Machine Learning In Power Markets

摘要

Intelligent operational planning ensures supply and demand matching in a power system, which is achieved traditionally by optimization and scheduling of government and private owned non-renewable power plants. Recently, encouragement has been extended to local and distributed power generators, due to uncertainty and long-term variability in renewable rich system. In the study, machine learning approaches are proposed in the context of power markets to learn and predict usage patterns to avoid power deficit. A case study is presented, which includes a solar plant and a wind farm for base load along with bio-gas plant for peak load. To predict peak load, logistic regression, a supervised machine learning approach, has been employed to classify the time of engagement, in order to ensure supply and demand balance. Applying logistic regression will result in reduced operational and economic cost for utility and price for consumer.