Internet of Things (IoT) computing offloading is a challenging issue, especially in remote areas where common edge/cloud infrastructure unavailable. In this paper, we present space-air-ground integrated network (SAGIN) architecture for the computation-intensive applications considering energy and computation constraints, flying unmanned aerial vehicles (UAVs) provide near-user edge satellites access to cloud computing. First, UAV servers, propose joint resource allocation task scheduling...

In this tutorial paper, we look into the evolution and prospect of network architecture propose a novel conceptual for 6th generation (6G) networks. The proposed has two key elements, i.e., holistic virtualization pervasive artificial intelligence (AI). consists slicing digital twin, from aspects service provision demand, respectively, to incorporate service-centric user-centric networking. integrates AI future networks perspectives networking networking, respectively. Building on...

In this article, we investigate a computing task scheduling problem in space-air-ground integrated network (SAGIN) for delay-oriented Internet of Things (IoT) services. the considered scenario, an unmanned aerial vehicle (UAV) collects tasks from IoT devices and then makes online offloading decisions, which can be processed at UAV or offloaded to nearby base station remote satellite. Our objective is design policy that minimizes delay all given energy capacity constraint. To end, first...

With the global rollout of fifth generation (5G) networks, it is necessary to look beyond 5G and envision 6G networks. networks are expected have space-air-ground integrated advanced network virtualization, ubiquitous intelligence. This article presents an artificial intelligence (AI)-native slicing architecture for enable synergy AI slicing, thereby facilitating intelligent management supporting emerging services. AI-based solutions first discussed across life cycle intelligently manage...

In this article, we investigate the UAV-aided edge caching to assist terrestrial vehicular networks in delivering high-bandwidth content files. Aiming at maximizing overall network throughput, formulate a joint and trajectory optimization (JCTO) problem make decisions on placement, delivery, UAV simultaneously. As interact with each other energy is limited, formulated JCTO intractable directly timely. To end, propose deep supervised learning scheme enable intelligent for real-time...

Split learning (SL) is a collaborative framework, which can train an artificial intelligence (AI) model between device and edge server by splitting the AI into device-side server-side at cut layer. The existing SL approach conducts training process sequentially across devices, incurs significant latency especially when number of devices large. In this paper, we design novel scheme to reduce latency, named <underline xmlns:mml="http://www.w3.org/1998/Math/MathML"...

In this paper, we investigate a radio access network (RAN) slicing problem for Internet of vehicles (IoV) services with different quality service (QoS) requirements, in which multiple logically-isolated slices are constructed on common roadside infrastructure. A dynamic RAN framework is presented to dynamically allocate spectrum and computing resource, distribute computation workloads the slices. To obtain an optimal policy accommodating spatial-temporal dynamics vehicle traffic density,...

Collaboration among industrial Internet of Things (IoT) devices and edge networks is essential to support computation-intensive deep neural network (DNN) inference services, which require low delay high accuracy. Sampling rate adaption, dynamically configures the sampling rates IoT according conditions, key in minimizing service delay. In this article, we investigate collaborative DNN problem networks. To capture channel variation task arrival randomness, formulate as a constrained Markov...

Due to the flexibility and low deployment cost, unmanned aerial vehicles (UAVs) have been widely used assist cellular networks in providing extended coverage for Internet of Things (IoT) networks. Existing throughput or delay-based UAV trajectory planning methods cannot meet requirement collecting fresh information from IoT devices. In this paper, by taking age-of-information (AoI) as a measure freshness, we investigate AoI-based data collection. To model complicated association interaction...

As an indispensable component of the emerging 6G networks, Space-Air-Ground Integrated Networks (SAGINs) are envisioned to provide ubiquitous network connectivity and services by integrating satellite aerial terrestrial networks. In SAGINs, a wide variety with features diverse requirements, complex mobility, multi-dimensional resources will pose great challenges service provisioning, which urges development service-oriented SAGINs. this paper, we conduct comprehensive review SAGINs from new...

