Photovoltaic System Performance Forecasting Using LSTM Neural Networks
Deep learning has proven to be a valued contributor to recent technological advancements within energy systems. This thesis project explores methods of photovoltaic (PV) system power output forecasting through the utilization of long short-term memory (LSTM) neural networks. An encoder-decoder archi...
Main Author: | |
---|---|
Format: | Others |
Language: | English |
Published: |
Uppsala universitet, Institutionen för informationsteknologi
2021
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-455665 |
id |
ndltd-UPSALLA1-oai-DiVA.org-uu-455665 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-UPSALLA1-oai-DiVA.org-uu-4556652021-10-13T05:36:33ZPhotovoltaic System Performance Forecasting Using LSTM Neural NetworksengHamberg, LukasUppsala universitet, Institutionen för informationsteknologi2021Machine LearningLSTMneural networksPhotovoltaic systemspv-systemsDeep learningpower output forecastingComputer SciencesDatavetenskap (datalogi)Deep learning has proven to be a valued contributor to recent technological advancements within energy systems. This thesis project explores methods of photovoltaic (PV) system power output forecasting through the utilization of long short-term memory (LSTM) neural networks. An encoder-decoder architecture (ED-LSTM) and a stacked vector output architecture (SVO-LSTM) were compared in terms of their ability to accurately produce power output forecasts with a 24-hour forecast horizon. The datasets which were used for model training were composed of historical meteorological observations and PV system power output readings. The results indicate that the encoder-decoder model and the stacked vector output model were somewhat equally skilled at producing power output forecasts. Best results were obtained by the encoder-decoder LSTM model which achieved a 26.63% improvement over a persistence model when trained on data sequences which preceded the forecast horizon, and a 44.96% improvement over a persistence model when the model was provided meteorological data from an oracle forecaster. Student thesisinfo:eu-repo/semantics/bachelorThesistexthttp://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-455665UPTEC IT, 1401-5749 ; 21008application/pdfinfo:eu-repo/semantics/openAccess |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Machine Learning LSTM neural networks Photovoltaic systems pv-systems Deep learning power output forecasting Computer Sciences Datavetenskap (datalogi) |
spellingShingle |
Machine Learning LSTM neural networks Photovoltaic systems pv-systems Deep learning power output forecasting Computer Sciences Datavetenskap (datalogi) Hamberg, Lukas Photovoltaic System Performance Forecasting Using LSTM Neural Networks |
description |
Deep learning has proven to be a valued contributor to recent technological advancements within energy systems. This thesis project explores methods of photovoltaic (PV) system power output forecasting through the utilization of long short-term memory (LSTM) neural networks. An encoder-decoder architecture (ED-LSTM) and a stacked vector output architecture (SVO-LSTM) were compared in terms of their ability to accurately produce power output forecasts with a 24-hour forecast horizon. The datasets which were used for model training were composed of historical meteorological observations and PV system power output readings. The results indicate that the encoder-decoder model and the stacked vector output model were somewhat equally skilled at producing power output forecasts. Best results were obtained by the encoder-decoder LSTM model which achieved a 26.63% improvement over a persistence model when trained on data sequences which preceded the forecast horizon, and a 44.96% improvement over a persistence model when the model was provided meteorological data from an oracle forecaster. |
author |
Hamberg, Lukas |
author_facet |
Hamberg, Lukas |
author_sort |
Hamberg, Lukas |
title |
Photovoltaic System Performance Forecasting Using LSTM Neural Networks |
title_short |
Photovoltaic System Performance Forecasting Using LSTM Neural Networks |
title_full |
Photovoltaic System Performance Forecasting Using LSTM Neural Networks |
title_fullStr |
Photovoltaic System Performance Forecasting Using LSTM Neural Networks |
title_full_unstemmed |
Photovoltaic System Performance Forecasting Using LSTM Neural Networks |
title_sort |
photovoltaic system performance forecasting using lstm neural networks |
publisher |
Uppsala universitet, Institutionen för informationsteknologi |
publishDate |
2021 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-455665 |
work_keys_str_mv |
AT hamberglukas photovoltaicsystemperformanceforecastingusinglstmneuralnetworks |
_version_ |
1719489617043914752 |