Non-technical line loss state evaluation method based on multi-scale spatial-temporal feature fusion in low-voltage distribution network environment

By employing a multi-scale spatiotemporal feature fusion and integration strategy, the problem of imbalance in power signal feature extraction and clustering in low-voltage distribution networks was solved, enabling accurate assessment and efficient early warning of line loss status, and improving the decision support capability of power operation and maintenance.

CN121882971AActive Publication Date: 2026-04-17SHENYANG UNIVERSITY OF TECHNOLOGY
4 Cites 2 Cited by

Patent Information

Application Number
CN202512002763.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-29
Publication Date
2026-04-17
Estimated Expiration
2045-12-29

AI Technical Summary

Technical Problem

Existing technologies struggle to extract discriminative state features from noisy, non-stationary load signals in low-voltage distribution networks. Furthermore, traditional clustering methods lack robustness against class imbalance, leading to inaccurate line loss assessments and difficulty in guiding on-site troubleshooting decisions.

Method used

A multi-scale spatiotemporal feature fusion method is adopted, which combines a multi-scale temporal convolutional network (TCN) and a long short-term memory network (LSTM). Multi-scale local features and long-term temporal dependency features are extracted through a cross-attention fusion module. Stable cluster labels are generated through cluster balance constraints and ensemble strategies, and accurate early warning is achieved by combining the loss fluctuation trajectory of the transformer area table.

Benefits of technology

It achieves robust feature extraction for complex power environments, ensuring the balance and stability of assessments, improving the accuracy of line loss assessments and the precision of on-site inspections, reducing the risk of missed anomaly reports, and providing direct operation and maintenance guidance.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a non-technical line loss state evaluation method based on multi-scale spatial-temporal feature fusion in a low-voltage distribution network environment, and relates to the technical field of electric power big data analysis and intelligent operation and maintenance of a distribution network. According to the invention, a fusion architecture based on a multi-scale time convolution network and a long short-term memory network is constructed; extracting multi-scale spatio-temporal characteristics of a user from instantaneous electricity utilization abrupt change to a periodic load rule through an MSTBlock unit; designing a cluster balance constraint mechanism to ensure that rare and key non-technical line loss abnormal early warning signals are not covered by mass normal power utilization data; according to the data scale, adaptively selecting a graph segmentation or spectral clustering integration strategy to output a clustering label, and mapping the clustering label into a user power consumption behavior evolution track; according to the method, the power utilization abnormal level can be identified from the original load signal with random fluctuation interference, and the troubleshooting priority is calculated in combination with the transformer area correlation analysis, so that the accuracy and interpretability of the non-technical line loss unsupervised evaluation decision of the power distribution network are remarkably improved.
Need to check novelty before this filing date? Find Prior Art