Forecasting solar photosynthetic photon flux density under cloud cover effects: novel predictive model using convolutional neural network integrated with long short-term memory network

Abstract

Forecast models of solar radiation incorporating cloud effects are useful tools to evaluate the impact of stochastic behaviour of cloud movement, real-time integration of photovoltaic energy in power grids, skin cancer and eye disease risk minimisation through solar ultraviolet (UV) index prediction and bio-photosynthetic processes through the modelling of solar photosynthetic photon flux density (PPFD). This research has developed deep learning hybrid model (i.e., CNN-LSTM) to factor in role of cloud effects integrating the merits of convolutional neural networks with long short-term memory networks to forecast near real-time (i.e., 5-min) PPFD in a sub-tropical region Queensland, Australia. The prescribed CLSTM model is trained with real-time sky images that depict stochastic cloud movements captured through a total sky imager (TSI-440) utilising advanced sky image segmentation to reveal cloud chromatic features into their statistical values, and to purposely factor in the cloud variation to optimise the CLSTM model. The model, with its competing algorithms (i.e., CNN, LSTM, deep neural network, extreme learning machine and multivariate adaptive regression spline), are trained with 17 distinct cloud cover inputs considering the chromaticity of red, blue, thin, and opaque cloud statistics, supplemented by solar zenith angle (SZA) to predict short-term PPFD. The models developed with cloud inputs yield accurate results, outperforming the SZA-based models while the best testing performance is recorded by the objective method (i.e., CLSTM) tested over a 7-day measurement period. Specifically, CLSTM yields a testing performance with correlation coefficient r = 0.92, root mean square error RMSE = 210.31 μ mol of photons m−2 s−1, mean absolute error MAE = 150.24 μ mol of photons m−2 s−1, including a relative error of RRMSE = 24.92% MAPE = 38.01%, and Nash Sutcliffe’s coefficient ENS = 0.85, and Legate and McCabe’s Index LM = 0.68 using cloud cover in addition to the SZA as an input. The study shows the importance of cloud inclusion in forecasting solar radiation and evaluating the risk with practical implications in monitoring solar energy, greenhouses and high-value agricultural operations affected by stochastic behaviour of clouds. Additional methodological refinements such as retraining the CLSTM model for hourly and seasonal time scales may aid in the promotion of agricultural crop farming and environmental risk evaluation applications such as predicting the solar UV index and direct normal solar irradiance for renewable energy monitoring systems.

Multi-step solar UV index prediction using deep learning methods

“…To reduce the length of this work, the theoretical descriptions of the models used in this paper are not presented because they are well explained elsewhere in different sources. The detail of the CLSTM theory has been introduced in [14][15][16][17] for successfully predicting various datasets including solar photosynthetic photon ux density, solar radiation, photovoltaic power, and thermal displacement. Additionally, the studies in [18][19][20][21][22][23] present the mathematical formulas of the other deep learning models (LSTM, CNN, DNN, MLP) used in this study.…”

“…In another study [12], the authors employed Coral Reefs, and Extreme Learning Machine (ELM) to construct a forecasting model of solar radiation on data from southern Spain. The study in [13] developed an algorithm by combining two deep leaning techniques, CNN and LSTM, to forecast solar photosynthetic photon ux density in the state of Queensland, Australia, and the results were compared to CNN, LSTM, deep neural network, extreme learning machine and multivariate adaptive regression spline.…”

Hybrid Convolutional Neural Network-Multilayer Perceptron Model for Solar Radiation Prediction

“…Therefore, the datasets in this study limited to cloud area fraction may bound the full assessment of intermittency in energy supply. An independent future study could also consider various cloud chromatic properties, cloud top height, water vapor, ozone, and cloud movements [101,102] that could be factored to test the overall performance of the CMLP model.…”