AI-Enabled Energy-Efficient Fog Computing for Internet of Vehicles

Algorithm 1

VIA.

Input: state-space , action space , reward , transition probability , rate of convergence

Output: the optimal policy

Initialization: set value function for all and

1. For every state

2.  

3.   Ifthen

4.   For each system state do

5.   

6. Else

7.    back to line 1

9. Return the optimal policy