Abstract
A practical approach to continuously monitor and provide real-time solar energy prediction can help support reliable renewable energy supply and relevant energy security systems. In this study on the Korean Peninsula, contemporaneous solar radiation images obtained from the Communication, Ocean and Meteorological Satellite (COMS) Meteorological Imager (MI) system, were used to design a convolutional neural network and a long short-term memory network predictive model, ConvLSTM. This model was applied to predict one-hour ahead solar radiation and spatially map solar energy potential. The newly designed ConvLSTM model enabled reliable prediction of solar radiation, incorporating spatial changes in atmospheric conditions and capturing the temporal sequence-to-sequence variations that are likely to influence solar driven power supply and its overall stability. Results showed that the proposed ConvLSTM model successfully captured cloud-induced variations in ground level solar radiation when compared with reference images from a physical model. A comparison with ground pyranometer measurements indicated that the short-term prediction of global solar radiation by the proposed ConvLSTM had the highest accuracy [root mean square error (RMSE) = 83.458 W · m−2, mean bias error (MBE) = 4.466 W · m−2, coefficient of determination (R2) = 0.874] when compared with results of conventional artificial neural network (ANN) [RMSE = 94.085 W · m−2, MBE = −6.039 W · m−2, R2 = 0.821] and random forest (RF) [RMSE = 95.262 W · m−2, MBE = −11.576 W · m−2, R2 = 0.839] models. In addition, ConvLSTM better captured the temporal variations in predicted solar radiation, mainly due to cloud attenuation effects when compared with two selected ground stations. The study showed that contemporaneous satellite images over short-term or near real-time intervals can successfully support solar energy exploration in areas without continuous environmental monitoring systems, where satellite footprints are available to model and monitor solar energy management systems supporting real-life power grid systems.
Highlights
Successful integration of the rapidly growing renewable predicted interpreting physical processes of energy production into existing or future power grid atmospheric flows, as well as by considering cloud systems is an important challenge for the future global movement and other atmospheric components
In hydropower can control their energy production according particular, very short-term forecasts of 1–2 h an us cri by pt atmospheric properties
This study highlights a new pathway for using was able to predict maps of solar radiation relatively well, contemporaneous satellite images to capture the nonlinear even in the presence of nonlinearities, which are inherent in any dynamical system
Summary
Successful integration of the rapidly growing renewable predicted interpreting physical processes of energy production into existing or future power grid atmospheric flows, as well as by considering cloud systems is an important challenge for the future global movement and other atmospheric components. Any electricity operator needs to ensure a solar energy power generating systems require short-term precise balance between electricity production and predictions (within 6h). NWP models are consumption to reduce overall costs and sustain electricity relatively less reliable for short-term prediction of solar production [1]. Existing energy plants that run on nuclear radiation because the models need to derive a physical power, steam (thermal resources), fossil fuels (coal), and valid state after initialization (called the spin-up time). Solar radiation is ahead, derived by NWP, are less accurate than those temporal horizons of their operational power systems [2]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have