Architectural Options for the Next-Generation Networking Paradigm: Is Optical Internet the Answer?

Recent advances in optical networking technologies are setting the foundation for the next-generation data-centric networking paradigm, an “Optical Internet”. This work addresses one of the most challenging issues facing today's service providers and data vendors; how will the SONET/SDH-based legacy infrastructure currently in place make a graceful transition to the next generation networking paradigm?

A simplified, two-tiered architecture that requires two types of sub-systems will set the stage for a truly optical internet: service delivery platforms that enforce service policies; and transport platforms that intelligently deliver the necessary bandwidth to these service platforms. If IP can be mapped directly onto the WDM layer, some of the unnecessary network layers can be eliminated, opening up new possibilities for the potential of collapsing today's vertically layered network architecture into a horizontal model where all network elements work as peers to dynamically establish optical paths through the network. This paper presents a balanced view of the vision of the next-generation optical internet

The work presented here builds on the IETF multi-protocol lambda switching (MPλS) initiative and addresses the implementation issues of the path selection component of the traffic-engineering problem in a hybrid IP-centric DWDM-based optical network. An overview of the methodologies and associated algorithms for dynamic lightpath computation is presented. Specifically, we show how the complex problem of real-time provisioning of optical channels can be simplified by using a simple dynamic constraint-based routing and wavelength assignment (RWA) algorithm that compute solutions to three sub-problems: (a) routing; (b) constrained-based shortest-route selection; (c) wavelength assignment.

We present two different schemes for dynamic provisioning of the optical channels. The two schemes use the same dynamic lightpath computation approach proposed here, except that the third component, that is the wavelength assignment algorithm and its implementation, is different for each of the two schemes.

     

智能产品配网绑定时效问题的定位方法

本文针对智能产品配网绑定耗时偏长又极难排查的行业性问题，对业界应用最广的“Soft AP”和“快联”机制进行细致分析后，提出了通过智能手机终端、智能产品终端、智能产品服务后台联合抓包来定位配网绑定时效问题的方法.将该方法应用于智能热水器、智能空调等产品后，成功定位到影响配网绑定时效的关键环节和因素.以此为依据的优化措施有效降低了产品配网绑定的耗时，显著提升了用户体验.     

融合的蜂窝网络/无线局域网中资源管理的性能分析

Wireless Local Area Network (WLAN) with high data bit rates can be used with cellular network to achieve higher level of Quality of Service (QoS) by sharing their total resources efficiently. The integration between cellular and WLAN networks should be ensured considering different channel allocation strategies of both networks and efficient resource management techniques should be developed. In this paper, we propose a new call admission scheme to use the coupled resource effectively. The proposed scheme, by taking the different resource sharing strategies for two access networks, limits the new, horizontal and vertical handoff voice and data call arrivals with respect to their call level QoS requirements. Numerical results show that the proposed integrated cellular/WLAN network model uses the resources more effectively and achieves all upper bound QoS requirements for voice and data users as compared with the non integrated network model.     

An Operation Support System Architecture and Process for Optical Access Network Allocation During Service Provisioning

An operation support system architecture has been developed for network element allocation in optical access networks (OANs). Rather than deploying OAN elements to meet all potential customer demand, which would be very costly, only enough elements to meet current demand are installed. These elements are then allocated during service provisioning. The sequence of element allocation and re-allocation is controlled because OANs consist of various types of elements, including outside fibers, inside fibers, and equipment. Functions are provided for allocating each type of element; also provided is an allocation integration function to control the element allocation processes. Moreover, an efficient process for allocating the elements has been determined: first, the outside fiber is allocated, then the equipment, and finally the inside fiber.     

Overview on MPLS Virtual Private Networks

The basic idea, features, and necessity of multiprotocol label switching (MPLS) are given in this paper, with a special focus on virtual private networks (VPN) as one of the most important features that MPLS as technology enables and supports. In this context, we first describe the general VPN models, the overlay and the peer model, and than analyze different models, such as the BGP/MPLS virtual private networks and the layer-2 MPLS virtual private networks. All over the paper, the benefits provided by using MPLS for different VPN models are emphasized, with particular attention to improved scalability, management, and quality of service (QoS).     

