An Adaptive Deep Learning Framework for Day-ahead Forecasting of Photovoltaic Power Generation

Accurate forecasts of photovoltaic power generation (PVPG) are essential to optimize operations between energy supply and demand. Recently, the propagation of sensors and smart meters has produced an enormous volume of data, which supports the development of databased PVPG forecasting. Although emerging deep learning (DL) models, such as the long short-term memory (LSTM) model, based on historical data, have provided effective solutions for PVPG forecasting with great successes, these models utilize offline learning. As a result, DL models cannot take advantage of the opportunity to learn from newly-arrived data, and are unable to handle concept drift caused by installing extra PV units and unforeseen PV unit failures. Consequently, to improve day-ahead PVPG forecasting accuracy, as well as eliminate the impacts of concept drift, this paper proposes an adaptive LSTM (AD-LSTM) model, which is a DL framework that can not only acquire general knowledge from historical data, but also dynamically learn specific knowledge from newly-arrived data. A two-phase adaptive learning strategy (TP-ALS) is integrated into AD-LSTM, and a sliding window (SDWIN) algorithm is proposed, to detect concept drift in PV systems. Multiple datasets from PV systems are utilized to assess the feasibility and effectiveness of the proposed approaches. The developed AD-LSTM model demonstrates greater forecasting capability than the offline LSTM model, particularly in the presence of concept drift. Additionally, the proposed AD-LSTM model also achieves superior performance in terms of day-ahead PVPG forecasting compared to other traditional machine learning models and statistical models in the literature.

[1]  Mo M. Jamshidi,et al.  Data-Analytic-Based Adaptive Solar Energy Forecasting Framework , 2018, IEEE Systems Journal.

[2]  M. Raza,et al.  On recent advances in PV output power forecast , 2016 .

[3]  Chunxiang Yang,et al.  An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data , 2015, IEEE Transactions on Sustainable Energy.

[4]  Jizhen Liu,et al.  Weather-Classification-MARS-Based Photovoltaic Power Forecasting for Energy Imbalance Market , 2019, IEEE Transactions on Industrial Electronics.

[5]  Rob J Hyndman,et al.  Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond , 2016 .

[6]  Stefan Jakubek,et al.  Energy management of heavy-duty fuel cell vehicles in real-world driving scenarios: Robust design of strategies to maximize the hydrogen economy and system lifetime , 2021 .

[7]  Mohammad Navid Fekri,et al.  Deep learning for load forecasting with smart meter data: Online Adaptive Recurrent Neural Network , 2021, Applied Energy.

[8]  Bernhard Sick,et al.  Deep Learning for solar power forecasting — An approach using AutoEncoder and LSTM Neural Networks , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[9]  C. K. Simoglou,et al.  Comparison of SARIMAX, SARIMA, modified SARIMA and ANN-based models for short-term PV generation forecasting , 2016, 2016 IEEE International Energy Conference (ENERGYCON).

[10]  Dongxiao Zhang,et al.  Deep learning based forecasting of photovoltaic power generation by incorporating domain knowledge , 2021 .

[11]  Jianchun Peng,et al.  A review of deep learning for renewable energy forecasting , 2019, Energy Conversion and Management.

[12]  Mohamed Abdel-Nasser,et al.  Accurate photovoltaic power forecasting models using deep LSTM-RNN , 2017, Neural Computing and Applications.

[13]  Shady S. Refaat,et al.  Performance Evaluation of Deep Recurrent Neural Networks Architectures: Application to PV Power Forecasting , 2019, 2019 2nd International Conference on Smart Grid and Renewable Energy (SGRE).

[14]  A. Dolara,et al.  Comparison of different physical models for PV power output prediction , 2015 .

[15]  Daniel Koster,et al.  Short-term and regionalized photovoltaic power forecasting, enhanced by reference systems, on the example of Luxembourg , 2019, Renewable Energy.

[16]  Wai Lok Woo,et al.  Multi‐GRU prediction system for electricity generation's planning and operation , 2019, IET Generation, Transmission & Distribution.

[17]  Zhao Liu,et al.  Solar forecasting by K-Nearest Neighbors method with weather classification and physical model , 2016, 2016 North American Power Symposium (NAPS).

[18]  Jianxue Wang,et al.  K-nearest neighbors and a kernel density estimator for GEFCom2014 probabilistic wind power forecasting , 2016 .

[19]  Vita Lystianingrum Budiharto Putri,et al.  Photovoltaic Power Forecasting Using Recurrent Neural Network Based On Bayesian Regularization Algorithm , 2021, 2021 IEEE International Conference in Power Engineering Application (ICPEA).

[20]  R. Inman,et al.  Solar forecasting methods for renewable energy integration , 2013 .

[21]  Bangyin Liu,et al.  Online 24-h solar power forecasting based on weather type classification using artificial neural network , 2011 .

[22]  John Boland,et al.  Short term solar radiation forecasting: Island versus continental sites , 2016 .

[23]  Bohong Wang,et al.  Time series prediction for output of multi-region solar power plants , 2020 .

[24]  Fei Wang,et al.  Generative adversarial networks and convolutional neural networks based weather classification model for day ahead short-term photovoltaic power forecasting , 2019, Energy Conversion and Management.

[25]  Shanlin Yang,et al.  Residential electricity consumption behavior: Influencing factors, related theories and intervention strategies , 2018 .

[26]  Mohamed Abuella,et al.  Solar power forecasting using artificial neural networks , 2015, 2015 North American Power Symposium (NAPS).

[27]  Luca Delle Monache,et al.  Short-term photovoltaic power forecasting using Artificial Neural Networks and an Analog Ensemble , 2017 .

[28]  Abinet Tesfaye Eseye,et al.  Short-term photovoltaic solar power forecasting using a hybrid Wavelet-PSO-SVM model based on SCADA and Meteorological information , 2018 .

[29]  C. Varotsos,et al.  Abrupt changes in global tropospheric temperature , 2019, Atmospheric Research.

[30]  Guangquan Zhang,et al.  Learning under Concept Drift: A Review , 2019, IEEE Transactions on Knowledge and Data Engineering.

[31]  Jian Xiao,et al.  Short-Term Solar Power Forecasting Based on Weighted Gaussian Process Regression , 2018, IEEE Transactions on Industrial Electronics.

[32]  Saad Mekhilef,et al.  Review on forecasting of photovoltaic power generation based on machine learning and metaheuristic techniques , 2019, IET Renewable Power Generation.

[33]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[34]  Z. Şen.  Solar energy in progress and future research trends , 2004 .

[35]  Jan Kleissl,et al.  Solar variability of four sites across the state of Colorado , 2010 .

[36]  Antonello Monti,et al.  On the Necessity of Exogenous Variables for Load, PV and Wind Day-Ahead Forecasts using Recurrent Neural Networks , 2018, 2018 IEEE Electrical Power and Energy Conference (EPEC).