A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation

Mehrnoosh Torabi, Amir Mosavi, Pinar Ozturk, A. Várkonyi-Kóczy, Vajda Istvan

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

In this paper, we present a Cluster-Based Approach (CBA) that utilizes the support vector machine (SVM) and an artificial neural network (ANN) to estimate and predict the daily horizontal global solar radiation. In the proposed CBA-ANN-SVM approach, we first conduct clustering analysis and divided the global solar radiation data into clusters, according to the calendar months. Our approach aims at maximizing the homogeneity of data within the clusters, and the heterogeneity between the clusters. The proposed CBA-ANN-SVM approach is validated and the precision is compared with ANN and SVM techniques. The mean absolute percentage error (MAPE) for the proposed approach was reported lower than those of ANN and SVM.

Original languageEnglish
Title of host publicationLecture Notes in Networks and Systems
PublisherSpringer
Pages266-274
Number of pages9
DOIs
Publication statusPublished - Jan 1 2019

Publication series

NameLecture Notes in Networks and Systems
Volume53
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Fingerprint

Solar radiation
Support vector machines
Learning systems
Neural networks

Keywords

  • Artificial neural networks (ANN)
  • Global solar radiation
  • Machine learning
  • Prediction
  • Support vector machine (SVM)

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Control and Systems Engineering

Cite this

Torabi, M., Mosavi, A., Ozturk, P., Várkonyi-Kóczy, A., & Istvan, V. (2019). A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation. In Lecture Notes in Networks and Systems (pp. 266-274). (Lecture Notes in Networks and Systems; Vol. 53). Springer. https://doi.org/10.1007/978-3-319-99834-3_35

A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation. / Torabi, Mehrnoosh; Mosavi, Amir; Ozturk, Pinar; Várkonyi-Kóczy, A.; Istvan, Vajda.

Lecture Notes in Networks and Systems. Springer, 2019. p. 266-274 (Lecture Notes in Networks and Systems; Vol. 53).

Research output: Chapter in Book/Report/Conference proceedingChapter

Torabi, M, Mosavi, A, Ozturk, P, Várkonyi-Kóczy, A & Istvan, V 2019, A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation. in Lecture Notes in Networks and Systems. Lecture Notes in Networks and Systems, vol. 53, Springer, pp. 266-274. https://doi.org/10.1007/978-3-319-99834-3_35
Torabi M, Mosavi A, Ozturk P, Várkonyi-Kóczy A, Istvan V. A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation. In Lecture Notes in Networks and Systems. Springer. 2019. p. 266-274. (Lecture Notes in Networks and Systems). https://doi.org/10.1007/978-3-319-99834-3_35
Torabi, Mehrnoosh ; Mosavi, Amir ; Ozturk, Pinar ; Várkonyi-Kóczy, A. ; Istvan, Vajda. / A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation. Lecture Notes in Networks and Systems. Springer, 2019. pp. 266-274 (Lecture Notes in Networks and Systems).
@inbook{36bc89004d2448b5888179bfe07b0110,
title = "A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation",
abstract = "In this paper, we present a Cluster-Based Approach (CBA) that utilizes the support vector machine (SVM) and an artificial neural network (ANN) to estimate and predict the daily horizontal global solar radiation. In the proposed CBA-ANN-SVM approach, we first conduct clustering analysis and divided the global solar radiation data into clusters, according to the calendar months. Our approach aims at maximizing the homogeneity of data within the clusters, and the heterogeneity between the clusters. The proposed CBA-ANN-SVM approach is validated and the precision is compared with ANN and SVM techniques. The mean absolute percentage error (MAPE) for the proposed approach was reported lower than those of ANN and SVM.",
keywords = "Artificial neural networks (ANN), Global solar radiation, Machine learning, Prediction, Support vector machine (SVM)",
author = "Mehrnoosh Torabi and Amir Mosavi and Pinar Ozturk and A. V{\'a}rkonyi-K{\'o}czy and Vajda Istvan",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-319-99834-3_35",
language = "English",
series = "Lecture Notes in Networks and Systems",
publisher = "Springer",
pages = "266--274",
booktitle = "Lecture Notes in Networks and Systems",

}

TY - CHAP

T1 - A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation

AU - Torabi, Mehrnoosh

AU - Mosavi, Amir

AU - Ozturk, Pinar

AU - Várkonyi-Kóczy, A.

AU - Istvan, Vajda

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this paper, we present a Cluster-Based Approach (CBA) that utilizes the support vector machine (SVM) and an artificial neural network (ANN) to estimate and predict the daily horizontal global solar radiation. In the proposed CBA-ANN-SVM approach, we first conduct clustering analysis and divided the global solar radiation data into clusters, according to the calendar months. Our approach aims at maximizing the homogeneity of data within the clusters, and the heterogeneity between the clusters. The proposed CBA-ANN-SVM approach is validated and the precision is compared with ANN and SVM techniques. The mean absolute percentage error (MAPE) for the proposed approach was reported lower than those of ANN and SVM.

AB - In this paper, we present a Cluster-Based Approach (CBA) that utilizes the support vector machine (SVM) and an artificial neural network (ANN) to estimate and predict the daily horizontal global solar radiation. In the proposed CBA-ANN-SVM approach, we first conduct clustering analysis and divided the global solar radiation data into clusters, according to the calendar months. Our approach aims at maximizing the homogeneity of data within the clusters, and the heterogeneity between the clusters. The proposed CBA-ANN-SVM approach is validated and the precision is compared with ANN and SVM techniques. The mean absolute percentage error (MAPE) for the proposed approach was reported lower than those of ANN and SVM.

KW - Artificial neural networks (ANN)

KW - Global solar radiation

KW - Machine learning

KW - Prediction

KW - Support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=85055710201&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055710201&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-99834-3_35

DO - 10.1007/978-3-319-99834-3_35

M3 - Chapter

T3 - Lecture Notes in Networks and Systems

SP - 266

EP - 274

BT - Lecture Notes in Networks and Systems

PB - Springer

ER -