International Science Community Association Research Journal of Engineering Sciences 2278-9472 13 1 2024 01 26 Power Quality Improvement of Power Electronics Systems by using Machine Learning 24 27 EN Olushola Olukunle IFABIYI 1 Department of Chemical and Petroleum Engineering, College of Engineering, Afe Babalola University, Ado Ekiti, Ekiti State, Nigeria Adekunle Tirimisiyu ADENIYI 2 Department of Chemical and Petroleum Engineering, College of Engineering, Afe Babalola University, Ado Ekiti, Ekiti State, Nigeria Jha Sujeet Kumar 1 Department of Electronics and Computer Engineering, Institute of Engineering, Pulchowk Campus, Tribhuvan University, Nepal Pangeni Bibek Raj 2 Department of Electronics and Computer Engineering, Institute of Engineering, Pulchowk Campus, Tribhuvan University, Nepal Kaushik Arti 1 Department of Mathematics, Maharaja Agrasen Institute of Technology, Delhi, India Kaiwart Jyotsana 1 Department of Electrical Engineering, Bhilai Institute of Technology, Durg, CG, India Huddar Anupama 2 Department of Electrical Engineering, Bhilai Institute of Technology, Durg, CG, India > Review Paper 2023 1 17 2024 01 26 The power electronic components or devices are the main focus of this report. It gains more popularity because of its reduced size and smooth control on output voltage & current. It is very popular in areas of renewable energy sources (as converters & inverters) and industrial drives (as controlling devices). In both cases, the power electronic components and devices act as non-linear loads due to its switching process. This causes system to generate the harmonics or cause of power quality problem. This should be mitigated or eliminated by using different methods, recommended by some standards e.g. IEEE-519. The limits and guidelines are also given by them to help the customers and manufacturers. The improvement in power quality can be achieved by Machine learning algorithms. Machine learning is another very popular area, which uses the data of any system and predicts the system output after training the model (e.g. for classification of fault type and identification of exact location of faults, predicting the life of power electronics components, detection of voltage disturbances). Depending on different techniques of machine learning, different applications can be achieved. Copyright@ International Science Community Association