Fast MLE-Based Device Activity Detection for Massive Grant-Free Access via PSCA and PSCANet

Fast and accurate device activity detection is the critical challenge in grant-free access for supporting massive machine-type communications (mMTC). The state-of-the-art methods have an unsatisfactory error rate or computation time. To address these outstanding issues, we propose new maximum likelihood estimation (MLE)-based device activity detection methods that achieve superior tradeoffs between the error rate and computation time using optimization and deep learning techniques. Specifically, we propose an innovative parallel successive convex approximation (PSCA) algorithm for solving the noncon-vex MLE problem. We show that it allows parallel computations, uses up to the objective function’s second-order information, converges to the problem’s stationary points, and has a low per-iteration computational complexity compared to the state-of-the-art algorithms for the MLE problem. Then, we propose a PSCA-driven deep unrolling neural network implementation, called PSCANet, to reduce the overall computation time of PSCA. PSCANet elegantly marries PSCA’s parallel computation mechanism with the parallelizable neural network architecture and effectively optimizes its step sizes based on vast data samples. Numerical results demonstrate that PSCA and PSCANet can significantly reduce the error rate and computation time compared to the state-of-the-art methods, revealing their significant values for mMTC in 5G and beyond.