Back to Search
Start Over
A Hybrid Machine Learning Approach for Daily Prediction of Solar Radiation
- Source :
- Recent Advances in Technology Research and Education ISBN: 9783319998336
- Publication Year :
- 2018
- Publisher :
- Springer International Publishing, 2018.
-
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.
- Subjects :
- 060102 archaeology
Artificial neural network
business.industry
Computer science
020209 energy
Homogeneity (statistics)
Computer Science::Neural and Evolutionary Computation
Pattern recognition
06 humanities and the arts
02 engineering and technology
Radiation
Support vector machine
Global solar radiation
ComputingMethodologies_PATTERNRECOGNITION
Mean absolute percentage error
0202 electrical engineering, electronic engineering, information engineering
Cluster (physics)
0601 history and archaeology
Artificial intelligence
Cluster analysis
business
GeneralLiterature_REFERENCE(e.g.,dictionaries,encyclopedias,glossaries)
Subjects
Details
- ISBN :
- 978-3-319-99833-6
- ISBNs :
- 9783319998336
- Database :
- OpenAIRE
- Journal :
- Recent Advances in Technology Research and Education ISBN: 9783319998336
- Accession number :
- edsair.doi...........d7d86c695657a09b7dce0030241619f8
- Full Text :
- https://doi.org/10.1007/978-3-319-99834-3_35