基于深度强化学习的多租户算网资源分配算法
Multi-tenant computing network resource allocation algorithm based on deep reinforcement learning
胡宇翔 1冯旭 2董永吉 1和孟佯 3庄雷 4宋艳蕊4
作者信息
- 1. 信息工程大学信息技术研究所,河南 郑州 450002;先进通信网全国重点实验室,河南 郑州 450002
- 2. 信息工程大学信息技术研究所,河南 郑州 450002
- 3. 郑州大学网络空间安全学院,河南 郑州 450002;嵩山实验室,河南 郑州 450002
- 4. 郑州大学计算机与人工智能学院,河南 郑州 450001
- 折叠
摘要
随着智能化业务的迅猛发展,传统网络架构与计算能力之间的既有关系已难以满足当前需求,算网融合的实施势在必行.在算网融合所催生的新型算力网络框架下,高效且智能的资源调度策略成为提升用户体验的关键环节,但现有的资源调度算法优化目标单一,无法满足多租户差异化的业务需求.为此,提出了一种基于深度强化学习的多目标资源调度(MODRLRS,Multi objective deep reinforcement learning resource scheduling)算法来调用网络中的计算资源和网络资源,该算法通过构建帕累托最优解集的方法对算网资源进行多目标调度优化以满足不同租户的个性化业务需求.仿真对比实验表明,相比其他多目标资源调度算法,新算法提升了 4.9%的请求接受率和 4.78%的符合时延请求率,能够灵活适应各种计算业务的独特需求.
Abstract
With the rapid advancement of intelligent businesses,the pre-existing relationship between traditional network architectures and computing capabilities has made it difficult to meet the current demands,making the implementation of computing-network convergence inevitable.Under the new computing power network framework brought about by the convergence of computing networks,efficient and intelligent resource scheduling strategy has become a key link to im-prove user experience.However,the existing resource scheduling algorithms have a single optimization objective and can-not meet the differentiated business needs of multi-tenants.To this end,a Multi objective deep reinforcement learning re-source scheduling(MODRLRS)was proposed to call the computing resources and network resources in the computing power network.The algorithm performs multi-objective scheduling optimization of computing network resources by con-structing a Pareto optimal solution set to meet the personalized business needs of different tenants.Simulation experimen-tal results show that compared with other multi-objective resource scheduling algorithms,the proposed algorithm im-proves the request acceptance rate by 4.9%and the compliant delay request rate by 4.78%,which can flexibly adapt to the unique requirements of various computing services.
关键词
算网融合/算力网络/资源调度/多目标优化/深度强化学习Key words
integration of computing and networking/computing power network/resource scheduling/multi objective optimization/deep reinforcement learning引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据