基于自适应权重MOEAD的台区电能表误差在线预测  被引量:2

On-line error prediction method for station area power meter based on WA-MOEA/D

在线阅读下载全文

作  者:滕永兴 翟术然 卢静雅 孙源祥 李琳 李祺 TENG Yongxing;ZHAI Shuran;LU Jingya;SUN Yuanxiang;LI Ling;LI Qi(Tianjin Electric Power Company Marketing Service Centre(Center of Measurement),Tianjin 300202,China;School of Electrical Engineering and Automation,Tianjin Uni versity,Tianjin 300072,China)

机构地区:[1]国网天津市电力公司营销服务中心(计量中心),天津300202 [2]天津大学电气自动化与信息工程学院,天津300072

出  处:《中国测试》2023年第S01期225-230,共6页China Measurement & Test

基  金:国家电网公司总部科技项目(KJ22-1-12)

摘  要:对台区电能表的运维管理主要采用现场定期轮换检定,此意味着人力、物力的大量浪费。该文基于物联网技术搭建电能表在线校准评价系统,利用台区电能量守恒原理构建电能表误差预测模型。采用双权重自适应调整的MOEA/D(WA-MOEA/D)实现快速多目标优化,构建电能表状态评价数学模型。通过实验对比WA-MOEA/D与MOEA/D。收敛性方面,WA-MOEA/D收敛性指标IGD为0.235,而MOEA/D为0.16;准确性方面,WA-MOEA/D其电能表误差综合效用为0.2,而MOEA/D为0.0018;快速性方面,在迭代200次时,WA-MOEA/D计算时间为2.66s,而MOEA/D为7.87s。因此采用WA-MOEA/D算法更加快速地分析得到更加准确的电能表误差值,实现台区电能表误差在线预测。The operation and maintenance management of the electric energy meters in the substation area mainly adopts the on-site periodic rotation verification,resulting in the waste of human and material resources.In this paper,an online calibration and evaluation system of watt-hour meter is built using the Internet of Things technology.Based on the principle of energy conservation in the station area,an error prediction model of watt-hour meter is built.The non-convex sparse multi-objective optimization is realized based on the dual-type weight adaptive adjustment MOEA/D algorithm(WA-MOEA/D).The effectiveness of WA-MOEA/D and MOEA/D is compared through experiments.In terms of convergence,the IGD of WA-MOEA/D is 0.235,while the MOEA/D is 0.16.In terms of accuracy,using the WA-MOEA/D,the comprehensive utility of the electricity meter error is 0.2,while using the MOEA/D is 0.0018.In terms of speed,when iterating 200 times,the WA-MOEA/D has a calculation time of 2.66 seconds,while the MOEA/D takes 7.87 seconds.Therefore,the WA-MOEA/D is used to analyze and obtain more accurate error values of electricity meters more quickly for its online prediction.

关 键 词:WA-MOEA/D 多目标优化 台区电能表 在线校准 电能量守恒 

分 类 号:TM933.4[电气工程—电力电子与电力传动]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象