智慧协同网络服务内容在传输路径上的缓存分配策略

doi:10.11959/j.issn.1000-436x.2016060

通信学报 ›› 2016, Vol. 37 ›› Issue (3): 129-138.doi: 10.11959/j.issn.1000-436x.2016060

智慧协同网络服务内容在传输路径上的缓存分配策略

冯博昊¹,周华春¹,张宏科¹,张明川^1,²

¹ 北京交通大学电子信息工程学院，北京100044
² 河南科技大学信息工程学院，河南洛阳471023

出版日期:2016-03-25 发布日期:2017-08-04
基金资助:
国家基础研究发展计划（“973”计划）基金资助项目;国家高技术研究发展计划（“863”计划）基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目

Cache allocation policy of service contents along delivery paths for the smart collaborative network

Bo-hao FENG¹,Hua-chun ZHOU¹,Hong-ke ZHANG¹,Ming-chuan ZHANG^1,²

¹ Institute of Electronic and Information Engineering,Beijing Jiaotong University,Beijing 100044,China
² Information Engineering College,Henan University of Science and Technology,Luoyang 471023,China

Online:2016-03-25 Published:2017-08-04
Supported by:
The National Basic Research Program of China(973 Program);The National High Technology of China(863 Program);The National Natural Science Foundation of China;The National Natural Science Foundation of China

摘要/Abstract

摘要：

针对智慧协同网络提出一种服务内容在传输路径上的缓存分配策略。该策略根据服务内容的流行度部署其在传输路径上的缓存位置，以求充分、高效地发挥网络缓存作用，进而提升网络的总体性能。所提分配策略分别在5层树型拓扑和由279个节点组成的真实网络拓扑中进行了性能测试。结果显示，该策略在所测的性能参数中表现出色，就平均服务获取距离而言，较命名数据网络（NDN,named data nerworking）所使用的LCE（leave copy everywhere）策略，其性能提高20%以上。

关键词: 缓存分配策略, 智慧协同网络, 智慧标识网络, 以信息为中心网络, 未来网络体系架构

Abstract:

A cache allocation policy(CA)of service contents along delivery paths was proposed for the smart collabora-tive network.CA allocates on-path caches to service contents based on their popularity,expecting to fully and efficiently utilize the cache resource along the delivery path and further improving the network performance.The performance of proposed policy CA was evaluated under a 5-layer tree topology and a 279-node real network topology.The results show that CA outperforms others in terms of tested performance indexes.Compared with LCE(leave copy everywhere)used by named data networking(NDN),CA reduces the distance that users fetch service contents over 20%.

Key words: cache allocation policy, smart collaborative network, smart identifier network, information centric network-ing, future network architecture

冯博昊,周华春,张宏科,张明川. 智慧协同网络服务内容在传输路径上的缓存分配策略[J]. 通信学报, 2016, 37(3): 129-138.

Bo-hao FENG,Hua-chun ZHOU,Hong-ke ZHANG,Ming-chuan ZHANG. Cache allocation policy of service contents along delivery paths for the smart collaborative network[J]. Journal on Communications, 2016, 37(3): 129-138.

图/表 14

图1

图2

表1

表2

图3

图4

图5

图6

表3

图7

图8

图9

图10

表4

参考文献 22

[1]	张宏科，罗洪斌 . 智慧协同网络体系基础研究[J]. 电子学报， 2013,41(7): 1249-1254. ZHANG H K , LUO H B . Fundamental research on theories of smart and cooperative networks[J]. Acta Electronic Silica, 2013,41(7): 1249-1254.
[2]	苏伟，陈佳，周华春，等. 智慧协同网络中的服务机理研究[J]. 电子学报， 2013,41(7): 1255-1260. SU W , CHEN J , ZHOU H C , et al. Research on the service mechan-isms in smart and cooperative networks[J]. Acta Electronic Silica, 2013,41(7): 1255-1260.
[3]	ZHANG L , ESTRIN D , BURKE J , et al. Named data networking (NDN)project NDN-0001[J]. Acm Sigcomm Computer Communica-tion Review, 2010,44(3): 66-73.
[4]	TROSSEN D , PARISIS G , VISALA K , et al. Conceptual architecture:principles,patterns and subcomponents descriptions[R]. Technical Report,FP7-INFSO-ICT-257217_PURSUIT_D2.2, 2011.
[5]	AHLGREN B , D'AMBROSIO M , DANNEWITZ C , et al. Second NetInf architecture description[R]. Technical Report,FP7-ICT-2007-1-216041-4WARD/D-6.2, 2010.
[6]	ROSSI D , ROSSINI G . On sizing CCN content stores by exploiting topological information[C]// Computer Communications Workshops (INFOCOM WKSHPS),IEEE Conference. Orlando, c2012:280-285.
[7]	LI Z , XIE G , WANG Y , et al. Optimal cache allocation for con-tent-centric networking[C]// IEEE International Conference on Net-work Protocols(ICNP). Goettingen, c2013:1-10.
[8]	XU Y , LI Y , LIN T , et al. A novel cache size optimization scheme based on manifold learning in content centric networking[J]. Journal of Network＆Computer Applications, 2014,37(1): 273-281.
[9]	LAOUTARIS N , SYNTILA S , STAVRAKAKIS I , Meta algorithms for hierarchical Web caches[C]// IEEE International Conference on Perfor-mance,Computing,and Communications. Phoenix, c2004:445-452.
[10]	WEI K C , HE D , PSARAS I , et al. Cache "less for more"in informa-tion-centric networks(extended version)[J] Computer Communica-tions, 2013,36(7): 758-770.
[11]	PAVLOU G , PSARAS I , WEI K C , Probabilistic in-network caching for information-centric networks[C]// The Second Edition of the ICN Workshop on Information-Centric Networking,ICN'12. New York, c2012:55-60.
[12]	PSARAS I , WEI K C , PAVLOU G . In-network cache management and resource allocation for information-centric networks[J]. Parallel ＆Distributed Systems IEEE Transactions, 2014,25(11): 2920-2931.
[13]	ROSENSWEIG E J , KUROSE J , Breadcrumbs:efficient,best-effort content location in cache networks[C]// IEEE Conference on Comput-er Communications Workshops(INFOCOM WKSHPS). Rio de Janeiro, c2009:2631-2635.
[14]	ZHU Y , CHEN M , NAKAO A , CONIC:content-oriented network with indexed caching[C]// IEEE Conference on Computer Communi-cations Workshops(INFOCOM WKSHPS). San Diego, c2010:1-6.
[15]	SOURLAS V , GKATZIKIS L , FLEGKAS P , et al. Distributed cache management in information-centric networks[J]. IEEE Transactions on Network＆Service Management, 2013,10(3): 286-299.
[16]	KIM Y , YEOM I . Performance analysis of in-network caching for con-tent-centric networking[J]. Computer Networks, 2013,57(13): 2465-2482.
[17]	PENTIKOUSIS K , OHLMAN B , DAVIES E , et al. Informationcentric networking:evaluation methodology[J/OL]. .
[18]	EWMA[EB/OL]. .
[19]	ARLITT M , CHERKASOVA L , DILLEY J , et al. Evaluating content management techniques for web proxy caches[R]. Technical Report,HPL-98-173, 1999.
[20]	NS-3[EB/OL]. .
[21]	ndnSIM documentation[EB/OL]. .
[22]	SPRING N , MAHAJAN R , WETHERALL D . Measuring ISP topolo-gies with rocketfuel[J]. Networking IEEE/ACM Transactions, 2002,32(4): 133-145.

