数据与知识联合驱动的人工智能方法在电力调度中的应用综述  

Review on Application of Combined Data-knowledge-driven Artificial Intelligence Methods in Power Dispatching

作　　者：李鹏 黄文琦[1,2] 王鑫 梁凌宇[1,2] 闫昆鹏[2,3] 孙凌云 LI Peng;HUANG Wenqi;WANG Xin;LIANG Lingyu;YAN Kunpeng;SUN Lingyun(Digital Grid Research Institute Co.,Ltd.,China Southern Power Grid,Guangzhou 510663,China;Zhejiang University-China Southern Power Grid Joint Research Centre on AI,Hangzhou 310058,China;College of Computer Science and Technology,Zhejiang University,Hangzhou 310058,China)

机构地区：[1]南方电网数字电网研究院有限公司,广东省广州市510663 [2]浙江大学南方电网人工智能创新联合研究中心,浙江省杭州市310058 [3]浙江大学计算机科学与技术学院,浙江省杭州市310058

出　　处：《电力系统自动化》2024年第1期160-175,共16页Automation of Electric Power Systems

基　　金：国家重点研发计划资助项目(2020YFB0906005)。

摘　　要：数据与知识联合驱动的人工智能方法是利用数据驱动和知识驱动各自优势、取长补短形成的一种更优的联合方法。文中对联合驱动方法的特点和现状进行了分析,并对其电力调度重点应用场景进行了分类统计。总结了各类场景中联合方法的创新性、相较于单一方法的提升以及应用优势。归纳出了电力调度数据与知识联合驱动方法的3种联合建模方式:数据驱动优化知识驱动、知识驱动辅助数据驱动、数据驱动与知识驱动混合模式。最后,从准确性和高效性的平衡、有效性、可靠性等5个维度讨论了联合建模时存在的挑战性问题,对联合驱动方法在电力调度中的适用场景进行了总结及展望。The combined data-knowledge-driven artificial intelligence method is a better combined method that utilizes the advantages of data-driven and knowledge-driven methods,complementing each other's strengths and weaknesses.The paper analyzes the characteristics and current situation of the combined-driven methods,classifies and calculates its key application scenarios in power dispatching.The innovation,improvement,and application advantages of combined-driven methods in various scenarios compared to single methods are summarized.Three combined modeling methods for power dispatching combined dataknowledge-driven methods have been summarized:data-driven optimizing knowledge-driven mode,knowledge-driven assisting data-riven mode,and hybrid data-knowledge-driven mode.Finally,the challenging issues in combined modeling are discussed from five dimensions:the balance between accuracy and efficiency,effectiveness,and reliability.The application scenarios of combined-driven methods in power dispatching are discussed and prospected.

关 键 词：电力调度 人工智能 数据驱动 知识驱动 联合驱动 

分 类 号：TM73[电气工程—电力系统及自动化] TP18[自动化与计算机技术—控制理论与控制工程]