Research Article
Stabilizing Transmission Capacity in Millimeter Wave Links by Q-Learning-Based Scheme
Algorithm 4
The Q-table-based decision and update process.
| Run at the edge computing facility | | Input: rth, the trained Q table for UE i, and the current state | | Output: the target state | (1) | and | (2) | Compute the real energy efficiency value for UE i according to the personalized information reported by UE i and formula (5), and then save it in | (3) | If then | (4) | For each do | (5) | Get by Q table according to and | (6) | If then | (7) | | (8) | | (9) | End if | (10) | End for | (11) | Compute according to formula (5) | (12) | If and the action can transfer to the next state then | (13) | Compute according to formula (7) | (14) | Update the corresponding entry of Q table | (15) | and go to 4 | (16) | End if | (17) | End if |
|