One-Class Classifier Based Fault Detection in Distribution Systems With Varying Penetration Levels of Distributed Energy Resources

Abstract

The integration of Distributed Energy Resources (DERs) into distribution systems greatly increases the system complexity and introduces two-way power flow. Conventional protection schemes are based upon local measurements and simple linear system models, and are thus not capable of handling the new complexity and power flow patterns in systems with high DER penetration. In this paper, we propose a data-driven protection framework to address the challenges introduced by DERs. Firstly, considering the limited available data under fault conditions, we adopt the Support Vector Data Description (SVDD) method, a commonly used one-class classifier, for distribution system fault detection, which only requires the normal data for its training process. Secondly, incremental learning is incorporated into the proposed SVDD-based protection framework to accommodate variations of the integration level of DERs in distribution systems over time. In particular, the artificial uniform-hyperspherical data generation model is incorporated into the incremental SVDD to boost the training speed. Finally, we validate the proposed method under the IEEE 123-node test feeder. Simulation results demonstrate that our proposed SVDD-based fault detection framework significantly improves the robustness and resilience against DERs in comparison with conventional protection systems. Meanwhile, the proposed online updating model outperforms the existing incremental SVDD models in terms of successful training speed.

Fault Detection and Fault Diagnosis in Power System Using AI: A Review

“…The model uses Support Vector Data Description (SVDD) and vectors for training, incorporating new data and previous support vectors. Hybrid Incremental SVDD (HISVDD), is an online updating model that incorporates new data and previous support vectors to retrain the SVDD model and adapt to system changes [34].…”

“…80% of faults occur in distribution lines; hence, this area is of particular importance for researchers [3]. Moreover, with the integration of renewable sources in the system like wind and solar, two-way power flows are introduced, adding to the complexity of a distribution system [4], and [5]. The paper focuses on distribution networks, so it only discusses faults in distribution networks and their effects.…”

Research on online anomaly detection methods for bearing degradation

“…Additionally, the boundary between categorizing samples outside the original model range as either abnormal or degenerated normal samples is unclear, leading to lower accuracy in anomaly detection. HISVDD [19] integrates the accumulated fewer new samples, enhanced through data augmentation, with the old samples near the original model's decision boundary for joint training. This approach enhances the robustness of the model.…”