5G delivers ultra-reliable low-latency communications and mobile edge computing (MEC) for industrial applications, enabling distributed computing resource collaboration and promoting traditional automation systems toward networked control paradigms. However, industrial networked automation systems face significant challenges in optimally allocating limited computing and communication resources to meet strict QoS requirements for massive control tasks while maintaining system stability and efficiency. Thus, we propose a computing-communication-control collaboration mechanism to enhance coordination between MEC and local controllers, enabling complex control tasks to be processed despite limited local computing resources. To jointly optimize hybrid control tasks migration with communication constraints and computing resources allocation with incomplete information, we design a dual double deep Q-network embedded with the Stackelberg game model. Simulation results demonstrate that the proposed mechanism achieves better performance compared with other benchmarks, and extremely decreases the convergence time compared with the classical Stackelberg game solution.

Connected and autonomous vehicle (CAV) platoon control has been considered as a promising technology to improve the safety and efficiency of intelligent transportation systems. In the platoon control decision-making process, vehicle-to-vehicle (V2V) communications are required to perform information exchange between vehicles. Existing studies commonly assume ideal V2V communication conditions, where the vehicles can receive completely accurate V2V data. However, in realistic scenarios, the V2V communication is subject to channel fading or communication attacks, which makes the vehicles to receive inaccurate or malicious V2V data, causing ‘V2V data uncertainty’. To tackle this problem, we investigate the CAV platoon control problem under the V2V data uncertainty. Firstly, we formulate a stability optimization problem under the V2V data uncertainty, based on an improved car-following model that incorporates multiple predecessors following-based V2V communication topology. Secondly, by employing linear stability theory in conjunction with the improved car-following model, we derive the stability constraint for the optimization problem. Then, by solving this optimization problem at every time step, an optimal control input is obtained to maintain system stability, thereby indirectly controlling the CAV platoon. To learn the optimal control strategy, we propose a robust deep reinforcement learning (DRL) approach. This approach demonstrates that the difference between the value function under optimal state perturbation and that under unperturbed conditions is bounded by a tunable upper limit. Since data uncertainty is intuitively reflected in the state, adjusting this upper bound enables the robust DRL approach to counteract the effects of V2V data uncertainty. Finally, simulation results indicate that the proposed approach significantly outperforms baseline approaches and the average allocation method in terms of platoon state control, stability, and comfort. Moreover, it is markedly superior to the baseline approaches regarding convergence and overall model performance.

The development of intelligent transportation has generated many ultra reliable low latency communication (URLLC) tasks, which require sufficient communication and computation resources for task offloading and processing. Although mobile edge computing (MEC) provides a promising solution, its efficiency is subject to the limited knowledge and analysis capability on the physical networks. Therefore, in this paper, we propose a digital twin (DT) empowered MEC framework to strengthen the MEC task offloading efficiency in cellular vehicle-to-everything (C-V2X) networks. Our proposed DT is constructed through a hybrid data-driven and model-driven approach to capture the realistic transportation network features. Then, DT leverages the metric of time to collision to predict vehicular safety levels and estimates the corresponding URLLC task requirements of future time slots. The prediction results are further utilized to make decisions on the URLLC resource reservation. Different from conventional studies, we consider the influence of DT’s inaccurate predictions (i.e., the prediction with error) on the resource allocations. Specifically, the inaccurate DT prediction results are considered as uncertain constraints of the resource reservation problem. A robust parameter from the robust optimization is adopted to adjust the tradeoff between the problem uncertainty and solution optimality degree. Further, we leverage the optimized resource reservation results to construct the task offloading problem. The problem is decoupled into two sub-problems of channel resource allocation and computation resource allocation, respectively. And a two-stage matching algorithm is developed to solve each sub-problem based on the resource reservation constraints. Finally, realistic road information is mapped into DT for simulations. Simulation results validate the advantages of our proposed approach by comparing with existing schemes.

