![Sample our Built Environment journals, sign in here to start your access, Latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5926/TOC-Subject-Sample-2021-Built-Environment.jpg"})
ABSTRACT
Photovoltaic power generation is impacted by various meteorological factors leading to significant intermittent and volatile, so dispatch of photovoltaic power plants and safe operation of power systems hinge on accurate prediction of PV power output. Researchers have proposed a variety of ways to improve the performance of predictions, and a hybrid model often performs better than a single model. Considering that the sequence decomposition method can alleviate the volatile nature of the original sequence, we propose a new hybrid model VMD-GA-Conv-A-LSTM, design a method to determine the optimal parameters of the VMD and utilize the parameter-optimized VMD for sequence decomposition, combining with a novel deep learning model for more accurate prediction. The model first calculates the optimal parameters for the variational mode decomposition (VMD) using a search algorithm over a specified parameter range, and uses these parameters to decompose the photovoltaic power sequence into several sub-sequences. Then, the sub-sequences and preprocessed historical meteorological data are input into several long short-term memory (LSTM) integrated with 1D convolution and attention mechanism (Conv-A-LSTM) separately. The predictions corresponding to each sub-sequence are accumulated to get the predictions of the hybrid model. The hybrid model was validated on the dataset generated from the 5.20 kW Photovoltaic site in Alice Springs, Australia, and ERA5 data, respectively. Compared with baseline models, the proposed hybrid model achieves the best prediction accuracy. The RMSE, MAE, and R2 of the 2-hour prediction performed on the Australia dataset are 0.1884 kW, 0.0758 kW and 0.9876, respectively. Therefore, the hybrid model proposed in this study is able to provide statistical data support for photovoltaic plant operation and scheduling.
Nomenclature
| PV | = | Photovoltaic |
| DL | = | Deep Learning |
| VMD | = | Variational Mode Decomposition |
| WT | = | Wavelet Transform |
| GA | = | Genetic Algorithm |
| IMF | = | Intrinsic Moe Function |
| EMD | = | Empirical Mode Decomposition |
| EEMD | = | Ensemble Empirical Mode Decomposition |
| CEEMD | = | Complementary Ensemble Empirical Mode Decomposition |
| CEEMDAN | = | Complete Ensemble Empirical Mode Decomposition Adaptive Noise |
| ISSA | = | Improved Sparrow Search Algorithm |
| EE | = | Envelope Entropy |
| NWP | = | Numerical Weather Prediction |
| RMSE | = | Root Mean Square Error |
| MAE | = | Mean Absolute Error |
| MSE | = | Mean Square Error |
| R2 | = | Determination Coefficient |
| CNN | = | Convolution Neural Network |
| TCN | = | Temporal Convolutional Network |
| RNN | = | Recurrent Neural Network |
| LSTM | = | Long Short-Term Memory |
| LSSVM | = | Least Squares Support Vector Machines |
| NLP | = | Natural Language Processing |
| ESN | = | Echo State Network |
| ARIMA | = | Autoregressive Integrated Moving Average |
| GRU | = | Gated Recurrent Unit |
| ECWMF | = | European Centre for Medium-Range Weather Forecasts |
Disclosure statement
No potential conflict of interest was reported by the author(s).
Data availability statement
DKASC Alice Springs: https://dkasolarcentre.com.au/source/alice-springs/dka-m17-c-phase.
Additional information
Notes on contributors
Kejun Tao
Kejun Tao is a graduate student in the computer science department at Qingdao University of Science and Technology. His research interests are in time-series prediction. He has extensive experience in photovoltaic power forecasting. This is his first published paper as first author.
Jinghao Zhao
Jinghao Zhao is an engineer at the Extended Energy Big Data and Strategy Research Center of the Qingdao Institute of Bioenergy and Process Research, Chinese Academy of Sciences. His research interests include artificial intelligence and energy activity prediction, and he has published five papers in related research.
Nana Wang
Nana Wang is a senior engineer in the Chinese Academy of Sciences Qingdao Institute of Bioenergy and Bioprocess Technology. She has long been engaged in energy big data platform construction, data governance and application, data sharing and protection and has won many awards for her research.
Ye Tao
Ye Tao is a professor in the Department of Computer Science at Qingdao University of Science and Technology. His research focus is on key technologies in the fields of network collaborative manufacturing and modern service industry. He has published over 30 papers in major journals and has won many awards for his research.
Yajun Tian
Yajun Tian is a researcher of the Chinese Academy of Sciences Qingdao Institute of Bioenergy and Bioprocess Technology, and director of the Extended Energy Big Data and Strategic Research Center. Mainly engaged in work related to energy big data, energy strategy, full lifecycle assessment, technical and economic evaluation, energy environment, energy economy research, etc.