CCN中基于业务类型的多样化内容分发机制

针对内容中心网络(Content Centric Networking,CCN)如何提供差异化的业务需求服务的问题,采用区分服务的思想,从内容传输和缓存决策的角度出发,提出了一种基于业务类型的多样化内容分发机制.该机制依据不同的业务请求特征,分别设计了持久推送、并行预测和逐包请求的数据分发模式,对应提出了透明转发、边缘概率缓存和渐进式推进的沿途存储策略,实现了内容传递对于业务类型的感知和匹配.仿真结果表明,该机制减小了内容请求时延,提高了缓存命中率,以少量额外的控制开销提升了CCN网络整体的内容分发性能.     

一种基于SDN的CCN集中控制缓存决策方法

在软件定义网络(SDN)和内容中心网络(CCN)融合架构下,为了充分利用控制层对网络拓扑和缓存资源的全局感知,在全网中实现缓存资源的优化使用,提出了一种集中控制的缓存决策优化方案.在该方案中,应用粒子群优化算法(PSO)并且根据节点边缘度、节点重要度以及内容流行度对缓存资源和内容进行集中缓存决策,使得内容在不同的节点进行合理的缓存.仿真结果表明,通过评估缓存大小对缓存性能的影响,PSO缓存决策方法取得了比LCE、PROB缓存决策策略更优的缓存命中率和路径延展率,明显降低了缓存节点的缓存替换数,使得缓存达到了整体缓存优化.     

基于概率的启发式ICN缓存内容放置方法

提出一种基于概率存储的启发式住处中心网络内容缓存方法（PCP）。主要思想是请求消息和数据消息在传输过程中统计必要信息,当数据消息返回时,沿途各缓存节点按照一定概率决策是否在本地缓存该内容。设计缓存概率时综合考虑内容热度和缓存放置收益,即内容热度越高,放置收益越大的内容被缓存的概率越高。实验结果表明,PCP在缓存服务率、缓存命中率、平均访问延迟率等方面,与现有方法相比具有显著优势,同时PCP开销较小。     

基于节点介数和替换率的内容中心网络网内缓存策略

网内缓存技术是内容中心网络(CCN)的关键技术之一,CCN采用传统的ALWAYS缓存策略,会造成较大冗余。改进的Betw方案仅考虑了节点介数,容易造成高介数节点缓存更替频繁,内容可用性下降。为了解决这个问题,该文提出一种综合使用网络节点介数和节点缓存内容更替速率作为缓存决策度量的新型网内缓存策略BetwRep,通过权衡节点位置重要性和缓存内容时效性实现回传内容的最佳放置。最后,基于ndnSIM平台进行的网络仿真表明,该文提出的BetwRep缓存策略取得了比Betw方案和ALWAYS方案更低的源端请求负载和更少的平均跳数。     

基于收益感知的信息中心网络缓存机制

针对信息中心网络（ICN）内置缓存系统中的海量内容块流行度获取和存储资源高效利用问题,以最大化节省内容访问总代价为目标,建立针对内容块流行度的缓存收益优化模型,提出了一种基于收益感知的缓存机制。该机制利用缓存对请求流的过滤效应,在最大化单点缓存收益的同时潜在地实现节点间协作和多样化缓存;使用基于布隆过滤器的滑动窗口策略,在检测请求到达间隔时间的同时兼顾从源服务器获取内容的代价,捕获缓存收益高的内容块。分析表明,该方法能够大幅压缩获取内容流行度的存储空间开销;仿真结果表明,该方法能够较为准确地实现基于流行度的缓存收益感知,且在内容流行度动态变化的情况下,在带宽节省和缓存命中率方面更具优势。     

CCN中基于替换率的缓存空间动态借调机制

针对内容中心网络(CCN, content centric networking)节点存储资源的有效利用和优化配给问题,在同质化缓存分配的基础上,提出了一种基于替换率的缓存空间动态借调机制。该机制从节点存储空间使用状态的动态差异性出发,首先对于缓存资源借调的合理性给予证明,进而,依据节点对于存储资源的需求程度,动态地执行缓存借调,将相对空闲的存储资源分配给需求程度更大的节点支配,换取过载节点缓存性能的提升。该机制减小了内容请求跳数,提高了缓存命中率,以少量额外的代价换取了内容请求开销的显著下降,提升了存储资源整体利用率,仿真结果验证了其有效性。     

