D2D communication resource allocation algorithm based on multi-agent reinforcement learning
Taoshen Li, Zhijun Qi · 2023
To solve the interference problem of device-to-device (D2D) communication in cellular network, a distributed resource allocation algorithm based on simultaneous wireless information and power transfer technology and dual deep Q-network is proposed to achieve distributed resource allocation and maximize energy efficiency of D2D links. Firstly, the resource allocation problem of D2D communication is formulated as a Markov decision process. Secondly, the allocation problem is decomposed into two sub problems: power control and channel allocation. Then, the reinforcement learning technique is introduced to model the optimization problem as a multi-agent learning optimal strategy problem. Finally, by continuously iterative updating and learning better action strategies, the optimization goals and reasonable allocation of resources are achieved. Experimental results show that the proposed algorithm can effectively improve the energy efficiency of D2D link layer and the throughput of D2D link, and has certain feasibility and effectiveness.