endogenous and exogenous uncertainties [J]. Proceedings of the CSEE , 2024 , 44 ( 12 ): 4732 - 4747 .
Fan W , Fan Y , Liu P J , et al . Distributionally robust optimization scheduling model for electric power and computing power coordination considering spatiotemporal response [J]. Applied Energy , 2025 , 402 : 126895 .
Fan J Q , Yan R J , He Y , et al . Stochastic optimization of combined energy and computation task scheduling strategies of hybrid system with multi-energy storage system and data center [J]. Renewable Energy , 2025 , 242 : 122466 .
崔杨 , 程禹烽 , 赵钰婷 , 等 . 考虑特性分类批处理负荷可调节能力的数据中心微网灵活性设备分布鲁棒容量配置方法 [J]. 电力自动化设备 , 2024 , 44 ( 7 ): 180 - 188 .
Cui Yang , Cheng Yufeng , Zhao Yuting , et al . Distributionally robust capacity allocation method for flexibility device of data center microgrid considering adjustable capability of characteristic classification batch processing loads [J]. Electric Power Automation Equipment , 2024 , 44 ( 7 ): 180 - 188 .
张程 , 江炜龙 , 罗玉锦 , 等 . 考虑风光不确定性的多数据中心微网与共享储能协同优化运行 [J]. 电力系统保护与控制 , 2025 , 53 ( 4 ): 72 - 84 .
Zhang Cheng , Jiang Weilong , Luo Yujin , et al . Collaborative optimal operation of multiple data center microgrids and shared energy storage considering wind power and photovoltaic uncertainty [J]. Power System Protection and Control , 2025 , 53 ( 4 ): 72 - 84 .
梁晨 , 曾博 , 雷乐意 , 等 . 算力-电力联合市场下数据中心与配电网集成规划:一种多目标区间-随机优化方法 [J]. 电力系统保护与控制 , 2025 , 53 ( 16 ): 120 - 135 .
Liang Chen , Zeng Bo , Lei Yueyi , et al . Integrated planning of data centers and distribution networks under the computing-electricity joint market: a multi-objective interval-stochastic optimization approach [J]. Power System Protection and Control , 2025 , 53 ( 16 ): 120 - 135 .
Li T G , Ying S , Zhao Y S , et al . Batch jobs load balancing scheduling in cloud computing using distributional reinforcement learning [J]. IEEE Transactions on Parallel and Distributed Systems , 2024 , 35 ( 1 ): 169 - 185 .
Zhang C , Wu F , Wang Z Y , et al . A graph-based deep reinforcement learning model for task scheduling on heterogeneous resource-elastic management of resource pool [J]. IEEE Transactions on Cloud Computing , 2025 , 13 ( 4 ): 1327 - 1342 .
Yan J C , Huang Y F , Gupta A , et al . Energy-aware systems for real-time job scheduling in cloud data centers: a deep reinforcement learning approach [J]. Computers and Electrical Engineering , 2022 , 99 : 107688 .
Kahil H , Sharma S , Välisuo P , et al . Reinforcement learning for data center energy efficiency optimization: a systematic literature review and research roadmap [J]. Applied Energy , 2025 , 389 : 125734 .
Liang S S , Yang Z , Jin F , et al . Data centers job scheduling with deep reinforcement learning [C]// Advances in Knowledge Discovery and Data Mining , 2020 : 906 - 917 .
马浩然 , 袁至 , 王维庆 , 等 . 考虑数据中心和储能接入的主动配电网经济调度研究 [J]. 发电技术 , 2025 , 46 ( 4 ): 748 - 757 .
Ma Haoran , Yuan Zhi , Wang Weiqing , et al . Research on economic scheduling of active distribution networks with inclusion of data center and energy storage [J]. Power Generation Technology , 2025 , 46 ( 4 ): 748 - 757 .
Liang B , Bai J Q . Low-energy resource classification algorithm for cross-regional cloud data centers based on K-means clustering algorithm [J]. IEEE Transactions on Industrial Informatics , 2024 , 20 ( 8 ): 10084 - 10091 .
方和平 , 刘曙光 , 冉泳屹 , 等 . 基于深度强化学习的多数据中心一体化调度优化 [J]. 计算机应用 , 2023 , 43 ( 6 ): 1884 - 1892 .
Fang Heping , Liu Shuguang , Ran Yongyi , et al . Integrated scheduling optimization of multiple data centers based on deep reinforcement learning [J]. Journal of Computer Applications , 2023 , 43 ( 6 ): 1884 - 1892 .
Chen G X , Qi J , Sun Y , et al . A collaborative scheduling method for cloud computing heterogeneous workflows based on deep reinforcement learning [J]. Future Generation Computer Systems , 2023 , 141 : 284 - 297 .
Zhang S X , Wang Z , Zhou Z Y , et al . Blockchain and federated deep reinforcement learning based secure cloud-edge-end collaboration in power IoT [J]. IEEE Wireless Communications , 2022 , 29 ( 2 ): 84 - 91 .
Zhu K G , Zhang Z J , Zeadally S , et al . Learning to optimize workflow scheduling for an edge-cloud computing environment [J]. IEEE Transactions on Cloud Computing , 2024 , 12 ( 3 ): 897 - 912 .
Griner C , Avin C , Einziger G . Beyond matchings: dynamic multi-hop topology for demand-aware datacenters [J]. Computer Networks , 2024 , 240 : 110143 .
Yang R Z , Yi Z K , Xu Y , et al . Noise-aware Bayesian optimization approach for capacity planning of the distributed energy resources in an active distribution network [J]. Sustainable Energy, Grids and Networks , 2025 , 43 : 101781 .
Ghodsi A , Zaharia M A , Hindman B , et al . Dominant resource fairness: fair allocation of multiple resource types [C]// Symposium on Networked Systems Design and Implementation , 2011 : 323 - 336 .
Carvalho D S , Santos P A , Melo F S . Reinforcement learning in convergently non-stationary environments: feudal hierarchies and learned representations [J]. Artificial Intelligence , 2025 , 347 : 104382 .
周钱雨凡 , 杨苹 , 万思洋 , 等 . 算力电力节点可调节资源的双向协同优化调度 [J]. 电力建设 , 2025 , 46 ( 2 ): 13 - 25 .
Zhou Qianyufan , Yang Ping , Wan Siyang , et al . Bidirectional collaborative optimization scheduling of adjustable resources in computing node and power node [J]. Electric Power Construction , 2025 , 46 ( 2 ): 13 - 25 .
Jang S , Ozay N , Mathieu J L . Probabilistic constraint construction for network-safe load coordination [J]. IEEE Transactions on Power Systems , 2024 , 39 ( 2 ): 4473 - 4485 .
Haarnoja T , Zhou A , Abbeel P , et al . Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor [C]// Proceedings of the 35th International Conference on Machine Learning , 2018 : 1861 - 1870 .
Wang L C , Wang T , Huang G , et al . Softly collaborated voltage control in PV rich distribution systems with heterogeneous devices [J]. IEEE Transactions on Power Systems , 2024 , 39 ( 4 ): 5991 - 6003 .
Wang R J , Gao H J , Qiu H F , et al . A cloud-edge intelligence-based optimization method for distribution network partitioning and operation considering simulation inaccuracy [J]. IEEE Transactions on Power Systems , 2025 , 40 ( 5 ): 3750 - 3762 .
Sun Y M , Ding Z H , Yan Y J , et al . Privacy-preserving energy sharing among cloud service providers via collaborative job scheduling [J]. IEEE Transactions on Smart Grid , 2025 , 16 ( 2 ): 1168 - 1180 .
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