Review of Machine Learning Applications to Power System Studies

Abstract

The complexity of electric power networks from generation, transmission, and distribution stations in modern times has resulted in the generation of big and more complex data that requires more technical and mathematical analysis because it deals with monitoring, supervisory, control, and data acquisition in real time. This has necessitated the need for more accurate analysis and predictions in power system studies especially under transient, uncertainty or emergency conditions without interference from humans. This is necessary so as to minimise errors with the aim targeted at improving the overall performance. Also, the need to use more technical but very intelligent predictive tools has become very relevant. Machine Learning (ML) is a computational tool used to bring into existence an informed guess about subsequent characteristics of data resulting from past experiences. ML algorithms involve building a model (mathematical/pictorial) from input data so as to make future predictions/decisions. ML can be used in combination with big data with a view to either building effective predictive systems or solving data analytic problems of a complex nature. Electric power generation in combination with forecasting systems that can predict the amount of electricity demands at any instant have been proposed in the literature. This paper reviews applications of ML tools in power system studies.