Digital twinHybrid Edge-Cloud Digital Twin for Poultry ControlarXiv — Systems and Control (eess.SY) · yesterdayModellingShared Control Between DRL and MPC for Multi-Class Transport NetworksarXiv — Systems and Control (eess.SY) · yesterdayDigital twinMulti-Viewpoint Modeling Framework for DT Integration with LLM AnalysisarXiv API — полнотекстовый поиск "digital twin" · 19hDigital twinStructured Persona Extraction for LLM-Based Digital TwinsarXiv — Computers and Society (cs.CY) · yesterdayForecastingLLM-Agent Stress Test: Feed Effects on Lexical DiversityarXiv — Multiagent Systems (cs.MA) · yesterdayModellingHow to manage behavior of multi-agent systemsХабр · yesterdayDigital twinDigital Twin for Ground-to-QEYSSat Quantum LinkarXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinAligning Upper Ontologies for Defence: IES, HQDM, and BFOarXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinReliability-Aware Scheduling for Digital Twin MaintenancearXiv API — полнотекстовый поиск "digital twin" · 2dDigital twinAI disrupts glass fiber manufacturing: predictive maintenance, digital twins, and infrastructureGlobeNewswire · 3dDigital twinKMG implements digital twins at 12 fieldsdprom.kz — промышленность · 4dDigital twinDigital Twin of SWER Networks for Narrowband CommunicationarXiv API — полнотекстовый поиск "digital twin" · 4d
A ground-truth-aware simulation framework is presented to assess the impact of sensor errors on smart-building control. The synthetic twin includes 20 zones simulated at 15-minute intervals over 30 days, modeling CO2 dynamics, ventilation energy trade-offs, sensor drift, measurement noise, and missing data. Policies based on sensor data are compared with an oracle controller.
Why it matters
Important for understanding reliability of digital twins with imperfect data, which is critical for building and other system management.
A hybrid edge-cloud digital twin architecture is introduced for climate control in poultry facilities. It integrates distributed sensing, on-device state estimation, a grey-box physics-data model, and model predictive control to handle biological variability and welfare constraints.
The paper discusses sharing control authority between deep reinforcement learning (DRL) and model predictive control (MPC) for multi-class transportation networks. It aims to overcome limitations of each method: DRL's learning capacity in high-dimensional state spaces and MPC's computational cost.
A multi-viewpoint modeling framework is proposed for integrating and reusing digital twins. It treats integration as a cross-model consistency problem and uses LLM for compatibility analysis.
