Skip to main content

Advances, Systems and Applications

Table 3 Parameter values

From: A collaborative computation and dependency-aware task offloading method for vehicular edge computing: a reinforcement learning approach

Parameter

Value

the transmission power p

\(2 \pm 0.2\) Watt [40]

the channel gain \(\delta\)

\(144 \pm 14.4\) dB [41]

noise power \({\sigma ^{ - 2}}\)

\(1.5 \times {10^{ - 8}}\) Watt [41]

the computation capacity of a vehicle

\(0.3 \pm 0.03\) Gigacycles/s [9]

the size of the experience pool D

2000

min-batch size of \(D_t\)

32

the learning rate

0.01

the communication capability of a MEC server

40 MHz

The computation capability of a MEC server

5 Gigacycle/s

\(t_{off}^{cloud}\)

1000ms