面向多任务联邦学习的移动设备调度方法
Mobile Devices Scheduling Method for Multi-task Federated Learning
焦翔 1魏祥麟 2范建华 2薛羽 1贾茹娜1
作者信息
- 1. 南京信息工程大学计算机与软件学院,南京 210044
- 2. 国防科技大学第六十三研究所,南京 210007
- 折叠
摘要
边缘指挥控制场景下,将多任务联邦学习中的移动设备调度问题建模为多目标优化问题,在模型收敛性、传输可靠性、计算资源有限性约束下,最小化联邦学习任务每轮的训练时延和能耗.为了求解该 0-1 整数规划问题,提出了一种基于差分进化的移动设备调度算法,将调度方案作为个体,通过交叉变异迭代进化得到具有最佳适应度的次优解.仿真结果表明,所提算法能够在保证模型准确率的前提下,有效降低训练过程中的时延与能量消耗.
Abstract
In edge command and control scenario,the mobile device scheduling problem in multi-task federated learning(FL)is modelled as a multi-objective optimization problem.Under the constraints of model convergence,transmission reliability,and limited computation resources,the optimization goal is to minimize the training delay and energy consumption of each round of multiple FL tasks.To solve the 0-1 integer programming problem,a mobile device scheduling algorithm based on differential evolution is proposed.The proposed algorithm treats each feasible scheduling policy as an individual,and obtains a sub-optimal solution with optimum fitness through crossover and mutation iterative evolution.Simulation results show that the proposed algorithm can ensure the accuracy of the model,and can effectively reduce the time and energy consumption in the training process.
关键词
多任务联邦学习/移动边缘计算/时延/能量消耗Key words
multi-task federated learning/mobile edge computing/time delay/energy consumption引用本文复制引用
出版年
2024
NETL
NSTL
万方数据