Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach
Solar energy is the key to clean energy, which can generate large amounts of electricity for the future smart grid. Unfortunately, the randomness and intermittency of solar energy resources bring difficulties to the stable operation and management of the power systems. To reduce the negative impact...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9203843/ |
id |
doaj-e2c6051a806e400eaf601e78e7108be2 |
---|---|
record_format |
Article |
spelling |
doaj-e2c6051a806e400eaf601e78e7108be22021-03-30T03:59:22ZengIEEEIEEE Access2169-35362020-01-01817587117588010.1109/ACCESS.2020.30258609203843Photovoltaic Power Forecasting With a Hybrid Deep Learning ApproachGangqiang Li0https://orcid.org/0000-0002-7363-1060Sen Xie1https://orcid.org/0000-0002-4074-3998Bozhong Wang2https://orcid.org/0000-0001-5288-6390Jiantao Xin3https://orcid.org/0000-0002-0307-828XYunfeng Li4Shengnan Du5College of Electronics and Information Engineering, Shenzhen University, Shenzhen, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, ChinaState Grid Hunan Electric Power Corporation Maintenance Company, Changsha, ChinaCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen, ChinaCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen, ChinaCollege of Electrical and Information Engineering, Hunan University, Changsha, ChinaSolar energy is the key to clean energy, which can generate large amounts of electricity for the future smart grid. Unfortunately, the randomness and intermittency of solar energy resources bring difficulties to the stable operation and management of the power systems. To reduce the negative impact of photovoltaic (PV) plants accessing on the power systems, it is great significant to predict PV power accurately. In light of this, we propose a hybrid deep learning approach based on convolutional neural network (CNN) and long-short term memory recurrent neural network (LSTM) for the PV output power forecasting. The CNN model is leveraged to discover the nonlinear features and invariant structures exhibited in the previous output power data, thereby facilitating the prediction of PV power. The LSTM is used to model the temporal changes in the latest PV data, and predict the PV power of next time step. Then, the prediction results in the two models are comprehensively considered to obtain the expected output power. The proposed approach is extensively evaluated on real PV data in Limberg, Belgium, and numerical results demonstrate that the proposed approach can provide good prediction performance in PV systems.https://ieeexplore.ieee.org/document/9203843/Solar energydeep learningphotovoltaic (PV) power forecastingpower systems |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Gangqiang Li Sen Xie Bozhong Wang Jiantao Xin Yunfeng Li Shengnan Du |
spellingShingle |
Gangqiang Li Sen Xie Bozhong Wang Jiantao Xin Yunfeng Li Shengnan Du Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach IEEE Access Solar energy deep learning photovoltaic (PV) power forecasting power systems |
author_facet |
Gangqiang Li Sen Xie Bozhong Wang Jiantao Xin Yunfeng Li Shengnan Du |
author_sort |
Gangqiang Li |
title |
Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach |
title_short |
Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach |
title_full |
Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach |
title_fullStr |
Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach |
title_full_unstemmed |
Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach |
title_sort |
photovoltaic power forecasting with a hybrid deep learning approach |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Solar energy is the key to clean energy, which can generate large amounts of electricity for the future smart grid. Unfortunately, the randomness and intermittency of solar energy resources bring difficulties to the stable operation and management of the power systems. To reduce the negative impact of photovoltaic (PV) plants accessing on the power systems, it is great significant to predict PV power accurately. In light of this, we propose a hybrid deep learning approach based on convolutional neural network (CNN) and long-short term memory recurrent neural network (LSTM) for the PV output power forecasting. The CNN model is leveraged to discover the nonlinear features and invariant structures exhibited in the previous output power data, thereby facilitating the prediction of PV power. The LSTM is used to model the temporal changes in the latest PV data, and predict the PV power of next time step. Then, the prediction results in the two models are comprehensively considered to obtain the expected output power. The proposed approach is extensively evaluated on real PV data in Limberg, Belgium, and numerical results demonstrate that the proposed approach can provide good prediction performance in PV systems. |
topic |
Solar energy deep learning photovoltaic (PV) power forecasting power systems |
url |
https://ieeexplore.ieee.org/document/9203843/ |
work_keys_str_mv |
AT gangqiangli photovoltaicpowerforecastingwithahybriddeeplearningapproach AT senxie photovoltaicpowerforecastingwithahybriddeeplearningapproach AT bozhongwang photovoltaicpowerforecastingwithahybriddeeplearningapproach AT jiantaoxin photovoltaicpowerforecastingwithahybriddeeplearningapproach AT yunfengli photovoltaicpowerforecastingwithahybriddeeplearningapproach AT shengnandu photovoltaicpowerforecastingwithahybriddeeplearningapproach |
_version_ |
1724182571709890560 |