Heuristic optimization applied to ANN training for predicting renewable energy sources production
-
Published:2022-03-15
Issue:6
Volume:41
Page:2010-2021
-
ISSN:0332-1649
-
Container-title:COMPEL - The international journal for computation and mathematics in electrical and electronic engineering
-
language:en
-
Short-container-title:COMPEL
Author:
Lorenti Gianmarco,Mariuzzo Ivan,Moraglio Francesco,Repetto Maurizio
Abstract
Purpose
This paper aims to compare stochastic gradient method used for neural network training with global optimizer without use of gradient information, in particular differential evolution.
Design/methodology/approach
This contribute shows the application of heuristic optimization algorithms to the training phase of artificial neural network whose aim is to predict renewable power production as function of environmental variables such as solar irradiance and temperature. The training problem is cast as the minimization of a cost function whose degrees of freedom are the parameters of the neural network. A differential evolution algorithm is substituted to the more usual gradient-based minimization procedure, and the comparison of their performances is presented.
Findings
The two procedures based on stochastic gradient and differential evolution reach the same results being the gradient based moderately quicker in convergence but with a lower value of reliability, as a significant number of runs do not reach convergence.
Research limitations/implications
The approach has been applied to two forecasting problems and, even if results are encouraging, the need for extend the approach to other problems is needed.
Practical implications
The new approach could open the training of neural network to more stable and general methods, exploiting the potentialities of parallel computing.
Originality/value
To the best of the authors’ knowledge, the research presented is fully original for the part regarding the neural network training with differential evolution.
Subject
Applied Mathematics,Electrical and Electronic Engineering,Computational Theory and Mathematics,Computer Science Applications
Reference13 articles.
1. Differential evolution for neural networks optimization;Mathematics,2020
2. Optimization for training neural nets;IEEE Transactions on Neural Networks,1992
3. Chollet, F. (2015), “Keras”, available at: https://keras.io (accessed 13 October 2021).
4. Differential evolution: a survey and analysis;Applied Sciences,2018
5. Day-Ahead hourly forecasting of power generation from photovoltaic plants;IEEE Transactions on Sustainable Energy,2017
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献