Choosing an energy-efficient software architecture for building system diagnostic support

2026-10-05

AI Summary

This study addresses the limitation of existing building fault detection and diagnosis (FDD) evaluations, which focus solely on computational energy consumption while neglecting the environmental impact of diagnostic performance. We propose a holistic assessment framework that integrates FDD accuracy with software energy consumption, thereby incorporating diagnostic performance into the energy evaluation paradigm for the first time. Employing energy modeling, simulation analysis, random forests, and large language model (LLM) fine-tuning, we compare the net energy savings across rule-based, physics-based, and machine learning architectures. Our findings reveal a nonlinear trade-off between building scale and algorithmic energy efficiency: lightweight machine learning methods are optimal for small buildings, whereas LLM-based approaches yield greater benefits for large-scale facilities. These insights provide a scientific foundation for minimizing the overall ecological footprint of FDD systems.

Abstract

Around 30\% of global energy expenditure can be attributed to the building sector, where a large portion of energy-consumption could be avoided by repairing existing faults. Fault detection and diagnosis (FDD) software addresses this issue; however, its creation and operation also have an environmental impact. The magnitude of this impact is influenced by the diagnosis architecture, as different architectures and methods have different energy demands. Yet, simply considering the energy consumed by the software itself is not sufficient to assess its overall environmental impact, since the diagnostic performance, e.g., number of detected faults or number of faults missed, also contributes to its ecological footprint. In this paper, we propose an energy-consumption model that considers FDD performance and energy spend directly by the diagnosis software. In an initial experiment, we compare several FDD architecture families, i.e., rule-based, model-based, classical machine learning, and large-language-model-based, in simulation using performance and energy-consumption values collected from prior literature. The results show that considering the computational energy and accuracy of FDD can change the relative benefit of the different approaches. Computationally efficient machine learning methods, such as random forest, provide the largest net savings on smaller buildings, whereas more resource-intensive approaches, such as fine-tuned large language models, become advantageous as building size increases. Our findings suggest that overall energy efficiency depends not only on the computational demand of the FDD software, but also on its diagnostic performance and the scale of the building.

Problem

• Fault detection and diagnosis
• Energy efficiency
• Software architecture
• Environmental impact
• Building systems

Innovation

• Fault Detection and Diagnosis
• Energy-Consumption Model
• Software Architecture
• Machine Learning
• Large Language Models