移动边缘计算辅助智能驾驶中基于高效联邦学习的碰撞预警算法

Collision Warning Algorithm Based on Efficient Federated Learning in Mobile Edge Computing Assisted Intelligent Driving

智能驾驶中的碰撞避免任务存在对时延要求极高和隐私保护等挑战。首先,该文提出一种基于自适应调整参数的半异步联邦学习(SFLAAP)的门控循环单元联合支持向量机(GRU_SVM)碰撞多级预警算法,SFLAAP可根据训练和资源情况动态调整两个训练参数:本地训练次数和参与聚合的局部模型数量。然后,为解决资源受限的移动边缘计算(MEC)下碰撞预警模型协作训练的效率问题,根据上述参数与SFLAAP训练时延的关系,建立训练总时延最小化模型,并将其转化为马尔可夫决策过程(MDP)。最后,在所建立的MDP中采用异步优势演员-评论家(A3C)学习求解,自适应地确定最优训练参数,从而减少碰撞预警模型的训练完成时间。仿真结果表明,所提算法有效地降低训练总时延并保证预测精度。

Collision avoidance tasks in intelligent driving have challenges such as extremely high latency requirements and privacy protection.First,a Gated Recurrent Unit_Support Vector Machine(GRU_SVM)collision multi-level warning algorithm based on Semi-asynchronous Federated Learning with Adaptive Adjustment of Parameters(SFLAAP)is proposed.SFLAAP can dynamically adjust two training parameters according to training and resource conditions:the number of local training times and the number of local models participating in aggregation.Then,in order to solve the efficiency problem of collaborative training of collision warning model under resource-constrained Mobile Edge Computing(MEC),according to the relationship between the above parameters and SFLAAP training delay,a model for minimizing the total training delay is established,and it is transformed into a Markov Decision Process(MDP).Finally,in the established MDP,the Asynchronous Advantage Actor-Critic(A3C)algorithm is employed to determine adaptively the optimal training parameters,thereby reducing the training completion time of the collision warning model.The simulation results show that the proposed algorithm can effectively reduce the total training delay and ensure prediction accuracy.