ENROUTE: An Entropy Aware Routing Scheme for Information-Centric Networks (ICN)

With the exponential growth of end users and web data, the internet is undergoing the change of paradigm from a user-centric model to a content-centric one, popularly known as information-centric networks (ICN). Current ICN research evolves around three key-issues namely (i) content request searching, (ii) content routing, and (iii) in-network caching scheme to deliver the requested content to the end user. This would improve the user experience to obtain requested content because it lowers the download delay and provides higher throughput. Existing researches have mainly focused on on-path congestion or expected delivery time of a content to determine the optimized path towards custodian. However, it ignores the cumulative effect of the link-state parameters and the state of the cache, and consequently it leads to degrade the delay performance. In order to overcome this shortfall, we consider both the congestion of a link and the state of on-path caches to determine the best possible routes. We introduce a generic term entropy to quantify the effects of link congestion and state of on-path caches. Thereafter, we develop a novel entropy dependent algorithm namely ENROUTE for searching of content request triggered by any user, routing of this content, and caching for the delivery this requested content to the user. The entropy value of an intra-domain node indicates how many popular contents are already cached in the node, which, in turn, signifies the degree of enrichment of that node with the popular contents. On the other hand, the entropy for a link indicates how much the link is congested with the traversal of contents. In order to have reduced delay, we enhance the entropy of caches in nodes, and also use path with low entropy for downloading contents. We evaluate the performance of our proposed ENROUTE algorithm against state-of-the-art schemes for various network parameters and observe an improvement of 29–52% in delay, 12–39% in hit rate, and 4–39% in throughput.

     

基于内容流行度和节点中心度匹配的信息中心网络缓存策略

在信息中心网络(Information-Centric Network, ICN)中,利用网络内置缓存提高内容获取及传输效率是该网络构架最重要的特性。然而,网络内置的缓存存在应对大量的需要转发的内容时能力相对弱小,对内容放置缺乏均衡分布的问题。该文提出基于内容流行度和节点中心度匹配的缓存策略(Popularity and Centrality Based Caching Scheme, PCBCS),通过对经过的内容进行选择性缓存来提高内容分发沿路节点的缓存空间使用效率,减少缓存冗余。仿真结果表明,该文提出的算法和全局沿路缓存决策方案,LCD(Leave Copy Down)以及参数为0.7及0.3的Prob(copy with Probability)相比较,在服务器命中率上平均减少30%,在命中缓存内容所需的跳数上平均减少20%,最重要的是,和全局沿路缓存决策方案相比总体缓存替换数量平均减少了40%。     

Dynamic Probabilistic Caching Algorithm with Content Priorities for Content‐Centric Networks

This paper presents a caching algorithm that offers better reconstructed data quality to the requesters than a probabilistic caching scheme while maintaining comparable network performance. It decides whether an incoming data packet must be cached based on the dynamic caching probability, which is adjusted according to the priorities of content carried by the data packet, the uncertainty of content popularities, and the records of cache events in the router. The adaptation of caching probability depends on the priorities of content, the multiplication factor adaptation, and the addition factor adaptation. The multiplication factor adaptation is computed from an instantaneous cache‐hit ratio, whereas the addition factor adaptation relies on a multiplication factor, popularities of requested contents, a cache‐hit ratio, and a cache‐miss ratio. We evaluate the performance of the caching algorithm by comparing it with previous caching schemes in network simulation. The simulation results indicate that our proposed caching algorithm surpasses previous schemes in terms of data quality and is comparable in terms of network performance.     

