1.西安邮电大学,计算机学院,西安 710121
2.西安邮电大学,科研处,西安 710121
3.陕西省大数据集团有限公司,西安712000
4.西安超算中心有限公司,西安 710100
马帅印(1990),男,副教授,博士,从事大模型、人工智能、绿色智算、绿色制造等方面的研究,masy@xupt.edu.cn;
牛晨阳(2002),男,硕士生,从事人工智能及绿色智算等方面的研究,niucy@stu.xiyou.edu.cn;
栾龙源(1984),男,工程师,硕士,从事人工智能、数据中心、智慧能源等方面的研究,luanlongyuan@snbigdata.cn;
庄严(1985),男,工程师,硕士,从事超算中心运维调试等方面的工作,zhuangy1@126.com;
岳本勇(1982),男,高级工程师,硕士,从事人工智能和数字经济等方面的研究,13720429658@126.com。
收稿:2026-08-13,
修回:2026-08-20,
网络首发:2026-08-25,
纸质出版:2026-08-25
移动端阅览
马帅印,牛晨阳,栾龙源等.人工智能赋能算电协同的关键技术[J].综合智慧能源,2026,48(08):69-81.
MA Shuaiyin,NIU Chenyang,LUAN Longyuan,et al.Key technologies of AI-empowered computing-electricity coordination[J].BLASTING,2026,48(08):69-81.
马帅印,牛晨阳,栾龙源等.人工智能赋能算电协同的关键技术[J].综合智慧能源,2026,48(08):69-81. DOI: 10.3969/j.issn.2097-0706.2026.08.006.
MA Shuaiyin,NIU Chenyang,LUAN Longyuan,et al.Key technologies of AI-empowered computing-electricity coordination[J].BLASTING,2026,48(08):69-81. DOI: 10.3969/j.issn.2097-0706.2026.08.006.
随着生成式人工智能和大模型的快速发展,以及算力需求和用电需求的持续增长,算力负荷与电力供给在时间、空间及运行目标上的协调难度不断增加。针对算力系统与电力系统在数据结构、运行周期、调节方式和安全边界等方面的差异,从系统工程视角研究人工智能赋能算电协同的总体架构、运行机制与关键技术。构建由基础支撑、技术引擎、场景应用和治理保障组成的4层总体架构,并以人工智能赋能算电协同运行为核心,形成涵盖状态映射、供需时空匹配、耦合传导、多目标权衡和双向闭环调控的运行机制。在此基础上,构建由多源感知与融合、算电供需预测、算电耦合建模、协同优化决策以及自适应控制与安全执行组成的关键技术链,重点分析时空特征表征、任务与功率映射、模型与学习协同决策、滚动控制及安全约束校验等技术,并进一步归纳跨域数据融合、多尺度决策耦合以及模型泛化与安全验证等关键难点。结合陕西省可再生能源电力消纳和智能算力供给情况开展案例分析,结果表明,陕西可再生能源电力利用基础持续增强,智能算力具有较高的可统筹调度比例且呈现一定空间差异,为算力负荷与新能源供给的时序协同及跨节点算力资源配置提供了现实条件。针对上述难点及区域资源特征,提出完善跨域数据融合与可信共享、构建分层滚动协同决策以及建立策略验证与安全运行机制等对策,以提升算力利用效率、可再生能源电力消纳水平和系统运行韧性。
With the rapid development of generative AI and foundation models, computing demand and the associated electricity demand continue to grow, making the coordination between computing loads and electricity supply increasingly challenging in terms of time, space, and operational objectives. Considering the differences between computing systems and power systems in data structures, operating cycles, regulation mechanisms, and security boundaries, the overall architecture, operational mechanism, and key technologies of AI-empowered computing-electricity coordination are investigated from a system engineering perspective. A four-layer architecture comprising basic support, technology engine, scenario application, and governance assurance is constructed. With AI-empowered computing-electricity coordination as the core, an operational mechanism is established that integrates state mapping, spatiotemporal supply-demand matching, coupling transmission, multi-objective trade-offs, and bidirectional closed-loop regulation. On this basis, a key technology chain is constructed, covering multi-source sensing and fusion, computing-electricity supply-demand prediction, computing-electricity coupling modeling, coordinated optimization and decision-making, and adaptive control and safe execution. Key technologies, including spatiotemporal feature representation, task-to-power mapping, model- and learning-driven coordinated decision-making, rolling control, and safety constraint checking, are analyzed. Furthermore, major challenges involving cross-domain data fusion, multiscale decision coupling, model generalization, and safety verification are summarized. A case study of Shaanxi Province is conducted based on renewable electricity consumption and the supply of intelligent computing capacity. The results show that the foundation for renewable electricity utilization in Shaanxi Province has been continuously strengthened. Intelligent computing resources exhibit a relatively high proportion of coordinately schedulable capacity and certain spatial disparities, providing practical conditions for temporal coordination between computing loads and renewable energy supply, as well as for cross-node allocation of computing resources. In response to these challenges and regional resource characteristics, the following measures are proposed: improving cross-domain data fusion and trusted sharing, establishing hierarchical rolling coordinated decision-making mechanisms, and developing strategy validation and safe operation mechanisms. This will further enhance computing resource utilization efficiency, renewable electricity consumption, and system operational resilience.
