Anomaly detection for carbon trading data in power system based on improved isolation forest method
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 mana...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Harbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd.
2025-06-01
|
| Series: | Diance yu yibiao |
| Subjects: | |
| Online Access: | http://www.emijournal.net/dcyyb/ch/reader/create_pdf.aspx?file_no=20240919002&flag=1&journal_id=dcyyb&year_id=2025 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | 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. |
|---|---|
| ISSN: | 1001-1390 |