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
本文引入事前可解释AI方法，结合梯度提升法与Partial Dependence、Accumulated Local Effects、SHAP三种事后方法，评估区域供热系统热需求预测ML模型的全局特征重要性，以提升模型可解释性与可信度，解决相关标准、满意度及责任风险问题。
AI 中文摘要
本文引入事前可解释人工智能（XAI）方法，评估用于区域供热系统智能控制中热需求预测的机器学习模型的全局特征重要性，旨在提升模型的可解释性与可信度，从而解决与遵守公共标准、客户满意度及责任风险相关的挑战。所采用的方法包括梯度提升法的内在可解释性，以及选定的事后方法：部分依赖图（Partial Dependence）、累积局部效应（Accumulated Local Effects）和SHAP。所选方法均不假设特征置换或扰动，此类操作可能因引入数据实例的随机不现实值而产生偏差。文中对结果进行了讨论，包括在适用情况下对互补性的评估，并结合区域供热过程的背景给出了具体解释。
英文摘要
The paper introduces the ante-hoc Explainable AI methodology to assess the global feature importance of the Machine Learning models used for heat demand forecasting in intelligent control of District Heating Systems, with motivation to facilitate their interpretability and trustworthiness, hence addressing the challenges related to adherence to communal standards, customer satisfaction and liability risks. Methodology includes use of four different approaches, namely intrinsic interpretability of Gradient Boosting method and selected post-hoc methods, namely Partial Dependence, Accumulated Local Effects and SHAP. None of the selected methods assume feature permutation or perturbations which can introduce bias due to introduction of random unrealistic values of data instances. Discussion of results is provided, including the assessment of complementarities where applicable, with specific interpretations in context of the district heating processes.
Comments9 pages, 5 figures. This preprint corresponds to the paper published in Thermal Science 2025 Volume 29, Issue 5 Part A, Pages: 3355-3365
Journal refThermal Science 2025 Volume 29, Issue 5 Part A, Pages: 3355-3365
