Learning From High-Dimensional Cyber-Physical Data Streams for Diagnosing Faults in Smart Grids

TL;DR

The paper addresses fault-diagnosis in cyber-physical power systems under high-dimensional, noisy data by evaluating a data-driven framework that combines feature selection (FS) and dimensionality reduction (DR) with classifiers on an IEEE $118$-bus case study. It systematically compares FS, DR, and their combinations across six datasets with varying signal-to-noise ratio and fault resistance, using multiple FS/DR methods (e.g., CFMI, Relief, CFMI; CADR, MDS, LLE) and classifiers (kNN, SVM, RF) with 10-fold cross-validation. Key findings show that FS-classifier combinations, particularly CFMI-SVM, generally outperform DR-based approaches, while nonlinear DR (CADR) yields notable improvements over linear methods; overall, FS reductions outperform DR reductions for this fault-diagnosis task. The results inform practical recommendations for data-quality-focused fault diagnosis in smart grids and point to future work in scaling with deep learning to handle even larger cyber-physical datasets.

Abstract

The performance of fault diagnosis systems is highly affected by data quality in cyber-physical power systems. These systems generate massive amounts of data that overburden the system with excessive computational costs. Another issue is the presence of noise in recorded measurements, which prevents building a precise decision model. Furthermore, the diagnostic model is often provided with a mixture of redundant measurements that may deviate it from learning normal and fault distributions. This paper presents the effect of feature engineering on mitigating the aforementioned challenges in cyber-physical systems. Feature selection and dimensionality reduction methods are combined with decision models to simulate data-driven fault diagnosis in a 118-bus power system. A comparative study is enabled accordingly to compare several advanced techniques in both domains. Dimensionality reduction and feature selection methods are compared both jointly and separately. Finally, experiments are concluded, and a setting is suggested that enhances data quality for fault diagnosis.

Figures (2)

• Figure 1: The single-line diagram of the IEEE 118-bus system li2017robust.
• Figure 2: General framework of the proposed methodology.