ZHU H Y , ZHANG D D , GOH H H , et al . Future data center energy-conservation and emission-reduction technologies in the context of smart and low-carbon city construction [J]. Sustainable Cities and Society , 2023 , 89 : 104322 .
陈敏 , 高赐威 , 郭庆来 , 等 . 互联网数据中心负荷时空可转移特性建模与协同优化: 驱动力与研究架构 [J]. 中国电机工程学报 , 2022 , 42 ( 19 ): 6945 - 6958 .
CHEN Min , GAO Ciwei , GUO Qinglai , et al . Modeling and coordinated optimization for spatiotemporal load regulation potentials of Internet data centers: Motivation and architecture [J]. Proceedings of the CSEE , 2022 , 42 ( 19 ): 6945 - 6958 .
车凯 . “算电协同”现状及未来趋势展望 [J]. 通信世界 , 2025 ( 20 ): 22 - 24 .
CHE Kai . Present situation and future trend prospect of "computing and electricity collaboration" [J]. Communications World , 2025 ( 20 ): 22 - 24 .
曹雨洁 , 丁肇豪 , 王鹏 , 等 . 能源互联网背景下数据中心与电力系统协同优化(二): 机遇与挑战 [J]. 中国电机工程学报 , 2022 , 42 ( 10 ): 3512 - 3527 .
CAO Yujie , DING Zhaohao , WANG Peng , et al . Coordinated operation for data center and power system in the context of energy Internet(Ⅱ): Opportunities and challenges [J]. Proceedings of the CSEE , 2022 , 42 ( 10 ): 3512 - 3527 .
帅文利 , 杨秀 , 赵晓莉 , 等 . 计及数据中心负载特性的多时间尺度优化调度 [J]. 智慧电力 , 2025 , 53 ( 7 ): 1 - 10 .
SHUAI Wenli , YANG Xiu , ZHAO Xiaoli , et al . Multi-timescale optimal scheduling considering data center load characteristics [J]. Smart Power , 2025 , 53 ( 7 ): 1 - 10 .
唐伟 , 单葆国 , 郑海峰 , 等 . 数据中心两阶段源荷协同优化调度研究 [J]. 电力系统及其自动化学报 , 2023 , 35 ( 4 ): 49 - 58 .
TANG Wei , SHAN Baoguo , ZHENG Haifeng , et al . Research on two-stage source-load coordinated optimal scheduling of data centers [J]. Proceedings of the CSU-EPSA , 2023 , 35 ( 4 ): 49 - 58 .
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 .
ZHU N Y , WANG Y , YUAN K , et al . GGNet: A novel graph structure for power forecasting in renewable power plants considering temporal lead-lag correlations [J]. Applied Energy , 2024 , 364 : 123194 .
MAHBOD M HBIN , CHNG C B , LEE P S , et al . Energy saving evaluation of an energy efficient data center using a model-free reinforcement learning approach [J]. Applied Energy , 2022 , 322 : 119392 .
