摘要
针对电网调控多维信息缺乏有效地检索手段,提出面向电网调控信息智能检索的知识图谱构建方法,基于深度学习识别调度运行规程关键信息间的语义关系,采用规则转换方法抽取电网模型信息,通过融合对象化的调度运行规程知识和电网模型知识建立调控信息知识图谱,同时提出基于知识图谱的调控信息智能检索应用方案。通过算例验证了所提方法具有较高的识别准确率,能够支撑不同场景下调控信息的智能检索。
Lack of effective retrieval means for the multi-dimensional information of power grid dispatching and control,a knowledge graph construction method for the intelligent retrieval of power grid dispatching and control information is proposed.The semantic relationship of dispatching operation procedures key information is recognized based on deep learning,and the rule conversion method is used to extract the power grid model information.The dispatching and control information knowledge map is established by integrating the targeted knowledge of dispatching operation procedures and power grid model knowledge,and the application scheme of intelligent retrieval of dispatching and control information based on knowledge graph is proposed.The proposed method has been verified to have high recognition accuracy through numerical examples,and can support intelligent retrieval of regulatory information in different scenarios.
作者
刘东
张越
皮俊波
单连飞
刘赫
宋鹏程
姜涛
LIU Dong;ZHANG Yue;PI Junbo;SHAN Lianfei;LIU He;SONG Pengcheng;JIANG TAO(National Electric Power Dispatching and Control Center of State Grid Corporation of China,Beijing 100031,China;NARI Group Corporation(State Grid Electric Power Research Institute),Nanjing 211106,China;Beijing Kedong Electric Power Control System Co.,Ltd.,Beijing 100192,China)
出处
《中国电力》
CSCD
北大核心
2023年第7期78-84,共7页
Electric Power
基金
国家电网公司总部科技项目(5100-202118456A-0-0-00)。
关键词
电网调度
深度学习
知识抽取
知识图谱
power grid dispatching
deep learning
knowledge extraction
knowledge graph
作者简介
刘东(1982-),男,硕士,从事电力系统调度运行控制研究,E-mail:liu-dong@sgcc.com.cn;通信作者:张越(1989-),男,硕士,从事人工智能技术在电力系统的应用研究,E-mail:zhangyue3655@163.com。
