Multitask Support Vector Regression for Solar and Wind Energy Prediction
Given the impact of renewable sources in the overall energy production, accurate predictions are becoming essential, with machine learning becoming a very important tool in this context. In many situations, the prediction problem can be divided into several tasks, more or less related between them b...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/13/23/6308 |
_version_ | 1797546275258761216 |
---|---|
author | Carlos Ruiz Carlos M. Alaíz José R. Dorronsoro |
author_facet | Carlos Ruiz Carlos M. Alaíz José R. Dorronsoro |
author_sort | Carlos Ruiz |
collection | DOAJ |
description | Given the impact of renewable sources in the overall energy production, accurate predictions are becoming essential, with machine learning becoming a very important tool in this context. In many situations, the prediction problem can be divided into several tasks, more or less related between them but each with its own particularities. Multitask learning (MTL) aims to exploit this structure, training several models at the same time to improve on the results achievable either by a common model or by task-specific models. In this paper, we show how an MTL approach based on support vector regression can be applied to the prediction of photovoltaic and wind energy, problems where tasks can be defined according to different criteria. As shown experimentally with three different datasets, the MTL approach clearly outperforms the results of the common and specific models for photovoltaic energy, and are at the very least quite competitive for wind energy. |
first_indexed | 2024-03-10T14:27:43Z |
format | Article |
id | doaj.art-f3c0c40a35494ce8bec1b73c0d341bf7 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T14:27:43Z |
publishDate | 2020-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-f3c0c40a35494ce8bec1b73c0d341bf72023-11-20T22:54:52ZengMDPI AGEnergies1996-10732020-11-011323630810.3390/en13236308Multitask Support Vector Regression for Solar and Wind Energy PredictionCarlos Ruiz0Carlos M. Alaíz1José R. Dorronsoro2Department of Computer Engineering, Universidad Autónoma de Madrid, 28049 Madrid, SpainDepartment of Computer Engineering, Universidad Autónoma de Madrid, 28049 Madrid, SpainDepartment of Computer Engineering, Universidad Autónoma de Madrid, 28049 Madrid, SpainGiven the impact of renewable sources in the overall energy production, accurate predictions are becoming essential, with machine learning becoming a very important tool in this context. In many situations, the prediction problem can be divided into several tasks, more or less related between them but each with its own particularities. Multitask learning (MTL) aims to exploit this structure, training several models at the same time to improve on the results achievable either by a common model or by task-specific models. In this paper, we show how an MTL approach based on support vector regression can be applied to the prediction of photovoltaic and wind energy, problems where tasks can be defined according to different criteria. As shown experimentally with three different datasets, the MTL approach clearly outperforms the results of the common and specific models for photovoltaic energy, and are at the very least quite competitive for wind energy.https://www.mdpi.com/1996-1073/13/23/6308wind energyphotovoltaic energysupport vector regressionmulti-task learning |
spellingShingle | Carlos Ruiz Carlos M. Alaíz José R. Dorronsoro Multitask Support Vector Regression for Solar and Wind Energy Prediction Energies wind energy photovoltaic energy support vector regression multi-task learning |
title | Multitask Support Vector Regression for Solar and Wind Energy Prediction |
title_full | Multitask Support Vector Regression for Solar and Wind Energy Prediction |
title_fullStr | Multitask Support Vector Regression for Solar and Wind Energy Prediction |
title_full_unstemmed | Multitask Support Vector Regression for Solar and Wind Energy Prediction |
title_short | Multitask Support Vector Regression for Solar and Wind Energy Prediction |
title_sort | multitask support vector regression for solar and wind energy prediction |
topic | wind energy photovoltaic energy support vector regression multi-task learning |
url | https://www.mdpi.com/1996-1073/13/23/6308 |
work_keys_str_mv | AT carlosruiz multitasksupportvectorregressionforsolarandwindenergyprediction AT carlosmalaiz multitasksupportvectorregressionforsolarandwindenergyprediction AT joserdorronsoro multitasksupportvectorregressionforsolarandwindenergyprediction |