Relying on the powerful communication capabilities and rapidly changing geometric configurations, Low Earth Orbit (LEO) satellites have become strong candidates for offering the integrated communication and navigation (ICAN) services in future sixth generation (6G) networks. Considering the distinct performance and resource requirements, how to strike a balance between communication and navigation is one of the key design issues in LEO-ICAN systems. Against this backdrop, we take the transmission rate and geometric dilution of precision (GDOP) as evaluation metrics of communication and navigation performance, respectively, and formulate a weighted rate and GDOP maximization problem by jointly optimizing the beamforming design and satellite selection. To deal with the optimization problem, we split the original problem into the beamforming design and satellite selection subproblems, and propose a two-layer resource allocation algorithm to solve these subproblems iteratively until convergence. Specifically, in the inner layer, the beamforming design is modeled as a difference-of-convex (DC) problem, and the DC programming method is applied to maximize the communication rate. In the outer layer, the satellite selection is modeled as an overlapping coalition formation (OCF) game, and the OCF-based satellite selection algorithm is proposed to simultaneously reconcile the navigation GDOP. Extensive simulation results demonstrate the effectiveness of our proposed algorithms and reveal the trade-off between communication and navigation performance.

Low earth orbit (LEO) satellite communication has been seen as a promising solution for achieving global ubiquitous connectivity and high data rates. However, the propagation delays between satellites and cells are time-varying and significantly different, resulting in asynchronous inter-cell interference. Most existing research assume that the signals from all satellites are received simultaneously, which oversimplifies the interference situation and limits their applicability. To address this challenge, a beam management approach with asynchronous interference mitigation is proposed to improve network throughput. Firstly, a primary serving duration allocation method is developed based on convex optimization, while asynchronous interference is ignored. Subsequently, considering that inter-cell interference can be mitigated by appropriately setting guard periods, a beam scheduling with guard period selection method is designed under given service duration constraints, where conflict graphs are constructed to characterize interference situations. Extensive simulation results validate that our proposed scheme can effectively mitigate asynchronous inter-cell interference and significantly enhance network throughput. Specifically, the network through-put is increased by 20% compared with baselines that ignore asynchronous interference.

To achieve ubiquitous wireless connectivity, low earth orbit (LEO) satellite networks have drawn much attention. However, effective beam management is challenging due to time-varying cell load, high dynamic network topology, and complex interference situations. In this paper, under inter-satellite handover frequency and satellite-terrestrial/inter-beam interference constraints, we formulate a practical beam management problem, aiming to maximize the long-term service satisfaction of cells. Particularly, Lyapunov framework is leveraged to equivalently transform the primal problem into multiple single epoch optimization problems, where virtual queue stability constraints replace inter-satellite handover frequency constraints. Since each single epoch problem is NP-hard, we further decompose it into three subproblems, including inter-satellite handover decision, beam hopping design and satellite-terrestrial spectrum sharing. First, a proactive inter-satellite handover mechanism is developed to balance handover frequency and satellite loads. Subsequently, a beam hopping design algorithm is presented based on conflict graphs to achieve interference mitigation among beams, and then a flexible satellite-terrestrial spectrum sharing algorithm is designed to satisfy the demands of beam cells and improve spectral efficiency. Simulation results show that our proposal significantly improves service satisfaction compared with baselines, where the average data queue length of beam cells is reduced by over 20% with affordable handover frequency.

Driven by diverse applications, radio access networks (RAN) are expected to embrace built-in computing and intelligence, forming a versatile wireless computing platform that closely integrates communication and computing. To fully unleash the potential of such a synergistic system, it is essential to coordinate communication and computing with intelligence unlocked by the radio intelligent controllers (RICs) in O-RAN. Building on the groundwork established by existing theoretical studies and simulations, we develop a platform that can emulate the events in the real-world system in more detail, bringing theoretical works closer to practical implementation. In this paper, we first introducens-GP-O-RAN, a software simulation platform developed over ns-3, enabling communication, computation task processing, large-scale data collection, and testing of system-level orchestration policies through user-level control. Taking virtual reality (VR) as an example, we formulate the computation offloading problem and develop a prediction-based computation offloading xAPP, which contains a prediction phase to predict users’ end-to-end (E2E) performance with the deep neural network and a system-level decision-making phase for global orchestration with the differential evolution algorithm. We evaluate the system capacity and E2E latency over the developed ns-GP-O-RAN, which is more effective than existing approaches.

