Study: Machine learning-enhanced MPC optimizes energy use in commercial buildings
pastramimachine · x · 2026-08-25
This experimental study, published in June 2026, explores using machine learning to enhance Model Predictive Control (MPC) for demand flexibility in small commercial buildings.
- Context: SMCBs often lack centralized automation, making advanced control for load shifting and cost savings challenging.
- Methodology: A Hybrid MPC framework is proposed, integrating a physics-based gray-box thermal model (identified via a lumped disturbance approach) with an ML model to forecast unmeasured disturbances like internal heat gains.
- Application: Optimizes the coordinated scheduling of multiple heat pumps under dynamic electricity prices while respecting comfort constraints.
- Results: Simulations and experiments show substantial load shifting and peak demand reduction, approaching the performance of an ideal MPC with perfect disturbance knowledge.
More from Research
- Opinion: Discrepancy theory could optimize resource allocation for AI agents — JosephJacks_ · 2026-08-25
- Geometric modeling of Occam's razor explains deep learning generalization — FrnkNlsn · 2026-08-25
- MVAP-G paper demonstrates fooling Visual Geometry Grounded Transformers — kwangmoo_yi · 2026-08-25
- PhysCaP enables robots to physically probe hidden properties like mass and stiffness — chris_j_paxton · 2026-08-25
- Prime Agent: An Open-Source Harness for Self-Improving RLM — PrimeIntellect · 2026-08-25
- TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference — Hanzhi Zhang · 2026-08-25