結合未來氣象預報與雙流式 ViT 架構的可解釋太陽能發電量預測模型

NCU Institutional Repository > 工學院 > 機械工程研究所 > 博碩士論文 > Item 987654321/98750

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/98750

题名:	結合未來氣象預報與雙流式 ViT 架構的可解釋太陽能發電量預測模型
作者:	顏宏庭;Yan, Hong-Ting
贡献者:	機械工程學系
关键词:	多變量時間序列預測;太陽能發電預測;未來天氣預報整合;多頭預測模組;模型可解釋性;Multivariate time series forecasting;solar power forecasting;integration of future weather forecasts;multi-heads predict module;model interpretability
日期:	2025-08-20
上传时间:	2025-10-17 13:15:04 (UTC+8)
出版者:	國立中央大學
摘要:	近期已有許多深度學習模型被提出用於多變量時間序列（MTS）預測的研究。其中，以 Transformer 為基礎的模型因其具備有效捕捉長期依賴關係的特性，展現出極大的潛力與應用價值。然而，現有模型在應用於太陽能發電預測時，未能充分考量太陽能發電本身具有的間歇性與高度依賴氣象條件的特性。此外，這些模型通常未將未來天氣預報資訊納入考量，使預測的精準度受限。此外，現有的時間序列預測模型普遍呈現「黑盒」特性，缺乏足夠的可解釋性，導致使用者難以理解模型決策的依據與運作原理。這些問題凸顯出在太陽能發電預測領域，仍缺乏專門針對該領域需求所設計的模型。為填補這項研究空白，本論文提出一種創新的太陽能發電預測模型，結合了過去的發電數據與氣象資料，以及未來的天氣預報資訊。模型設計上透過將過去與未來資訊依特定時間間隔切割為多個時間段，從不同時間角度有效地預測未來太陽能發電量。此外，本論文特別設計多發電預測頭模組，透過多發電區段的預測方法，有效提升預測準確度，同時賦予模型良好的可解釋性，使得使用者能明確理解模型如何根據不同因素做出預測。透過實驗驗證，本論文所提出之模型不僅具備高精確性，並因未來天氣預報資訊的加入及多預測頭模組設計，性能及解釋性明顯優於傳統方法，能夠為能源管理者提供清晰明確的決策支援，提升其實務應用價值。;In recent years, numerous deep learning models have been proposed for multivariate time series (MTS) forecasting. Among them, Transformer-based models have demonstrated significant potential and practical value due to their ability to effectively capture long-term dependencies. However, existing models applied to solar power forecasting often overlook the inherent intermittency and strong dependency on meteorological conditions specific to solar energy generation. Furthermore, these models typically fail to incorporate future weather forecasts, thereby limiting their prediction accuracy. In addition, current time series forecasting models generally exhibit "black box" characteristics, lacking sufficient interpretability, which makes it difficult for users to understand the basis and rationale behind model decisions. These limitations highlight the absence of models specifically designed to meet the unique demands of solar power forecasting. To address this research gap, this thesis proposes an innovative solar power forecasting model that integrates historical power generation data, past meteorological data, and future weather forecasts. The model is designed to segment both past and future information into multiple time intervals, enabling effective prediction of future solar power generation from different temporal perspectives. In particular, the model introduces a multi-heads predict module that forecasts power generation across multiple time segments, thereby improving prediction accuracy and enhancing model interpretability. This allows users to clearly understand how the model makes predictions based on various contributing factors. Experimental results validate the effectiveness of the proposed model, demonstrating not only high accuracy but also significantly improved performance and interpretability due to the incorporation of future weather forecasts and the multi-head prediction architecture. These advancements provide clear and actionable decision support for energy managers, enhancing the model’s practical applicability.
显示于类别:	[機械工程研究所] 博碩士論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	10	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....