Prediction Of Full Load Electrical Power Output Of A Power Plant Using Machine Learning Methods

Predicting full load electrical power output of a base load power plant is important in order to maximize the profit from the available megawatt hours.In order for accurate system analysis with thermodynamical approaches,a high number of assumptions is necessary such that these assumptions account for the unpredictability in the solution.Without these assumptions,a thermodynamical analysis of a real application compels thousands of nonlinear equations,whose solution is either almost impossible or takes too much computational time and effort.To eliminate this barrier,the machine learning approaches are used mostly as alternative instead of thermodynamical approaches,in particular,to analyze the systems for arbitrary input and output patterns.The base load operation of a power plant is influenced by four main parameters,such as ambient temperature,atmospheric pressure,relative humidity,and exhaust steam pressure,which are used as input variables in the dataset.These parameters affect electrical power output,which is considered as the target variable.The dataset,which consists of these input and target variables,was collected over a six-year period by Chaoyang power plant.Firstly,this paper examines and compares some sets of input variables to develop a predictive model,the best subset of the dataset is explored among all feature subsets in the experiments,the best performance of the best subset,which contains a complete set of input variables.Then,this paper examines and compares some machine learning regression methods to develop a predictive model,which can predict hourly full load electrical power output of a combined cycle power plant.Thus,has been observed using the most successful method,which is Bagging algorithm with REPTree,the most successful machine learning regression method is sought for predicting full load electrical power output.Ten images,ten tables,and 46 references were used to illustrate and analyze the process and conclusion of the study.