Internet of things (IoT) computing offloading is a challenging issue, especially in remote areas where common edge/cloud infrastructure is unavailable. In this paper, we present a space-air-ground integrated network (SAGIN) edge/cloud computing architecture for offloading the computation-intensive applications considering remote energy-and computation-constraints, where flying unmanned aerial vehicles (UAVs) provide near-user edge computing and satellites provide access to the cloud computing. Firstly, for UAV edge servers, we propose a joint resource allocation and task scheduling approach to efficiently allocate the computing resources to virtual machines and schedule the offloaded tasks. Secondly, we investigate the computing offloading problem in SAGIN and propose a learning-based approach to learn the optimal offloading policy from the dynamic SAGIN environments. Specifically, we formulate the offloading decision making as a Markov decision process where the system state considers the network dynamics. To cope with the system dynamics and complexity, we propose a deep reinforcement learning-based computing offloading approach to learn the optimal offloading policy on-the-fly, where we adopt the policy gradient method to handle the large action space and actor-critic method to accelerate the learning process. Simulation results show that the proposed edge virtual machine allocation and task scheduling approach can achieve near-optimal performance with very low complexity, and that the proposed learning-based computing offloading algorithm not only converges fast, but also achieves a lower total cost compared with other offloading approaches.

In this tutorial paper, we look into the evolution and prospect of network architecture and propose a novel conceptual architecture for the 6th generation (6G) networks. The proposed architecture has two key elements, i.e., holistic network virtualization and pervasive artificial intelligence (AI). The holistic network virtualization consists of network slicing and digital twin, from the aspects of service provision and service demand, respectively, to incorporate service-centric and user-centric networking. The pervasive network intelligence integrates AI into future networks from the perspectives of networking for AI and AI for networking, respectively. Building on holistic network virtualization and pervasive network intelligence, the proposed architecture can facilitate three types of interplay, i.e., the interplay between digital twin and network slicing paradigms, between model-driven and data-driven methods for network management, and between virtualization and AI, to maximize the flexibility, scalability, adaptivity, and intelligence for 6G networks. We also identify challenges and open issues related to the proposed architecture. By providing our vision, we aim to inspire further discussions and developments on the potential architecture of 6G.

Split learning (SL) is a collaborative learning framework, which can train an artificial intelligence (AI) model between a device and an edge server by splitting the AI model into a device-side model and a server-side model at a cut layer. The existing SL approach conducts the training process sequentially across devices, which incurs significant training latency especially when the number of devices is large. In this paper, we design a novel SL scheme to reduce the training latency, named Cluster-based Parallel SL (CPSL) which conducts model training in a “first-parallel-then-sequential” manner. Specifically, the CPSL is to partition devices into several clusters, parallelly train device-side models in each cluster and aggregate them, and then sequentially train the whole AI model across clusters, thereby parallelizing the training process and reducing training latency. Furthermore, we propose a resource management algorithm to minimize the training latency of CPSL considering device heterogeneity and network dynamics in wireless networks. This is achieved by stochastically optimizing the cut layer selection, device clustering, and radio spectrum allocation. The proposed two-timescale algorithm can jointly make the cut layer selection decision in a large timescale and device clustering and radio spectrum allocation decisions in a small timescale. Extensive simulation results on non-independent and identically distributed data demonstrate that the proposed solution can greatly reduce the training latency as compared with the existing SL benchmarks, while adapting to network dynamics.

In this paper, we investigate a computing task scheduling problem in space-air-ground integrated network (SAGIN) for delay-oriented Internet of Things (IoT) services. In the considered scenario, an unmanned aerial vehicle (UAV) collects computing tasks from IoT devices and then makes online offloading decisions, in which the tasks can be processed at the UAV or offloaded to the nearby base station or the remote satellite. Our objective is to design a task scheduling policy that minimizes offloading and computing delay of all tasks given the UAV energy capacity constraint. To this end, we first formulate the online scheduling problem as an energy-constrained Markov decision process (MDP). Then, considering the task arrival dynamics, we develop a novel deep risk-sensitive reinforcement learning algorithm. Specifically, the algorithm evaluates the risk, which measures the energy consumption that exceeds the constraint, for each state and searches the optimal parameter weighing the minimization of delay and risk while learning the optimal policy. Extensive simulation results demonstrate that the proposed algorithm can reduce the task processing delay by up to 30% compared to probabilistic configuration methods while satisfying the UAV energy capacity constraint.

In this paper, we investigate the UAV-aided edge caching to assist terrestrial vehicular networks in delivering high-bandwidth content files. Aiming at maximizing the overall network throughput, we formulate a joint caching and trajectory optimization (JCTO) problem to make decisions on content placement, content delivery, and UAV trajectory simultaneously. As the decisions interact with each other and the UAV energy is limited, the formulated JCTO problem is intractable directly and timely. To this end, we propose a deep supervised learning scheme to enable intelligent edge for real-time decision-making in the highly dynamic vehicular networks. In specific, we first propose a clustering-based two-layered (CBTL) algorithm to solve the JCTO problem offline. With a given content placement strategy, we devise a time-based graph decomposition method to jointly optimize the content delivery and trajectory design, with which we then leverage the particle swarm optimization (PSO) algorithm to further optimize the content placement. We then design a deep supervised learning architecture of the convolutional neural network (CNN) to make fast decisions online. The network density and content request distribution with spatio-temporal dimensions are labeled as channeled images and input to the CNN-based model, and the results achieved by the CBTL algorithm are labeled as model outputs. With the CNN-based model, a function which maps the input network information to the output decision can be intelligently learnt to make timely inference and facilitate online decisions. We conduct extensive trace-driven experiments, and our results demonstrate both the efficiency of CBTL in solving the JCTO problem and the superior learning performance with the CNN-based model.

In this paper, we investigate a radio access network (RAN) slicing problem for Internet of vehicles (IoV) services with different quality of service (QoS) requirements, in which multiple logically-isolated slices are constructed on a common roadside network infrastructure. A dynamic RAN slicing framework is presented to dynamically allocate radio spectrum and computing resource, and distribute computation workloads for the slices. To obtain an optimal RAN slicing policy for accommodating the spatial-temporal dynamics of vehicle traffic density, we first formulate a constrained RAN slicing problem with the objective to minimize long-term system cost. This problem cannot be directly solved by traditional reinforcement learning (RL) algorithms due to complicated coupled constraints among decisions. Therefore, we decouple the problem into a resource allocation subproblem and a workload distribution subproblem, and propose a twolayer constrained RL algorithm, named Resource Allocation and Workload diStribution (RAWS) to solve them. Specifically, an outer layer first makes the resource allocation decision via an RL algorithm, and then an inner layer makes the workload distribution decision via an optimization subroutine. Extensive trace-driven simulations show that the RAWS effectively reduces the system cost while satisfying QoS requirements with a high probability, as compared with benchmarks.