Autonomous decentralized community communication for information dissemination

To meet the increasing demand for real-time content delivery, the proposed autonomous decentralized community communication system offers an efficient information dissemination infrastructure with a decentralized architecture. ADCC's aim is to help end-user communities communicate and exchange information efficiently; to meet this goal, the system uses an application-level multicast technique that arbitrarily scales to large groups. The ADCC system also features a scalable community construction and maintenance scheme that eases the burden of organizing an online community network.     

A generic architecture for autonomic service and network management

As the Internet evolves into an all-IP communication infrastructure, a key issue to consider is that of creating and managing IP-based services with efficient resource utilization in a scalable, flexible, and automatic way. In this paper, we present the Autonomic Service Architecture (ASA), a uniform framework for automated management of both Internet services and their underlying network resources. ASA ensures the delivery of services according to specific service level agreements (SLAs) between customers and service providers. As an illustrative example, ASA is applied to the management of DiffServ/MPLS networks, where we propose an autonomic bandwidth sharing scheme. With the proposed scheme, the bandwidth allocated for each SLA can be automatically adjusted according to the measured traffic load and under policy control for efficient resource utilization, while SLA compliance over the network is always guaranteed.     

Dynamic Partitioning and Popularity based Caching for Optimized Performance in content-centric fog networks: DPPCOP

With the massive growth of information generation, processing, and distribution in the Internet of Things (IoT), the existing cloud architectures need to be designed more effectively using fog networks. The current IP-address-based Internet architecture is unable to deliver the desired Quality-of-Service (QoS) towards the increasing demands of fog networking-based applications. To this end, Content-Centric Networking (CCN) has been developed as the potential future Internet architecture. CCN provides name-based content delivery and is established as an architecture for next-generation fog applications. The CCN-based fog environment uses the cache of in-network fog nodes to place the contents near the end-user devices. Generally, the caching capacity of the fog nodes is very small as compared to the content catalog size. Therefore, efficient content placement decisions are vital for improving the network performance. To enhance the content retrieval performance for the end-users, a novel content caching scheme named “Dynamic Partitioning and Popularity based Caching for Optimized Performance (DPPCOP)” has been proposed in this paper. First, the proposed scheme partitions the fog network by grouping the fog nodes into non-overlapping partitions to improve content distributions in the network and to ensure efficient content placement decisions. During partitioning, the scheme uses the Elbow method to obtain the “good” number of partitions. Then, the DPPCOP scheme analyzes the partition’s information along with the content popularity and distance metrics to place the popular contents near the end-user devices. Extensive simulations on realistic network topologies demonstrate the superiority of the DPPCOP caching strategy on existing schemes over various performance measurement parameters such as cache hit ratio, delay, and average network traffic load. This makes the proposed scheme suitable for next-generation CCN-based fog networks and the futuristic Internet architectures for industry 4.0.     

Efficient algorithms for block-cyclic array redistribution betweenprocessor sets

Run-time array redistribution is necessary to enhance the performance of parallel programs on distributed memory supercomputers. In this paper, we present an efficient algorithm for array redistribution from cyclic(x) on P processors to cyclic(Kx) on Q processors. The algorithm reduces the overall time for communication by considering the data transfer, communication schedule, and index computation costs. The proposed algorithm is based on a generalized circulant matrix formalism. Our algorithm generates a schedule that minimizes the number of communication steps and eliminates node contention in each communication step. The network bandwidth is fully utilized by ensuring that equal-sized messages are transferred in each communication step. Furthermore, the time to compute the schedule and the index sets is significantly smaller. It takes O(max(P, Q)) time and is less than 1 percent of the data transfer time. In comparison, the schedule computation time using the state-of-the-art scheme (which is based on the bipartite matching scheme) is 10 to 50 percent of the data transfer time for similar problem sizes. Therefore, our proposed algorithm is suitable for run-time array redistribution. To evaluate the performance of our scheme, we have implemented the algorithm using C and MPI on an IBM SP2. Results show that our algorithm performs better than the previous algorithms with respect to the total redistribution time, which includes the time for data transfer, schedule, and index computation     