服务标识	本周期请求数	流行度
SID1	Count₁	Value₁
SID2	Count₂	Value₂
M	M	M

服务标识	排序
SID1	Rank1
SID2	Rank2
M	M

参数	设定值
请求分布	Zipf(1.0)
服务内容数量	2.5×10⁴
拓扑类型	树型拓扑(31个节点)、真实拓扑(279个节点)
缓存大小	25
单个用户请求频率	100 Hz
仿真时间	1 000 s
所测策略	CA、LCD、MCD、Prob(0.3)、ProbCache(PRC)、ProbCache⁺(PRC+)、Betw以及LCE
缓存替代策略	LRU
性能指标	服务获取距离、缓存删除操作总量、请求报文数量

策略	服务获取距离				缓存删除操作总量				请求报文数量
	树型拓扑		真实拓扑		树型拓扑		真实拓扑		树型拓扑		真实拓扑
	平均值	减小率	平均值	减小率	平均值	减小率	平均值	减小率	平均值	减小率	平均值	减小率
CA	3.81	20.47%	4.13	22.14%	95.98	98.42%	680.44	97.95%	30 548.28	20.34%	211 615.98	12.27%
LCD	4.16	13.20%	4.53	14.67%	1 076.90	82.22%	6 413.18	80.71%	33 345.95	13.04%	227 571.49	5.66%
MCD	4.26	11.25%	4.99	5.97%	1 075.05	82.25%	5 991.55	81.98%	34 092.95	11.09%	235 987.36	2.17%
Betw	4.19	12.67%	4.58	13.74%	1 076.08	82.24%	5 584.23	83.20%	30 290.57	21.01%	225 086.92	6.69%
PRC	4.42	7.93%	4.72	11.07%	761.88	87.42%	5 022.37	84.89%	35 363.64	7.78%	227 967.82	5.49%
PRC+	4.32	9.95%	4.52	14.79%	217.75	96.41%	1 162.75	96.50%	34 591.54	9.79%	227 308.99	5.76%
Prob(0.3)	4.56	4.92%	4.87	8.25%	1 709.41	71.78%	10 300.91	69.01%	36 507.35	4.80%	228 771.90	5.16%
LCE	4.80	0%	5.30	0%	6 058.11	0%	33 243.98	0%	38 346.72	0%	241 212.06	0%

智慧协同网络服务内容在传输路径上的缓存分配策略

Cache allocation policy of service contents along delivery paths for the smart collaborative network

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 22

相关文章 5

Metrics

推荐阅读 0

[1]	贾濡,郜帅,罗洪斌,张宏科,万明. 智慧协同网络中基于流量矩阵的负载均衡路由机制[J]. 通信学报, 2016, 37(4): 128-138.
[2]	黄韬，刘江，霍如，魏亮，刘韵洁. 未来网络体系架构研究综述[J]. 通信学报, 2014, 35(8): 23-197.
[3]	黄韬,刘江,霍如,魏亮,刘韵洁. 未来网络体系架构研究综述[J]. 通信学报, 2014, 35(8): 184-197.
[4]	刘韵洁，黄韬，张娇，刘江，姚海鹏，谢人超. 服务定制网络[J]. 通信学报, 2014, 35(12): 1-9.
[5]	刘韵洁,黄韬,张娇,刘江,姚海鹏,谢人超. 服务定制网络[J]. 通信学报, 2014, 35(12): 1-9.