Energy-Minimization-Driven Communication and Computation Resource Allocation in Hybrid NOMA-RSMA Industrial IoT

This is the authors' abstract. We don't add key points for this paper.

In the Industrial Internet of Things (IIoT), the latency-sensitive task can be efficiently performed based on real-time data collection, transmission, and computation. In this article, we thus propose a hybrid nonorthogonal multiple access-rate splitting multiple access (NOMA-RSMA) edge-cloud service computing framework for the IIoT consisting of end devices (EDs), edge servers (ESs), and cloud servers (CSs), in which the tasks are allowed to be computed at the EDs, the ESs, or a CS. When the task computation takes place at the ESs or the CS, tasks would be first compressed at EDs, and then be offloaded to the ESs via nonorthogonal multiple access (NOMA). After that, the ESs offload tasks to the CS via rate splitting multiple access (RSMA) if tasks are intended to be processed at the CS. Otherwise, the ESs perform computation locally. Specifically, under the delay constraints, we aim to minimize the total system energy consumption by jointly optimizing the transmit power of the EDs and the ESs, the transmission delays of each NOMA group and RSMA, the signal splitting ratio of the ESs, the computation power of the EDs, the ESs, and the CS, the compression delay, the offloading decisions of the EDs and the ESs. To address the formulated nonconvex problem, we employ a hierarchical decomposition approach to layer it into a top-level offloading decision problem and a bottom-level resource allocation problem. We design a block coordinate descent (BCD)-based method to solve the bottom-level problem. Additionally, we propose an algorithm based on deep reinforcement learning and online offloading (DROO) to obtain the suboptimal offloading decisions for EDs and ESs in the top-level problem. Numerical results validate the accuracy and effectiveness of our algorithms in terms of the total energy consumption, compared with three heuristic algorithms, i.e., the genetic algorithm, and the cross-entropy algorithm, the Deep Q-Network algorithm.