Ridesharing programs, as a new form of shared mobility, offer opportunities to build a more efficient and sustainable society. This paper first examines the mode choices of travelers in cities where ridesharing services are available. Specifically, travelers choose among four modes: solo drivers, ridesharing drivers, ridesharing riders, and public transit riders. To capture the mode choice behaviors of travelers, we build a stochastic ridesharing user equilibrium (SRUE) model with heterogeneous travelers in terms of car ownership. However, because of the inseparability of cost functions along with asymmetry in link interactions, the stochastic ridesharing user equilibrium is formulated as a variational inequality (VI) problem and an equivalent mixed complementarity problem (MiCP). Moreover, we prove the existence and uniqueness of the solution of SRUE under certain conditions. Besides, to address the decision-making problem of optimal car ownership in cities with ridesharing programs, we establish a bilevel optimization model that determines the optimal car ownership at the upper level and the equilibrium traffic flow solution at the lower level. Then, it is reformulated and solved as a mathematical problem with complementarity constraints (MPCC). Finally, numerical experiments are conducted to demonstrate our results and optimal car ownership in different scenarios.

Roadside Units (RSUs) deployment optimization for vehicle-to-road communication is crucial in improving the performance of the vehicular and transportation networks. Current researches on RSU deployment optimization overlooks the inequal supply-demand relationship of vehicular communications caused by unbalanced vehicular density. In addition, the impact of traffic safety risks on RSU optimization is not considered. To cope with these challenges, this paper presents a data-driven and multi-factor RSU deployment strategy, which can be divided into two stages. The first stage adopts a data-driven approach to analyze vehicular density using realistic vehicle trajectory data, which helps identify preliminary deployment positions based on unbalanced vehicular density. In the second stage, an RSU deployment model is constructed that considers RSU deployment costs, geographical environment constraints, road coverage, and traffic safety risks. This model calculates the cumulative Poisson probability of simple and general traffic crashes to evaluate the traffic safety risks within the RSU coverage range. Afterward, this paper proposes an improved genetic algorithm to obtain the optimal position of RSUs within the deployment area. The algorithm employs a new method for population initialization and adopts a linear ranking-based selection mechanism. Finally, we conduct a joint simulation of transportation and communication networks by linking SUMO with OMNET++ through the TraCI interface and Veins framework. The results evaluate and demonstrate the performance of the proposed method in vehicle coverage, traffic safety risk coverage, and average notification time in comparison with the existing schemes.

To provide a better support for various vehicular applications, digital twin (DT), as an emerging technology, can enable a virtual presentation of physical vehicular networks to reflect the current network state through real-time data updating. However, the constrained resources and high data updating cost may degrade the performance of DT. In this paper, we trade off the data updating cost and the performance of DT to adaptively determine the resource management and computation offloading in vehicular networks. Specifically, we propose a novel vehicle to vehicle pairing prediction algorithm assisted by DT to improve the offloading decision efficiency and investigate the effect of data updating frequency on prediction accuracy. Based on the prediction results, we formulate a joint data updating frequency selection, offloading decision and channel allocation problem with the objective of minimizing the computation and communication costs. To solve the formulated problem, we propose a prediction-based stability maximum pairing algorithm to obtain the proper task offloading strategy. Moreover, a deep Q-learning network algorithm is proposed to select the optimal DT data updating frequency according to the real-time vehicular network state. Based on the obtained optimal solution, we further propose an alternating direction method of multipliers-based iteration algorithm to optimize the computation and channel resource allocation and minimize the total costs. Numerical results are provided to validate the effectiveness and efficiency of our proposed algorithms.

Reinforcement learning has been adopted to improve the efficiency of vehicular lane changing (LC) decisions. However, since the local vehicular data needs to be uploaded to the edge node for accomplishing the learning and decision tasks, the data and traffic safety are under critical threat. Illegal data usage or attacks can generate misleading LC decisions such as collisions or rollover, which severely degrades the traffic safety. Therefore, this article investigates a blockchain-federated reinforcement learning (FRL) approach for the LC decisions, which jointly accounts for the traffic, data, and training safety of the LC decision making. A vehicular reputation model based on the Bayesian risk situation is constructed and combined with the FRL. The proposed model can help evaluate the traffic safety, select the vehicles for participating in the FRL training, and adjust the FRL aggregation weights. The FRL can protect the data safety by enabling the exchange and aggregation of the LC decision network parameters. The blockchain can ensure the FRL training safety by recording the FRL task information. In addition, a Proof-of-Work (PoW) consensus scheme is devised to increase the FRL robustness, where the vehicles can collaboratively join the blockchain consensus and accomplish the FRL aggregation in a distributed manner. Two typical scenarios are selected for the experimental evaluation, including the highway scenario and the merging scenario. The experimental results indicate that the proposed method shows better efficiency, convergence, and message safety delivery ratio by comparing with the existing studies.