Under the advancement of emerging communication technologies, the utilization of Internet of Things (IoT) is progressively expanding across diverse domains. The age of information (AoI) stands as a crucial measurement in evaluating the efficiency of IoT networks. For efficient and reliable data collection, Unmanned aerial vehicle (UAV) have been extensively applied in IoT networks. However, the escalating number of sensor nodes and random data sampling mode within IoT networks have made it challenging for UAV trajectory planning with the constraint of energy consumption. In response to this challenge, our solution entails an attention-based actor-critic algorithm for multi-UAV path planning in a pre-clustered IoT network, which takes into account both the average AoI of clusters and the energy consumption of each UAV. The simulation outcomes validate that our algorithm achieves a trade-off between the information freshness and energy consumption in the multi-UAV data gathering scenario.

Satellite communication with beam hopping is a promising approach to meeting wide-area user traffic demands under on-board resource limitation. However, there is currently a lack of theoretical models that characterize the impact of beam hopping on user uplink transmission performance. In this article, two simplified beam hopping modes for satellite communication are proposed, namely, probabilistic beam hopping and deterministic beam hopping. Based on these two modes, two Markov chain models are established, which describe the states and state transitions of users. In the first model, the user state incorporates only user queue length, while the state in the second model considers both user queue length and time slot index. For both models, we first derive their steady-state probabilities and state transition probabilities, and then the steady-state probability of successful packet transmission is solved through a numerical method. Further, we theoretically derive the explicit expressions of various user performance metrics based on the steady-state probability of successful packet transmission, such as average throughput, buffer occupancy rate, packet loss rate, and transmission delay, and simulation results verify the correctness of all expressions. By simulation, it is shown that the minimum beam illumination probability or time length can be determined given specific performance requirements to guide system design, and there is an inflection point for the improvement in system performance with the increase of beam resource. Moreover, it is found that deterministic beam hopping achieves lower user delay compared to probabilistic beam hopping when the system is near to saturation.

Wireless-based federated learning (FL), as an emerging distributed learning approach, has been widely studied for 6G systems. When the paradigm shifts from terrestrial to non-terrestrial networks (NTN), FL may need to address several open challenges, e.g., the limited service time of low earth orbit (LEO) satellites, the straggler issue in synchronous FL, and time-efficient uploading and aggregation for massive devices. In this work, we exploit the synergy of LEO and FL for future integrated 6G-satellite systems by taking advantage of ubiquitous wireless access provided by LEO and appealing characteristics of collaborative training and data privacy preservation in FL. The studied LEO-FL framework may need to improve multi-metric performance in practice. Different from most FL works, we simultaneously improve the communication-training efficiency and local training accuracy from a multi-objective optimization (MOO) perspective. To solve the problem, we propose a decomposition and meta-deep reinforcement learning based MOO algorithm for FL (DMMA-FL), aiming at adapting to the dynamic satellite-terrestrial environments, achieving efficient uploading and aggregation, and approaching Pareto optimal sets. Compared to single-objective optimization, heuristics-based, and learning-based MOO algorithms, the effectiveness and advantages of the proposed LEO-FL framework and DMMA-FL algorithm are assessed on MNIST and CIFAR-10 datasets.

Mega low earth orbit (LEO) satellite constellation is promising in achieving global coverage with high capacity. However, forwarding packets in mega constellation faces long end-to-end delay caused by multi-hop routing and highcomplexity routing table construction, which will detrimentally impair the network transmission efficiency. To overcome this issue, a distributed low-complexity satellite-terrestrial cooperative routing approach is proposed in this paper, and its core idea is that each node forwards packets to next-hop node under the constraints of minimum end-to-end hop-count and queuing delay. Particularly, to achieve an accurate and low-complexity minimum end-to-end hop-count estimation in satellite-terrestrial cooperative routing scenario, we first introduce a satellite realtime position based graph (RTPG) to simplify the description of three-dimensional constellation, and further abstract RTPG into a key node based graph (KNBG). Considering the frequent regeneration of KNBG due to satellite movement, a low complexity generation method of KNBG is studied as well. Finally, utilizing KNBG as input, we design the minimum end-to-end hop-count estimation method (KNBG-MHCE). Meanwhile, the computational complexity, routing path survival probability and practical implementation of our proposal are all deeply discussed. Extensive simulations are also conducted in systems with Ka and laser band inter-satellite links to verify the superiority of our proposal

