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.

Performing deep neural network (DNN) inference in real time requires excessive network resources, which poses a big challenge to the resource-limited industrial Internet of things (IIoT) networks. To address the challenge, in this paper, we introduce an end-edge-cloud orchestration architecture, in which the inference task assignment and DNN model placement are flexibly coordinated. Specifically, the DNN models, trained and pre-stored in the cloud, are properly placed at the end and edge to perform DNN inference. To achieve efficient DNN inference, a multi-dimensional resource management problem is formulated to maximize the average inference accuracy while satisfying the strict delay requirements of inference tasks. Due to the mix-integer decision variables, it is difficult to solve the formulated problem directly. Thus, we transform the formulated problem into a Markov decision process which can be solved efficiently. Furthermore, a deep reinforcement learning based resource management scheme is proposed to make real-time optimal resource allocation decisions. Simulation results are provided to demonstrate that the proposed scheme can efficiently allocate the available spectrum, caching, and computing resources, and improve average inference accuracy by 31.4$\%$ compared with the deep deterministic policy gradient benchmark.

In this paper, an Air-Ground Integrated VEhicular Network (AGIVEN) architecture is proposed, where the aerial High Altitude Platforms (HAPs) proactively push contents to vehicles through large-area broadcast while the ground roadside units (RSUs) provide high-rate unicast services on demand. To efficiently manage the multi-dimensional heterogeneous resources, a service-oriented network slicing approach is introduced, where the AGIVEN is virtually divided into multiple slices and each slice supports a specific application with guaranteed quality of service (QoS). Specifically, the fundamental problem of multi-resource provisioning in AGIVEN slicing is investigated, by taking into account typical vehicular applications of location-based map and popularity-based content services. For the location-based map service, the capability of HAPvehicle proactive pushing is derived with respect to the HAP broadcast rate and vehicle cache size, wherein a saddle point exists indicating the optimal communication-cache resource trading. For the popular contents of common interests, the average on-board content hit ratio is obtained, with HAPs pushing newly generated contents to keep on-board cache fresh. Then, the minimal RSU transmission rate is derived to meet the average delay requirements of each slice. The obtained analytical results reveal the service-dependent resource provisioning and trading relationships among RSU transmission rate, HAP broadcast rate, and vehicle cache size, which provides guidelines for multi-resource network slicing in practice. Simulation results demonstrate that the proposed AGIVEN network slicing approach matches the multi-resources across slices, whereby the RSU transmission rate can be saved by 40% while maintaining the same QoS.

Unmanned aerial vehicles (UAVs) are widely used in Internet-of-Things (IoT) networks, especially in remote areas where communication infrastructure is unavailable, due to flexibility and low cost. However, the joint optimization of locations of UAVs and relay path selection can be very challenging, especially when the numbers of IoT devices and UAVs are very large. In this paper, we formulate the joint optimization of UAV locations and relay paths in UAV-relayed IoT networks as a graph problem, and propose a graph neural network (GNN)-based approach to solve it in an efficient and scalable way. In the training procedure, we design a reinforcement learning-based relay GNN (RGNN) to select the best relay path for each user. The theoretical analysis shows that the time complexity of RGNN is two orders lower than the conventional optimization method. Then, we jointly exploit location GNN (LGNN) and RGNN trained to optimize the locations of all UAVs. Both GNNs can be trained without relying on the training data, which is usually unavailable in the context of wireless networks. In inference procedure, LGNN is first used to optimize the location of UAVs, and then RGNN is used to select the best relay path based on the output of LGNN. Simulation results show that the proposed approach can achieve comparable performance to brute-force search with much lower time complexity when the network is relatively small. Remarkably, the proposed approach is highly scalable to large-scale networks and adaptable to dynamics in the environment, which can hardly be achieved using conventional methods.

Efficient transmission control is an intricate issue in vehicular networks due to the inherent topology dynamics and unreliable link conditions. Leveraging flexible management in software-defined vehicular networks, we propose a software-defined adaptive transmission control protocol (SATCP) for selecting various transmission control policies to adapt to the time-varying vehicular environment. We formulate the optimal transmission control problem, and develop a practical heuristic algorithm for adaptive transmission control. NS-3 based preliminary simulations are conducted to verify that SATCP achieves an improvement by 27.8% than TcpHtcp, and by 54.4% than TcpVegas in terms of average network throughput.

The sixth generation (6G) wireless networks are envisioned to feature wide-area coverage, diversified full-scenario services, massive connections and dynamic heterogeneity, resulting in large-scale and complex network optimization problems. Traditional model-based methods, while effective in simple scenarios with precise mathematical models, struggle with high computational intensity and long processing times in the realistic and intricate applications of 6G. Pure data-driven deep learning (DL) methods offer powerful approximation capabilities and fast online inference but are hindered by insufficient datasets and poor interpretability. To address these issues, knowledge-driven DL integrates domain knowledge into neural networks, combining the strengths of both model-based and data-driven approaches. This survey systematically reviews knowledge-driven DL in wireless networks from a novel perspective of the knowledge integration approach. It provides a comprehensive definition of domain knowledge in wireless networks and clarifies the types of knowledge and their representations that can be integrated into neural networks. Furthermore, a leading taxonomy of knowledge integration approaches in wireless networks is proposed, encompassing the integration of domain knowledge into neural network model selection, neural network model customization, knowledge and data fusion architecture construction, loss function design, and hyperparameter configuration. Based on this taxonomy, literature on knowledge-driven resource allocation and signal processing is thoroughly reviewed. This survey aims to provide an insightful guideline for effectively incorporating domain knowledge into neural networks in the field of wireless communications, ultimately advancing efficient and reliable intelligent 6G networks.