Scattercast: an adaptable broadcast distribution framework

Internet broadcasting - the simultaneous distribution of live content streams to a large audience - has a number of interesting applications ranging from real-time broadcasts of audio/video streams for online concerts or sporting events to efficient and reliable large-scale software distribution. We identify three fundamental requirements for scalable broadcasting services: an efficient infrastructure for large-scale broadcasting, an ability to adapt the infrastructure to suit the requirements of a wide range of applications, and ease of deployment of the infrastructure. Although solutions such as the network-layer IP multicast approach and a slew of overlay distribution networks exist today, none of these technologies satisfactorily addresses all of the above concerns. In this paper, we argue that an application-customizable hybrid overlay is well suited to meet these challenges. To this end, we propose an architecture called scattercast that relies on a network of strategically located agents called ScatterCast proXies or SCXs. These agents collaboratively provide the broadcast service for a session. Clients locate a nearby SCX and tap into the session via that SCX. Scattercast constructs a hybrid overlay network composed of unicast links between SCXs that interconnect locally scoped multicast regions. Rather than define a single standardized service model for transmitting data on top of the overlay, scattercast builds a customizable transport framework that provides adaptability by leveraging application-defined semantics to drive the distribution of content. We demonstrate the ability of our architecture to provide efficient distribution via a set of simulation experiments. Finally, we present our experience with the adaptability of the framework by describing two applications, a real-time Internet radio and an online slide-presentation tool, both of which we have built on top of a prototype implementation of the architecture.Received: 15 March 2002, Accepted: 2 October 2002,     

多路路由算法及其在QoS路由中的应用

提出一个分布式服务质量路由算法,以求在不影响已存在连接的服务质量的前提下,寻找满足服务质量要求的可行路,该算法根据网络运营状况不同,改变寻路范围,当网络资源很充裕,寻路花费可忽略,可行路的存在性是首要问题时,寻路范围可以是整个网络,使得只要存在可行路,就一定能找到;当网络资源匮乏,寻路信息应尽可能少时,寻路范围将减少,直至每点只向一个邻点发送寻路信息,但其接通率不少于最短路算法。     

中国大陆CDN的测量方法研究与性能分析

内容分发网络CDN根据网络的实时环境,对用户请求的内容进行合理的分发,可以有效避免网络拥塞,优化用户体验。CDN已经成为网络基本架构中非常重要的部分。针对CDN的测量,对于分析CDN网络性能、优化CDN网络结构进而提升服务质量都有重要的意义。然而,由于缺乏有效的测量方法,以及中国大陆网络基础设施服务的复杂性,针对中国大陆CDN测量的研究还比较欠缺。提出一种基于HTTP代理服务器作为测量源的CDN测量技术,通过对中国大陆的主要CDN服务商进行广泛深入的测量,获取到不同CDN服务商的节点分布,并分析了CDN节点的部署策略、负载均衡以及不同CDN服务商的节点调度策略。     

内容中心网络中基于区域集中化控制的协作缓存路由机制*

针对在内容中心网络(Content Centric Networking, CCN)中如何合理放置与高效利用应答数据的问题,该文将集中化控制的思想引入到内容缓存与查找中,提出一种协作缓存路由机制。缓存决策时,通过兴趣包和数据包携带标签的方式,确定沿途最大缓存收益区域;在最大缓存收益区域内,结合内容全局活跃度和节点可用缓存空间,选择内容最佳放置位置。路由查找时,将区域内容放置与路由转发相结合,增大缓存资源可用性。仿真结果表明,与经典算法相比,该机制以少量额外的开销提高了缓存命中率和跳数减少率,改善了缓存负载分布均衡性,提升了CCN网络缓存和传输效率。     

移动边缘计算中一种贪心策略的内容卸载方案

基于移动边缘计算的内容卸载技术可以有效降低骨干网络的流量压力，提升终端用户体验。针对终端用户与小基站之间的异质接触率，设计了一种贪心策略的内容卸载方案。首先，将内容最优卸载问题转化为内容最大投递率问题；其次，证明最大投递率问题满足子模性，在此基础上，采用贪心算法部署内容，该算法可以以概率（1-1/e）保证其最优性；最后，详细分析了内容流行度指数以及缓存大小对不同卸载方案的影响。实验结果表明，所提方案提高了内容投递率同时降低了内容传输时延。     

Towards efficient device-to-device multicast content delivery with social awareness

Frequent content retrieval leads to significant energy consumption in cellular networks. Thereby, device-to-device (D2D) communication is used for proximal content delivery. Be aware that social friends may have common content interests, D2D content delivery is further improved by considering social network. However, how to implement efficient D2D multicast with the aid of social relationship needs further consideration. In this paper, with a proposed architecture on combined networks, the cooperation range of content sharing is investigated for D2D multicast to minimize the average energy consumption of serving a content request. Based on combined networks, a cooperation group formation scheme is proposed. Simulation results verify our analyzes and the advantage of proposed scheme.     

