AI RESEARCH

Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference

arXiv CS.AI

ArXi:2605.00005v1 Announce Type: cross The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on execution platforms, posing challenges to real-time control deadlines. Traditional distributed CPS architectures typically favor on-device inference to avoid network variability and contention-induced delays on remote platforms. However, this design choice places significant energy and computational demands on the local hardware.