From: Adaptive resource optimization for edge inference with goal-oriented communications
\(\rho\) | \(N_{UE}^{max}\) (deep) | \(N_{UE}^{max}\) (short) | \(N_{UE}^{max}\) (DS) | \(N_{s}^{max}\) |
---|---|---|---|---|
2 | 3 | 3 | 3 | 2 |
4 | 5 | 6 | 7 | 6 |
8 | 5 | 7 | 10 | 11 |
16 | 5 | 9 | 15 | 16 |
32 | 6 | 14 | 28 | 18 |
64 | 5 | 14 | 29 | 18 |