Efficient algorithms to solve the link-orientation problem for multi-square, convex-bipartite, and convex-split networks

This paper studies the issue of assigning orientations to all links of an undirected network, which is called the link-orientation problem (LOP). First, we describe some practical variations and address some complexity analysis in LOPs for general networks. Then, we design efficient algorithms to solve these LOPs issues. The proposed approach employs the recursive shortest path rules and the efficient cost cores scheme to resolve the LOP issues for some weighted network systems. These classes of networks include multi-square, convex-bipartite, and convex-split networks. Next, we use the cost core algorithm for adjusting LOP and obtain the more efficient LOP for the weighted convex-bipartite and convex-split networks. In general, the LOP scheme can support the actual applications requirements to realize a WFQ (weighted fair queuing) task for multicast routing in real networks. Finally, the findings of this paper can be mainly applied to some network applications, including efficient revision of load balancing in a ATM switch network, quick selection of a firm’s PCS (Proxy Cache Server) on the Web, and dynamic adjusting of link’s changing conditions in a workflow system on the Internet.     

Estimating the long-term cost to serve new customers in joint distribution

One of the most important concerns for logistics service providers is to identify the distribution cost to serve each new customer for pricing. Compared to the analysis through cost allocation on delivery routes, cost estimation possesses the advantage of robust costing rules but is a very challenging problem due to the complex collaborative mechanisms of distribution. Based on the activities leading to a distribution cost, we analyze the relationship between multiple geographic factors and cost, and then construct appropriate attributes for estimation. Combining a data selection approach and regression or artificial neural network techniques, a prediction scheme is proposed to build models, and an explicit continuous approximation model is suggested for efficient implementation. Computational experiments demonstrate the importance of the constructed attributes and the accuracy of the proposed cost estimation method. The impacts from cost stability and delivery frequency are examined to provide further explanation and support for practical implementation.     

Multi-message and multi-receiver heterogeneous signcryption scheme for ad-hoc networks

Security is a significant issue for ad-hoc networks. Heterogeneous signcryption schemes proposed in recent years satisfy privacy and authentication of messages and reduce cost of computation and communication in a logical step. In this article, we present a new efficient heterogeneous signcryption scheme that shifts between the public key infrastructure (PKI) and the identity-based cryptosystem (IBC). The proposed scheme is suitable for broadcast communication conditions in which senders can signcrypt multiple messages for multiple receivers simultaneously in the ad-hoc networks. This scheme is proved to satisfy confidentiality and unforgeability on the basis of the assumptions of bilinear Diffie-Hellman problem (BDHP), q-Diffie-Hellman inversion problem (q-DHIP), q-bilinear Diffie-Hellman inversion problem (q-BDHIP), and computational Diffie-Hellman problem (CDHP) in the random oracle model. We discuss the efficiency of our scheme theoretically. In the efficiency analysis phase, we show that our scheme is practical and efficient. In the performance analysis phase, we present additional tests, data, and explanations to prove that our scheme can be applied in ad-hoc networks. Finally, we apply our scheme to a simulated ad-hoc network.     

From content delivery today to information centric networking

Today, content delivery is a heterogeneous ecosystem composed by various independent infrastructures. The ever increasing growth of Internet traffic has encouraged the proliferation of different architectures to serve content provider needs and user demand. Despite the differences among the technology, their low level implementation can be characterized in a few fundamental building blocks: network storage, request routing, and data transfer. Existing solutions are inefficient because they try to build an information centric service model over a network infrastructure which was designed to support host-to-host communications. The Information-Centric Networking (ICN) paradigm has been proposed as a possible solution to this mismatch. ICN integrates content delivery as a native network feature. The rationale is to architect a network that automatically interprets, processes, and delivers content (information) independently of its location. This paper makes the following contributions: (1) it identifies a set of building blocks for content delivery, (2) it surveys the most popular approaches to realize the above building blocks, (3) it compares content delivery solutions relying on the current Internet infrastructure with novel ICN approaches.     

Towards efficient and practical network coding in delay tolerant networks

Network coding techniques offer an emerging solution to efficient data transmission in Delay Tolerant Networks (DTN). To date, abundant techniques have been developed on exploiting network coding in DTN, however, most of them bring additional overhead due to the extra coded message redundancy. In this paper, we analyze the coded message redundancy issue, and then propose NTC, an efficient network coding scheme for DTN. In NTC, a novel metric named “redundancy ratio” is introduced within the anti-entropy message exchange process. We also discuss the design and implementation of practical NTC in detail. To evaluate the performance of our proposed NTC scheme, we implement NTC in ONE, the current state-of-the-art simulator for DTN. Simulation results show that, comparing with existing schemes, our proposed NTC scheme has significant advantages in enhancing the message delivery ratio and reducing the transmission overhead.     