With the development of vehicular networks, the vehicle-to-everything (V2X) communication aided emergency warning is envisioned to improve the safety of driving service in intelligent transportation systems (ITS). By considering the delay sensitivity of different vehicles receiving warning information, this paper investigates the V2X communication aided emergency message dissemination. Specifically, according to the distance between the vehicle and the emergency point, we divide the vehicles in the coverage of the roadside unit (RSU) into two groups, namely, the primary priority group and the secondary priority group. Then, we formulate a joint optimization problem for content partition, user grouping and channel allocation to improve the resource utilization and the efficiency of emergency message delivery. The objective is to ensure that all vehicles in the primary priority group can reliably receive the warning messages within a fixed deadline, and meanwhile, the RSU can send as many warning messages as possible to the vehicles in the secondary priority group. Despite the nature of mixed integer and non-linear programming problem, we propose a layered approach to solve the problem. Finally, we conduct simulations to validate the efficiency and effectiveness of the proposed algorithm, compared to some benchmark algorithms.

The air ground integrated networks can leverage unmanned aerial vehicle (UAV) communications to tackle the ever-increasing and unbalanced traffic load in future communication systems. This paper investigates the UAV enabled traffic offloading problem in air ground integrated networks with mixed user traffic. The problem jointly maximizes the system load balance and the total UAV reward, which can be formulated under a two-layer network graph model. In the cellular network graph, the association between the delay-sensitive users and the access points (APs) as well as the association between the UAVs and the APs are formulated. In the UAV network graph, the association between the delay-insensitive users and the UAVs is formulated. By observing the coupling relationship of the decision variables, we decouple the problem into three sub-problems and solve the first two sub-problems with reduced complexity. Then, we devise a Deep Neural Network (DNN) empowered genetic algorithm to solve the last sub-problem. The DNN can be leveraged to filter out the non-optimal solutions in the initialization operator of the genetic algorithm for improving the efficiency. Performance comparisons are provided between the proposed traffic offloading scheme and the existing ones, which validate the advantages of the DNN empowered genetic algorithm regarding its convergence, accuracy, and robustness.

As a prevailing concept in 5G, virtualisation provides efficient coordination among multiple radio access technologies (RATs) and enables multiple service providers to share different RATs’ physical infrastructures. This study proposes a generic framework for virtualising heterogeneous networks with different RATs. A novel virtual medium access control concept is introduced to realise resource offloading (allocation) and mobility management of the framework. The offloading and handover protocols are designed in detail. A novel resource offloading strategy is devised: First, to model the fact that different RATs possess different adaptability to different services, an ‘adaptability ratio’ concept is introduced and calculated using grey relational analysis. After that, a matching theory based framework is proposed to formulate the resource offloading problem and a ‘deferred acceptance’ algorithm is introduced to solve it. Through simulation, it is proved that the proposed protocols can efficiently reduce the service interruptions and improve the resource usage.

With mobile applications sharply developing, the battery technology becomes the bottleneck. Meanwhile, mobile users are increasingly sensitive to the latency of an application. The computation offloading in Small Cell Cloud (SCC) can economize the energy consumption of mobile devices efficiently and guarantee the makespan of an application. In this paper, we model the mobile application as a directed acyclic graph (DAG), and formulate an optimization problem of collaborative task execution to minimize the energy consumption on the mobile device while meeting a prescribed latency constraint. In order to solve this NP-hard problem, we propose a greedy algorithm based on partial critical path (GA-PCP) which can solve the problem approximately. The algorithm partitions the DAG into chains and processes these chains with the ``Add- Compare-Select" strategy to obtain the execution strategy. The algorithm can obtain a polynomial time complexity. Simulation results show that the solution of the GA-PCP is close to the optimal solution of the enumeration algorithm. Besides, the GA-PCP execution strategy can significantly save the energy consumption on the mobile device thereby prolonging its battery life, compared to the local execution.

