mlsanityData to 14 Oct 2026

Efficient Deep Learning for Short-Term Solar Irradiance Time Series Forecasting: A Benchmark Study in Ho Chi Minh City

arXiv 2512.23898 ↗First posted 29 Dec 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 22 references that are in the map. First posted on arXiv 29 Dec 2025.

Builds on

13 of 22 references.

References · 13

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  6. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  7. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  8. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  9. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  10. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  11. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 761
  12. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
1 more
  1. 20191D Convolutional Neural Networks and Applications: A Surveycited by 153

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Benchmarking State Space Models, Transformers, and Recurrent Networks for US Grid Forecasting
  2. 2026FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting
  3. 2026Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting
  4. 2026Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems
  5. 2024A Comprehensive Survey of Deep Learning for Time Series Forecasting: Architectural Diversity and Open Challenges
  6. 2026A Controlled Visual-Backbone Benchmark for Multimodal Short-Term Solar Irradiance Forecasting
  7. 2025Semi-Supervised Deep Domain Adaptation for Predicting Solar Power Across Different Locations
  8. 2025Data-driven solar forecasting enables near-optimal economic decisions