Anomaly detection for carbon trading data in power system based on improved isolation forest method

ZHANG Xu; WANG Xudong; HE Xin; WANG Lin; FENG Quehe; LIU Bin

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Anomaly detection for carbon trading data in power system based on improved isolation forest method

更新时间：2025-12-06

- Anomaly detection for carbon trading data in power system based on improved isolation forest method
- Vol. 62, Issue 6, (2025)
- 作者机构：
  
  1. 国网天津市电力公司
  2. 国网信息通信产业集团有限公司
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2025
- 稿件说明：
移动端阅览
ZHANG Xu, WANG Xudong, HE Xin, et al. Anomaly detection for carbon trading data in power system based on improved isolation forest method[J]. 2025, 62(6).
DOI：

ZHANG Xu, WANG Xudong, HE Xin, et al. Anomaly detection for carbon trading data in power system based on improved isolation forest method[J]. 2025, 62(6). DOI：

摘要

随着我国电力系统碳资产交易机制的逐步完善，交易日趋活跃，碳资产交易种类和数据量的快速增加为碳资产运营部门的数据归集和管理等带来了挑战。为了提高运营部门对碳资产归集数据的管理效率，文中研究了基于改进孤立森林算法的多源碳资产归集数据异常检测方法。文中论述了交易中常见的多源碳资产类型和归集数据的特点，提出了基于互信息分割归集数据维度的孤立树构建方法，旨在依据相关性分割维度以降低孤立树的数据维度并提高计算结果的平稳性，进而提高算法的计算效率。实验结果表明，所述改进方法在碳资产归集数据异常值检测中具有更好的检测效率。

Abstract

With the improvement of carbon asset trading mechanism in China

trading has become increasingly active. The rapid increase of carbon asset types and data volume from trading has brought challenges to data aggregation and management of carbon asset operation departments. In order to improve the management efficiency

this paper studies an anomaly detection method for multi-source carbon assets aggregation data based on improved isolation forest algorithm. Types of multi-source carbon assets and the characteristics of aggregation data are discussed. Mutual information-based segmentation of aggregation data is proposed to construct the isolation tree

aiming to reduce data dimension of isolation tree and improve the stability of calculation result

thereby improving the computational efficiency of the algorithm. Experimental results indicate that the proposed improved method has higher efficiency in anomaly detection for carbon assets aggregation data.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Improved PSO-SVM based on short-term power load forecasting

A Method of Distributed Generators’ Optimization Allocation

Voltage optimization adjustment and management based on immune genetic algorithm

A Fault Location Method Based on Transient Current

Application of Improved Particle Swarm Optimizationin Reactive Power Optimization of Power System

Related Author

WANG Yi-jun

LI Dian-wen

Gao-chao

Zhang Hong-he

YANG Chang-yu

ZHOU Bu-xiang

LIN Hong-jiang

WANG Da-gang

Related Institution

辽宁省本溪供电公司

国网吉林省电力有限公司检修公司

东北电力大学电气工程学院

国网四川省电力公司达州供电公司

四川大学电气信息学院

AI问答

⁰