Software-defined satellite-terrestrial integrated networks (SDSTNs) are seen as a promising paradigm for achieving high resource flexibility and global communication coverage. However, low latency service provisioning is still challenging due to the fast variation of network topology and limited onboard resource at low earth orbit satellites. To address this issue, we study service provisioning in SDSTNs via joint optimization of virtual network function (VNF) placement and routing planning with network dynamics characterized by a time-evolving graph. Aiming at minimizing average service latency, the corresponding problem is formulated as an integer nonlinear programming under resource, VNF deployment, and time-slotted flow constraints. Since exhaustive search is intractable, we transform the primary problem into an integer linear programming by involving auxiliary variables and then propose a Benders decomposition based branch-and-cut (BDBC) algorithm. Towards practical use, a time expansion-based decoupled greedy (TEDG) algorithm is further designed with rigorous complexity analysis. Extensive experiments demonstrate the optimality of BDBC algorithm and the low complexity of TEDG algorithm. Meanwhile, it is indicated that they can improve the number of completed services within a configuration period by up to 58% and reduce the average service latency by up to 17% compared to baseline schemes.

To satisfy the low-latency requirements of emerging computation-intensive vehicular services, offloading these services to edge or cloud servers has been recognized as an effective solution. Due to the limited resources of edge servers and the faraway distance of cloud servers, it is challenging to provide an efficient resource allocation strategy to balance the latency, throughput and the resource utilization. In this paper, an end–edge–cloud collaboration paradigm is presented for computation offloading in fog-based vehicular networks (FVNETs) by incorporating vehicles with idle resources as fog user equipments (F-UEs). To adaptively orchestrate end–edge–cloud resources in different load cases, a two-timescale resource reservation and allocation framework is proposed. Wherein, a Stackelberg-game-based dynamic F-UE incentive problem is first formulated with the cloud server as the leader and multiple F-UEs as the followers, and then an iterative algorithm is proposed to achieve the Stackelberg equilibrium of the computation resource pricing and reservation. On a small timescale, the joint communication and computation resource allocation problem is transferred into a multiagent stochastic game and a lenient multiagent deep-reinforcement-learning-based distributed algorithm is developed to minimize the sum latency. When latency performance deteriorates, F-UE incentive optimization will be triggered to reserve more resources of F-UEs. Simulation results show that the proposed end–edge–cloud orchestrated computation offloading scheme in FVNETs outperforms baselines in terms of average latency.

Intelligent radio access networks (RANs) have been seen as a promising paradigm aiming to better satisfy diverse application demands and support various service scenarios. In this paper, a comprehensive survey of recent advances in intelligent RANs is conducted. First, the efforts made by standard organizations and vendors are summarized, and several intelligent RAN architectures proposed by the academic community are presented, such as intent-driven RAN and network with enhanced data analytic. Then, several enabling techniques are introduced which include AI-driven network slicing, intent perception, intelligent operation and maintenance, AI-based cloud-edge collaborative networking, and intelligent multi-dimensional resource allocation. Furthermore, the recent progress achieved in developing experimental platforms is described. Finally, given the extensiveness of the research area, several promising future directions are outlined, in terms of standard open data sets, enabling AI with a computing power network, realization of edge intelligence, and software-defined intelligent satellite-terrestrial integrated network.

Despite the advantages of Federated Learning (FL), such as devolving model training to intelligent devices and preserving data privacy, FL still faces the risk of the single point of failure and attack from malicious participants. Recently, blockchain is considered a promising solution that can transform FL training into a decentralized manner and improve security during training. However, traditional consensus mechanisms and architecture for blockchain can hardly handle the large-scale FL task due to the huge resource consumption, limited throughput, and high communication complexity. To this end, this paper proposes a two-layer blockchain-driven FL framework, called as ChainsFL, which is composed of multiple Raft-based shard networks (layer-l) and a Direct Acyclic Graph (DAG)-based main chain (layer-2) where layer-l limits the scale of each shard for a small range of information exchange, and layer-2 allows each shard to update and share the model in parallel and asynchronously. Furthermore, FL procedure in a blockchain manner is designed, and the refined DAG consensus mechanism to mitigate the effect of stale models is proposed. In order to provide a proof-of-concept implementation and evaluation, the shard blockchain base on Hyperledger Fabric is deployed on the self-made gateway as layer-l, and the self-developed DAG-based main chain is deployed on the personal computer as layer-2. The experimental results show that ChainsFL provides acceptable and sometimes better training efficiency and stronger robustness comparing with the typical existing FL systems.

