Search

Anomaly detection in power systems is crucial for operational reliability and safety, often addressed through binary classification in existing research. However, a research gap exists in multiclass classification for enhanced reliability. To bridge this gap, this study employs four machine learning (ML) classifiers: Random Forest (RF), Decision Tree, Naive Bayes (NB), and Support Vector Machine (SVM) using comprehensive testing on a dataset comprising sixteen indices and their pair combinations (totaling 136 pairs). These classifiers, trained on a dataset derived from simulating a test system with hybrid DGs, exhibit superior anomaly detection, especially with the $\frac {dv}{dq}\& \frac {dv}{dp}$ pair. Among them, RF and DT classifier achieves precision, recall, and F score of unity and outperforming NB and SVM. The performance of the proposed RF and DT classifiers with $\frac {dv}{dq}\& \frac {dv}{dp}$ pair is compared with existing research papers in terms of accuracy and data division. The comparison shows that the proposed RF and DT classifiers with $\frac {dv}{dq}\& \frac {dv}{dp}$ pair achieve 100% accuracy even with 50% data division, whereas other techniques fail to achieve it even at 20% for testing and 80% for training. The study underscores the critical role of pair selection and classifier combinations in effective anomaly detection, facilitating the implementation of robust mitigating strategies for power system stability.

The increasing penetration of renewable generation and large implementation of the DC loads are challenges that stress the current distribution systems by causing uncertain voltage variations. The AC−DC hybrid distribution network is seen as an innovative solution to address the problem of accommodating highly dispersed sustainable energy. Specifically, the solid-state transformer (SST), which is capable of enhancing power-quality performance and controllability of the power distribution, has attracted increasing focus in this decade as a promising advanced converter. It is of great interest to investigate how to operate the multiple SSTs with different modes in a coordinated manner to optimise the distribution network performance. This paper formulates the coordinated operation model for multiple SSTs to enable fast voltage regulation for the hybrid active distribution network equipped with large-scale penetration of invertor-based solar power and DC load. A hybrid optimal power flow describing the controlling modes of SSTs and operating interaction between AC−DC subsystems is proposed in this paper. The case studies on a modified IEEE 33-AC−DC hybrid power distribution system show that the voltage profile can be optimised by using the flexible controlling resource of SSTs, facilitating the timely performance adjustment in the presence of fast fluctuating distributed generator's output.

The increasing penetration of renewable generation and large implementation of the DC loads are challenges that stress the current distribution systems by causing uncertain voltage variations. The AC−DC hybrid distribution network is seen as an innovative solution to address the problem of accommodating highly dispersed sustainable energy. Specifically, the solid-state transformer (SST), which is capable of enhancing power-quality performance and controllability of the power distribution, has attracted increasing focus in this decade as a promising advanced converter. It is of great interest to investigate how to operate the multiple SSTs with different modes in a coordinated manner to optimise the distribution network performance. This paper formulates the coordinated operation model for multiple SSTs to enable fast voltage regulation for the hybrid active distribution network equipped with large-scale penetration of invertor-based solar power and DC load. A hybrid optimal power flow describing the controlling modes of SSTs and operating interaction between AC−DC subsystems is proposed in this paper. The case studies on a modified IEEE 33-AC−DC hybrid power distribution system show that the voltage profile can be optimised by using the flexible controlling resource of SSTs, facilitating the timely performance adjustment in the presence of fast fluctuating distributed generator's output. [ABSTRACT FROM AUTHOR]