Software Engineering for AI-driven Building Operation

Philipp Zech; Sascha Hammes; Johannes Weninger; Jürgen Pannosch; Gernot Steidl

cs.SEAug 17, 2026

Software Engineering for AI-driven Building Operation

Authors: Philipp Zech, Sascha Hammes, Johannes Weninger, Jürgen Pannosch, Gernot Steidl

Organizations: University of Innsbruck, Tyrol, Austria · Bartenbach - The Lighting Innovators, Wattens, Austria · University of Applied Sciences Burgenland, Austria

Abstract

Building operations are energy-inefficient. Artificial Intelligence (AI)-driven control systems promise benefits through optimization and predictive control, but deploying them in real buildings reveals a significant software engineering (SE) challenge. SE for AI practices assume digital environments where failures mean poor user experience. Buildings are different. A bad control decision wastes energy irreversibly, violates occupant comfort, or accelerates equipment wear. Although actual safety-critical failures are rare, as real building automation systems are inherently fault-tolerant, the physical and lasting nature of even minor failures fundamentally changes SE4AI requirements. Rooted in two interdisciplinary research projects in civil engineering and computer science that target the AI-driven optimization of building operations, we identify the missing perspectives in SE4AI that currently stymie the successful deployment of AI-based systems for building operations. We further share lessons learned and best practices, and discuss broader implications for engineering AI-driven building operations and cyber-physical systems more generally. Our work proposes a foundation for SE4AI in systems where failure has physical consequences - one the research agenda below will need to validate.

Figures & tables

	General SE4AI Perspective	The Missing Perspective
P1	The cost of failure is digital	The cost of failure is physical
P2	The world is data	Physical dynamics dominate over data patterns
P3	Testing is data-driven	Testing is simulation-driven and risky
P4	Humans are end-users	Humans are in-the-loop stakeholders
P5	Data is abundant but often unlabeled	Data is physical, sparse, and noisy
P6	Time scales are fast	Time scales are slow and delayed

Table 1: The missing perspectives in SE4AI for building operations. The contrasts highlight differences in emphasis, not categorical absences. Domains like autonomous driving also engage with physical models; buildings are structurally distinct due to their combination of slow feedback loops, legacy infrastructure, and continuously occupied environments.

Software Engineering

Software engineering studies how to design, build, test, deploy, and maintain reliable software systems and the processes behind them.

See all 274 papers

The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale
Oct 13, 2026Judah Goldfeder, Ayush Rai, Philippe M. Wyder +11Building Energy Management Transfer Learning
Columbia University · Harvard University · Distyl AI +6
Which Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework for AI Question Answering and Actuation
Oct 6, 2026Wooyoung JungAgentic AI
University of Arizona, Tucson, USA
An Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers
Sep 29, 2026Hadiza Umar Yusuf, Khouloud GaaloulCyber-Physical Systems Safety-Critical Control
University of Michigan-Dearborn Dearborn, USA.

Oct 13, 2026J/K move · Enter open · S save

The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale

Judah Goldfeder, Ayush Rai, Philippe M. Wyder, Na Li+10

Columbia University · Harvard University · Distyl AI+6

Building Energy Management Transfer Learning Benchmark Construction

Open paper AskPDF arXiv

Buildings cause nearly 40% of carbon emissions in the US. Of total building emissions, HVAC systems are responsible for approximately 40-60% and account for 15% of global energy consumption. Despite advances in artificial intelligence, most buildings still operate as inefficiently as they did decades ago. Building optimization, perhaps more so than any other optimization problem, has enormous potential for Machine Learning (ML) driven impact on climate change, in both the short and long term. One of the biggest obstacles for building optimization is the lack of policy transfer. Most building control systems, whether simulation or learning based, don't generalize: they only work well for the building they were developed for, but not for other buildings. To solve this problem, we propose a challenge for the development of building foundation models that easily adapt to new buildings with minimal configuration and thereby enable building optimization to scale across the globe. Participants will build control policies on a set of simulated buildings, and have their policies evaluated on an unseen set of buildings. The buildings vary in size, layout, weather, material properties, and HVAC system. Successful outcomes from this initiative promise a massive leap forward in global sustainability efforts and demonstrate the great potential of ML to combat climate change.

Abstract

Software Engineering

Explore similar work

The Smart Buildings Challenge: Learning Foundation Models for Real-World Optimization at Scale

Which Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework for AI Question Answering and Actuation

An Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers