CAJ | 학술논문

内容云系统的检索延迟取决于边缘节点内容的可用性，而节点内容的可用性又取决于边缘节点的缓存机制。对同时考虑边缘节点、服务器缓存及检索容量情况下的检索延迟最小化问题进行分析。在随机选择和最短队列选择两种策略以及利己型、集体型和自适应型等三种缓存机制场景下考察内容检索延迟。该分析能够对缓存与检索容量对性能的关联影响进行量化，也能够探究相应的设计空间。仿真实验结果表明，自适应缓存机制与最短队列选择策略结合在一起能够很好地支持各种网络配置，并能适应负载变化。
내용운계통적검색연지취결우변연절점내용적가용성，이절점내용적가용성우취결우변연절점적완존궤제。대동시고필변연절점、복무기완존급검색용량정황하적검색연지최소화문제진행분석。재수궤선택화최단대렬선택량충책략이급이기형、집체형화자괄응형등삼충완존궤제장경하고찰내용검색연지。해분석능구대완존여검색용량대성능적관련영향진행양화，야능구탐구상응적설계공간。방진실험결과표명，자괄응완존궤제여최단대렬선택책략결합재일기능구흔호지지지각충망락배치，병능괄응부재변화。
Retrieval latency in content cloud system depends on the availability of edge nodes content,while in turn this availability depends on the caching policy at edge nodes.In this paper,we analyse the problem of minimising the retrieval latency under the circumstance of considering both the caches of edge nodes and server and the retrieval capacity.We inspect the content retrieval latency under two source selection strategies,i.e.,random and shortest-queue,and three caching policies:selfish,collective,and adaptive.Our analyses permit the quantification of the interrelated impacts on performance by caching and retrieval capacity,and the exploration of the corresponding design space.Simulation experimental results show that the adaptive caching policy combined with shortest-queue selection scales well with various network configurations and adapts to the load changes.