Soft Actor Critic Framework for Resource Allocation in Backscatter-NOMA Networks

With the use of power domain non-orthogonal multiple access (NOMA) and backscatter communication (BAC), future sixth-generation ultra massive machine type communications networks are expected to connect large-scale Internet of things (IoT) devices. However, due to NOMA co-channel interference, the power allocation to large-scale IoT devices becomes critical. The existing convex optimization-based solutions are highly complex hence, it is difficult to find the optimal solution to the resource allocation problem in a highly dynamic environment. Therefore, this work develops an efficient model-free BACNOMA system to assist the base station for complex resource scheduling tasks in a dynamic BAC-NOMA IoT network. More specifically, we jointly optimize the transmit power of downlink IoT users and the reflection coefficient of uplink backscatter devices using a reinforcement learning algorithm, namely, softactor critic. Numerical results show that the proposed algorithm obtained a higher reward and converges to an optimal solution with respect to a large number of iterations. The proposed algorithm increases the sum rate by 57.6% as compared to the conventional optimization (benchmark) approach. Moreover, we show that the proposed algorithm outperforms the conventional BAC-NOMA scheme and BAC with orthogonal multiple access in terms of average sum rate with the increasing number of backscatter devices.