Knowledge-Assisted Few-Shot Fault Diagnosis in Cellular Networks
Authors:
- 4 December 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1292-1297
Abstract
Data-driven network fault diagnosis faces the great challenge of lacking sufficient high-quality labeled data from real networks. Also, how to exploit existing domain knowledge to aid the diagnosis in an efficient and effective manner needs to be addressed. To obtain a high-performance diagnosis system based on a coarse data set and knowledge base, we propose a Robust Belief Weighting Framework (RBWF) based on abductive learning and belief rule structure for the few-shot fault diagnosis. The correction weight is obtained by the matching rules selected from the insufficient knowledge base to revise pseudo-labels for model retraining. Moreover, the revised pseudo-labels enhance the coarse knowledge base to become more comprehensive. Therefore, the knowledge base and the data-driven model can mutually reinforce to improve the respective performance. Experimental results illustrate the effectiveness and stability of the proposed framework using the cellular network data. Our method enables the automation of fault diagnosis for 5G and 6G networks to achieve highly reliable communication services.Keywords
This publication has 18 references indexed in Scilit:
- Combination of multiple diagnosis systems in Self-Healing networksExpert Systems with Applications, 2016
- XGBoost2016
- Methodology for the Design and Evaluation of Self-Healing LTE NetworksIEEE Transactions on Vehicular Technology, 2015
- Automatic Root Cause Analysis for LTE Networks Based on Unsupervised TechniquesIEEE Transactions on Vehicular Technology, 2015
- Diagnosis Based on Genetic Fuzzy Algorithms for LTE Self-HealingIEEE Transactions on Vehicular Technology, 2015
- A Survey of Self Organisation in Future Cellular NetworksIEEE Communications Surveys & Tutorials, 2012
- Knowledge acquisition for diagnosis model in wireless networksExpert Systems with Applications, 2009
- Belief rule-base inference methodology using the evidential reasoning Approach-RIMERIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2006
- Tri-training: exploiting unlabeled data using three classifiersIEEE Transactions on Knowledge and Data Engineering, 2005
- Nonlinear principal component analysis using autoassociative neural networksAIChE Journal, 1991