A meta-analysis of distribution network faults and associated prediction models
Abstract
As the core of power supply, the distribution network accounts for over 70% of total power system faults. Its complexity has significantly increased with distributed energy integration, new load growth, and extreme weather events, rendering traditional maintenance methods inadequate and urgent for data-driven fault prediction. This study first clarifies the research status and development trends of the field through meta-analysis of 1309 literatures (1233 English, 76 Chinese) from WoS, Scopus, and CNKI, then proposes an empirical modeling approach using multi-source data (meteorological, operational, environmental) and the SVM model to address the fault prediction challenge. Experimental results show that the model achieves an accuracy of 0.873 and an AUC of 0.888, verifying its feasibility. Further analysis identifies key bottlenecks of existing models: nonlinear fusion inefficiency, poor generalization, and the balance between interpretability and real-time performance. Future research should focus on adaptive attention optimization, few-shot/federated learning, lightweight interpretable design, and digital twin integration. This study provides a concise overview of the field’s development and a practical fault prediction solution, offering references for academic research and engineering practice to promote intelligent operation and maintenance of distribution networks.
How strong is the evidence?
Evidence Hub reads this as a meta-analysis. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Chaos and quantum thermalization
- The Dalton quantum chemistry program system
- Cord Blood Leptin and Adiponectin as Predictors of Adiposity in Children at 3 Years of Age: A Prospective Cohort Study
- Quantitative metabolomics by H-NMR and LC-MS/MS confirms altered metabolic pathways in diabetes
- Stable adiabatic quantum batteries
- A novel self-lipid antigen targets human T cells against CD1c(+) leukemias
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.