Prediction of Full Load Electrical Power Output of a Base Load Operated Combined Cycle Power Plant Using Machine Learning Methods

2021 ◽  
Author(s):  
Deekshith chary
Keyword(s):  
Machine Learning ◽  
Power Plant ◽  
Power Output ◽  
Electrical Power ◽  
Combined Cycle ◽  
Combined Cycle Power Plant ◽  
Full Load ◽  
Machine Learning Methods ◽  
Electrical Power Output ◽  
Base Load

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

2021 ◽  
Vol 6 (8 (114)) ◽  
Author(s):  
Nader S. Santarisi ◽  
Sinan S. Faouri
Keyword(s):  
Power Plant ◽  
Power Output ◽  
Mean Squared Error ◽  
Electrical Power ◽  
Combined Cycle ◽  
Full Load ◽  
Squared Error ◽  
Dimensionality Reduction Technique ◽  
Regression Algorithms ◽  
Electrical Power Output

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.

scholarly journals Genetic Algorithm Approach to Design of Multi-Layer Perceptron for Combined Cycle Power Plant Electrical Power Output Estimation

Energies ◽  
2019 ◽  
Vol 12 (22) ◽  
pp. 4352 ◽  
Author(s):  
Ivan Lorencin ◽  
Nikola Anđelić ◽  
Vedran Mrzljak ◽  
Zlatan Car
Keyword(s):  
Genetic Algorithm ◽  
Power Plant ◽  
Power Output ◽  
Electrical Power ◽  
Combined Cycle ◽  
Training Dataset ◽  
Multi Layer Perceptron ◽  
Combined Cycle Power Plant ◽  
Data Points ◽  
Electrical Power Output

In this paper a genetic algorithm (GA) approach to design of multi-layer perceptron (MLP) for combined cycle power plant power output estimation is presented. Dataset used in this research is a part of publicly available UCI Machine Learning Repository and it consists of 9568 data points (power plant operating regimes) that is divided on training dataset that consists of 7500 data points and testing dataset containing 2068 data points. Presented research was performed with aim of increasing regression performances of MLP in comparison to ones available in the literature by utilizing heuristic algorithm. The GA described in this paper is performed by using mutation and crossover procedures. These procedures are utilized for design of 20 different chromosomes in 50 different generations. MLP configurations that are designed with GA implementation are validated by using Bland - Altman (B-A) analysis. By utilizing GA, MLP with five hidden layers of 80,25,65,75 and 80 nodes, respectively, is designed. For aforementioned MLP, k - fold cross-validation is performed in order to examine its generalization performances. The Root Mean Square Error ( R M S E ) value achieved with aforementioned MLP is 4.305 , that is significantly lower in comparison with MLP presented in available literature, but still higher than several complex algorithms such as KStar and tree based algorithms.

HRSG Duct Firing Revisited

2018 ◽  
Author(s):  
S. Can Gülen
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Power Output ◽  
Gas Turbines ◽  
Heat Recovery ◽  
Fossil Fuel ◽  
Heat Rate ◽  
Combined Cycle ◽  
Efficiency Improvement ◽  
Combined Cycle Power Plant

Duct firing in the heat recovery steam generator (HRSG) of a gas turbine combined cycle power plant is a commonly used method to increase output on hot summer days when gas turbine airflow and power output lapse significantly. The aim is to generate maximum possible power output when it is most needed (and, thus, more profitable) at the expense of power plant heat rate. In this paper, using fundamental thermodynamic arguments and detailed heat and mass balance simulations, it will be shown that, under certain boundary conditions, duct firing in the HRSG can be a facilitator of efficiency improvement as well. When combined with highly-efficient aeroderivative gas turbines with high cycle pressure ratios and concomitantly low exhaust temperatures, duct firing can be utilized for small but efficient combined cycle power plant designs as well as more efficient hot-day power augmentation. This opens the door to efficient and agile fossil fuel-fired power generation opportunities to support variable renewable generation.

scholarly journals Power Prediction of Combined Cycle Power Plant (CCPP) Using Machine Learning Algorithm-Based Paradigm

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Raheel Siddiqui ◽  
Hafeez Anwar ◽  
Farman Ullah ◽  
Rehmat Ullah ◽  
Muhammad Abdul Rehman ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Power Plant ◽  
Learning Algorithm ◽  
Absolute Error ◽  
Combined Cycle ◽  
Machine Learning Algorithms ◽  
Power Prediction ◽  
Boosted Regression Tree ◽  
Combined Cycle Power Plant

Power prediction is important not only for the smooth and economic operation of a combined cycle power plant (CCPP) but also to avoid technical issues such as power outages. In this work, we propose to utilize machine learning algorithms to predict the hourly-based electrical power generated by a CCPP. For this, the generated power is considered a function of four fundamental parameters which are relative humidity, atmospheric pressure, ambient temperature, and exhaust vacuum. The measurements of these parameters and their yielded output power are used to train and test the machine learning models. The dataset for the proposed research is gathered over a period of six years and taken from a standard and publicly available machine learning repository. The utilized machine algorithms are K -nearest neighbors (KNN), gradient-boosted regression tree (GBRT), linear regression (LR), artificial neural network (ANN), and deep neural network (DNN). We report state-of-the-art performance where GBRT outperforms not only the utilized algorithms but also all the previous methods on the given CCPP dataset. It achieves the minimum values of root mean square error (RMSE) of 2.58 and absolute error (AE) of 1.85.

Second Law Efficiency of the Rankine Bottoming Cycle of a Combined Cycle Power Plant

2008 ◽  
Author(s):  
S. Can Gulen ◽  
Raub W. Smith
Keyword(s):  
Power Plant ◽  
Gas Turbine ◽  
Power Output ◽  
Gas Turbines ◽  
Power Plants ◽  
Combined Cycle ◽  
Cycle Performance ◽  
Second Law ◽  
Modeling Tools ◽  
Combined Cycle Power Plant

A significant portion of the new electrical generating capacity installed in the past decade has employed heavy-duty gas turbines operating in a combined cycle configuration with a steam turbine bottoming cycle. In these power plants approximately one third of the power is generated by the bottoming cycle. To ensure that the highest possible combined cycle efficiency is realized it is important to develop the combined cycle power plant as a system. Doing so requires a solid understanding of the efficiency entitlement of both, topping and bottoming, cycles separately and as a whole. This paper describes a simple but accurate method to estimate the Rankine bottoming cycle power output directly from the gas turbine exhaust exergy utilizing the second law of thermodynamics. The classical first law approach, i.e. the heat and mass balance method, requires lengthy calculations and complex computer-based modeling tools to evaluate Rankine bottoming cycle performance. In this paper, a rigorous application of the fundamental thermodynamic principles embodied by the second law to the major cycle components clearly demonstrates that the Rankine cycle performance can be accurately represented by several key parameters. The power of the second law approach lies in its ability to highlight the theoretical entitlement and state-of-the-art design performances simultaneously via simple, fundamental relationships. By considering economically and technologically feasible upper limits for the key parameters, the maximum achievable bottoming cycle power output is readily calculable for any given gas turbine from its exhaust exergy.

Sign in / Sign up

Export Citation Format

Share Document