摘要
虚拟网络嵌入问题是网络虚拟化技术中的一项重要技术,主要用于分配物理网络资源。为解决虚拟网络嵌入问题,需将该问题转变为一种混合整数规划问题,并设计一个基于强化学习策略和注意力机制的虚拟网络嵌入模型。实验证明,与其他算法相比,本文所提算法模型有效地减少了资源碎片化程度,同时提高了虚拟网络请求的接受率。
Virtual network embedding is an important technology in network virtualization technology.Its purpose is how to effectively allocate physical network resources.In order to solve the problem of virtual network embedding,it is necessary to transform the problem into a mixed integer programming problem,and design a virtual network embedding model based on reinforcement learning strategy and attention mechanism.Experiments show that compared with other algorithms,the proposed algorithm model effectively reduces the degree of resource fragmentation and improves the acceptance rate of virtual network requests.
作者
刘祥宇
LIU Xiangyu(School of Information,Yunnan University of Finance and Economics,Kunming Yunnan 650221,China)
出处
《信息与电脑》
2022年第3期55-58,共4页
Information & Computer
基金
云南财经大学研究生创新基金项目(项目编号:2021YUFEYC088)。
关键词
虚拟网络嵌入
强化学习
网络虚拟化
virtual network embedding
reinforcement learning
network virtualization
