On a real 5G testbed, offloading a CNN with early exits and splits to a MEC server reduces inference delay by up to 2.5x and energy by up to 2.6x versus local processing, but the analytical models are fitted without independent validation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Real-World Modeling of Computation Offloading for Neural Networks with Early Exits and Splits
On a real 5G testbed, offloading a CNN with early exits and splits to a MEC server reduces inference delay by up to 2.5x and energy by up to 2.6x versus local processing, but the analytical models are fitted without independent validation.