Decentral Smart Grid Control System Stability Analysis Using Machine Learning

Abstract

Electrical Grid Systems transmit power produced from various facilities to end-users. Supply and demand must be in balance to achieve secure and stable use in the power grid. To ensure this stability, the amount of electricity fed into the system must always be the same as the amount of demand. High demand makes electrical grid systems' stability more important than ever. Current electrical infrastructures are hard to adapt to these needs. A smart grid system enables two-way electricity flow according to the demand from end-users. Digital communication in smart grid systems enables the system to detect demands, problems, and changes. Also collects information to ensure stability in the system. This study is using the Electrical Grid Stability data set shared at UC Irvine (UCI) Machine Learning repository. Multi-Layer Perceptron (MLP), Radial Basis Function (RBF) Network, K-Nearest Neighbors (K-NN), and Naive Bayes (NB) Machine Learning (ML) algorithms were used to examine the stability performance of the Smart Grid system. Acquired performance metrics compared using Accuracy, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and F-Score. According to the results obtained, the system and its performance are interpreted.