A Resource Allocation Method of Deep Reinforcement Transfer Learning in WSN

In WSN environment, aiming at the problem of multi-objective and multi constraint resource allocation, a resource allocation mathematical model is established to seek the optimal solution. The deep reinforcement transfer learning (DRTL) method is adopted by introducing reliability and the idea of transfer learning. In the process of DRTL forward transmission and backward propagation, the maximum group is selected as the optimal allocation strategy. Finally, in the same environment, we compared with ant colony and discrete particle swarm algorithm, found that it has a significant impact on energy consumption, transmission time and reliability.