Virtualization is a promising technique to solve the ossification of current wireless networks and meet the ever-increasing mobile data volume. This paper analyses the requirements in wireless network virtualization and proposes a generalized virtualization framework to overcome these challenges. A novel VMAC (virtual medium access control) concept is devised to perform resource virtualization and management, and the functionalities of VMAC are presented in detail, including user plane as well as data control plane. Through VMAC, heterogeneous RANs (radio access networks) can be aggregated with a unified protocol stack, packaged in the form of a service, reconfigured to provide end-to-end user services. The paper is concluded by identifying important open issues to be studied in future research.

Nowadays, multiple access points and subcarrier transmission are widely used in visible light communication(VLC) to achieve seamless coverage and high spectral efficiency. However, the reuse of subcarriers may cause severe interference for users located in overlapping areas using co-channel. Those existing methods utilize interference managements to solve this issue, but at the cost of bandwidth inefficiency. Hence, a designated resource allocation that includes interference mitigation is needed without degrading the performance of the network. In this paper, a graph theory based resource allocation algorithm in the downlink is proposed, which not only mitigates the interference, but also improves the capacity and fairness of the system. Numeric results demonstrate that the proposed scheme exhibits a 133.6% and a 25.0% average system throughput improvement compared to the Round Robin scheme and proportional fairness scheme. Additionally, a better performance in fairness is obtained by the proposed scheme.

Visible light communication (VLC) is considered as a promising high speed wireless access technology. However, the line-of-sight (LOS) nature of visible light limits VLC coverage and user mobility. On the contrary, radio frequency (RF) provides much more extensive coverage, though its link bit rate is lower by contrast. A cooperation of VLC and RF can allow them to enhance each other in certain aspects. Therefore, following existing studies, a hybrid VLC-LTE system is employed. One big challenge for realizing such a heterogeneous network is mobility management due to dynamic traffic and network conditions. Based on two basic vertical handover (VHO) schemes, this paper proposes a VHO algorithm through prediction (PVHO). Interruption durations, message sizes and access delays are critical metrics for prejudging the system state. A mobile terminal (MT) records these key parameters in real time and then processes them to offer guidance for proper handover decisions. Through simulation, the advantages of PVHO are validated by comparing with existing algorithms. Analysis of the numeric results gives an indication that the performance of PVHO is superior under various circumstances.

Network virtualization is considered a promising solution to the gradual ossification of current wireless networks. This paper proposes a two-stage power allocation scheme in LTE air interface virtualization where radio resources are coordinated by a hypervisor among different virtual operators (VOs). In the first stage, VCG auction game is utilized to generate an initial allocation. In the game, VOs are modeled as bidders bidding for power resources on behalf of their users while hypervisor is modeled as the auctioneer. In the second stage, Shapley value in coalition game is introduced to adjust the initial power allocation. The adjustment is made according to users' rate requirements to guarantee a fair allocation among users of different VOs. Simulation proves our scheme can balance between the energy efficiency and users' rate requirements compared with two conventional schemes.

Due to the lack of spectrum resources in wireless networks, to efficiently make use of the existing heterogeneous wireless networks is of significant importance. Network selection mechanism plays an important role for mobile users to target a network under the principle “always best connected (ABC)” in heterogeneous wireless environment. In this paper, a novel approach for network selection based on the combination of analytic hierarchy process (AHP) and bankruptcy game which is a special type of an N-person cooperative game is proposed and investigated. The AHP method takes the responsibility of evaluating weights of multiple decision criteria, which depends more on the consideration from the user side. On the other hand, the bankruptcy game is mainly used to assess the potentials of available candidate networks. Finally, the combination of AHP and bankruptcy game evaluates the potential contribution ratio (PCR) of each candidate network and the network with the largest PCR is selected.