基于元学习与强化学习的跨域自组织网络流量测量优化方法
Traffic Measurement Optimization for Cross-Domain Ad Hoc Networks Based on Meta-Learning and Reinforcement Learning
宋健 1聂来森 1陶醉 1袁奇恩东1
作者信息
- 1. 西北工业大学电子信息学院,陕西西安,710072
- 折叠
摘要
跨域自组织网络是一种将不同介质上的节点进行自组织、网络拓扑自适应的网络.在跨域通信网络中,直接测量技术可获得准确的端到端网络流量信息.但跨域网络中部分节点的低算力和低存储特性,影响了所有节点运行网络流量测量进程.针对此,文中提出一种基于元学习与近端策略优化的网络流量测量优化方法,该方法根据上一时隙网络运行环境,来确定下一时隙执行网络流量测量的节点集合,目标是在尽可能少的节点上执行测量进程从而获取尽可能多的网络流量信息.文中同时通过 3 个网络数据集对所提方法进行仿真验证,实验结果表明,基于元学习和强化学习的跨域自组织网络流量测量优化算法可以有效选择流经流量大的节点,具有较快的收敛速度和测量效率.
Abstract
Cross-domain Ad Hoc network is a network that self-organizes nodes on different media and adapts to network topology.In cross-domain communication networks,direct measurement technology helps obtain accurate end-to-end network traffic information.However,the low computational power and low storage characteristics of some nodes in the cross-domain network hinder all nodes from running the network traffic measurement process.To address this issue,a network traffic measurement optimization method based on meta-learning and proximal policy optimization(PPO)was proposed.This method determined the set of nodes that performed network traffic measurement in the next time slot according to the network operating environment of the previous time slot,so as to perform the measurement process on as few nodes as possible to obtain as much network traffic information as possible.Three network datasets were used to verify the proposed method.The experimental results show that the traffic measurement optimization algorithm for cross-domain Ad Hoc networks based on meta-learning and reinforcement learning can effectively select the nodes with large traffic flow,with faster convergence speed and higher measurement efficiency.
关键词
跨域自组织网络/网络流量测量/元学习/近端策略优化/强化学习Key words
cross-domain Ad Hoc network/network traffic measurement/meta-learning/proximal policy optimization/reinforcement learning引用本文复制引用
基金项目
国家自然科学基金面上项目(62171378)
出版年
2024
国家科技期刊平台
NSTL
万方数据