计算机科学 ›› 2014, Vol. 41 ›› Issue (1): 105-110.

• 2013 CCF人工智能会议 • 上一篇    下一篇

CDN缓存资源分配的细胞优化算法

冯翔,马美怡,虞慧群   

  1. 华东理工大学信息科学与工程学院 上海200237;华东理工大学信息科学与工程学院 上海200237;华东理工大学信息科学与工程学院 上海200237
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金(60905043,7,61173048),上海市教育委员会科研创新项目,中央高校基本科研业务费资助

Cell Optimization Algorithm for Cache Resource Allocation of CDN

FENG Xiang,MA Mei-yi and YU Hui-qun   

  • Online:2018-11-14 Published:2018-11-14

摘要: 为了缓解Internet网络拥挤状况,提高用户访问网站的响应速度,从技术上解决由于网络带宽小、用户访问量大、网点分布不均等原因所造成的用户访问网站响应速度慢的问题,提出了一种新的缓存资源分配方法——细胞优化算法。该算法是模仿自然细胞系统功能的一种智能优化方法,其通过模拟细胞内部结构和原理,对细胞核、细胞质的浓度、细胞间的亲和度、细胞优化机制、细胞的动态演化过程建立数学模型。给出了算法的并行计算结构和步骤。最后,通过理论证明、仿真实验与同类算法的比较,验证了算法求解CDN缓,存资源分配问题的有效性。

关键词: CDN,缓存资源分配,细胞优化算法,分布并行算法

Abstract: The Internet bandwidth capacity expansion,on the other hand,is lagging behind,making the Web a major performance bottleneck.For solving the crowd of Internet network and improving the responding rate of users accessing the webpage,we need a new policy of cache resource distribution.This paper investigated and developed a new bio-inspired parallel Cell Optimization Algorithm (COA) for parallel cache resource allocation of Content Delivery Network (CDN).To simulate the functions of cell system,models of COA,including the nuclear,cytoplasm consistency,affinity of cells,hybrid energy function and dynamical evolution of cells,were built biologically and mathematically.Furthermore,the parallel computing architecture and steps of COA were designed.Via numerous simulations and comparison with other classical algorithms,the characters of high efficiency,parallel distribution and effectiveness for CDN were illustrated,which are especially crucial for the functioning of large-scale distribution problems.

Key words: Content delivery betworks (CDN),Cache resource allocation,Cell optimization algorithm,Distributed and parallel algorithm

[1] Denning P.Computing is a natural science [J].Communications of the ACM,2007,50(7):13-18
[2] Durbin R,Willshaw D.An analogue approach to the travelling salesman problem using an elastic net method [J].Nature,1987,326(6114):689-691
[3] 惠雯,尹浩,林闯,等.内容分发网络请求路由研究[J].计算机科学,2012,39(2):1-7
[4] So J C H,Wong P.Genetic Algorithm in Resource Provider Selection for Personal Live Content Delivery in User-Provided Platform[C]∥2012IEEE 11th International Conference on Trust,Security and Privacy in Computing and Communications (TrustCom).Liverpool,United Kingdom,2012:1748-1754
[5] Mondal A,Trestian I,Qin Z,et al.P2P as a CDN:A new service model for file sharing [J].Computer Networks,2012,56(14):3233-3246
[6] Kideok C,Hakyung J,et al.How can an ISP merge with a CDN? [J].IEEE Communications,2011,49(10):156-162
[7] 叶剑虹,叶双.基于混合模式的流媒体缓存调度算法[J].计算机科学,2013,40(2):61-64
[8] Mondal A,Trestian I,Qin Z,et al.P2P as a CDN:A new service model for file sharing[J].Computer Networks,2012,56(9):3233-3246
[9] Calafate C T,Fortino G,Fritsch S,et al.An efficient and robust content delivery solution for IEEE 802.11p vehicular environments [J].Journal of Network and Computer Applications,2012,35(2):753-762
[10] Manfredi S,Oliviero F,Romano S P.Optimised balancing algorithm for content delivery networks[J].IET communications,2012,6(7):733-739
[11] Chakareski J.Multi-path content delivery:Efficiency analysisand optimization algorithms [J].Journal of Visual Communication and Image Representation,2012,23(11):1189-1198
[12] Isalan M.Systems biology:a cell in a computer [J].Nature,2012,488(7409):40-41
[13] Kelly T P,Jarmin S,MacKie-Mason J K.Variable QoS fromShared Web Caches:User-Centered Design and Value Sensitive Replacement [C]∥Proc.MIT Workshop Internet Service Qua-lity Economics.1999,2:14
[14] Breslau L,Cao L P,et al.Web Caching and Zipf-Like Distributions:Evidence and Implications [J].Proc.INFOCOM,1999,1(1):126-13

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!