In this article, the problem of training federated learning (FL) algorithms over a realistic wireless network is studied. considered model, users execute an FL algorithm while their local models using own data and transmitting trained to base station (BS) that generates global model sends back users. Since all parameters are transmitted links, quality affected by factors such as packet errors availability resources. Meanwhile, due limited bandwidth, BS needs select appropriate subset so...

In order to effectively provide ultra reliable low latency communications and pervasive connectivity for Internet of Things (IoT) devices, next-generation wireless networks can leverage intelligent, data-driven functions enabled by the integration machine learning (ML) notions across core edge infrastructure. this context, paper provides a comprehensive tutorial that overviews how artificial neural (ANNs)-based ML algorithms be employed solving various networking problems. For purpose, we...

In this paper, the problem of proactive deployment cache-enabled unmanned aerial vehicles (UAVs) for optimizing quality-of-experience (QoE) wireless devices in a cloud radio access network is studied. considered model, can leverage human-centric information, such as users' visited locations, requested contents, gender, job, and device type to predict content request distribution, mobility pattern each user. Then, given these behavior predictions, proposed approach seeks find user-UAV...

In this paper, the problem of resource management is studied for a network wireless virtual reality (VR) users communicating over small cell networks (SCNs). order to capture VR users' quality-of-service (QoS) in SCNs, novel model, based on multi-attribute utility theory, proposed. This model jointly accounts metrics, such as tracking accuracy, processing delay, and transmission delay. base stations (SBSs) act control centers that collect information from cellular uplink. Once collected,...

In this paper, the problem of proactive caching is studied for cloud radio access networks (CRANs). model, baseband units (BBUs) can predict content request distribution and mobility pattern each user determine which to cache at remote heads BBUs. This formulated as an optimization problem, jointly incorporates backhaul fronthaul loads caching. To solve algorithm that combines machine learning framework echo state (ESNs) with sublinear algorithms proposed. Using ESNs, BBUs user's while...

In this paper, the problem of joint caching and resource allocation is investigated for a network cache-enabled unmanned aerial vehicles (UAVs) that service wireless ground users over LTE licensed unlicensed bands. The considered model focuses on can access both bands while receiving contents from either cache units at UAVs directly or via content server-UAV-user links. This formulated as an optimization problem, which jointly incorporates user association, spectrum allocation, caching. To...

Uplink-downlink decoupling in which users can be associated to different base stations the uplink and downlink of heterogeneous small cell networks (SCNs) has attracted significant attention recently. However, most existing works focus on simple association mechanisms LTE SCNs that operate only licensed band. In contrast, this paper, problem resource allocation with uplink-downlink is studied for an SCN incorporates unlicensed Here, access both bands while being stations. This formulated as...

In this paper, the problem of enhancing virtual reality (VR) experience for wireless users is investigated by minimizing occurrence breaks in presence (BIP) that can detach from their world. To measure BIP VR users, a novel model jointly considers application type, transmission delay, video quality, and users' awareness environment proposed. developed model, base stations (BSs) transmit videos to using directional links so as provide high data rates thus, reducing number each user. Since...

It is predicted that billions of intelligent devices and networks, such as wireless sensor networks (WSNs), will not be isolated but connected integrated with computer in future Internet Things (IoT). In order to well maintain those devices, it often necessary evolve function correctly by allowing device management (DM) entities remotely monitor control without consuming significant resources. this paper, we propose a lightweight RESTful Web service (WS) approach enable devices....

The rapid growth of the internet usage and distributed computing resources edge devices create a necessity to have reasonable controller ensure efficient utilization in mobile (MEC). We envision future MEC services, where quality experience (QoE) services is further enhanced by software defined networks (SDNs) capabilities reduce application-level response time without service disruptions. SDN, which not proposed specifically for computing, can fact serve as an enabler lower complexity...

In this paper, the problem of content caching and transmission is studied for a wireless virtual reality (VR) network in which cellular-connected unmanned aerial vehicles (UAVs) capture videos on live games or sceneries transmit them to small base stations (SBSs) that service VR users. To meet delay requirements, UAVs can extract specific visible (e.g., user field view) from original 360° data send users so as reduce traffic load over backhaul radio access links. The extracted consists 120°...

In this paper, the problem of training federated learning (FL) algorithms over a realistic wireless network is studied. particular, in considered model, users perform an FL algorithm that trains their local models using own data and send trained to base station (BS) will generate global model it back users. Since all parameters are transmitted links, quality be affected by factors such as packet errors availability resources. Meanwhile, due limited bandwidth, BS must select appropriate...

