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 aim to make the best joint decision of device selection and computing and spectrum resource allocation for optimizing federated learning (FL) performance in distributed industrial Internet of Things (IIoT) networks. To implement efficient FL over geographically dispersed data, we introduce a three-layer collaborative FL architecture to support deep neural network (DNN) training. Specifically, using the data dispersed in IIoT devices, the industrial gateways locally train the DNN model and the local models can be aggregated by their associated edge servers every FL epoch or by a cloud server every a few FL epochs for obtaining the global model. To optimally select participating devices and allocate computing and spectrum resources for training and transmitting the model parameters, we formulate a stochastic optimization problem with the objective of minimizing FL evaluating loss while satisfying delay and long-term energy consumption requirements. Since the objective function of the FL evaluating loss is implicit and the energy consumption is temporally correlated, it is difficult to solve the problem via traditional optimization methods. Thus, we propose a “ Reinforcement on Federated ” (RoF) scheme, based on deep multi-agent reinforcement learning, to solve the problem. Specifically, the RoF scheme is executed decentralizedly at edge servers, which can cooperatively make the optimal device selection and resource allocation decisions. Moreover, a device refinement subroutine is embedded into the RoF scheme to accelerate convergence while effectively saving the on-device energy. Simulation results demonstrate that the RoF scheme can facilitate efficient FL and achieve better performance compared with state-of-the-art benchmarks.

The integration of communications with different scales, diverse radio access technologies, and various network resources renders next-generation wireless networks (NGWNs) highly heterogeneous and dynamic. Emerging use cases and applications, such as machine to machine communications, autonomous driving, and factory automation, have stringent requirements in terms of reliability, latency, throughput, and so on. Such requirements pose new challenges to architecture design, network management, and resource orchestration in NGWNs. Starting from illustrating these challenges, this paper aims at providing a good understanding of the overall architecture of NGWNs and three specific research problems under this architecture. First, we introduce a network-slicing based architecture and explain why and where artificial intelligence (AI) should be incorporated into this architecture. Second, the motivation, research challenges, existing works, and potential future directions related to applying AI-based approaches in three research problems are described in detail, i.e., flexible radio access network slicing, automated radio access technology selection, and mobile edge caching and content delivery. In summary, this paper highlights the benefits and potentials of AI-based approaches in the research of NGWNs.

With proliferation of computation-intensive Internet of Things (IoT) applications, the limited capacity of end devices can deteriorate service performance. To address this issue, computation tasks can be offloaded to the Mobile Edge Computing (MEC) for processing. However, it consumes considerable energy to transmit and process these tasks. In this paper, we study the energy efficient task offloading in MEC. Specifically, we formulate it as a stochastic optimization problem, with the objective of minimizing the energy consumption of task offloading while guaranteeing the average queue length. Solving this offloading optimization problem faces many technical challenges due to the uncertainty and dynamics of wireless channel state and task arrival process, and the large scale of solution space. To tackle these challenges, we apply stochastic optimization techniques to transform the original stochastic problem into a deterministic optimization problem, and propose an energy efficient dynamic offloading algorithm called EEDOA. EEDOA can be implemented in an online way to make the task offloading decisions with polynomial time complexity. Theoretical analysis is given to demonstrate that EEDOA can approximate the minimal transmission energy consumption while still bounding the queue length. Experiments results are presented which shows the EEDOA's effectiveness.