Explainable AI based System for Supply Air Temperature Forecast

2025-01-09

AI Summary

To address the lack of model transparency and interpretability in air supply air temperature (ASAT) prediction for air handling units (AHUs), this paper proposes an explainable AI (XAI) framework. Methodologically, it employs a Huber loss-based linear regression model to enhance prediction robustness against outliers; introduces Shapley values—novelly applied to ASAT control curve analysis—to establish a setpoint-driven comparative feature attribution method; and generates semantically meaningful, physically interpretable, and customer-verifiable attribution slices. Furthermore, it enables intuitive visualization of feature contributions. The framework maintains high predictive accuracy while significantly improving model auditability and traceability. As a result, facility operators can rapidly identify dominant influencing factors, thereby supporting trustworthy, interpretable, and dynamic optimization of HVAC systems.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper explores the application of Explainable AI (XAI) techniques to improve the transparency and understanding of predictive models in control of automated supply air temperature (ASAT) of Air Handling Unit (AHU). The study focuses on forecasting of ASAT using a linear regression with Huber loss. However, having only a control curve without semantic and/or physical explanation is often not enough. The present study employs one of the XAI methods: Shapley values, which allows to reveal the reasoning and highlight the contribution of each feature to the final ASAT forecast. In comparison to other XAI methods, Shapley values have solid mathematical background, resulting in interpretation transparency. The study demonstrates the contrastive explanations--slices, for each control value of ASAT, which makes it possible to give the client objective justifications for curve changes.

Problem

• Gas Temperature Prediction
• Explainable AI
• Complex Machine Learning

Innovation

• Shapley Values
• Explainable AI (XAI)
• Huber Loss