Anti-Byzantine Attacks Enabled Vehicle Selection for Asynchronous Federated Learning in Vehicular Edge Computing

In vehicle edge computing(VEC),asynchronous federated learning(AFL)is used,where the edge receives a local model and updates the global model,effectively reducing the global aggregation latency.Due to different amounts of local data,computing capabilities and locations of the vehicles,renewing the global model with same weight is inappropriate.The above factors will affect the local calculation time and upload time of the local model,and the vehicle may also be affected by Byzantine attacks,leading to the deterioration of the vehicle data.However,based on deep reinforcement learning(DRL),we can consider these factors comprehensively to eliminate vehicles with poor performance as much as possible and exclude vehicles that have suffered Byzantine attacks before AFL.At the same time,when aggregating AFL,we can focus on those vehicles with better performance to improve the accuracy and safety of the system.In this paper,we proposed a vehicle selection scheme based on DRL in VEC.In this scheme,vehicle’s mobility,channel conditions with temporal variations,computational resources with temporal variations,different data amount,transmission channel status of vehicles as well as Byzantine attacks were taken into account.Simulation results show that the proposed scheme effectively improves the safety and accuracy of the global model.

Joint computation offloading and resource allocation in vehicular edge computing networks

Vehicular Edge Computing(VEC)is a promising technique to accommodate the computation-intensive and delaysensitive tasks through offloading the tasks to the RoadSide-Unit(RSU)equipped with edge computing servers or neighboring vehicles.Nevertheless,the limited computation resources of edge computing servers and the mobility of vehicles make the offloading policy design very challenging.In this context,through considering the potential transmission gains brought by the mobility of vehicles,we propose an efficient computation offloading and resource allocation scheme in VEC networks with two kinds of offloading modes,i.e.,Vehicle to Vehicle(V2V)and Vehicle to RSU(V2R).We define a new cost function for vehicular users by incorporating the vehicles’offloading delay,energy consumption,and expenses with a differentiated pricing strategy,as well as the transmission gain.An optimization problem is formulated to minimize the average cost of all the task vehicles under the latency and computation capacity constraints.A distributed iterative algorithm is proposed by decoupling the problem into two subproblems for the offloading mode selection and the resource allocation.Matching theorybased and Lagrangian-based algorithms are proposed to solve the two subproblems,respectively.Simulation results show the proposed algorithm achieves low complexity and significantly improves the system performance compared with three benchmark schemes.

Lyapunov-Guided Optimal Service Placement in Vehicular Edge Computing

Vehicular Edge Computing(VEC)brings the computational resources in close proximity to the service requestors and thus supports explosive computing demands from smart vehicles.However,the limited computing capability of VEC cannot simultaneously respond to large amounts of offloading requests,thus restricting the performance of VEC system.Besides,a mass of traffic data can incur tremendous pressure on the front-haul links between vehicles and the edge server.To strengthen the performance of VEC,in this paper we propose to place services beforehand at the edge server,e.g.,by deploying the services/tasks-oriented data(e.g.,related libraries and databases)in advance at the network edge,instead of downloading them from the remote data center or offloading them from vehicles during the runtime.In this paper,we formulate the service placement problem in VEC to minimize the average response latency for all requested services along the slotted timeline.Specifically,the time slot spanned optimization problem is converted into per-slot optimization problems based on the Lyapunov optimization.Then a greedy heuristic is introduced to the drift-plus-penalty-based algorithm for seeking the approximate solution.The simulation results reveal its advantages over others in terms of optimal values and our strategy can satisfy the long-term energy constraint.

Task Offloading Based on Vehicular Edge Computing for Autonomous Platooning

Autonomous platooning technology is regarded as one of the promising technologies for the future and the research is conducted actively.The autonomous platooning task generally requires highly complex computations so it is difficult to process only with the vehicle’s processing units.To solve this problem,there are many studies on task offloading technique which transfers complex tasks to their neighboring vehicles or computation nodes.However,the existing task offloading techniques which mainly use learning-based algorithms are difficult to respond to the real-time changing road environment due to their complexity.They are also challenging to process computation tasks within 100 ms which is the time limit for driving safety.In this paper,we propose a novel offloading scheme that can support autonomous platooning tasks being processed within the limit and ensure driving safety.The proposed scheme can handle computation tasks by considering the communication bandwidth,delay,and amount of computation.We also conduct simulations in the highway environment to evaluate the existing scheme and the proposed scheme.The result shows that our proposed scheme improves the utilization of nearby computing nodes,and the offloading tasks can be processed within the time for driving safety.