杨秀 , 张相寅 , 黄海涛 , 等 . 基于多智能体近端策略网络的数据中心双层优化调度 [J]. 南方电网技术 , 2025 , 19 ( 4 ): 107 - 121, 131 .
YANG Xiu , ZHANG Xiangyin , HUANG Haitao , et al . Dual-layer optimization scheduling of data center based on multi-agent proximal strategy network [J]. Southern Power System Technology , 2025 , 19 ( 4 ): 107 - 121, 131 .
COLANGELO P , COSKUN A K , MEGRUE J , et al . AI data centres as grid-interactive assets [J]. Nature Energy , 2026 , 11 ( 2 ): 254 - 261 .
ZENG B , ZHOU Y Y , XU X Z , et al . Bi-level planning approach for incorporating the demand-side flexibility of cloud data centers under electricity-carbon markets [J]. Applied Energy , 2024 , 357 : 122406 .
ZHANG Y B , TANG H , LI H X , et al . Integration and interaction of next-generation AI-focused data centers with smart grids and district energy systems: The state-of-the-art, opportunities and challenges [J]. Renewable and Sustainable Energy Reviews , 2025 , 224 : 116097 .
向世林 , 向月 , 王晏亮 , 等 . 计及负载响应特性的多数据中心时空协同运行优化策略 [J]. 中国电力 , 2025 , 58 ( 4 ): 170 - 181 .
XIANG Shilin , XIANG Yue , WANG Yanliang , et al . Optimization strategy for spatiotemporal cooperative operation of multiple data centers considering load response characteristics [J]. Electric Power , 2025 , 58 ( 4 ): 170 - 181 .
王永真 , 韩艺博 , 郭凯 , 等 . 面向算力-电力-热力协同的术语及标准体系初探 [J]. 电力建设 , 2025 , 46 ( 4 ): 71 - 83 .
WANG Yongzhen , HAN Yibo , GUO Kai , et al . A preliminary exploration on the terminology and standard system for computing power-electricity-heat synergy [J]. Electric Power Construction , 2025 , 46 ( 4 ): 71 - 83 .
裴培 , 吴鹏 , 吕城锦 , 等 . 全国一体化算力网探索与研究 [J]. 通信世界 , 2025 ( 7 ): 36 - 41 .
PEI Pei , WU Peng , LYU Chengjin , et al . Exploration and research on national integrated computing power network [J]. Communications World , 2025 ( 7 ): 36 - 41 .
丁正阳 , 赵星 , 蔡昊 , 等 . 面向省内云边场景的电力通信网算网协同编排调度机制 [J]. 电力信息与通信技术 , 2025 , 23 ( 6 ): 78 - 84 .
DING Zhengyang , ZHAO Xing , CAI Hao , et al . Computing power and network cooperative scheduling mechanism of power communication network for intra-province cloud-edge scene [J]. Electric Power Information and Communication Technology , 2025 , 23 ( 6 ): 78 - 84 .
张文翰 , 周海浪 , 尤培培 , 等 . 考虑带宽和电力费用的数据中心工作流负载分配优化模型研究 [J]. 电力需求侧管理 , 2024 , 26 ( 3 ): 48 - 54 .
ZHANG Wenhan , ZHOU Hailang , YOU Peipei , et al . Research on the data center workflow load allocation optimization model considering bandwidth and electricity costs [J]. Power Demand Side Management , 2024 , 26 ( 3 ): 48 - 54 .
李彬 , 杜亚彬 , 曹望璋 , 等 . 计及负载特性的数据中心微电网双层优化配置 [J]. 电力工程技术 , 2023 , 42 ( 2 ): 75 - 83 .
LI Bin , DU Yabin , CAO Wangzhang , et al . Bi-level optimal configuration of microgrid in data center considering load characteristics [J]. Electric Power Engineering Technology , 2023 , 42 ( 2 ): 75 - 83 .
宋坤 , 顾文波 . 考虑不确定性的综合能源系统建模及优化研究进展 [J]. 综合智慧能源 , 2025 , 47 ( 7 ): 32 - 43 .
