基于分布式实时计算框架的低压台区线损智能诊断分析

Intelligent Diagnosis and Analysis of the Station Area Line Loss Based on Distributed Real-Time Computing Framework

针对低压台区复杂的现场情况,通过研究分析影响台区线损率的因素,实时准确的分析线损率变化的原因,便于对台区线损进行个性化细化管理,更加准确的定位问题台区。本文致力于进一步推动台区线损管理由结果管理向过程管理转变,提高低压台区线损管理水平和工作质量,从硬件、软件、服务三个方面提出了改善低压台区线损治理问题的方法。通过加装智能硬件设备可提供数据支撑,识别台户关系,实现分时、分段、分支、分相的线损计算,定位高损、负损台区具体位置。基于业务规则判断台区线损是否异常,利用智能用电大数据及数据挖掘分析技术对台区线损异常进行智能诊断分析,生成智能诊断分析报告,为线损异常问题整改提供咨询支撑,辅助现场人员做分析决策。另外在提升系统运行效率的同时也保障系统的业务扩展性与灵活性,增加实时计算功能的同时对现有的集中式关系型数据库进行分布式化改造。在国网某省级电力公司用电信息采集系统优化升级改造项目中的工程应用,对提升线损异常智能化、精益化的管控能力取得了很好的成效。

In view of the complex site situation of the station area, through the study and analysis of the factors affecting the line loss rate of the station area, real-time and accurate analysis of the reasons for the change of the line loss rate, it is convenient for personalized and detailed management of the line loss of the station area, and more accurate positioning of the problem platform area. This article is committed to further promoting the transformation of the line loss management in the station area from result management to process management, improving the level of line loss management and work quality in the low-voltage station area, and proposes ways to improve the line loss management of the low-voltage station area from the three aspects of hardware, software and service. By installing intelligent hardware equipment, it can provide data support, identify the relationship between users, realize time-sharing, segment, branch, and phase loss calculations, and locate the specific locations of high-loss and negative-loss stations. Determine whether the line loss in the station area is abnormal based on business rules, use intelligent electricity big data and data mining analysis technology to perform intelligent diagnosis and analysis on the abnormal line loss in the station area, generate an intelligent diagnosis analysis report, and provide consulting support and assistance for the correction of abnormal line loss problems on-site personnel make analytical decisions. In addition, while improving the operating efficiency of the system, it also guarantees the business scalability and flexibility of the system, adding real-time computing functions, and carrying out distributed transformation of the existing centralized relational database. The engineering application in the optimization and upgrading project of the electricity consumption information collection system of a provincial power company of State Grid has achieved good results in improving the abnormally intelligent and lean management and control capabilities of line loss.