融合多源数据和知识图谱的新型电力系统多尺度无功电压控制

周良才; 孙志豪; 李雷; 张楷

周良才,孙志豪,李雷,张楷.融合多源数据和知识图谱的新型电力系统多尺度无功电压控制[J].电测与仪表,2026,63(9):12-22.
Zhou liangcai,Sun Zhihao,Lilei,Zhangkai.Multi-scale reactive power and voltage control for novel power system based on multi-source data fusion and knowledge graph[J].Electrical Measurement & Instrumentation,2026,63(9):12-22.

融合多源数据和知识图谱的新型电力系统多尺度无功电压控制

Multi-scale reactive power and voltage control for novel power system based on multi-source data fusion and knowledge graph

DOI：10.19753/j.issn1001-1390.2026.09.002

中文关键词: 知识图谱深度强化学习多源数据融合无功优化

英文关键词:knowledge graph, deep reinforcement learning, multi-source data fusion, reactive power optimization

基金项目:国家电网有限公司华东分部科技项目（52992425001U）

作者中文名	作者英文名	单位
周良才	Zhou liangcai	国家电网有限公司华东分部
孙志豪	Sun Zhihao	国家电网有限公司华东分部
李雷	Lilei	国电南瑞南京控制系统有限公司
张楷	Zhangkai	国电南瑞南京控制系统有限公司

摘要点击次数: 70

中文摘要:

新型电力系统的“双高”特性给电力系统无功电压控制带来新挑战，文中提出了一种基于多源数据融合与知识图谱的电力系统多尺度无功电压控制方法，融合知识图谱和深度确定性策略梯度算法的逻辑推理和自主学习能力，构建高效、可解释的无功电压决策框架。文中基于知识图谱将电网实体和元件关系从高位空间映射到低维向量空间，采用TransE（translational embedding）模型量化三元组拟合度，并通过产生式规则和置信度计算进行符号逻辑推理，生成推荐执行动作集合，将知识图谱输出的推荐动作集成到深度确定性策略梯度算法框架中，综合考虑网损、电压偏差设计混合奖励函数，减少强化学习在探索过程中的盲目随机性，提升策略网络的收敛速度，通过实验验证了文中方法的有效性，引入知识图谱后算法在网损优化、电压稳定和控制效果等多指标效果显著。

英文摘要:

The “dual-high” characteristics of the novel power system pose new challenges to reactive power and voltage control in power systems. This paper proposes a multi-scale reactive power and voltage control method for power systems based on multi-source data fusion and knowledge graphs. It integrates the logical reasoning and autonomous learning capabilities of knowledge graphs and deep deterministic policy gradient algorithms to construct an efficient and interpretable reactive power and voltage decision-making framework. Based on knowledge graphs, the relationships between grid entities and components are mapped from high-dimensional space to low-dimensional vector space. The translational embedding (TransE) model is used to quantify the fit degree of triples, and symbolic logical reasoning is performed through production rules and confidence calculations to generate a set of recommended execution actions. The recommended actions output by the knowledge graphs are integrated into the deep deterministic policy gradient algorithm framework. A hybrid reward function is designed considering network loss and voltage deviation, reducing the blind randomness of reinforcement learning during exploration and improving the convergence speed of the policy network. Experiments verify the effectiveness of the proposed method. The algorithm achieves significant multi-index effects in network loss optimization, voltage stability, and control performance after introducing knowledge graphs.

查看全文查看/发表评论下载PDF阅读器

关闭