TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting
arXiv:2607.06349v1 Announce Type: new Abstract: 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, separat
The proliferation of IoT sensors in buildings generates vast amounts of data, creating a pressing need for efficient and accurate forecasting solutions that leverage AI without continuous human intervention.
This development allows for more efficient management of building resources (e.g., energy, HVAC), crucial for sustainability and operational costs, by automating the selection of relevant data for predictive models.
Traditional forecasting methods that treat IoT data as isolated time series or rely on fixed covariates are being replaced by agentic, knowledge graph-driven systems, enhancing accuracy and reducing manual configuration.
- · Smart building developers
- · Facilities management companies
- · Energy efficiency solution providers
- · AI agent developers
- · Legacy building management systems
- · Manual data scientists
- · Static forecasting model providers
Improved operational efficiency and reduced energy consumption in commercial and residential buildings.
Accelerated adoption of AI-driven autonomous systems across other complex physical infrastructures beyond buildings.
New standards and regulations for AI integration in critical infrastructure, emphasizing explainability and robustness.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI