A State-of-Art Review on Applications of Machine Learning Based Approaches on DSM Programs

As the electricity supply demand is continuously increasing, the generation also has to be increased to meet the need. However, the generation from conventional sources leads to high environmental emissions. Hence there is a need to find an alternative solution. In this regard, the generation from renewable energy sources (RES) offers a viable solution. However, certain RES such as solar and winds are generally not predictive in nature. Therefore, Demand Side Management (DSM) has been recognized as an effective solution to optimally utilize the available resources. In order to effectively design new innovative and efficient DSM programs, the use of machine learning algorithms have been found to be quite suitable. This paper offers a state-of-art review on different machine learning techniques applied for DSM programs. The paper also intends to discuss the observations which may be further useful to find the research avenues in this area.