Software Engineering for AI-driven Building Operation
2026-08-17 • Software Engineering
Software EngineeringArtificial Intelligence
AI summaryⓘ
The authors explain that using AI to control building operations can save energy but brings special software challenges because mistakes can cause real damage like wasted energy or discomfort, unlike typical software where errors mostly annoy users. They show that standard software engineering approaches for AI don't fully address these physical risks in buildings. Based on their research combining civil engineering and computer science, they highlight missing considerations and share lessons for safely deploying AI in building systems. Their work aims to create a foundation for engineering AI systems in places where failures have real-world consequences.
Artificial Intelligence (AI)Building OperationsSoftware Engineering (SE)Predictive ControlCyber-Physical SystemsEnergy EfficiencyFault ToleranceOccupant ComfortAI-driven OptimizationSafety-critical Failures
Authors
Philipp Zech, Sascha Hammes, Johannes Weninger, Jürgen Pannosch, Gernot Steidl
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.