Kezhi Wang

TL;DR: The proposed NN architecture invokes a module named long short-term memory that admits the NN to benefit from exploiting temporal and frequency correlations of wireless channels to enhance the accuracy of quantized CSI feedback in MIMO communications.

TL;DR: The AI-based joint Resource schEduling (ARE) framework with two differentAI-based mechanisms, i.e., Deep neural network (DNN)-based and deep reinforcement learning (DRL)-based architectures, are proposed and DNN-based solution with online incremental learning applies the global optimizer and therefore has better performance than the DRL-based architecture with online policy updating, but requires longer training time.

TL;DR: In this paper, a cross-entropy approach with iterative learning of the probability of elite solution samples is proposed to solve the integer programming problem in a multi-tier network with mobile edge computing.

TL;DR: This paper proposes a Resource onlIne sCHeduling (RICH) algorithm using Lyapunov optimization technique to approach a time average profit that is close to the optimum with a diminishing gap for MSP while still maintaining strong system stability and low congestion to guarantee the QoS for mobile users.

TL;DR: A new differential evolution (DE) algorithm, called DEMiDRA, is proposed, in which each individual represents the resource allocation of a participating miner and the resource allocations of all participating miners constitute the whole population.