Evaluation of Machine Learning Methods on Large-Scale Spatiotemporal Data for Photovoltaic Power Prediction

The exponential increase in photovoltaic (PV) arrays installed globally, particularly given the intermittent nature of PV generation, has emphasized the need to accurately forecast the predicted output power of the arrays. Regardless of the length of the forecasts, the modeling of PV arrays is made...

Full description

Bibliographic Details
Main Authors: Evan Sauter, Maqsood Mughal, Ziming Zhang
Format: Article
Language:English
Published: MDPI AG 2023-06-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/16/13/4908
_version_ 1797591844412981248
author Evan Sauter
Maqsood Mughal
Ziming Zhang
author_facet Evan Sauter
Maqsood Mughal
Ziming Zhang
author_sort Evan Sauter
collection DOAJ
description The exponential increase in photovoltaic (PV) arrays installed globally, particularly given the intermittent nature of PV generation, has emphasized the need to accurately forecast the predicted output power of the arrays. Regardless of the length of the forecasts, the modeling of PV arrays is made difficult by their dependence on weather. Typically, the model projections are generated from datasets at one location across a couple of years. The purpose of this study was to compare the effectiveness of regression models in very short-term deterministic forecasts for spatiotemporal projections. The compiled dataset is unique given that it consists of weather and output power data of PVs located at five cities spanning 3 and 6 years in length. Gated recurrent unit (GRU) generalized the best for same-city and cross-city predictions, while long short-term memory (LSTM) and ensemble bagging had the best cross-city and same-city predictions, respectively.
first_indexed 2024-03-11T01:43:10Z
format Article
id doaj.art-94e240a1187f43aaa6e0b8786fa13283
institution Directory Open Access Journal
issn 1996-1073
language English
last_indexed 2024-03-11T01:43:10Z
publishDate 2023-06-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj.art-94e240a1187f43aaa6e0b8786fa132832023-11-18T16:27:37ZengMDPI AGEnergies1996-10732023-06-011613490810.3390/en16134908Evaluation of Machine Learning Methods on Large-Scale Spatiotemporal Data for Photovoltaic Power PredictionEvan Sauter0Maqsood Mughal1Ziming Zhang2Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, 100 Institute Road, Worcester, MA 01609, USADepartment of Electrical and Computer Engineering, Worcester Polytechnic Institute, 100 Institute Road, Worcester, MA 01609, USADepartment of Electrical and Computer Engineering, Worcester Polytechnic Institute, 100 Institute Road, Worcester, MA 01609, USAThe exponential increase in photovoltaic (PV) arrays installed globally, particularly given the intermittent nature of PV generation, has emphasized the need to accurately forecast the predicted output power of the arrays. Regardless of the length of the forecasts, the modeling of PV arrays is made difficult by their dependence on weather. Typically, the model projections are generated from datasets at one location across a couple of years. The purpose of this study was to compare the effectiveness of regression models in very short-term deterministic forecasts for spatiotemporal projections. The compiled dataset is unique given that it consists of weather and output power data of PVs located at five cities spanning 3 and 6 years in length. Gated recurrent unit (GRU) generalized the best for same-city and cross-city predictions, while long short-term memory (LSTM) and ensemble bagging had the best cross-city and same-city predictions, respectively.https://www.mdpi.com/1996-1073/16/13/4908machine learningdeep learningphotovoltaic generation forecastingspatiotemporal regression
spellingShingle Evan Sauter
Maqsood Mughal
Ziming Zhang
Evaluation of Machine Learning Methods on Large-Scale Spatiotemporal Data for Photovoltaic Power Prediction
Energies
machine learning
deep learning
photovoltaic generation forecasting
spatiotemporal regression
title Evaluation of Machine Learning Methods on Large-Scale Spatiotemporal Data for Photovoltaic Power Prediction
title_full Evaluation of Machine Learning Methods on Large-Scale Spatiotemporal Data for Photovoltaic Power Prediction
title_fullStr Evaluation of Machine Learning Methods on Large-Scale Spatiotemporal Data for Photovoltaic Power Prediction
title_full_unstemmed Evaluation of Machine Learning Methods on Large-Scale Spatiotemporal Data for Photovoltaic Power Prediction
title_short Evaluation of Machine Learning Methods on Large-Scale Spatiotemporal Data for Photovoltaic Power Prediction
title_sort evaluation of machine learning methods on large scale spatiotemporal data for photovoltaic power prediction
topic machine learning
deep learning
photovoltaic generation forecasting
spatiotemporal regression
url https://www.mdpi.com/1996-1073/16/13/4908
work_keys_str_mv AT evansauter evaluationofmachinelearningmethodsonlargescalespatiotemporaldataforphotovoltaicpowerprediction
AT maqsoodmughal evaluationofmachinelearningmethodsonlargescalespatiotemporaldataforphotovoltaicpowerprediction
AT zimingzhang evaluationofmachinelearningmethodsonlargescalespatiotemporaldataforphotovoltaicpowerprediction