部分可观测条件下的配电网数据驱动最优潮流模型  

A Data-Driven Optimal Power Flow Model under Partial Observability

作　　者：李鹏华 宋卓然 吴文传[1] LI Penghua;SONG Zhuoran;WU Wenchuan(Tsinghua University,Beijing 100091,China;State Grid Liaoning Electric Power Supply Co.,Ltd.,Shenyang 11006,China)

机构地区：[1]清华大学,北京100091 [2]国网辽宁省电力有限公司,辽宁沈阳110006

出　　处：《中国电力》2023年第12期51-57,共7页Electric Power

基　　金：国家电网有限公司科技项目(面向新型电力系统的配电网二次系统规划设计关键技术研究,5400-202256273A-2-0-XG)。

摘　　要：电力系统最优潮流计算是典型的非线性非凸问题,线性化潮流模型主要用于将原始最优潮流问题转化为凸优化问题。配电网覆盖范围广,设备众多,模型参数维护困难,已有的基于数据驱动的线性化潮流模型多基于完备的系统量测数据,而实际中考虑经济性安装的测量单元,无法覆盖所有设备,系统量测通常是部分可观测的。为解决量测的部分可观测性问题,提出一种数据驱动线性潮流模型,并基于此构建基于数据驱动的线性化最优潮流模型,该模型对量测中的不良数据具有鲁棒性。通过对不同部分可观测场景的测试,验证了所提模型的有效性。The linearized power flow(PF)model is mainly used to make the optimal power flow(OPF)problem convex.However,existing data-driven linear PF models are mostly based on complete system measurement data.Moreover,the systems are usually partially observable due to limited measuring devices for economical installation.This paper addresses the partial observability issue by proposing a data-driven linear PF model,which can be embedded in OPF.The model is robust against bad data in measurements,with its accuracy verified by numerical tests.The work is supported by Science and Technology Project of SGCC(Research on Critical Technology of secondary system planning and Design of Distribution Network for Novel Power System,No.5400-202256273A-2-0-XG).

关 键 词：数据驱动 线性化最优潮流 部分可观测 

分 类 号：TM744[电气工程—电力系统及自动化]