Solver parameter influence on the results of multilayer perceptron for estimating power output of a combined cycle power plant (CROSBI ID 691645)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Prpić-Oršić, Jasna ; Mrzljak, Vedran ; Baressi Šegota, Sandi ; Lorencin, Ivan
engleski
Solver parameter influence on the results of multilayer perceptron for estimating power output of a combined cycle power plant
Previous work has determined the ability of using the Multilayer Perceptron (MLP) type of Artificial Neural Network (ANN) to estimate the power output of a Combined Cycle Power Plant (CCPP) in which optimization did not focus on the solver parameter optimization. In previous work, the solvers used the default parameters. Possibility exists that optimizing solver parameters will net better results. Two solver algorithm's parameters are optimized: Stochastic Gradient Descent (SGD) and Adam, with 140 and 720 parameter combinations respectively. Solutions are estimated through the use of Root Mean Square Error (RMSE). Lowest RMSE achieved is 4.275 [MW] for SGD and 4.259 [MW] for Adam, achieved with parameters: a=0.05, u=0.02, and nesterov=True for SGD and with parameters a=0.001, b1=0.95, b2=0.99, and amsgrad=False for Adam. Only a slight improvement is shown in comparison to previous results (RMSE=4.305 [MW]) which points towards the fact that solver parameter optimization with the goal of improving results does not justify the extra time taken for training.
Combined cycle power plant ; Multilayer perceptron ; Artificial neural networks ; Stochastic gradient descent ; Adam ; Solver algorithm
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
8-11.
2020.
objavljeno
Podaci o matičnoj publikaciji
V INTERNATIONAL SCIENTIFIC CONFERENCE - SUMMER SESSION - INDUSTRY 4.0 - 2020 - PROCEEDINGS
Popov, Georgi ; Ovtcharova, Jivka
Sofija: Scientific technical union of mechanical engineering Industry - 4.0
2535-0153
2535-0161
Podaci o skupu
5th International Scientific Conference Summer Session "Industry 4.0"
poster
24.06.2020-27.06.2020
Varna, Bugarska