对比10种深度模型，发现Transformer在光伏预测中精度最高。
Efficient Deep Learning for Short-Term Solar Irradiance Time Series Forecasting: A Benchmark Study in Ho Chi Minh City
- 用十种深度模型对比预测光照强度，选了最有效的Transformer。
- Transformer准确率最高，R²达0.9696，误差MAE为23.78 W/m²。
- 知识蒸馏让大模型变小23.5%还更准，适合边缘设备部署。
可靠的全球水平辐照度（GHI）预测对缓解电网中太阳能波动至关重要。本研究在胡志明市对十种深度学习架构进行了短时（1小时前瞻）GHI时间序列预测的全面基准测试，利用2011-2020年高分辨率NSRDB卫星数据，对比了经典模型（如LSTM、TCN）与新兴前沿架构（包括Transformer、Informer、iTransformer、TSMixer和Mamba）。实验结果表明，Transformer表现最优，预测准确率最高，R²达0.9696。通过SHAP分析揭示，Transformer表现出强烈的“近期偏好”，聚焦于即时大气条件；而Mamba则显式利用24小时周期性依赖进行预测。此外，研究证明知识蒸馏可将高性能Transformer压缩23.5%，同时意外降低误差（MAE: 23.78 W/m²），为在资源受限的边缘设备上部署低延迟预测提供了可行路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。