arXiv：cs.LG· Nikolaos A. Efkarpidis, Despoina Kothona, Georgios C. Christoforidis·· 4 小时前AI 评分25
混合预测模型用于建筑热负荷短期预测的对比综述
Comparative review of hybrid forecasting models for short-term prediction of building thermal load
AI 导读
一项对比综述评估了 13 种混合方法在建筑供暖与生活热水（DHW）短期需求预测中的表现，其中 EMD-LSTM-Markov 模型对日前功率曲线的预测精度最高，但对高功率骤升和尖峰存在低估；SVM-SA 与 RF-ISSA-LSTM 则倾向输出平滑曲线，同样低估多数功率峰值。研究基于苏格兰家庭的历史热需求数据与历史天气预报开展定性梳理与定量评测，并汇总了各方法的输入输出特征及优缺点。
正文
Abstract:In this paper, a comparative review of different hybrid models for short-term forecasting of building thermal demand is carried out. Particularly, the assessment tackles the comparison of data-driven models enhanced with other state-of-the-art techniques. At the first step, the existing techniques reported in the literature are analysed. It is concluded that Metaheuristics or a data-driven model are used to identify the parameters of the basic model. The qualitative evaluation includes for each method the input and output features, main advantages and drawbacks. At the second step, an existing dataset of historical thermal demand from Scottish households, as well as historical weather forecasts are utilized to assess additionally the performance of existing hybrid methods. From the assessment of 13 hybrid methods, the Empirical Modal Decomposition - long short-term memory - Markov (EMD-LSTM-Markov) model can predict with the highest accuracy the day-ahead power pattern of heating and domestic hot water (DHW) demands. Though local power peaks are also accurately predicted, high power swells and spikes are underestimated. Other methods, such as Support Vector Machine - Simulated Annealing (SVM-SA) and Random Forest - Improved Sparrow Search Algorithm - LSTM (RF-ISSA-LSTM) predict a smooth pattern of heating and DHW demand profiles with rapid changes underestimating most power peaks.
| Comments: | 27 pages, 15 tables, and 13 figures |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.06881 [cs.LG] |
| (or arXiv:2610.06881v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.06881 arXiv-issued DOI via DataCite |
Submission history
From: Nikolaos Efkarpidis [view email]
[v1]
Sat, 19 Sep 2026 09:22:00 UTC (16,136 KB)
来源：arXiv：cs.LG · arxiv.org