TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting
For building IoT forecasting, TopoBrick provides a practical zero-shot solution that leverages topological structure to improve accuracy without requiring training data.
TopoBrick is a training-free framework for zero-shot building IoT forecasting that uses building knowledge graphs and an agentic topology sampler to select target-specific exogenous variables. It outperforms zero-shot foundation-model baselines and remains competitive with fully trained building-specific models across three real-world buildings.
Building sensors are embedded in physical topology, spatial hierarchy, and operational context, yet existing forecasters often treat them as isolated time series or rely on fixed covariate sets. We present TopoBrick, a training-free framework for zero-shot building IoT (Internet-of-Things) forecasting. TopoBrick uses building knowledge graphs to construct a compact structural skeleton and employs an agentic topology sampler to select target-specific exogenous variables. The selected variables are organized by deployment-time availability, separating past-known sensor states from future-known calendar, schedule, and meteorological exogenous variables. Across three real-world buildings, TopoBrick outperforms strong zero-shot foundation-model baselines and remains competitive with fully trained building-specific models. Ablations show that topology-aware sampling is more reliable than random, ontology-only, or fixed-hop selection, especially for physically coupled HVAC and weather-driven sensing variables.