基于知识图谱的台区线损异常分析

Analysis of Abnormal Line Loss in Transformer Area Based on Knowledge Graph

电网公司的基本职能之一是提供安全可靠的电能,而线损率是衡量电能质量及电网经济效益的核心标准。能够及时发现并解决台区线损异常是电网公司关注的重点。近年新兴的知识图谱技术能够清楚地描述实体之间的关系,并能将复杂的自然语言转化成脉络清晰的三元组,因此,可将知识图谱技术运用到台区线损异常原因判断中。根据电网信息系统中的电力数据构建出台区线损异常知识图谱,分析各类异常原因特征并构建判断规则,经过推演格算法优化构建出台区线损异常原因判断方法。经实例验证,所提方法在台区线损异常原因判断方面的准确度优于电网方法,并极大地提升了判断速度,具有实用性和高效性,为知识图谱技术在电力行业的应用提供了新思路。

Providing safe and reliable power is one of the basic functions of a power grid company,and the line loss rate is the core measurement to indicate the power quality and economic benefits of the power grid.It is essential for a power grid company to find and cope with the abnormal transformer areas line loss in time.In recent years,the emerging knowledge graph technology can clearly describe the relationship among entities and transform complex natural language into unambiguous triples.Therefore,the knowledge graph can be adopted to determine the cause of abnormal transformer area line loss.The knowledge graph of abnormal transformer areas line loss was constructed according to the power data in the power grid information system,features of various anomaly causes were analyzed and the criteria rules were established meanwhile.The method to determine the cause of the abnormal transformer area line loss was established with optimization of the deduction lattice algorithm.In experiments,the accuracy of the proposed method in the judgment of the cause of abnormal transformer area line loss is better than the grid method.and it greatly improves the speed of judgment.The proposed method has practicability and efficiency,provides new ideas for the application of knowledge graph technology in the power industry.