Prediction of combined cycle power plant electrical output power using machine learning regression algorithms

Abstract

In order to monitor the performance and related efficiency of a combined cycle power plant (CCPP), in addition to the best utilization of its power output, it is vital to predict its full load electrical power output. In this paper, the full load electrical power output of CCPP was predicted employing practically efficient machine learning algorithms, including linear regression, ridge regression, lasso regression, elastic net regression, random forest regression, and gradient boost regression. The original data came from an actual confidential power plant, which was working on a full load for 6 years, with four major features: ambient temperature, relative humidity, atmospheric pressure, and exhaust vacuum, and one target (electrical power output per hour). Different regression performance measures were used, including R2 (coefficient of determination), MAE (Mean Absolute Error), MSE (Mean Squared Error), RMSE (Root Mean Squared Error), and MAPE (Mean Absolute Percentage Error). Research results revealed that the gradient boost regression model outperformed other models with and without using the dimensionality reduction technique (PCA) with the highest R2 of 0.912 and 0.872, respectively, and had the lowest MAPE of 0.872 % and 1.039 %, respectively. Moreover, prediction performance dropped slightly after using the dimensionality reduction technique almost in all regression algorithms used. The novelty in this work is summarized in predicting electrical power output in a CCPP based on a few features using simpler algorithms than reported deep learning and neural networks algorithms combined. That means a lower cost and less complicated procedure as per each, however, resulting in practically accepted results according to the evaluation metrics used.

Self-optimizing neural network in the classification of real valued data

“…Using the recursive k-means tool ( Miniak-Gorecka, Podlaski & Gwizdalla, submitted ), we divide the response set (EP) into three classes. There are many references to the classification issue related to these data in the literature i.e., ( Saleel, 2021 ; Santarisi & Faouri, 2021 ; Alketbi et al, 2020 ; Siidiqui et al, 2021 ).…”

Modelling and Output Power Estimation of a Combined Gas Plant and a Combined Cycle Plant Using an Artificial Neural Network Approach

“…A gradient-based generalized additive model provides optimum performance measures that beneft the plant's consistency and its fnancial performance [13]. Te incorporation of simpler learning algorithms instead of the combined deep machine learning algorithms and neural networks with optimum outcomes at the lowest computational cost is proposed [14,15]. Te main confguration and the operational attributes of a combined cycle power plant will be explained briefy in the methodology section.…”