基于时空网络的充电桩电能表测量不确定度评定方法研究

李博; 廖耀华; 范云方; 邱鹏锦; 戴煊丁

李博,廖耀华,范云方,邱鹏锦,戴煊丁.基于时空网络的充电桩电能表测量不确定度评定方法研究[J].电测与仪表,2026,63(2):188-194.
LI Bo,LIAO Yaohua,FAN Yunfang,QIU Pengjin,DAI Xuanding.Research on measurement uncertainty evaluation method for smart meter of charger piles based on spatio-temporal neural networks[J].Electrical Measurement & Instrumentation,2026,63(2):188-194.

基于时空网络的充电桩电能表测量不确定度评定方法研究

Research on measurement uncertainty evaluation method for smart meter of charger piles based on spatio-temporal neural networks

DOI：10.19753/j.issn1001-1390.2026.02.020

中文关键词: 新能源汽车充电桩智能电能表卷积双向长短期记忆网络时间切片方法测量不确定度

英文关键词:new energy vehicle charging piles, smart meter, convolutional bidirectional long short-term memory

基金项目:中国南方电网有限责任公司科技项目（YNKJXIM20220175）

作者中文名	作者英文名	单位
李博	LI Bo	1、云南电网有限责任公司电力科学研究院 2、云南省绿色能源与数字电力量测及控保重点实验室
廖耀华	LIAO Yaohua	1、云南电网有限责任公司电力科学研究院 2、云南省绿色能源与数字电力量测及控保重点实验室
范云方	FAN Yunfang	云南电网有限责任公司曲靖供电局
邱鹏锦	QIU Pengjin	云南电网有限责任公司曲靖供电局
戴煊丁	DAI Xuanding	中国计量大学

摘要点击次数: 77

中文摘要:

对现有运营类充电桩电能表开展强检及监管面临着成本高、效率低、任务重、人员短缺等问题，且目前基于数据驱动的电能表性能分析精度有待提高。为此，文章提出一种基于卷积双向长短期记忆网络的时间切片方法来估计电能表的测量不确定度。针对智能电能表采集到的充电设施运行数据存在的时空特性，设计卷积网络提取变量间空间特征，并将提取的特征输入双向长短期记忆网络中，用以进一步捕捉数据时序特征,考虑到电能表运行过程受环境和充电需求影响而长期处于非平稳状态，因此采用时间切片方案实时计算局部时段内的测量不确定度。该方案在某地新能源汽车充电站中进行了验证，并与PSO-BPNN、DREM-DRLS和EKF-LMRLS模型进行对比，实验结果表明文章所提方法在充电桩电能表测量不确定度预测精度上有较大优势，设计的三种模型性能评价指标至少有11.45%以上的提升。

英文摘要:

The inspection and regulation of existing operational charging pile meters face problems such as high cost, low efficiency, heavy workload, and shortage of personnel. Additionally, the current performance analysis accuracy of data-driven electricity metering needs improvement. To solve this problem, a time-slicing method based on convolutional bidirectional long short-term memory networks(C-BiLSTM-TS) is proposed to estimate the measurement uncertainty of electricity meters. Considering the spatiotemporal characteristics of the charging facility operation data collected by smart meters, convolutional networks are employed to extract spatial features between variables. The extracted features are then fed into the BiLSTM networks to capture temporal characteristics of the data. Furthermore, since the operation of electricity meters is influenced by the environment and charging demands, which results in long-term non-stationary states, a time-slice method is used to calculate the measurement uncertainty in real-time within time intervals. The proposed method has been validated in a new energy vehicle charging station and compared with PSO-BPNN, DREM-DRLS, and EKF-LMRLS models. The experimental results show that the proposed method has a significant advantage in predicting the measurement uncertainty of charging pile meters, and three performance evaluation indicators of the model have improved by at least 11.45%.

查看全文查看/发表评论下载PDF阅读器

关闭