A comprehensive research of machine learning algorithms for power quality disturbances classifier based on time-series window

The importance of power quality monitoring, detection, and classification on electrical systems increased recently in terms of economics, security, the efficiency depending on the spreading of the smart grid. The current monitoring systems are based on IEEE 1159 and similar standards under some stable conditions and assuming. But the detailed measurements of power quality disturbances should be evaluated robustly even in a noisy environment with a specific method for each power quality disturbance (PQD) for every window. Because this approach is very time-consuming and not feasible, most studies with different techniques promote primarily detection of the PQDs and then classifications of these. For this purpose, a study using hyperparameter optimization of machine learning algorithms (MLAs) is executed for the detection and classification (D&C) of PQDs. 21 class datasets consisting of single and multiple PQDs with different-level noise are prepared randomly. These datasets are trained and tested with a lot of MLAs in a workstation as the time-series signals with no preprocessing apart from the other methods. The results obtained from comparative MLAs show that the best MLA and the hyperparameters of that are kNN, RF, LightGBM, and XGBoost with an accuracy of 99.82%, 98.78%, 98.10%, and 94.77%, respectively. In as much as the optimized parameters and the related MLAs were obtained by investigating the time-series signal datasets with no preprocessing in the whole hyperparameter space, this approach brings the advantages of high accuracy.