As a typical and prominent component of the Internet of Things, vehicular communication and the corresponding vehicular networks (VNETs) are promising to improve spectral efficiency, decrease transmission delay, and increase reliability. The ever-increasing number of vehicles and the demand of passengers/drivers for rich multimedium services bring key challenges to VNETs, which requiring huge capacity, ultralow delay, and ultrahigh reliability. To meet these performance requirements, a fog computing-based VNET is presented in this article, where the resource allocation as the corresponding key technique is researched. In particular, joint optimization of user association and radio resource allocation scheme is investigated to minimize the transmission delay of the concerned VNET. The proposed optimization problem is formulated as a mixed-integer nonlinear program and transformed into a convex problem by Perron–Frobenius theory and a weighted minimum mean square error method. Numerical results show that the proposed solution can significantly reduce the transmission delay with fast convergence.

Fog computing is seen as a key enabler to meet the stringent requirements of industrial Internet of Things (IIoT). Specifically, lower latency and IIoT devices’ energy consumption can be achieved by offloading computation-intensive tasks to fog access points (F-APs). However, traditional computation offloading optimization methods often possess high complexity, making them inapplicable in practical IIoT. To overcome this issue, this article proposes a deep reinforcement learning (DRL) based approach to minimize long-term system energy consumption in a computation offloading scenario with multiple IIoT devices and multiple F-APs. The proposal features a multi-agent setting to deal with the curse of dimensionality of the action space by creating a DRL model for each IIoT device, which identifies its serving F-AP based on network and device states. After F-AP selection is finished, a low complexity greedy algorithm is executed at each F-AP under a computation capability constraint to determine which offloading requests are further forwarded to the cloud. By conducting offline training in the cloud and then making decisions online, iterative online optimization procedures are avoided and, hence, F-APs can quickly adjust F-AP selection for each device with trained DRL models. Via simulation, the impact of batch size on system performance is demonstrated and the proposed DRL-based approach shows competitive performance compared to various baselines including exhaustive search and genetic algorithm based approaches. In addition, the generalization capability of the proposal is verified as well.

Cellular vehicle-to-everything (V2X) communication is crucial to support future diverse vehicular applications. However, for safety-critical applications, unstable vehicle-to-vehicle (V2V) links, and high signaling overhead of centralized resource allocation approaches become bottlenecks. In this article, we investigate a joint optimization problem of transmission mode selection and resource allocation for cellular V2X communications. In particular, the problem is formulated as a Markov decision process, and a deep reinforcement learning (DRL)-based decentralized algorithm is proposed to maximize the sum capacity of vehicle-to-infrastructure users while meeting the latency and reliability requirements of V2V pairs. Moreover, considering training limitation of local DRL models, a two-timescale federated DRL algorithm is developed to help obtain robust models. Wherein, the graph theory-based vehicle clustering algorithm is executed on a large timescale and in turn, the federated learning algorithm is conducted on a small timescale. The simulation results show that the proposed DRL-based algorithm outperforms other decentralized baselines, and validate the superiority of the two-timescale federated DRL algorithm for newly activated V2V pairs.

Featuring edge caching and computing, fog radio access networks have been seen as promising architectures. However, the joint optimization of cache and radio resource can put heavy burden on the resource manager in the cloud. To overcome this issue, hierarchical radio and cache resource management is studied in this paper. The core idea is to fully utilize the resource management capabilities of fog access points (FAPs) to divide time-domain resource on a small timescale by participating a coalitional game while make the resource manager allocate cache resource on a large timescale to maximize a long-term utility. Based on defined FAP preference, a low-complexity and distributed coalition formation algorithm is first developed under per-FAP fronthaul capacity constraints. Then, facing the challenges incurred by no closed form, discrete variables and the curse of dimensionality, multi-agent reinforcement learning (MARL) based caching is proposed for the resource manager. In the proposal, multiple agents are created, one for each content-FAP pair, who jointly learn a caching strategy via the interaction with a history network environment. By simulation, the effectiveness of the MARL based caching is demonstrated.

