半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
考虑分时段状态行为的非侵入式负荷分解方法
作者:
作者单位:

华北电力大学电气与电子工程学院,北京市 102206

作者简介:

崔亮节(1996—),男,通信作者,硕士研究生,主要研究方向:非侵入式负荷监测。E-mail: 565838529@qq.com
孙毅(1972—),男,教授,博士生导师,主要研究方向:电力系统通信与信息处理、智能用电与需求响应。E-mail: sy@ncepu.edu.cn
刘耀先(1990—),男,博士研究生,主要研究方向:非侵入式负荷分解、智能电表数据挖掘。E-mail: lpxlyx@126.com

通信作者:

基金项目:

国家自然科学基金资助项目(5177068)。


Non-intrusive Load Disaggregation Method Considering Time-phased State Behavior
Author:
Affiliation:

School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China

Fund Project:

This work is supported by National Natural Science Foundation of China (No. 51777068).

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    负荷监测是智能用电的一个重要环节,针对现有低频非侵入式负荷分解方法需要较多先验信息,且对功率相近或小功率负荷的辨识精度较低的问题,提出了一种考虑分时段状态行为的非侵入式负荷分解方法。首先,对负荷设备的功率数据进行聚类分析,构建负荷状态模板。提出一种不需要指定时间段个数的负荷典型行为时间段智能寻优方法,分时段提取负荷状态行为规律,构建负荷行为模板。然后,在传统功率特征的基础上,综合考虑概率和时间2个维度,将分时段状态概率因子(TSPF)作为负荷新特征引入目标函数,通过多特征遗传优化迭代实现负荷分解。最后,在公开数据集上验证了所提方法的有效性和准确性。

    Abstract:

    Load monitoring is an important part of intelligent electricity consumption. A non-intrusive load disaggregation method considering time-phased state behavior is proposed to solve the problem that existing low frequency non-intrusive load disaggregation methods require more priori information and have lower accuracy for load with similar or lower power. Firstly, power data of the load device is clustered to construct a load state template.An intelligent optimization method for the typical behavior time period that does not require a specified number of time periods is proposed. Load state behavior law is extracted by time-phase to construct a load behavior template. Then, on the basis of the traditional power characteristics, considering the two dimensions of probability and time, the time-phased state probability factor (TSPF) is introduced into the objective function as a new load characteristic, and the load disaggregation is realized by multi-feature genetic optimization iteration. Finally, the validity and accuracy of the method are verified on the public data set.

    表 3 各方法功率分解准确度对比Table 3 Comparison of power decomposition accuracy for each method
    表 4 Table 4
    表 9 Table 9
    表 5 Table 5
    表 7 Table 7
    图1 染色体编码方案Fig.1 Coding scheme for chromosome
    图2 考虑分时段状态行为的NILM方法流程图Fig.2 Flow chart of NILM method considering time-phased state behavior
    图3 所提方法求解时间Fig.3 Solution time of proposed method
    图 典型负荷有功功率时间分布图Fig. Time distribution chart of active power of typical load
    图 负荷典型状态行为时间段智能寻优流程图Fig. Intelligent optimization flow chart of load typical state behavior time period
    图 场景1各负荷状态聚类结果Fig. The clustering results of load states in scene 1
    图 场景1各负荷全天状态行为概率分布图Fig. Probability distribution of all-day state behavior of each load in scene 1
    图 场景1各负荷典型行为时间段智能寻优结果Fig. The results of typical behavioral time period intelligent optimization of each load in scene 1
    图 场景1各负荷分时段状态行为分布图Fig. Time-phased state behavior distribution of each load in scene 1
    图 场景1本文方法权重因子自适应选优结果Fig. Adaptive selection result of weighting factors of the method in scene 1
    图 场景1本文方法分解结果Fig. Decomposition results of the method in scene 1
    表 2 各方法状态识别准确率对比Table 2 Comparison of state recognition accuracy for each method
    表 1 3种负荷设备组合场景对比Table 1 Scenarios comparisons of three load equipment combinations
    表 6 Table 6
    表 8 Table 8
    参考文献
    相似文献
    引证文献
引用本文

崔亮节,孙毅,刘耀先,等.考虑分时段状态行为的非侵入式负荷分解方法[J].电力系统自动化,2020,44(5):215-222. DOI:10.7500/AEPS20190225006.
CUI Liangjie,SUN Yi,LIU Yaoxian,et al.Non-intrusive Load Disaggregation Method Considering Time-phased State Behavior[J].Automation of Electric Power Systems,2020,44(5):215-222. DOI:10.7500/AEPS20190225006.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-02-25
  • 最后修改日期:2019-07-09
  • 录用日期:
  • 在线发布日期: 2020-03-08
  • 出版日期: