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 amount...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.展开更多
This paper investigates the age of information(AoI)-based multi-user mobile edge computing(MEC)network with partial offloading mode.The weighted sum AoI(WSA)is first analyzed and derived,and then a WSA minimization pr...This paper investigates the age of information(AoI)-based multi-user mobile edge computing(MEC)network with partial offloading mode.The weighted sum AoI(WSA)is first analyzed and derived,and then a WSA minimization problem is formulated by jointly optimizing the user scheduling and data assignment.Due to the non-analytic expression of the WSA w.r.t.the optimization variables and the unknowability of future network information,the problem cannot be solved with known solution methods.Therefore,an online Joint Partial Offloading and User Scheduling Optimization(JPOUSO)algorithm is proposed by transforming the original problem into a single-slot data assignment subproblem and a single-slot user scheduling sub-problem and solving the two sub-problems separately.We analyze the computational complexity of the presented JPO-USO algorithm,which is of O(N),with N being the number of users.Simulation results show that the proposed JPO-USO algorithm is able to achieve better AoI performance compared with various baseline methods.It is shown that both the user’s data assignment and the user’s AoI should be jointly taken into account to decrease the system WSA when scheduling users.展开更多
Due to the fading property of wireless channels, the instant transmission capability of a fading channel, i.e., the instantaneous channel capacity, will change randomly along time. Usually, a finite size buffer is nee...Due to the fading property of wireless channels, the instant transmission capability of a fading channel, i.e., the instantaneous channel capacity, will change randomly along time. Usually, a finite size buffer is needed at the transmitter to match instant channel capacity with the source data stream. This paper is focused on the queuing process in the buffer. The temporal characteristics of the queueing process in the buffer are investigated, for a buffer-aided communication over block Rayleigh fading channel, in the low signal- to-noise ratio regime. Particularly, the average absorbing time for the buffer to transfer from empty state to overflow sate and from overflow state to empty state, as well as the stable working time in which neither buffer empty nor buffer overflow happens are derived. Theoretical and numerical results show that increasing the buffer size and traffic load properly will improve the efficiency of the transmission.展开更多
In multi-user wireless communication systems,dynamic power allocation is an important means to deal with the time-varying nature of the physical and network layers.However,the current layer optimization approach to po...In multi-user wireless communication systems,dynamic power allocation is an important means to deal with the time-varying nature of the physical and network layers.However,the current layer optimization approach to power allocation cannot achieve the global optimum of the overall system performance.To solve this problem,a cross-layer optimization framework is presented for downlink power allocation,which takes both the channel and buffer states into account.A cross-layer optimization problem is formulated to optimize the total throughput with queue length and power constraints.An analytical solution and a low complexity dynamic programming algorithm,which are referred as water-filling in cellar(WFIC)policy,are presented to optimize the downlink power allocation.Finally,simulation results are presented to demonstrate the potential of the proposed method.展开更多
基金supported in part by the National Natural Science Foundation of China(No.61701197)in part by the National Key Research and Development Program of China(No.2021YFA1000500(4))in part by the 111 Project(No.B23008).
文摘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.
基金supported in part by the Fundamental Research Funds for the Central Universities under Grant 2022JBGP003in part by the National Natural Science Foundation of China(NSFC)under Grant 62071033in part by ZTE IndustryUniversity-Institute Cooperation Funds under Grant No.IA20230217003。
文摘This paper investigates the age of information(AoI)-based multi-user mobile edge computing(MEC)network with partial offloading mode.The weighted sum AoI(WSA)is first analyzed and derived,and then a WSA minimization problem is formulated by jointly optimizing the user scheduling and data assignment.Due to the non-analytic expression of the WSA w.r.t.the optimization variables and the unknowability of future network information,the problem cannot be solved with known solution methods.Therefore,an online Joint Partial Offloading and User Scheduling Optimization(JPOUSO)algorithm is proposed by transforming the original problem into a single-slot data assignment subproblem and a single-slot user scheduling sub-problem and solving the two sub-problems separately.We analyze the computational complexity of the presented JPO-USO algorithm,which is of O(N),with N being the number of users.Simulation results show that the proposed JPO-USO algorithm is able to achieve better AoI performance compared with various baseline methods.It is shown that both the user’s data assignment and the user’s AoI should be jointly taken into account to decrease the system WSA when scheduling users.
文摘基于内生人工智能(AI,artificial intelligence)在大规模复杂异构网络中实现万物智联是6G的重要特征之一。联邦学习(FL,federated learning)因其数据处理本地化这一特有的机器学习架构,被认为是在6G场景中实现分布式泛在智联的重要途径,已成为6G的重要研究方向。为此,首先分析了在未来6G,特别是物联网(IoT,internet of things)场景中引入分布式AI的必要性,以此为基础论述了FL在满足相关6G指标要求的潜力,并从架构设计、资源利用、数据传输、隐私保护、服务提供角度综述了FL如何赋能6G网络,最后给出了FL赋能6G研究存在的一些关键挑战和未来有价值的研究方向。
文摘Due to the fading property of wireless channels, the instant transmission capability of a fading channel, i.e., the instantaneous channel capacity, will change randomly along time. Usually, a finite size buffer is needed at the transmitter to match instant channel capacity with the source data stream. This paper is focused on the queuing process in the buffer. The temporal characteristics of the queueing process in the buffer are investigated, for a buffer-aided communication over block Rayleigh fading channel, in the low signal- to-noise ratio regime. Particularly, the average absorbing time for the buffer to transfer from empty state to overflow sate and from overflow state to empty state, as well as the stable working time in which neither buffer empty nor buffer overflow happens are derived. Theoretical and numerical results show that increasing the buffer size and traffic load properly will improve the efficiency of the transmission.
基金supported by the National Natural Science Foundation of China(Grant No.60472027).
文摘In multi-user wireless communication systems,dynamic power allocation is an important means to deal with the time-varying nature of the physical and network layers.However,the current layer optimization approach to power allocation cannot achieve the global optimum of the overall system performance.To solve this problem,a cross-layer optimization framework is presented for downlink power allocation,which takes both the channel and buffer states into account.A cross-layer optimization problem is formulated to optimize the total throughput with queue length and power constraints.An analytical solution and a low complexity dynamic programming algorithm,which are referred as water-filling in cellar(WFIC)policy,are presented to optimize the downlink power allocation.Finally,simulation results are presented to demonstrate the potential of the proposed method.
