An Agentic AI Pipeline for Appliance-Level Energy Anomaly Detection and LLM-Driven Recommendations
arXiv:2606.28467v1 Announce Type: new Abstract: Appliance-level energy monitoring in office buildings produces noisy alerts that non-expert facility managers struggle to use. This paper proposes an end-to-end agentic pipeline that combines deep time-series forecasting, variational anomaly detection, and LLM-based reasoning to generate prioritized, actionable maintenance recommendations. The system tracks seven office appliances using a hybrid Singular Spectrum Analysis (SSA) and Long Short-Term Memory (LSTM) forecasting model, and applies a per-appliance LSTM Variational Autoencoder (VAE) with
Advances in AI, particularly LLMs and time-series forecasting, are enabling the development of more sophisticated and autonomous agentic systems for practical applications.
This development demonstrates a tangible application of AI agents for efficiency gains, specifically in facility management and energy optimization, impacting operational costs and sustainability efforts.
The ability to automatically detect energy anomalies and generate actionable, LLM-driven recommendations changes how non-expert managers can identify and address inefficiencies across a range of appliances.
- · Facility Management Companies
- · Smart Building Technology Providers
- · Energy Efficiency Consulting Firms
- · AI Agent Developers
- · Traditional Manual Energy Auditing Services
- · Reactive Maintenance Programs
Increased adoption of AI-powered energy management systems in commercial buildings.
Reduced operational costs and carbon footprints for businesses through improved energy efficiency.
Expansion of agentic AI systems into broader IoT and infrastructure management domains, creating more autonomous operational environments.
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.LG