基于防盗算法的多功能智能电力计量系统  

Multifunctional smart power metering system based on anti⁃theft algorithm

作　　者：何道远 潘韦 王志刚 李明冉 HE Daoyuan;PAN Wei;WANG Zhigang;LI Mingran(Nari-Tech Nanjing Control Systems Co.,Ltd.,Nanjing 211100,China)

机构地区：[1]国电南瑞南京控制系统有限公司,江苏南京211100

出　　处：《现代电子技术》2024年第12期177-181,共5页Modern Electronics Technique

基　　金：江苏省科技厅2016年产学研前瞻性基金项目(BY2016076)。

摘　　要：针对市场上传统数字电表的局限性,提出一种多功能智能电力计量系统。该系统通过集成物联网,实现智能电表的实时监控、波形谐波消除、防盗检测和负荷预测等功能。采用傅里叶分析对谐波进行分解,并使用电感器将失真降低30%,以满足IEEE 519标准。采用防盗算法,通过比较总用电量和单个电表用电量来识别异常情况。采用长短期记忆(LSTM)神经网络进行下一天的负荷预测,平均绝对百分误差为7.56%。实验结果表明,该系统在增强供电质量、安全性、实时监控以及合理的短期预测方面都较好地满足了市场的需求。In order to address limitations of conventional digital meters,a multi-functional smart electricity metering system is proposed.By integrating Internet of Things,the system can realize the real-time monitoring of smart meter,wave harmonics elimination,anti-theft detection,and load forecasting.Fourier analysis is used to decompose harmonics,and inductors are used to reduce distortion by 30%to meet IEEE 519 standards.In the anti-theft algorithm,the total and individual meter consumptions are compared to identify anomalies.A long short-term memory neural network can be used to provide next-day load forecasts with a mean absolute percentage error of 7.56%.The experimental results show that the system can meet the market demand well in enhancing power supply quality,safety,real-time monitoring,and reasonable short-term forecasting.

关 键 词：防盗算法 智能电表 电能计量系统 谐波消除 负荷预测 LSTM神经网络 

分 类 号：TN911.23-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]