Skip to main content

Advances, Systems and Applications

Table 3 Simulation parameters

From: Minimize average tasks processing time in satellite mobile edge computing systems via a deep reinforcement learning method

Parameters

Default Values

Ka-band carrier frequency

30GHz

Number of IMDs

[10,20,30,40,50,60,70]

Number of Sat-MEC server

5

\(d_i\)

[0.2-1]MB

\(c_i\)

[1-4] Gcycles

\(f^m\)

0.3 Gcycles/s

\(f^s\)

[10-15] Gcycles/s

\(N_0\)

-174dBm

\(B_0\)

500MHz

\(B_{TST}\)

800MHz

\(B_{Sat}\)

100MHz

\(R_e\)

6371Km

\(\lambda _m\)

5

\(\lambda _{Sat}\)

8

\(\theta\)

[0-1]

Replay memory capacities M,N

6000

Mini-batch sizes \(\overline{M}\)

200

Genetic Algorithm’s Population Size

200

Genetic Algorithm’s Number of Generations

2000

Genetic Algorithm’s Crossover Probability

0.5

Genetic Algorithm’s Mutation Probability

0.1