发表机构
Faculty of Mechanical Engineering; University of Niš（机械工程学院; 尼什大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文对比XGBoost与LSTM在区域供热系统热能预测中的表现，发现XGBoost性能更优，且计算成本更低、碳足迹更小，凸显传统ML算法在该场景的优势。
AI 中文摘要
本文针对区域供热系统（District Heating Systems，DHS）中传输热能的预测任务，开展了两种不同方法的对比研究，即XGBoost与长短期记忆网络（Long-Short Term Memory，LSTM）。研究目的是探究在时间序列预测场景中，传统机器学习算法是否比深度学习网络表现更优，以及对应的计算成本和环境影响方面的优势。研究聚焦于真实世界的DHS数据集，通过实验与分析表明，在该特定预测任务中，XGBoost的表现始终优于LSTM。误差分布的分析解释了这一差异：LSTM在数据可用性较低的区间会产生更显著的误差。传统机器学习方法降低的计算需求不仅能带来成本节约，还能最小化能源系统数据分析任务相关的碳足迹。
英文摘要
This paper presents a comparative study of two distinct approaches, XGBoost and Long-Short Term Memory (LSTM), for forecasting transmitted heat energy in District Heating Systems (DHS). The objective is to explore scenarios in which conventional ML algorithms demonstrate better performance over deep learning networks in time series forecasting and the associated benefits in terms of computational cost and environmental impact. The study focuses on a real-world DHS dataset. Through experimentation and analysis, it is demonstrated that XGBoost consistently outperforms LSTM in this specific forecasting task. The difference is explained by the error distribution illustrating that LSTM makes more significant errors in the intervals of less data availability. The reduced computational demands of conventional ML approaches not only result in cost savings but also minimize the carbon footprint associated with data analysis tasks in energy systems.
Comments9 pages, 7 figures. This preprint corresponds to the paper published in Lecture Notes in Networks and Systems, vol. 860 (ICIST 2024), Springer
Journal refLecture Notes in Networks and Systems, Vol. 860 (ICIST 2024), Springer, 2024
DOI：10.1007/978-3-031-71419-1_2
