Efficient Deep Learning for Short-Term Solar Irradiance Time Series Forecasting: A Benchmark Study in Ho Chi Minh City
It addresses the problem of solar energy variability for power grid operators, but it is incremental as it benchmarks existing methods on new data.
This study benchmarked ten deep learning architectures for 1-hour ahead solar irradiance forecasting in Ho Chi Minh City, finding that Transformer achieved the highest accuracy with an R^2 of 0.9696 and that Knowledge Distillation compressed the model by 23.5% while reducing error to an MAE of 23.78 W/m^2.
Reliable forecasting of Global Horizontal Irradiance (GHI) is essential for mitigating the variability of solar energy in power grids. This study presents a comprehensive benchmark of ten deep learning architectures for short-term (1-hour ahead) GHI time series forecasting in Ho Chi Minh City, leveraging high-resolution NSRDB satellite data (2011-2020) to compare established baselines (e.g. LSTM, TCN) against emerging state-of-the-art architectures, including Transformer, Informer, iTransformer, TSMixer, and Mamba. Experimental results identify the Transformer as the superior architecture, achieving the highest predictive accuracy with an R^2 of 0.9696. The study further utilizes SHAP analysis to contrast the temporal reasoning of these architectures, revealing that Transformers exhibit a strong "recency bias" focused on immediate atmospheric conditions, whereas Mamba explicitly leverages 24-hour periodic dependencies to inform predictions. Furthermore, we demonstrate that Knowledge Distillation can compress the high-performance Transformer by 23.5% while surprisingly reducing error (MAE: 23.78 W/m^2), offering a proven pathway for deploying sophisticated, low-latency forecasting on resource-constrained edge devices.