NOMA-Based Energy-Efficient Task Scheduling in Vehicular Edge Computing Networks: A Self-Imitation Learning-Based Approach

Mobile Edge Computing(MEC)is promising to alleviate the computation and storage burdens for terminals in wireless networks.The huge energy consumption of MEC servers challenges the establishment of smart cities and their service time powered by rechargeable batteries.In addition,Orthogonal Multiple Access(OMA)technique cannot utilize limited spectrum resources fully and efficiently.Therefore,Non-Orthogonal Multiple Access(NOMA)-based energy-efficient task scheduling among MEC servers for delay-constraint mobile applications is important,especially in highly-dynamic vehicular edge computing networks.The various movement patterns of vehicles lead to unbalanced offloading requirements and different load pressure for MEC servers.Self-Imitation Learning(SIL)-based Deep Reinforcement Learning(DRL)has emerged as a promising machine learning technique to break through obstacles in various research fields,especially in time-varying networks.In this paper,we first introduce related MEC technologies in vehicular networks.Then,we propose an energy-efficient approach for task scheduling in vehicular edge computing networks based on DRL,with the purpose of both guaranteeing the task latency requirement for multiple users and minimizing total energy consumption of MEC servers.Numerical results demonstrate that the proposed algorithm outperforms other methods.

Enhancing the robustness of object detection via 6G vehicular edge computing

Academic and industrial communities have been paying significant attention to the 6th Generation (6G) wireless communication systems after the commercial deployment of 5G cellular communications. Among the emerging technologies, Vehicular Edge Computing (VEC) can provide essential assurance for the robustness of Artificial Intelligence (AI) algorithms to be used in the 6G systems. Therefore, in this paper, a strategy for enhancing the robustness of AI model deployment using 6G-VEC is proposed, taking the object detection task as an example. This strategy includes two stages: model stabilization and model adaptation. In the former, the state-of-the-art methods are appended to the model to improve its robustness. In the latter, two targeted compression methods are implemented, namely model parameter pruning and knowledge distillation, which result in a trade-off between model performance and runtime resources. Numerical results indicate that the proposed strategy can be smoothly deployed in the onboard edge terminals, where the introduced trade-off outperforms the other strategies available.

Privacy-Preserving Incentive Mechanism for Platoon Assisted Vehicular Edge Computing with Deep Reinforcement Learning

Platoon assisted vehicular edge computing has been envisioned as a promising paradigm of implementing offloading services through platoon cooperation.In a platoon,a vehicle could play as a requester that employs another vehicles as performers for workload processing.An incentive mechanism is necessitated to stimulate the performers and enable decentralized decision making,which avoids the information collection from the performers and preserves their privacy.We model the interactions among the requester(leader)and multiple performers(followers)as a Stackelberg game.The requester incentivizes the performers to accept the workloads.We derive the Stackelberg equilibrium under complete information.Furthermore,deep reinforcement learning is proposed to tackle the incentive problem while keeping the performers’information private.Each game player becomes an agent that learns the optimal strategy by referring to the historical strategies of the others.Finally,numerical results are provided to demonstrate the effectiveness and efficiency of our scheme.

An energy-efficient resource allocation strategy in massive MIMO-enabled vehicular edge computing networks

The vehicular edge computing(VEC)is a new paradigm that allows vehicles to offload computational tasks to base stations(BSs)with edge servers for computing.In general,the VEC paradigm uses the 5G for wireless communications,where the massive multi-input multi-output(MIMO)technique will be used.However,considering in the VEC environment with many vehicles,the energy consumption of BS may be very large.In this paper,we study the energy optimization problem for the massive MIMO-based VEC network.Aiming at reducing the relevant BS energy consumption,we first propose a joint optimization problem of computation resource allocation,beam allocation and vehicle grouping scheme.Since the original problem is hard to be solved directly,we try to split the original problem into two subproblems and then design a heuristic algorithm to solve them.Simulation results show that our proposed algorithm efficiently reduces the BS energy consumption compared to other schemes.

