Electrical Energy Prediction of Combined Cycle Power Plant Using Gradient Boosted Generalized Additive Model

Pachauri, Nikhil; Ahn, Chang Wook

doi:10.1109/access.2022.3153720

Cited by 8 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modern computing resources, including hardware computers and software programs, play an important role in solving complex engineering or technology problems that can take much longer times and efforts if handled without the appropriate tools. Computational modeling enables rapid exploration of different designs, variables optimization, and performance testing in a safe virtual environment [1][2][3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Cantera-Based Python Computer Program for Solving Steam Power Cycles with Superheating

Marzouk¹

2023

IJETAE

View full text Add to dashboard Cite

One of the main sources of electricity generation is power plants that use water (steam) to rotate turbines, which drive large electric generators. The steam can be generated from renewable or non-renewable energy sources, such as geothermal energy and nuclear fuels. Having an analysis tool for modeling the performance of such steam power plants can greatly help in reaching optimum designs, leading to less fuel consumption, reduced pollution, and cheaper electricity. It is further advantageous if such modeling tool is free to access, does not require many inputs from the user, and gives results in a very short time. These remarks establish a motivation for the current study. This article documents a computer code written in the Python programming language for numerically analysing the main processes in a steam power cycle with superheating. The code utilizes built-in thermodynamic properties for water in the open-source software package “Cantera”. A validation case with a benchmarking example in the literature using an independent source of water properties suggests that the developed code is correct. The code can be viewed as an extension to the Python examples for thermodynamic and power generation applications. Cantera can handle both subcritical and supercritical types of superheating. In the subcritical superheating, the steam absolute pressure does not exceed 220.9 bar. In the supercritical superheating, water becomes in a special condition called supercritical fluid, with absolute pressures above 220.9 bar. Keywords—Cantera, Python, Code, Program, Superheating

show abstract

Section: Introductionmentioning

confidence: 99%

Cantera-Based Python Computer Program for Solving Steam Power Cycles with Superheating

Marzouk¹

2023

IJETAE

View full text Add to dashboard Cite

show abstract

“…Tree-based algorithms have also been applied to this research topic. According to [22,27], Decision Tree (DT), Gradient-Boosted Regression Tree (GBRT), and Bootstrap-Aggregated Tree algorithms could achieve extremely outstanding performance after performing certain preprocessing on the dataset. Furthermore, Prabhas and Rouzbeh [28] used Random Forest Regression (RFR) to predict the power output after using Z-score normalization to standardize the dataset.…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting Power Generation from a Combined Cycle Power Plant Using Transformer Encoders with DNN

2023

View full text Add to dashboard Cite

With the development of the Smart Grid, accurate prediction of power generation is becoming an increasingly crucial task. The primary goal of this research is to create an efficient and reliable forecasting model to estimate the full-load power generation of a combined-cycle power plant (CCPP). The dataset used in this research is a subset of the publicly available UCI Machine Learning Repository. It contains 9568 items of data collected from a CCPP during its full load operation over a span of six years. To enhance the accuracy of power generation forecasting, a novel forecasting method based on Transformer encoders with deep neural networks (DNN) was proposed. The proposed model exploits the ability of the Transformer encoder to extract valuable information. Furthermore, bottleneck DNN blocks and residual connections are used in the DNN component. In this study, a series of experiments were conducted, and the performance of the proposed model was evaluated against other state-of-the-art machine learning models based on the CCPP dataset. The experimental results illustrated that using Transformer encoders along with DNN can considerably improve the accuracy of predicting CCPPs power generation (RMSE = 3.5370, MAE = 2.4033, MAPE = 0.5307%, and R2 = 0.9555).

show abstract

“…A new methodology of a grid search optimised stacked ensemble machine learning algorithm with optimum performance compared with the random forest and the vote ensemble is identifed [12]. 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].…”

Section: Introductionmentioning

confidence: 99%

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

Xezonakis,

Samuel,

Enweremadu

2024

Journal of Engineering

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have gained prominence among contemporary computing techniques due to their capacity to handle complicated stochastic datasets and nonlinear modelling in combined gas and combined cycle power (COGAS) plants. Researchers, academicians, and stakeholders have been unable to predict, ensure effective operation, and prevent power outages in COGAS due to the nonlinearity. The first implementation of the simultaneous adoption of three types of ANNs using Levenberg–Marquardt (LM), Bayesian regularisation (BR), and scaled conjugate gradient (SCG) configurations for training and assessing a combined cycle power plant output is presented. The dataset used in this research is a 9568-unit full combined cycle power plant basis load dataset, accessible through the public UCI Machine Learning Repository. It incorporates ambient temperature, exhaust vacuum, ambient pressure, and relative humidity as input parameters to predict the electric output power. The most accurate and dependable electric power predictions could be identified for 70% of the total data, of which 6698 were trained, 15% were tested, and 15% were validated (2870). By using the three training techniques, namely, LM, BR, and SCG, the parameterized networks are studied, increasing the number of hidden layers from 20 to 500. The lowest root-mean-square error value for a multilayer perceptron (MLP) architecture is 3.631%, which is lower than the values of 4.17%, 4.35%, and 4.63% for comparable MLP structures (20 to 500), documented in the literature. The LM and BR algorithms outperform SCG. These adopted algorithms could be a cutting-edge application in the power plant industry and other real-world applications for reliable solutions, to satisfy emerging societal needs with environmental benefits.

show abstract

Electrical Energy Prediction of Combined Cycle Power Plant Using Gradient Boosted Generalized Additive Model

Cited by 8 publications

References 32 publications

Cantera-Based Python Computer Program for Solving Steam Power Cycles with Superheating

Cantera-Based Python Computer Program for Solving Steam Power Cycles with Superheating

Predicting Power Generation from a Combined Cycle Power Plant Using Transformer Encoders with DNN

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

Contact Info

Product

Resources

About