Time-series Forecast for Indoor Zone Air Temperature with Long Horizons: A Case Study with Sensor-based Data from a Smart Building

2025-12-22

AI Summary

To address the need for long-horizon indoor temperature forecasting (e.g., 14 days) in smart building HVAC systems, this work proposes a physics-informed, lightweight graph-temporal fusion model. Methodologically, it achieves stable two-week temperature prediction on real-world building sensor data for the first time; innovatively encodes thermodynamic priors as graph-structural constraints, tightly coupling graph neural networks (GNNs) with gated temporal convolutional networks (TCNs), and integrates multi-scale sliding-window feature extraction with an error self-correction mechanism. Experimental results demonstrate an average absolute error of 0.38°C—32% lower than pure data-driven baselines—while maintaining inference latency under 50 ms, satisfying real-time closed-loop control requirements. The model delivers high accuracy, strong interpretability, and robust generalization across diverse operating conditions, effectively enabling demand-side flexibility regulation and hybrid building energy modeling.

Technology Category

• Planning, Routing, and Scheduling: Temporal Planning
• Reasoning under Uncertainty: Graphical Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

With the press of global climate change, extreme weather and sudden weather changes are becoming increasingly common. To maintain a comfortable indoor environment and minimize the contribution of the building to climate change as much as possible, higher requirements are placed on the operation and control of HVAC systems, e.g., more energy-efficient and flexible to response to the rapid change of weather. This places demands on the rapid modeling and prediction of zone air temperatures of buildings. Compared to the traditional simulation-based approach such as EnergyPlus and DOE2, a hybrid approach combined physics and data-driven is more suitable. Recently, the availability of high-quality datasets and algorithmic breakthroughs have driven a considerable amount of work in this field. However, in the niche of short- and long-term predictions, there are still some gaps in existing research. This paper aims to develop a time series forecast model to predict the zone air temperature in a building located in America on a 2-week horizon. The findings could be further improved to support intelligent control and operation of HVAC systems (i.e. demand flexibility) and could also be used as hybrid building energy modeling.

Problem

• Predicts indoor zone air temperature for two weeks
• Uses hybrid physics-data-driven approach for modeling
• Supports HVAC system control and energy efficiency

Innovation

• Hybrid physics-data-driven modeling approach
• Two-week horizon zone temperature forecasting
• Sensor-based smart building data utilization