Fog radio access networks (F-RANs) are seen as potential architectures to support services of Internet of Things by leveraging edge caching and edge computing. However, current works studying resource management in F-RANs mainly consider a static system with only one communication mode. Given network dynamics, resource diversity, and the coupling of resource management with mode selection, resource management in F-RANs becomes very challenging. Motivated by the recent development of artificial intelligence, a deep reinforcement learning (DRL)-based joint mode selection and resource management approach is proposed. Each user equipment (UE) can operate either in cloud RAN (C-RAN) mode or in device-to-device mode, and the resource managed includes both radio resource and computing resource. The core idea is that the network controller makes intelligent decisions on UE communication modes and processors' on-off states with precoding for UEs in C-RAN mode optimized subsequently, aiming at minimizing long-term system power consumption under the dynamics of edge cache states. By simulations, the impacts of several parameters, such as learning rate and edge caching service capability, on system performance are demonstrated, and meanwhile the proposal is compared with other different schemes to show its effectiveness. Moreover, transfer learning is integrated with DRL to accelerate learning process.

Device-to-device (D2D)-enabled cloud radio access networks (C-RANs) are potential solutions for further improving spectral efficiency (SE) and decreasing latency by allowing direct communication between two users. However, due to the need to acquire global channel state information (CSI) and to execute centralized algorithms, heavy burdens are placed on the fronthaul and the baseband unit (BBU) pool. To alleviate these burdens, a distributed approach to mode selection and resource allocation for potential D2D pairs under pre-determined resource allocation of C-RAN users is proposed, in which pairs of users are endowed with decision-making capabilities. The proposed procedure is divided into three stages: communication mode and subchannel selection, utility value determination, and reinforcement-learning-based strategy update. The core idea is that the D2D pairs self-optimize the mode selection and resource allocation without global CSI under several practical constraints. Simulation results show that enabling D2D can significantly improve SE for C-RANs. Furthermore, the impacts of the fronthaul capacity, the centralized signal processing capability of the BBU pool, and the distance between the D2D transmitter and the remote radio head are demonstrated and analyzed.

Device-to-device (D2D) enabled cloud radio access networks (C-RANs) are potential solutions for further improving spectral efficiency (SE) and decreasing latency by allowing direct communication between two user equipments. Due to the acquirement of global channel state information (CSI) and the execution of centralized algorithms in the uplink D2D enabled C-RANs, heavy burdens are put on fronthaul and the baseband unit pool. To tackle this challenge, a game-theoretic approach to mode selection and resource allocation for potential D2D pairs is proposed with a distributed manner, in which pairs are endowed with decision-making capabilities. The proposal is categorized into three stages: communication mode and subchannel selection, remote radio head (RRH) association, and reinforcement learning based strategy update. The core idea is that D2D pairs autonomously optimize the mode selection and resource allocation without global CSIs under several practical constraints. Simulation results show that enabling D2D can significantly improve SE for C-RANs. Furthermore, the performance gain is mainly determined by the fronthaul capacity and the distance between D2D transmitters and RRHs.

Device-to-Device (D2D) technology provides a potential way to improve cellular network throughputs. However, severe interference is introduced with universal frequency reuse, which significantly degrades the network performance. In this paper, we investigate distributed power control strategies in a D2D underlaid cellular network. An enhanced single-leader-multiple-followers Stackelberg game model is presented, where the quality-of-service (QoS) constraints of both the macro base station user (leader) and the D2D users (followers) are considered simultaneously in the price update by using a discount factor. The conditions for the uniqueness of Stackelberg equilibrium (SE) are proposed, and a distributed power control algorithm related to the price update for the game model is proposed to achieve SE. The simulation results show that besides the reasonability and fairness in power allocation, our proposed scheme provides commendable QoS protection, and there exists a tradeoff between the QoS of the leader and followers by adopting different price policies.

The ability to accurately profile energy consumption is of great importance for energy management in low-power devices. This work presents a novel energy profiling architecture by combining the high-speed CPLD bus signaling capability of mPlatform with the smart TwinStar power board. By running mPlatform under different modes, we are able to utilize an MMSE estimator to analyze per-component energy consumption rates with sufficient accuracy. In our experiment, we use the profiling results to determine the working condition of individual components, as well as the hardware configuration of the sensor node.