The paper introduces CoCaR for joint submodel caching and request routing with dynamic DNNs in MEC, reporting 46% higher average inference precision in simulations and at least 32.3% QoE gain for its online variant.
Dynamic resource allocation for deep learning clusters with separated compute and storage,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Joint Optimization of DNN Model Caching and Request Routing in Mobile Edge Computing
The paper introduces CoCaR for joint submodel caching and request routing with dynamic DNNs in MEC, reporting 46% higher average inference precision in simulations and at least 32.3% QoE gain for its online variant.