Forecasting Solar Power Generation by LSTM Neural Networks
碩士 === 大同大學 === 電機工程學系(所) === 107 === Solar photovoltaic (PV) generation has received great attention in recent years due to the promotion of green environment awareness. Accurate forecasting of solar power benefits the preparation for switching other renewable energies into the power grids when PV...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/fx994p |
id |
ndltd-TW-107TTU05442022 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-107TTU054420222019-11-05T03:37:54Z http://ndltd.ncl.edu.tw/handle/fx994p Forecasting Solar Power Generation by LSTM Neural Networks 以長短期記憶模型實現太陽能發電量預測 Chun-Wei Li 李俊緯 碩士 大同大學 電機工程學系(所) 107 Solar photovoltaic (PV) generation has received great attention in recent years due to the promotion of green environment awareness. Accurate forecasting of solar power benefits the preparation for switching other renewable energies into the power grids when PV power becomes low. In particular, the harmful consequence from the large peak and off-peak gaps of the so-called “duck curve” for PV power can be mitigated. Motivated by the fact that the contingency reserve typically requires thirty to sixty minutes to start up, we mainly focus on the PV power prediction at the hourly level. Among numerous studies in the literature dealing with solar power forecasting via various machine learning methods, the application of long short-term memory (LSTM) on hourly PV power prediction has been recently proposed to capture both hourly patterns in a day and seasonal patterns across days. For hourly prediction, however, we argue that the contribution of seasonal factors might be marginal since the correlation of meteorological information between days is much higher than between years. In this paper, we consider the LSTM-based hourly PV power prediction with the daily factor (24 hours) instead of the seasonal factor (day and month) and improve the pattern learning by selecting the highly-effective features toward the different number of time steps. This design is to enhance the information of time-dependency between each set of training input which is crucial for hourly prediction. By using the real-world data, the experimental results show that the accuracy of hourly PV power prediction can improve from 92–95% to 94–95.5% in terms of coefficient of determination (R2) whilst using the same dataset. Chau-Yun Hsu 許超雲 2019 學位論文 ; thesis 40 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 大同大學 === 電機工程學系(所) === 107 === Solar photovoltaic (PV) generation has received great attention in recent years due to the promotion of green environment awareness. Accurate forecasting of solar power benefits the preparation for switching other renewable energies into the power grids when PV power becomes low. In particular, the harmful consequence from the large peak and off-peak gaps of the so-called “duck curve” for PV power can be mitigated. Motivated by the fact that the contingency reserve typically requires thirty to sixty minutes to start up, we mainly focus on the PV power prediction at the hourly level.
Among numerous studies in the literature dealing with solar power forecasting via various machine learning methods, the application of long short-term memory (LSTM) on hourly PV power prediction has been recently proposed to capture both hourly patterns in a day and seasonal patterns across days. For hourly prediction, however, we argue that the contribution of seasonal factors might be marginal since the correlation of meteorological information between days is much higher than between years. In this paper, we consider the LSTM-based hourly PV power prediction with the daily factor (24 hours) instead of the seasonal factor (day and month) and improve the pattern learning by selecting the highly-effective features toward the different number of time steps. This design is to enhance the information of time-dependency between each set of training input which is crucial for hourly prediction. By using the real-world data, the experimental results show that the accuracy of hourly PV power prediction can improve from 92–95% to 94–95.5% in terms of coefficient of determination (R2) whilst using the same dataset.
|
author2 |
Chau-Yun Hsu |
author_facet |
Chau-Yun Hsu Chun-Wei Li 李俊緯 |
author |
Chun-Wei Li 李俊緯 |
spellingShingle |
Chun-Wei Li 李俊緯 Forecasting Solar Power Generation by LSTM Neural Networks |
author_sort |
Chun-Wei Li |
title |
Forecasting Solar Power Generation by LSTM Neural Networks |
title_short |
Forecasting Solar Power Generation by LSTM Neural Networks |
title_full |
Forecasting Solar Power Generation by LSTM Neural Networks |
title_fullStr |
Forecasting Solar Power Generation by LSTM Neural Networks |
title_full_unstemmed |
Forecasting Solar Power Generation by LSTM Neural Networks |
title_sort |
forecasting solar power generation by lstm neural networks |
publishDate |
2019 |
url |
http://ndltd.ncl.edu.tw/handle/fx994p |
work_keys_str_mv |
AT chunweili forecastingsolarpowergenerationbylstmneuralnetworks AT lǐjùnwěi forecastingsolarpowergenerationbylstmneuralnetworks AT chunweili yǐzhǎngduǎnqījìyìmóxíngshíxiàntàiyángnéngfādiànliàngyùcè AT lǐjùnwěi yǐzhǎngduǎnqījìyìmóxíngshíxiàntàiyángnéngfādiànliàngyùcè |
_version_ |
1719287205961138176 |