SONG Kun , GU Wenbo . Research progress on modeling and optimization of integrated energy systems considering uncertainty [J]. Integrated Intelligent Energy , 2025 , 47 ( 7 ): 32 - 43 .
吴限 , 孙衍宁 , 马昊 , 等 . 基于AI Agent的数据中心冷水机组健康监测方法 [J]. 工业工程 , 2026 , 29 ( 3 ): 84 - 93 .
WU Xian , SUN Yanning , MA Hao , et al . A health monitoring method for data center chiller units based on AI agent [J]. Industrial Engineering Journal , 2026 , 29 ( 3 ): 84 - 93 .
MA S Y , DING W , LIU Y , et al . Digital twin and big data-driven sustainable smart manufacturing based on information management systems for energy-intensive industries [J]. Applied Energy , 2022 , 326 : 119986 .
ZHU H T , LIN B T . Digital twin-driven energy consumption management of integrated heat pipe cooling system for a data center [J]. Applied Energy , 2024 , 373 : 123840 .
LU R Y , LI X , CHEN R H , et al . An Alternative Reinforcement Learning (ARL) control strategy for data center air-cooled HVAC systems [J]. Energy , 2024 , 308 : 132977 .
林嘉瑜 , 韩俊涛 , 王永真 , 等 . 计及(火用)效率的低碳数据中心算力综合能源系统规划及运行优化 [J]. 上海交通大学学报 , 2025 , 59 ( 9 ): 1327 - 1337 .
LIN Jiayu , HAN Juntao , WANG Yongzhen , et al . Capacity planning and operational optimization for low-carbon data center integrated energy system considering exergy efficiency [J]. Journal of Shanghai Jiao Tong University , 2025 , 59 ( 9 ): 1327 - 1337 .
甘润东 , 龙玉江 , 汤杰 , 等 . 计及负荷时空转移需求响应的数据中心聚合商最优运行策略 [J]. 中国电力 , 2024 , 57 ( 3 ): 20 - 26 .
GAN Rundong , LONG Yujiang , TANG Jie , et al . Optimal operation strategy of data center aggregators for demand response considering temporal and spatial load shift [J]. Electric Power , 2024 , 57 ( 3 ): 20 - 26 .
RUAN J Q , ZHU Y F , CAO Y J , et al . Privacy-preserving bi-level optimization of Internet data centers for electricity-carbon collaborative demand response [J]. IEEE Internet of Things Journal , 2024 , 11 ( 14 ): 24948 - 24959 .
张东升 , 黄媛 , 许潇 , 等 . 基于个性化联邦强化学习的多园区综合能源系统低碳经济调度 [J]. 电网技术 , 2026 , 50 ( 1 ): 81 - 91 .
ZHANG Dongsheng , HUANG Yuan , XU Xiao , et al . Low-carbon economic dispatch of multi-park integrated energy systems based on personalized federated reinforcement learning [J]. Power System Technology , 2026 , 50 ( 1 ): 81 - 91 .
RADOVANOVIĆ A , KONINGSTEIN R , SCHNEIDER I , et al . Carbon-aware computing for datacenters [J]. IEEE Transactions on Power Systems , 2023 , 38 ( 2 ): 1270 - 1280 .
杨挺 , 姜含 , 侯昱丞 , 等 . 基于计算负荷时–空双维迁移的互联多数据中心碳中和调控方法研究 [J]. 中国电机工程学报 , 2022 , 42 ( 1 ): 164 - 176 .
YANG Ting , JIANG Han , HOU Yucheng , et al . Study on carbon neutrality regulation method of interconnected multi-datacenter based on spatio-temporal dual-dimensional computing load migration [J]. Proceedings of the CSEE , 2022 , 42 ( 1 ): 164 - 176 .
王辉东 , 高晋坤 , 黄佳斌 , 等 . 考虑数据中心负载灵活性的电力系统运行可靠性评估方法 [J]. 电力系统保护与控制 , 2023 , 51 ( 21 ): 96 - 105 .