The sixth generation (6G) networks are expected to enable immersive communications and bridge the physical virtual worlds. Integrating extended reality, holography, haptics, will revolutionize how people work, entertain, communicate by enabling lifelike interactions. However, unprecedented demand for data transmission rate stringent requirements on latency reliability create challenges 6G support communications. In this survey article, we present prospect of investigate emerging solutions...

With its potential versatility and reliability, the space-air-ground integrated vehicular network (SAGVN) is envisioned as a promising solution to deliver quality services anywhere at any time. This article proposes software defined framework for SAGVN achieve flexible, reliable, scalable resource management. First, key applications research challenges in management are identified. Then we propose hybrid hierarchical control architecture balance trade-off between system status acquisition...

Drone cell (DC) is envisioned to enable the dynamic service provisioning for radio access networks (RANs), in response spatial and temporal unevenness of user traffic. In this article, we propose a hierarchical deep reinforcement learning (DRL)-based multi-DC trajectory planning resource allocation (HDRLTPRA) scheme high-mobility users. The objective maximize accumulative network throughput while satisfying fairness, DC power consumption, DC-to-ground link quality constraints. To address...

Due to the versatile networking capability, space- air-ground integrated network (SAGIN) becomes a prominent future architecture support ever- increasing Internet of Things (IoT) applications. In this paper, we investigate IoT task offloading under an SAGIN scenario where multiple devices generate computing tasks be processed. We adopt unmanned aerial vehicle (UAV) fly along given trajectory collect within coverage area, and then makes online decision, i.e., processing locally, or nearby...

In this paper, we study Space-Air-Ground integrated Vehicular Network (SAGVN), and propose an online control framework to dynamically slice the SAG spectrum resource for isolated vehicular services provisioning. particular, at a given time slot, system makes decisions on request admission scheduling, UAV dispatching, slicing different services. To characterize impact of those parameters, construct time-averaged queue stability criteria by taking backlogs all into consideration, formulate...

Accurate cellular traffic load prediction is a pre-requisite for efficient and automatic network planning management. Considering diverse users' activities at different locations times, it technically challenging to characterize the resource demands time scales via traditional methods. In this paper, we propose combine long short-term memory (LSTM) Gaussian process regression (GPR) achieve accurate single-cell level prediction, using open Milan dataset provided by Telecom Italia. Firstly,...

Space-air-ground integrated networks (SAGINs) are envisioned to provide seamless coverage and enhanced flexibility compared with traditional terrestrial mobile networks, which has attracted much attention from both industry academia. However, orchestrating heterogeneous resources in such a large-scale dynamic network is challenging, especially encountering diverse services multi-dimensional requirements. In this paper, we first propose software-defined networking (SDN) function...

The Internet of Vehicles (IoV) can support applications in connected autonomous vehicles (CAVs), the implementation which effectively improve traffic efficiency. However, safety-related CAV have very strict requirements on reliability and latency each packet, is difficult to achieve due limited resources high dynamics CAVs. In this paper, we investigate communication resource scheduling for remote driving (AD) performance control system when network are constrained. Specifically, introduce a...

Edge intelligence leverages computing resources on the network edge to provide artificial (AI) services close users. As it enables fast inference and distributed learning, is envisioned be an important component of 6G networks. In this article, we investigate AI service provisioning for supporting intelligence. First, present features requirements services. Then introduce data management customize slicing Specifically, propose a novel resource-pooling method regularize exchange within while...

In this article, we present a novel content caching and delivery approach for mobile virtual reality (VR) video streaming. The proposed aims to maximize VR streaming performance, i.e., minimizing frame missing rate, by proactively popular chunks adaptively scheduling computing resources at an edge server based on user network dynamics. First, design scalable placement scheme deciding which cache the tradeoffs between resource consumption. Second, propose machine learning-assisted scheme,...

As an integral component of the space-air-ground integrated network (SAGIN), low Earth orbit (LEO) satellite has displayed immense potential in providing ubiquitous connectivity and broadband mobile communication. However, intrinsic dynamics LEO satellites pose unprecedented challenges management service delivery. In this paper, we investigate function chain (SFC) orchestration dynamic networks to achieve flexible efficient provision. Considering requirements limitations resources, formulate...