基于内容价值的缓存替换策略

缓存替换机制是内容中心网络的重要研究问题之一,考虑到缓存空间的有限性,合理地对缓存内容进行置换,成为影响网络整体性能的关键因素。因此,设计了一种基于内容价值的缓存替换方案。该方案综合考虑了内容的动态流行度、缓存代价以及最近被请求的时间,构建了更实际的内容价值函数,并依据该内容价值函数,设计了有效的内容存储与置换方案。具体地,当缓存空间不足时,对已有缓存内容按照价值从小到大进行置换。仿真结果表明,相比于传统替换算法 LRU、LFU 和 FIFO,本文提出的方案有效地提升了网络节点的内容缓存命中率,降低了用户获取内容的平均跳数。     

内容中心网络中面向隐私保护的协作缓存策略

针对内容中心网络节点普遍缓存带来的隐私泄露问题,在兼顾内容分发性能的基础上,该文提出一种面向隐私保护的协作缓存策略。该策略从信息熵的角度提出隐私度量指标,以增大攻击者的不确定度为目标,首先对于缓存策略的合理性给予证明;其次,通过构建空间匿名区域,扩大用户匿名集合,增大缓存内容的归属不确定性。缓存决策时,针对垂直请求路径和水平匿名区域,分别提出沿途热点缓存和局域hash协同的存储策略,减小缓存冗余和隐私信息泄露。仿真结果表明,该策略可减小内容请求时延,提高缓存命中率,在提升内容分发效率的同时增强了用户隐私保护水平。     

命名数据网络中基于内容请求相关性的协作缓存算法

针对命名数据网络(Named Data Networking, NDN)存储空间的有效利用和应答内容的高效缓存问题,该文采用差异化缓存的方式,提出一种依据内容请求序列相关性的协作缓存算法。在内容请求中,预先发送对于后续相关数据单元的并行预测请求,增大内容请求的就近响应概率;缓存决策时,提出联合空间存储位置与缓存驻留时间的2维差异化缓存策略。根据内容活跃度的变化趋势,空间维度上逐跳推进内容存储位置,时间维度上动态调整内容缓存时间,以渐进式的方式将真正流行的请求内容推送至网络边缘存储。该算法减小了内容请求时延和缓存冗余,提高了缓存命中率,仿真结果验证了其有效性。     

Node centrality metric based caching mechanism in content-centric network

In order to reduce the cache redundancy as well as increase the cache hit ratios in content-centric networks,the node centrality metric based caching mechanism (CMC) was proposed.CMC utilized controllers to obtain the topology of the whole network and the idle rate of cache space.According to the connection relation of the topology,the degree centrality,closeness centrality and betweenness centrality of nodes were calculated.When CMC choose the caching nodes,it took the three metrics and the idle rate of cache space into account.Simulation results show that CMC can effectively increase the cache hit ratios and reduce the content fetching hops and average request delay compared with the traditional routing algorithms in CCN.     

COD: caching on demand in information-centric networking

By overcoming the well-known challenges of the current internet, great expectations are focused on information-centric networking (ICN). ICN extensively uses universal in-network caching. However, developing an efficient caching scheme remains an open question. To overcome the useless caching and duplication caching of previous caching schemes, we propose an adaptive caching scheme—caching on demand (COD). By following the change in potential demand from the consumer and the temporal patterns of content popularity, COD allows content to be cached only by some necessary nodes instead of all nodes on the path from content provider to content consumer. At the same time, in accordance with trading off bandwidth for cache (bandwidth-for-cache), content can be pushed to the adjacent node with more cache capacity. We present a theoretical model to evaluate cache usage for COD. Finally, we evaluate COD through extensive experiments and a wide range of performance metrics. The experimental results under diverse setting demonstrate that COD can yield a steady improvement of network performance and caching efficiency compared with CEE, EgoBetw and Probcache. Notably, COD improves performance with negligible overhead.     

基于内容分块流行度分级的信息中心网络缓存策略

信息中心网络(ICN:Information-Centric Networking)域内缓存机制的研究大多假定单个内容的流行度相同,而忽视了同一内容的不同分块具有不同流行度的特性.本文提出了一种基于内容分块流行度以及缓存节点位置的分级缓存策略,通过兴趣包和数据包携带标签的方式实现隐式缓存协作.仿真实验证明相比于其他方案,该方案可以充分利用细粒度的内容分块流行度这一特性,提高缓存路由器缓存命中率,减小用户请求内容时延以及网络流量,进而提升用户对实时业务的服务体验.     