WANG Huidong , GAO Jinkun , HUANG Jiabin , et al . Power system operational reliability evaluation method considering data center load flexibility [J]. Power System Protection and Control , 2023 , 51 ( 21 ): 96 - 105 .
向梓旸 , 黄淳驿 , 李康平 , 等 . 考虑负载时空转移特性的数据中心集群算电协同优化调度 [J]. 电力信息与通信技术 , 2026 , 24 ( 3 ): 33 - 44 .
XIANG Ziyang , HUANG Chunyi , LI Kangping , et al . Computing-power synergistic scheduling of Internet data centre clusters considering spatio-temporal load transfer characteristics [J]. Electric Power Information and Communication Technology , 2026 , 24 ( 3 ): 33 - 44 .
兰洲 , 蒋晨威 , 谷纪亭 , 等 . 促进可再生能源发电消纳和碳减排的数据中心优化调度与需求响应策略 [J]. 电力建设 , 2022 , 43 ( 4 ): 1 - 9 .
LAN Zhou , JIANG Chenwei , GU Jiting , et al . Optimal dispatch and demand response strategies of data centers for promoting accommodation of renewable energy generation and reducing carbon emission [J]. Electric Power Construction , 2022 , 43 ( 4 ): 1 - 9 .
ZHAO J , CHEN Z Y , LI H N , et al . A model predictive control for a multi-chiller system in data center considering whole system energy conservation [J]. Energy and Buildings , 2024 , 324 : 114919 .
YANG T , HOU Y X , CAI S T , et al . Multi-data center tie-line power smoothing method based on demand response [J]. IEEE Transactions on Cloud Computing , 2024 , 12 ( 4 ): 983 - 995 .
MA S Y , ZHANG M M , CHENG S , et al . End-edge-cloud collaborative-driven waste-heat prediction of liquid cooling system for high-performance computing data centers [J]. Engineering Applications of Artificial Intelligence , 2026 , 171 : 114165 .
杨蓓佳 , 赵清松 , 刘 刚 , 等 . 考虑需求响应的风光热联合出力优化调度 [J]. 东北电力技术 , 2024 , 45 ( 3 ): 1 - 6 .
YANG Beijia , ZHAO Qingsong , LIU Gang , et al . Optimal scheduling of wind-PV-CSP hybrid power considering demand response [J]. Northeast Electric Power Technology , 2024 , 45 ( 3 ): 1 - 6 .
刘兴杰 , 王晨 , 梁英 , 等 . 基于TimesNet的多源特征融合非侵入式负荷监测 [J]. 综合智慧能源 , 2026 , 48 ( 7 ): 1 - 12 .
LIU Xingjie , WANG Chen , LIANG Ying , et al . Non-intrusive load monitoring based on multi-source feature fusion with TimesNet [J]. Integrated Intelligent Energy , 2026 , 48 ( 7 ): 1 - 12 .
王臻 , 刘东 , 徐重酉 , 等 . 新型电力系统多源异构数据融合技术研究现状及展望 [J]. 中国电力 , 2023 , 56 ( 4 ): 1 - 15 .
WANG Zhen , LIU Dong , XU Chongyou , et al . Status quo and prospect of multi-source heterogeneous data fusion technology for new power system [J]. Electric Power , 2023 , 56 ( 4 ): 1 - 15 .
吴兴扬 , 戴剑丰 . 基于多尺度自适应时空图卷积网络与BERT模型的多节点短期负荷预测 [J]. 电网技术 , 2025 , 49 ( 9 ): 3756 - 3766 .
WU Xingyang , DAI Jianfeng . Multi-node short-term load forecasting based on multi-scale adaptive spatio-temporal graph convolutional network and BERT model [J]. Power System Technology , 2025 , 49 ( 9 ): 3756 - 3766 .
ZHENG H W , LU Y , SUN Z K , et al . Energy optimisation in cloud datacentres with MC-TIDE: Mixed channel time-series dense encoder for workload forecasting [J]. Applied Energy , 2024 , 374 : 123903 .
MA S Y , CAO Y C , LIU Y . Edge computing-enabled energy efficiency prediction of immersion cooling system for supercomputing centers [J]. Cleaner Engineering and Technology , 2025 , 27 : 101014 .
