Deep Reinforcement Learning-Based UAV Data Collection and Offloading in NOMA-Enabled Marine IoT Systems

Algorithm 2

Power control and buoy-UAV association relationship algorithm (PCAR).

1. Input the UAV’s current position , and .

2. Input current channel gain , and sort it in descending order to obtain .

3. According to , get initial NOMA group and the number of initial associated buoys .

4. repeat

5.  Solve P2a to obtain the optimal solution and the optimal value .

6.  if the solution state is not optimal then

7.   Remove the one with the worst channel gain in the currently associated buoy.

8.   .

9.  end if

10. until

11. return and ;