In this article, a joint task, spectrum, and transmit power allocation problem is investigated for wireless network in which the base stations (BSs) are equipped with mobile-edge computing (MEC) servers to jointly provide computational communication services users. Each user can request one task from three types of tasks. Since data size each different, as requested varies, BSs must adjust their resource (subcarrier power) schemes effectively serve This formulated an optimization whose goal...

In this article, the problem of minimizing energy and time consumption for task computation transmission in mobile-edge computing-enabled balloon networks is investigated. considered network, high-altitude balloons (HABs), acting as flying wireless base stations, can use their powerful computational capabilities to process tasks offloaded from associated users. Since data size each user's varies over time, HABs must dynamically adjust resource allocation schemes meet users' needs. This posed...

Providing seamless connectivity for wireless virtual reality (VR) users has emerged as a key challenge future cloud-enabled cellular networks. In this paper, the problem of VR resource management is investigated network in which contents are sent by cloud to small base stations (SBSs). The SBSs will collect tracking data from users, over uplink, order generate content and transmit it end-users using downlink links. For model, requested or transmitted can exhibit correlation, since may engage...

In this paper, the problem of audio based semantic communication is investigated over wireless networks. considered model, edge devices must transmit large-sized data to a server using techniques. The techniques enable transmission information which captures contextual features signals. To extract from signals, wave vector (wav2vec) architecture autoencoder that consists convolutional neural networks (CNNs) proposed. proposed enables high-accuracy with small amounts data. further improve...

We present a squaring method to simplify the decoding of orthogonal space-time block codes in wireless communication system with an arbitrary number transmit and receive antennas. Using this method, closed-form expression signal-to-noise ratio after is also derived. It gives same performance as maximum-likelihood while it shows much lower complexity.

We study the scaling laws for throughputs and delays of two coexisting wireless networks that operate in same geographic region. The primary network consists Poisson distributed legacy users density <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> , secondary cognitive xmlns:xlink="http://www.w3.org/1999/xlink">m</i> with > . have a higher priority to access spectrum without particular considerations users, while act conservatively order...

With growing needs to better understand our environments, the Internet-of-Things (IoT) is gaining importance among information and communication technologies. IoT will enable billions of intelligent devices networks, such as wireless sensor be connected integrated with computer networks. In order support large scale IETF has defined routing protocol for low power lossy networks (RPL) facilitate multihop connectivity. this paper, we provide an in-depth review current research activities....

In this paper, the problem of joint caching and resource allocation is investigated for a network cache-enabled unmanned aerial vehicles (UAVs) that service wireless ground users over LTE licensed unlicensed (LTE-U) bands. The considered model focuses on can access both bands while receiving contents through UAV cache-user links content server-UAV-user links. This formulated as an optimization which jointly incorporates user association, spectrum allocation, caching. To solve problem,...

In this paper, the problem of training federated learning (FL) algorithms over a realistic wireless network is studied. particular, in considered model, users execute an FL algorithm while their local models using own data and transmitting trained to base station (BS) that will generate global model send it back users. Since all parameters are transmitted links, quality be affected by factors such as packet errors availability resources. Meanwhile, due limited bandwidth, BS must select...

Cellular networks assisted by flexibly placed high-maneuverability unmanned aerial vehicles (UAVs) have attracted virtual interests recently. In this paper, the utility maximization problem is investigated to determine how improve performance of multi-UAV enabled software-defined cellular (SDCNs) with wireless backhaul. The formulated jointly optimizes three dimensional (3D) UAV placement, user scheduling and association, spectrum resource allocation. proposed intractable since it a...

In this paper, the problem of minimizing weighted sum age information (AoI) and total energy consumption Internet Things (IoT) devices is studied. considered model, each IoT device monitors a physical process that follows nonlinear dynamics. As dynamics vary over time, should find an optimal sampling frequency to sample real-time system send sampled base station (BS). Due limited wireless resources, BS can only select subset transmit their information. Thus, edge cooperatively monitored...

Network function virtualization (NFV), software defined networks (SDNs), and mobile edge computing (MEC) are emerging as core technologies to satisfy increasing number of users' demands in 5G beyond wireless networks. SDN provides clean separation the control plane from data while NFV enables flexible on-the-fly creation placement virtual network functions (VNFs) able be executed within various locations a distributed system and, our case, NFV-enabled MEC nodes. VNF resource allocation...

In this article, the problem of vertical handover in software-defined network (SDN) based heterogeneous networks (HetNets) is studied. studied model, HetNets are required to offer diverse services for mobile users. Using an SDN controller, have capability managing users' access and mobility issues but still problems ping-pong effect service interruption during handover. To solve these problems, a mobility-aware seamless method on multipath transmission control protocol (MPTCP) proposed. The...