arXiv：cs.LG（机器学习，全量分类）· Rakib Abdullah, K. M. Tahlil Mahfuz Faruk·· 1 天前AI 评分32
迁移学习结合 CQR 用于停电导致数据稀缺下的光伏预测
Transfer Learning with Conformalized Quantile Regression for Solar PV Forecasting Under Load-Shedding-Driven Data Scarcity
AI 导读
研究提出迁移学习结合 Conformalized Quantile Regression（CQR）框架，用澳大利亚 Alice Springs 光伏数据预训练时序模型，再适配到模拟的孟加拉国光伏数据。仅一个月目标域数据时 RMSE 降低最多 23.7%，三个月时降低 13.7%；三个月数据下达到 94.3% 经验覆盖率，预测区间比不用迁移学习窄 14%。
正文
Abstract:Solar photovoltaic (PV) forecasting in regions affected by load shedding is challenging because reliable historical observations are scarce. This study proposes a transfer learning framework combined with Conformalized Quantile Regression (CQR) to improve PV power forecasting and provide reliable uncertainty estimates under severe data scarcity. A source-domain PV dataset from Alice Springs, Australia, is used to pretrain a temporal forecasting model, which is then adapted to simulated Bangladesh PV data representing different levels of historical availability. Experimental results show that transfer learning reduces RMSE by up to 23.7% when only one month of target-domain data is available and by 13.7% with three months of data. The proposed Transfer Learning plus CQR framework achieves 94.3% empirical coverage with three months of target data while producing prediction intervals that are 14% narrower than those obtained without transfer learning. These results demonstrate that combining transfer learning with conformal uncertainty quantification can improve both point forecasting accuracy and uncertainty reliability when target-domain PV data are severely limited.
| Comments: | 6 pages, 4 figures, 1st International Conference on Next-Generation Electrical & Electronics, Computer Systems, and Technologies (iCONEECT 2026) |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2609.26959 [cs.LG] |
| (or arXiv:2609.26959v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.26959 arXiv-issued DOI via DataCite |
Submission history
From: Rakib Abdullah [view email]
[v1]
Tue, 22 Sep 2026 18:49:40 UTC (1,251 KB)
[v2]
Thu, 1 Oct 2026 07:47:57 UTC (1,252 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org