ModellingStochastic Adaptive MPC for Load Frequency Control in MicrogridsarXiv — Systems and Control (eess.SY) · yesterdayForecastingCritical Review of LLMs for HVAC Operations in BuildingsarXiv — Systems and Control (eess.SY) · yesterdayDigital twinCyber-physical systems lab opens at Voronezh State UniversityВоронежский госуниверситет · 21hDigital twinAI-Powered CPS Urban Transportation Digital TwinarXiv — Systems and Control (eess.SY) · yesterdayModellingSelectel and ITMO JV develops multi-agent system technologies for businessspbIT · yesterdayForecastingGrid-Aware MPC for Smoothing AI Data Center Power DemandarXiv — Systems and Control (eess.SY) · yesterdayEnergyComparison of Direct vs Indirect Net Load Forecasting with RenewablesarXiv — Systems and Control (eess.SY) · yesterdayDigital twinBayesian thermal digital twin for space habitat under impactarXiv API — полнотекстовый поиск "digital twin" · 4dDigital twinData-driven transient forecasting for generator digital twin decision supportarXiv API — полнотекстовый поиск "digital twin" · 3dMarket & productsKorea and Africa Discuss AI and Digital Infrastructure at KOAFECAfDB Africa Newsroom (пресс-релизная витрина) · 4dModellingSeed-Anchored Graph Rendering for QA on Power-Grid CIM/CGMES ModelsarXiv — Systems and Control (eess.SY) · 5dDigital twinDNative-Twin: Graph-Native Digital Twins for Reconstructable Agentic DecisionsarXiv API — полнотекстовый поиск "digital twin" · 4d
Scalable Gaussian Process with Trigonometric Features for Safe MPC
US & West ·
Researchers developed DTF-GP, a finite-dimensional kernel approximation based on deterministic trigonometric features. This approach enables uniform uncertainty bounds needed for safety guarantees in learning-based MPC while scaling to large datasets.
Why it matters
Important for scalable learning-based control with safety guarantees in large-scale systems.
Original headline
Scalable Gaussian Process Regression via Deterministic Trigonometric Features: Uniform Bounds for Safe Model Predictive Control
A systematic review of 66 studies (2023-2026) on LLMs for HVAC operations classifies methods and applications, revealing concentration on building energy modeling but few pilot-level deployments and no sustained operational use.
A model predictive control framework for a hybrid energy storage system (battery plus supercapacitor) is proposed, embedding band-pass filter dynamics to smooth grid-side power demand of AI data centers. The receding-horizon optimization mitigates load-induced grid oscillations.
