A Deep Reinforcement Learning Scheme for Sum Rate and Fairness Maximization Among D2D Pairs Underlaying Cellular Network With NOMA

Device-to-device (D2D) communication is an emerging technology in 5G and the upcoming 6G networks due to its properties to enhanced sum rate. Despite these advantages, co-channel and cross-channel interference and ultra-massive connectivity are major issues. To address these issues, we integrate the power domain non-orthogonal multiple access techniques (PD-NOMA) on the base station (BS). NOMA serves more than one user and reduces the effect of interference at cellular users (CUs) using the successive interference cancellation (SIC). The problem is formulated as a mixed-integer non-linear programming (MINLP) with associated resources and power constraints of the base station (BS) and D2D pairs (DDPs) with an aim to maximize the sum rate and fairness among the NOMA-enabled CUs and DDPs. We first used the centralized deep deterministic policy gradient (DDPG) and arithmetic-geometric mean approximation (AGMA) technique to reduce cross-channel interference and control the power. Then, to provide fairness to all the users, we transformed the proposed solution into a distributed deep deterministic policy gradient (D3PG). Also, the successive approximation technique is then integrated into the D3PG to mitigate the effect of co-channel interference among DDPs. The experimental results reveal that the proposed scheme has 21.05%, 34.21%, and 49.8% higher sum rate and fairness in comparison to DDPG, Deep dueling, and DQN scheduling.