面向城域网的多业务提供平台技术

多业务传输平台技术是为了兼容目前城域网大量应用的TDM业务,同时满足日益增长的数据业务的要求而提出的,这种传输平台能更好地承载基于分组交换的数据业务,同时保证语音业务的高质量和可靠性。文中简要概括了多业务传输平台技术的基本特点、种类及其若干关键技术。     

A cost‐efficient resource provisioning algorithm for DHT‐based cloud storage systems

Personal cloud storage provides users with convenient data access services. Service providers build distributed storage systems by utilizing cloud resources with distributed hash table (DHT), so as to enhance system scalability. Efficient resource provisioning could not only guarantee service performance, but help providers to save cost. However, the interactions among servers in a DHT‐based cloud storage system depend on the routing process, which makes its execution logic more complicated than traditional multi‐tier applications. In addition, production data centers often comprise heterogeneous machines with different capacities. Few studies have fully considered the heterogeneity of cloud resources, which brings new challenges to resource provisioning. To address these challenges, this paper presents a novel resource provisioning model for service providers. The model utilizes queuing network for analysis of both service performance and cost estimation. Then, the problem is defined as a cost optimization with performance constraints. We propose a cost‐efficient algorithm to decompose the original problem into a sub‐optimization one. Furthermore, we implement a prototype system on top of an infrastructure platform built with OpenStack. It has been deployed in our campus network. Based on real‐world traces collected from our system and Dropbox, we validate the efficiency of our proposed algorithms by extensive experiments. Copyright © 2016 John Wiley & Sons, Ltd.     

内容中心网络中基于点击量的内容提供机制研究(英文)

In-network caching and Interest packets aggregation are two important features of Content-Centric Networking(CCN).CCN routers can directly respond to the Interest request by Content Store(CS)and aggregate the same Interest packets by Pending Interest Table(PIT).In this way,most popular content requests will not reach the origin content server.Thus,content providers will be unaware of the actual usages of their contents in network.This new network paradigm presents content providers with unprecedented challenge.It will bring a great impact on existing mature business model of content providers,such as advertising revenue model based on hits amount.To leverage the advantages of CCN and the realistic business needs of content providers,we explore the hits-based content provisioning mechanism in CCN.The proposed approaches can avoid the unprecedented impact on content providers' existing business model and promote content providers to embrace the real deployment of CCN network.     

Broker-based SLA-aware composite service provisioning

QoS-aware service composition aims to satisfy users’ quality of services (QoS) needs during service composition. Traditional methods simply attempt to maximize user satisfaction by provisioning the composite service instance with the best QoS. These “best-effort” methods fail to take into account that there also exist other consumers competing for the service resources and their decisions of service selection/composition can impact on QoS. Since user's QoS needs can be met once the demanded level is reached, in this paper, we propose an “on-demand” strategy for QoS-aware service composition to replace the traditional “best-effort” strategy. The service broker is introduced to facilitate implementation of this strategy: it first purchases a number of service instances for each component from providers and then provisions the composite services with different QoS classes to consumers. This paper focuses on how the broker follows the service level agreement (SLA) to provision composite services in the “on-demand” manner. This problem is formally expressed as the minimization of the QoS distance function between SLA and QoS of composite service instances, under a series of constraints. Heuristic approaches are proposed for the problem and experiments are conducted at last to verify their effectiveness and efficiency.     

Resource management for bursty streams on multi-tenancy cloud environments

The number of applications that need to process data continuously over long periods of time has increased significantly over recent years. The emerging Internet of Things and Smart Cities scenarios also confirm the requirement for real time, large scale data processing. When data from multiple sources are processed over a shared distributed computing infrastructure, it is necessary to provide some Quality of Service (QoS) guarantees for each data stream, specified in a Service Level Agreement (SLA). SLAs identify the price that a user must pay to achieve the required QoS, and the penalty that the provider will pay the user in case of QoS violation. Assuming maximization of revenue as a Cloud provider’s objective, then it must decide which streams to accept for storage and analysis; and how many resources to allocate for each stream. When the real-time requirements demand a rapid reaction, dynamic resource provisioning policies and mechanisms may not be useful, since the delays and overheads incurred might be too high. Alternatively, idle resources that were initially allocated for other streams could be re-allocated, avoiding subsequent penalties. In this paper, we propose a system architecture for supporting QoS for concurrent data streams to be composed of self-regulating nodes. Each node features an envelope process for regulating and controlling data access and a resource manager to enable resource allocation, and selective SLA violations, while maximizing revenue. Our resource manager, based on a shared token bucket, enables: (i) the re-distribution of unused resources amongst data streams; and (ii) a dynamic re-allocation of resources to streams likely to generate greater profit for the provider. We extend previous work by providing a Petri-net based model of system components, and we evaluate our approach on an OpenNebula-based Cloud infrastructure.