Non-intrusive load identification method based on optimal signatures and improved random forest

李利刚; 刘 浩; 陈建强; 王昊川; 罗世超; 高 源; 李凤朝

doi:10.3969/j.issn.1009-1831.2024.03.009

您当前的位置：

首页 >

文章列表页 >

Non-intrusive load identification method based on optimal signatures and improved random forest

更新时间：2026-03-05

- Non-intrusive load identification method based on optimal signatures and improved random forest
- Vol. 26, Issue 3, (2024)
- 作者机构：
  
  1. 国网天津市电力公司宝坻供电分公司,天津,301800
  2. 天津求实智源科技有限公司,天津,300392
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1009-1831.2024.03.009
  CLC：
- Published：2024
- 稿件说明：
移动端阅览
李利刚, 刘浩, 陈建强, et al. Non-intrusive load identification method based on optimal signatures and improved random forest[J]. 2024, 26(3).
DOI：

李利刚, 刘浩, 陈建强, et al. Non-intrusive load identification method based on optimal signatures and improved random forest[J]. 2024, 26(3). DOI： 10.3969/j.issn.1009-1831.2024.03.009.

摘要

非侵入式负荷监测方法是实现电网智能化的关键技术，有助于优化能量管理，促进能源高效利用。为了应对目前大多数负荷辨识模型存在的特征冗余、识别精度有限和计算效率低下等问题，提出了一种基于最优特征和改进随机森林的新型非侵入式负荷辨识方法。首先，通过递归特征消除方法从众多负荷特征中自主确定最优特征组合，以减少信息冗余。然后，确定不同决策树的权重数值，通过构建加权随机森林模型来实现电器负荷的辨识。为了进一步提高算法的精确度，利用改进鲸鱼算法对随机森林的重要参数进行优化。最终在公开数据集进行实验验证，证明所提负荷辨识方法具有准确性和优越性。

Abstract

Non-intrusive load monitoring method is a critical technology for realizing power system intelligence

which helps to optimize energy management and promote efficient energy utilization. In order to cope with the existing problems of feature redundancy

limited recognition accuracy and computational inefficiency

a novel non-intrusive load identification method based on optimal signatures and improved random forest is proposed. Firstly

the optimal feature combination is autonomously determined by recursive feature elimination method to reduce the information redundancy. Then load identification is realized by constructing a weighted random forest model. The weights are established by utilizing out-of-bag data. Construction parameters of random forest are optimized using the improved whale algorithm. Ultimately

the experimental results prove the accuracy and superiority of the proposed load identification method.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Short-term power load forecasting based on load decomposition and identification

Microgrid optimization based on hybrid sine and cosine operators improved whale algorithm

Comprehensive energy package recommendation method based on user feature clustering

Research on non-intrusive load identification method based on ADASYN and image analysis

Ultra-short-term photovoltaic power prediction for random forests based on multiple feature analysis and extraction

Related Author

袁越

邓振立

李虎军

李子钰

朱俊澎

赵奕岚

毕洪波

韩锦涛

Related Institution

国网河南省电力公司经济技术研究院

河海大学电气与动力工程学院

东北石油大学电气信息工程学院

云南电网有限责任公司电力科学研究院

国网江苏电力有限公司苏州供电分公司

AI问答

⁰