An adaptive DNN partitioning framework for heterogeneous edge-cloud systems reduces energy consumption by 27-36% and end-to-end latency by 6-23% versus static baselines on real hardware with VGG16, AlexNet, and MobileNetV2.
Exploring the potential of distributed computing continuum systems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.DC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Benchmarks of Chord, Pastry, and Kademlia on 4096-node stationary and churn scenarios show varying discovery reliability, startup behavior, and control-plane overhead for agent discovery in edge-to-cloud agentic AI.
citing papers explorer
-
Adaptive DNN Partitioning and Offloading in Heterogeneous Edge-Cloud Continuum
An adaptive DNN partitioning framework for heterogeneous edge-cloud systems reduces energy consumption by 27-36% and end-to-end latency by 6-23% versus static baselines on real hardware with VGG16, AlexNet, and MobileNetV2.
-
Trade-offs in Decentralized Agentic AI Discovery Across the Compute Continuum
Benchmarks of Chord, Pastry, and Kademlia on 4096-node stationary and churn scenarios show varying discovery reliability, startup behavior, and control-plane overhead for agent discovery in edge-to-cloud agentic AI.