Adaptive Digital Twin for Vehicular Edge Computing and Networks

To better support the emerging vehicular applications and multimedia services,vehicular edge computing(VEC)provides computing and caching services in proximity to vehicles, by reducing network transmission latency and alleviating network congestion. However, current VEC networks may face some implementation challenges, such as high mobility of vehicles, dynamic vehicular environment,and complex network scheduling. Digital twin, as an emerging technology, can make the virtual representation of physical networks to predict, estimate,and analyze the real-time network state. In this paper, we integrate digital twin into VEC networks to adaptively make network management and policy schedule. We first introduce the framework of VEC networks and present the key problems in a VEC network.Next,we give the concept of digital twin and propose an adaptive digital twin-enabled VEC network. In the proposed network, digital twin can enable adaptive network management via the two-closed loops between physical VEC networks and digital twins. Further,we propose a digital twin empowered VEC offloading problem with vehicle digital models and road side unit (RSU) digital models. A deep reinforcement learning (DRL)-based offloading scheme is designed to minimize the total offloading latency. Numerical results demonstrate the effectiveness of the proposed DRL-based algorithm for VEC offloading.

CA-DTS:A Distributed and Collaborative Task Scheduling Algorithm for Edge Computing Enabled Intelligent Road Network

Edge computing enabled Intelligent Road Network(EC-IRN)provides powerful and convenient computing services for vehicles and roadside sensing devices.The continuous emergence of transportation applications has caused a huge burden on roadside units(RSUs)equipped with edge servers in the Intelligent Road Network(IRN).Collaborative task scheduling among RSUs is an effective way to solve this problem.However,it is challenging to achieve collaborative scheduling among different RSUs in a completely decentralized environment.In this paper,we first model the interactions involved in task scheduling among distributed RSUs as a Markov game.Given that multi-agent deep reinforcement learning(MADRL)is a promising approach for the Markov game in decision optimization,we propose a collaborative task scheduling algorithm based on MADRL for EC-IRN,named CA-DTS,aiming to minimize the long-term average delay of tasks.To reduce the training costs caused by trial-and-error,CA-DTS specially designs a reward function and utilizes the distributed deployment and collective training architecture of counterfactual multi-agent policy gradient(COMA).To improve the stability of performance in large-scale environments,CA-DTS takes advantage of the action semantics network(ASN)to facilitate cooperation among multiple RSUs.The evaluation results of both the testbed and simulation demonstrate the effectiveness of our proposed algorithm.Compared with the baselines,CA-DTS can achieve convergence about 35%faster,and obtain average task delay that is lower by approximately 9.4%,9.8%,and 6.7%,in different scenarios with varying numbers of RSUs,service types,and task arrival rates,respectively.

Client selection and resource scheduling in reliable federated learning for UA V-assisted vehicular networks

Federated Learning(FL),a promising deep learning paradigm extensively deployed in Vehicular Edge Computing Networks(VECN),allows a distributed approach to train datasets of nodes locally,e.g.,for mobile vehicles,and exchanges model parameters to obtain an accurate model without raw data transmission.However,the existence of malicious vehicular nodes as well as the inherent heterogeneity of the vehicles hinders the attainment of accurate models.Moreover,the local model training and model parameter transmission during FL exert a notable energy burden on vehicles constrained in resources.In view of this,we investigate FL client selection and resource management problems in FL-enabled UAV-assisted Vehicular Networks(FLVN).We first devise a novel reputation-based client selection mechanism by integrating both data quality and computation capability metrics to enlist reliable high-performance vehicles.Further,to fortify the FL reliability,we adopt the consortium blockchain to oversee the reputation informa-tion,which boasts tamper-proof and interference-resistant qualities.Finally,we formulate the resource scheduling problem by jointly optimizing the computation capability,the transmission power,and the number of local training rounds,aiming to minimize the cost of clients while guaranteeing accuracy.To this end,we propose a reinforcement learning algorithm employing an asynchronous parallel network structure to achieve an optimized scheduling strategy.Simulation results show that our proposed client selection mechanism and scheduling algorithm can realize reliable FL with an accuracy of 0.96 and consistently outperform the baselines in terms of delay and energy consumption.