Performance of SolarTrans.

Accurate and interpretable solar power forecasting is critical for effectively integrating Photo-Voltaic (PV) systems into modern energy infrastructure. This paper introduces a novel two-stage hybrid framework that couples deep learning-based time series prediction with generative Large Language Models (LLMs) to enhance forecast accuracy and model interpretability. At its core, the proposed SolarTrans model leverages a lightweight Transformer-based encoder-decoder architecture tailored for short-term DC power prediction using multivariate inverter and weather data, including irradiance, ambient and module temperatures, and temporal features. Experiments conducted on publicly available datasets from two PV plants over 34 days demonstrate strong predictive performance. The SolarTrans model achieves a Mean Absolute Error (MAE) of 0.0782 and 0.1544, Root Mean Squared Error (RMSE) of 0.1760 and 0.4424, and R2 scores of 0.9692 and 0.7956 on Plant 1 and Plant 2, respectively. On the combined dataset, the model yields an MAE of 0.1105, RMSE of 0.3189, and R2 of 0.8967. To address the interpretability challenge, we fine-tuned the Flan-T5 model on structured prompts derived from domain-informed templates and forecast outputs. The resulting explanation module achieves ROUGE-1, ROUGE-2, ROUGE-L, and ROUGE-Lsum scores of 0.7889, 0.7211, 0.7759, and 0.7771, respectively, along with a BLEU score of 0.6558, indicating high-fidelity generation of domain-relevant natural language explanations.精准且可解释的太阳能功率预测，对于将光伏（Photo-Voltaic, PV）系统有效整合至现代能源基础设施中至关重要。本文提出一种全新的两阶段混合框架，将基于深度学习的时间序列预测与生成式大语言模型（Large Language Model, LLM）相结合，以提升预测精度与模型可解释性。所提出的SolarTrans模型以轻量化的基于Transformer的编码器-解码器架构为核心，该架构专为利用多变量逆变器与气象数据开展短期直流功率预测而定制，涵盖辐照度、环境温度、组件温度及时序特征。研究团队基于两座光伏电站的公开数据集开展了为期34天的实验，结果证明该模型具备优异的预测性能。在电站1与电站2上，SolarTrans模型的平均绝对误差（Mean Absolute Error, MAE）分别为0.0782与0.1544，均方根误差（Root Mean Squared Error, RMSE）分别为0.1760与0.4424，决定系数（R2）分别为0.9692与0.7956。在合并数据集上，该模型的MAE为0.1105、RMSE为0.3189、R2为0.8967。为解决可解释性难题，我们基于领域知识模板与预测输出构建结构化提示词，并在此基础上对Flan-T5模型进行微调。由此得到的解释模块在ROUGE-1、ROUGE-2、ROUGE-L以及ROUGE-Lsum指标上的得分分别为0.7889、0.7211、0.7759与0.7771，同时BLEU得分达到0.6558，表明该模块能够生成高保真度的、贴合领域相关的自然语言解释。