AI EMPOWERED RIS-ASSISTED NOMA NETWORKS: DEEP LEARNING OR REINFORCEMENT LEARNING

Abstract : A novel reconfigurable intelligent surfaces (RISs)- based transmission framework is proposed for downlink nonorthogonal multiple access (NOMA) networks. We propose a quality-of-service (QoS)-based clustering scheme to improve the resource efficiency and formulate a sum rate maximization problem by jointly optimizing the phase shift of the RIS and the power allocation at the base station (BS). A model-agnostic meta-learning (MAML)-based learning algorithm is proposed to solve the joint optimization problem with a fast convergence rate and low model complexity. Extensive simulation results demonstrate that the proposed QoS-based NOMA network achieves significantly higher transmission throughput compared to the conventional orthogonal multiple access (OMA) networkIt can also be observed that substantial throughput gain can be achieved by integrating RISs in NOMA and OMA networks. Moreover, simulation results of the proposed QoS-based clustering method demonstrate observable throughput gain against the conventional channel condition-based schemes
 EXISTING SYSTEM :
 ? A novel reconfigurable intelligent surfaces (RISs)- based transmission framework is proposed for downlink nonorthogonal multiple access (NOMA) networks. ? Simulation results indicate that the implementation of RIS can induce approximately 5% to 25% throughput gain as the number of RIS elements increases from 8 to 64, in both NOMA and OMA networks. Results also show that the proposed QoS-based clustering method achieves higher throughput than the conventional channel condition-based approach ? Hence, we proposed to tackle the joint optimization problem utilizing machine learning techniques
 DISADVANTAGE :
 ? A model-agnostic meta-learning (MAML)-based learning algorithm is proposed to solve the joint optimization problem with a fast convergence rate and low model complexity. ? To maximize sum rate while ensuring user fairness, the authors of formulated a max-min problem for RIS-enhanced NOMA networks by jointly optimizing the power allocation and the RIS phase shift ? The sum rate maximization problem of RIS-aided NOMA systems was investigated in , where the passive beamforming at the RIS was jointly optimized with the active beamforming at the base station (BS) under both the ideal and non-ideal RIS elements
 PROPOSED SYSTEM :
 ? To the best of our knowledge, there does not exist a DL-based solution for RIS-aided NOMA networks, which motivates this study. In this paper, we investigate the sum rate optimization problem in RIS-aided downlink MISO-NOMA networks, where both the RIS phase shift and the BS power allocation are optimized to maximize the total transmission sum rate. We adopt the zero-forcing (ZF) precoding method and the successive interference cancellation (SIC) decoding method to eliminate the effect of multi-user interference on the strong users.
 ADVANTAGE :
 ? where the passive beamforming at the RIS was jointly optimized with the active beamforming at the base station (BS) under both the ideal and non-ideal RIS elements. To maximize sum rate while ensuring user fairness, the authors of formulated a max-min problem for RIS-enhanced NOMA networks by jointly optimizing the power allocation and the RIS phase shift ? We adopt the zero-forcing (ZF) precoding method and the successive interference cancellation (SIC) decoding method to eliminate the effect of multi-user interference on the strong users. However, this approach causes the weak users to suffer from both inter-cluster and intra-cluster interference, leading to poor achievable rates.

We have more than 145000 Documents , PPT and Research Papers

Have a question ?

Mail us : info@nibode.com