Research Article
Intelligent Channel Allocation for Age of Information Optimization in Internet of Medical Things
Algorithm 1
Channel allocation algorithm for user j based on DQN
Input: Node list, gateway list | Initialization: | 1. Initialize cost and energy to 0. | 2. Initialize step to 1. | For episode =1 to maximum iteration time T do | Count =1; | Obtain state based on the input. | 1. Repeat: | (1) Select action | (2) Output the next state , reward , cost and energy according to the count and action | (3) Store transition (, , , ) in the replay memory | 2. If step >200 and step % 5 == 0: | Sample random minibatch of transitions (, , , ) from the replay memory pool. | Else: | Continue | 3. Update: | ; | += ; | +=; | Step + =1; | Count + =1; | For each node in node list | If packet size <= 0: | Break | 4. Update target value . | 5. Perform a gradient descent step on . | 6. Reset for every Z steps. | End for |
|