Power system contingency classification using machine learning technique

Abstract

One of the most effective ways for estimating the impact and severity of line failures on the static security of the power system is contingency analysis. The contingency categorization approach uses the overall performance index to measure the system's severity (OPI). The newton raphson (NR) load flow technique is used to extract network variables in a contingency situation for each transmission line failure. Static security is categorised into five categories in this paper: secure (S), critically secure (CS), insecure (IS), highly insecure (HIS), and most insecure (MIS). The K closest neighbor machine learning strategy is presented to categorize these patterns. The proposed machine learning classifiers are trained on the IEEE 30 bus system before being evaluated on the IEEE 14, IEEE 57, and IEEE 118 bus systems. The suggested k-nearest neighbor (KNN) classifier increases the accuracy of power system security assessments categorization. A fuzzy logic approach was also investigated and implemented for the IEEE 14 bus test system to forecast the aforementioned five classifications.

FPGA implementation of KNN Algorithm-Based Prediction for DPWM Methods

“…The residential electricity bill is evaluated using the 23-nodes cloud computing cluster combined with the KNN to give accurate prediction of the future load [1]. The failures in the transmission line are categorized as one among the five issues namely Secure, Critically Secure, Insecure Highly Insecure, and Most Insecure using the KNN algorithm [2]. The combined algorithm of KNN and LSTM uses the spatiotemporal features of traffic flow data to correlate between the nodes of the destination road section and has more accuracy in predicting than the other models [3].…”