Efficient Deep Learning Approach for Computational Offloading in Mobile Edge Computing Networks

Table 1

Algorithm design.

---

Algorithm: train deep network using EDLO data

---

BEGIN

(1): Input: Input the state vector of the computing task,  = (d, k, m, E_nt)

(2): Output: Optimal offloading decision,

(3): Initialization:

(4): Initialize the DNNs with random parameters, weight &paranoid item

(5): Empty the memory structure

(6): while i ≤ datasize do

while j ≤ c do

W_t < - V_dc-1;c

Si < - {d_i; k_i; m_i; E_i}

if p_t = 0 then

else

end if

end while

Ci<— C(S, P)

P∗<—

end while

(7): Store into the memory structure;

(8): Train the DNNs and update weight &paranoid item of DNNs;

(9): The optimal unloading scheme is solved

End

---