Multi-tier cooperative caching in fog radio access network

Aiming at the problem of reducing the load of the backward link in the edge buffer and fog wireless access network technology,a multi-tier cooperative caching scheme in F-RAN was proposed to further reduce the backhaul traffic load.In particular,by considering the network topology,content popularity prediction and link capacity,the optimization problem was decomposed into knapsack subproblems in multi-tiers,and effective greedy algorithms were proposed to solve the corresponding subproblems.Simulation results show that the proposed multi-tier cooperative caching scheme can effectively reduce the backhaul traffic and achieve relatively high cache hit rate.     

Cooperative caching for content dissemination in vehicular networks

The explosive growth of mobile data traffic has made cellular operators to seek low‐cost alternatives for cellular traffic off‐loading. In this paper, we consider a content delivery network where a vehicular communication network composed of roadside units (RSUs) is integrated into a cellular network to serve as an off‐loading platform. Each RSU subjecting to its storage capacity caches a subset of the contents of the central content server. Allocating the suitable subset of contents in each RSU cache such that maximizes the hit ratio of vehicles requests is a problem of paramount value that is targeted in this study. First, we propose a centralized solution in which, we model the cache content placement problem as a submodular maximization problem and show that it is NP‐hard. Second, we propose a distributed cooperative caching scheme, in which RSUs in an area periodically share information about their contents locally and thus update their cache. To this end, we model the distributed caching problem as a strategic resource allocation game that achieves at least 50% of the optimal solution. Finally, we evaluate our scheme using simulation for urban mobility simulator under realistic conditions. On average, the results show an improvement of 8% in the hit ratio of the proposed method compared with other well‐known cache content placement approaches.     

命名数据网络中基于局部请求相似性的协作缓存路由机制

该文针对命名数据网络(Named Data Networking, NDN)应答内容的高效缓存和利用问题,依据内容请求分布的局域相似特征,提出一种协作缓存路由机制。缓存决策时,将垂直请求路径上的冗余消除和水平局域范围内的内容放置进行有效结合。垂直方向上,提出基于最大内容活跃因子的路径缓存策略,确定沿途转发对应的最大热点请求区域;水平方向上,采用一致性Hash协同缓存思想,实现应答内容的局域定向存储。路由查找时,将局域节点缓存引入到路由转发决策中,依据内容活跃等级动态执行局域缓存查找,增大内容请求就近响应概率。该机制减小了内容请求时延和缓存冗余,提高了缓存命中率,以少量额外的代价换取了内容请求开销的大幅下降,仿真结果验证了其有效性。     

雾无线接入网中基于Q-learning的协作式内容缓存策略

为了提高雾无线接入网（Fog-Radio Access Networks,F-RAN）的边缘缓存效率,提出一种基于用户偏好预测和内容流行度预测的协作式内容缓存策略。首先,利用主题模型中隐含狄利克雷分布（Latent Dirichlet Allocation,LDA）模型动态的预测用户偏好;其次,利用网络中不同设备之间的拓扑关系和已预测的用户偏好以在线的方式预测内容流行度的变化,然后再结合基站之间的相关度,以减少缓存内容文件的重复率;最后,以最大化缓存命中率为目标,利用强化学习中的Q-learning算法获得了最优的内容缓存策略。仿真结果表明,与其他内容缓存策略相比,该内容缓存策略能有效的提高缓存命中率。      

Design of in-network caching scheme in CCN based on grey relational analysis

In-network caching is one of the most important issues in content centric networking （CCN）, which may extremely influence the performance of the caching system. Although much work has been done for in-network caching scheme design in CCN, most of them have not addressed the multiple network attribute parameters jointly during caching algorithm design. Hence, to fill this gap, a new in-network caching based on grey relational analysis （GRA） is proposed. The authors firstly define two newly metric parameters named request influence degree （RID） and cache replacement rate, respectively. The RID indicates the importance of one node along the content delivery path from the view of the interest packets arriving The cache replacement rate is used to denote the caching load of the node. Then combining hops a request traveling from the users and the node traffic, four network attribute parameters are considered during the in-network caching algorithm design. Based on these four network parameters, a GRA based in-network caching algorithm is proposed, which can significantly improve the performance of CCN. Finally, extensive simulation based on ndnSIM is demonstrated that the GRA-based caching scheme can achieve the lower load in the source server and the less average hops than the existing the betweeness （Betw） scheme and the ALWAYS scheme.