Spectral-Efficiency and Energy-Efficiency of Variable-Length XP-HARQ

A variable-length cross-packet hybrid automatic repeat request (VL-XP-HARQ) is proposed to boost the spectral efficiency (SE) and the energy efficiency (EE) of communications. The SE is firstly derived in terms of the outage probabilities, with which the SE is proved to be upper bounded by the ergodic capacity (EC). Moreover, to facilitate the maximization of the SE, the asymptotic outage probability is obtained at high signal-to-noise ratio (SNR), with which the SE is maximized by properly choosing the number of new information bits while guaranteeing outage requirement. By applying Dinkelbach's transform, the fractional objective function is transformed into a subtraction form, which can be decomposed into multiple sub-problems through alternating optimization. By noticing that the asymptotic outage probability is a convex function, each sub-problem can be easily relaxed to a convex problem by adopting successive convex approximation (SCA). Besides, the EE of VL-XP-HARQ is also investigated. An upper bound of the EE is found and proved to be attainable. Furthermore, by aiming at maximizing the EE via power allocation while confining outage within a certain constraint, the methods to the maximization of SE are invoked to solve the similar fractional problem. Finally, numerical results are presented for verification.

Graph Convolutional Network Enabled Power-Constrained HARQ Strategy for URLLC

In this paper, a power-constrained hybrid automatic repeat request (HARQ) transmission strategy is developed to support ultra-reliable low-latency communications (URLLC). In particular, we aim to minimize the delivery latency of HARQ schemes over time-correlated fading channels, meanwhile ensuring the high reliability and limited power consumption. To ease the optimization, the simple asymptotic outage expressions of HARQ schemes are adopted. Furthermore, by noticing the non-convexity of the latency minimization problem and the intricate connection between different HARQ rounds, the graph convolutional network (GCN) is invoked for the optimal power solution owing to its powerful ability of handling the graph data. The primal-dual learning method is then leveraged to train the GCN weights. Consequently, the numerical results are presented for verification together with the comparisons among three HARQ schemes in terms of the latency and the reliability, where the three HARQ schemes include Type-I HARQ, HARQ with chase combining (HARQ-CC), and HARQ with incremental redundancy (HARQ-IR). To recapitulate, it is revealed that HARQ-IR offers the lowest latency while guaranteeing the demanded reliability target under a stringent power constraint, albeit at the price of high coding complexity.

Zero-Forcing Based Downlink Virtual MIMO-NOMA Communications in IoT Networks

To support massive connectivity and boost spectral efficiency for internet of things (IoT), a downlink scheme combining virtual multiple-input multiple-output (MIMO) and nonorthogonal multiple access (NOMA) is proposed. All the single-antenna IoT devices in each cluster cooperate with each other to establish a virtual MIMO entity, and multiple independent data streams are requested by each cluster. NOMA is employed to superimpose all the requested data streams, and each cluster leverages zero-forcing detection to de-multiplex the input data streams. Only statistical channel state information (CSI) is available at base station to avoid the waste of the energy and bandwidth on frequent CSI estimations. The outage probability and goodput of the virtual MIMO-NOMA system are thoroughly investigated by considering Kronecker model, which embraces both the transmit and receive correlations. Furthermore, the asymptotic results facilitate not only the exploration of physical insights but also the goodput maximization. In particular, the asymptotic outage expressions provide quantitative impacts of various system parameters and enable the investigation of diversity-multiplexing tradeoff (DMT). Moreover, power allocation coefficients and/or transmission rates can be properly chosen to achieve the maximal goodput. By favor of Karush-Kuhn-Tucker conditions, the goodput maximization problems can be solved in closed-form, with which the joint power and rate selection is realized by using alternately iterating optimization.Besides, the optimization algorithms tend to allocate more power to clusters under unfavorable channel conditions and support clusters with higher transmission rate under benign channel conditions.

Federated Stochastic Gradient Descent Begets Self-Induced Momentum

Federated learning (FL) is an emerging machine learning method that can be applied in mobile edge systems, in which a server and a host of clients collaboratively train a statistical model utilizing the data and computation resources of the clients without directly exposing their privacy-sensitive data. We show that running stochastic gradient descent (SGD) in such a setting can be viewed as adding a momentum-like term to the global aggregation process. Based on this finding, we further analyze the convergence rate of a federated learning system by accounting for the effects of parameter staleness and communication resources. These results advance the understanding of the Federated SGD algorithm, and also forges a link between staleness analysis and federated computing systems, which can be useful for systems designers.

A New Look at AI-Driven NOMA-F-RANs: Features Extraction, Cooperative Caching, and Cache-Aided Computing

Non-orthogonal multiple access (NOMA) enabled fog radio access networks (NOMA-F-RANs) have been taken as a promising enabler to release network congestion, reduce delivery latency, and improve fog user equipments' (F-UEs') quality of services (QoS). Nevertheless, the effectiveness of NOMA-F-RANs highly relies on the charted feature information (preference distribution, positions, mobilities, etc.) of F-UEs as well as the effective caching, computing, and resource allocation strategies. In this article, we explore how artificial intelligence (AI) techniques are utilized to solve foregoing tremendous challenges. Specifically, we first elaborate on the NOMA-F-RANs architecture, shedding light on the key modules, namely, cooperative caching and cache-aided mobile edge computing (MEC). Then, the potentially applicable AI-driven techniques in solving the principal issues of NOMA-F-RANs are reviewed. Through case studies, we show the efficacy of AI-enabled methods in terms of F-UEs' latent feature extraction and cooperative caching. Finally, future trends of AI-driven NOMA-F-RANs, including open research issues and challenges, are identified.