Efficient Resource Allocation for DRL-NOMA Enabled TSIN in Industry 5.0

To meet sustainable and efficient communication demands of Industry 5.0, this paper proposes an Artificial Intelligence(AI)-driven downlink model for Terrestrial Satellite Integrated Network (TSIN), which integrates both ground and satellite network to serve terrestrial users. Non-Orthogonal Multiple Access (NOMA) improves effectiveness of TSIN, alleviating spectrum resource shortages caused by the explosive growth of User Equipment (UEs). Deep Reinforcement Learning (DRL) is utilized in TSIN to overcome suboptimal convergence. A optimization objective is established with system capacity maximization. The formula is broken down three sub-problems, and a user association scheme is proposed. The process of user association to base stations (BSs) relies on range between BSs and users and channel vectors connecting two. The channel condition ratio is used to determine BS and satellite user sets. NOMA is applied to entire user set. Deep Q-Network (DQN) is used for user grouping, while Deep Deterministic Policy Gradient (DDPG) network is employed for power allocation. The grouping results from DQN network are used as input to DDPG network for cascading training, achieving resource allocation policy optimization. MATLAB simulations show that compared with three typical algorithms, the proposed algorithm improves system capacity and spectral efficiency. This approach provides an efficient communication solution for massive device connectivity of Industry 5.0, effectively promoting sustainable and intelligent development.