文淅宇 , 朱继忠 , 李盛林 , 等 . 基于时空协同的多数据中心虚拟电厂低碳经济调度策略 [J]. 电力系统自动化 , 2024 , 48 ( 18 ): 56 - 65 .
WEN Xiyu , ZHU Jizhong , LI Shenglin , et al . Low-carbon economic dispatch for multiple data center virtual power plant based on spatio-temporal collaboration [J]. Automation of Electric Power Systems , 2024 , 48 ( 18 ): 56 - 65 .
岳佳明 , 钟建伟 , 梁会军 , 等 . 云储能与含数据中心的多微网系统双层优化调度 [J]. 山东电力技术 , 2025 , 52 ( 10 ): 91 - 101, 112 .
YUE Jiaming , ZHONG Jianwei , LIANG Huijun , et al . Bi-level optimal scheduling of cloud energy storage and multi-microgrid system with data center [J]. Shandong Electric Power , 2025 , 52 ( 10 ): 91 - 101, 112 .
XUE L , WANG J X , LI H T , et al . Online energy conservation scheduling for geo-distributed data centers with hybrid data-driven and knowledge-driven approach [J]. Energy , 2025 , 322 : 135714 .
ZHANG Q G , CHNG C B , CHUI C K , et al . Uncertainty-aware online learning of dynamic thermal control in data center with imperfect pretrained models [J]. Expert Systems with Applications , 2024 , 249 : 123767 .
张龙飞 , 徐辉 , 朱克东 , 等 . 考虑安全约束的物理信息引导智能调度方法研究 [J]. 电网技术 , 2026 , 50 ( 3 ): 1061 - 1070 .
ZHANG Longfei , XU Hui , ZHU Kedong , et al . Research on security-constrained physics-informed intelligent dispatch method [J]. Power System Technology , 2026 , 50 ( 3 ): 1061 - 1070 .
吴成邦 , 程志江 , 陆海峰 , 等 . 考虑隐私保护的含互联网数据中心的综合能源系统时空联合规划 [J]. 电力建设 , 2025 , 46 ( 4 ): 84 - 98 .
WU Chengbang , CHENG Zhijiang , LU Haifeng , et al . Spatio-temporal joint planning for integrated energy systems with Internet data center considering privacy preservation [J]. Electric Power Construction , 2025 , 46 ( 4 ): 84 - 98 .
鲁浩 , 李文博 , 蔡继增 , 等 . 计及风光不确定性与算力灵活性的数据中心两阶段随机优化 [J]. 电力建设 , 2026 , 47 ( 7 ): 14 - 24 .
LU Hao , LI Wenbo , CAI Jizeng , et al . Two-stage stochastic optimization for data centers considering wind and PV power uncertainty and computational flexibility [J]. Electric Power Construction , 2026 , 47 ( 7 ): 14 - 24 .
GAO Y Q , YU N P . Model-augmented safe reinforcement learning for Volt-var control in power distribution networks [J]. Applied Energy , 2022 , 313 : 118762 .
李明睿 , 朱介北 , 俞露杰 , 等 . 实现新能源最大利用的多数据中心自适应负荷调度算法 [J]. 中国电机工程学报 , 2025 , 45 ( 6 ): 2071 - 2083 .
LI Mingrui , ZHU Jiebei , YU Lujie , et al . Adaptive spatio-temporal tasks scheduling algorithm in regional interconnected data centers [J]. Proceedings of the CSEE , 2025 , 45 ( 6 ): 2071 - 2083 .
马子轩 , 翟季冬 , 韩文弢 , 等 . 高效训练百万亿参数预训练模型的系统挑战和对策 [J]. 中兴通讯技术 , 2022 , 28 ( 2 ): 51 - 58 .
MA Zixuan , ZHAI Jidong , HAN Wentao , et al . Challenges and measures for efficient training of trillion-parameter pre-trained models [J]. ZTE Technology Journal , 2022 , 28 ( 2 ): 51 - 58 .
0
浏览量
3
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