An encounter-based multicast scheme for disruption tolerant networks

Some ad hoc network scenarios are characterized by frequent partitions and intermittent connectivity. Hence, existing ad hoc routing schemes that assume that an end-to-end path exists from a source to a destination do not work in such challenging environment. A store-and-forward network architecture known as the disruption tolerant network (DTN) has been designed for such challenging network environments. Several unicast and multicast routing schemes have been designed for DTNs. However, the existing multicast routing schemes assume a route discovery process that is similar to the existing ad hoc network routing approach. Thus, in this paper, we design an encounter-based multicast routing (EBMR) scheme for DTNs which uses fewer hops for message delivery. We first describe how the EBMR scheme works and then present an analytical framework to estimate the delivery performance of the EBMR scheme. Next, we present some comparisons of the analytical and simulation results to show that our analytical framework provides delivery performance estimates that match closely the observed simulation results. Last but not least, we present simulation results to study the delivery performance of EBMR in different scenarios, e.g. different mobility models, different multicast group size, different number of multicast groups and different node speed. We also compare the performance of the EBMR scheme with other DTN multicast strategies. Our simulation results indicate that the EBMR scheme can achieve higher delivery ratio while maintaining high data transmission efficiency compared to other multicast strategies.     

Hybrid storage-based caching strategy for content delivery network services

This study proposes a novel caching scheme for content delivery network services. In general, video content users often watch the first part of video clips and then switch to other content. Therefore, a caching scheme is proposed, in which the first part of the frequently referenced content is stored on a solid state drive (SSD) while the remaining video content is stored on a hard disk drive (HDD),. The proposed hybrid (SSD/HDD) caching scheme offers several benefits, such as an improved average data output capacity due to the high average data rate and average hit capacity of the SSD. That is, performance can be significantly improved at a low extra cost with the cache server of a content delivery network (CDN).     

A novel ANN-based service selection model for ubiquitous computing environments

How to choose an appropriate service from all the usable services regardless of user's location and heterogeneous architecture of underlying software and hardware infrastructure is the most important study content in ubiquitous computing domain. In order to overcome the shortcomings of blindness and randomicity in traditional and improved trust-mechanism-based service selection models, we propose a novel ANN-based (Artificial Neural Network) service selection model (called the ANNSS model). We adopt a novel method which according to the earlier information of the cooperation between the devices and the context information, an ANN-based evaluation standard for the service quality of service provider is given out so that user can acquire an effective guidance and choose the most appropriate service. At the same time, we improved the traditional BP algorithm based on three-term method (called the TTMBP algorithm) consisting of a learning rate (LR), a momentum factor (MF) and a proportional factor (PF) in order to satisfy the requirements of time issue in real-time system. The convergence speed and stability were enhanced by adding the proportional factor. The self-adjusting architecture method is adopted so that a moderate scale of neural network can be obtained. We have implemented the ANNSS algorithm in an actual power supply system for communication devices and fulfilled various simulations. The results of simulation show that the proposed service selection scheme is not only scalable but also efficient, and that the novel BP algorithm based on three-term has high convergence speed and good convergence stability. The novel service selection scheme superior to the traditional and improved trust-mechanism-based service selection scheme. The novel scheme can exactly choose a most appropriate service from many service providers and provide the most perfect service performance to users.     

On demand synchronization and load distribution for database grid-based Web applications

With the availability of content delivery networks (CDN), many database-driven Web applications rely on data centers that host applications and database contents for better performance and higher reliability. However, it raises additional issues associated with database/data center synchronization, query/transaction routing, load balancing, and application result correctness/precision. In this paper, we investigate the issues in the context of data center synchronization for such load and precision critical Web applications in a distributed data center infrastructure. We develop a scalable scheme for adaptive synchronization of data centers to maintain the load and application precision requirements. A prototype has been built for the evaluation of the proposed scheme. The experimental results show the effectiveness of the proposed scheme in maintaining both application result precision and load distribution; adapting to traffic patterns and system capacity limits.     

短相遇接触时间网络环境中的时延容忍网络路由方案

为解决时延容忍网络在短接触时间下的路由问题,给出了一种短相遇接触时间网络环境中的时延容忍网络路由方案.该方案首先利用相遇接触时间、相遇间隔时间和消息时效等网络信息计算一跳传递概率和两跳传递概率,然后根据所得传递概率在当前接触节点和过去接触节点中选择转发节点,从而建立低成本路由.仿真性能分析结果表明:与其它经典的时延容忍网络路由方案相比,所给路由方案可以在降低路由成本的情况下,提高消息传递率,且能缩短平均时延.