Circuit-switched Networks Research Articles

Performance Analysis of Smart Optical Burst Switching Networks for Different Signaling Protocols

A future optical transport network needs an extremely high capacity to satisfy the rapid increase in traffic. Many technologies have been developed to increase throughput and energy efficiency and simplify the deployment of optical transport networks. Internet Protocol traffic transmission precedes optical transport networks in requiring new approaches for network nodes. Although optical fiber has a tremendous capacity, switching nodes limit the performance of optical networks. An optical burst switched network concept has been introduced as a promising solution to overcome this problem. Optical burst switched technology effectively utilizes the advantages of both circuit switching and packet switching networks, and also eliminates their drawbacks. Two important issues in achieving the best performance in optical burst switched networks are scheduling bursts and signaling protocols. In this paper, we provide a comprehensive analysis of optical burst switched signaling protocols. We study three protocols for signaling in optical burst switched networks that are used for various traffic types. The Tell-and-Wait and Just Enough Time protocols are used in extreme cases of loss-sensitive and delay-sensitive traffic, respectively. The third signaling protocol, called Intermediate Note Initiation, is a promising solution with an ability to adjust parameters depending upon traffic requirements. We analyze the blocking probability of core nodes with respect to the number of buffers and wavelengths for each signaling protocol. The simulation results show that when the number of optical buffers are five or higher, blocking probability tends to be zero, regardless of the number of wavelengths. Therefore, this tends to decrease loss due to a burst, and improves the overall performance of optical burst switched networks. The burst outstripping problem in optical fiber has been solved by determining a proper buffering policy for each burst, after considering the burst priorities and time delays between consistent bursts.

Optical multicast system for data center networks.

We present the design and experimental evaluation of an Optical Multicast System for Data Center Networks, a hardware-software system architecture that uniquely integrates passive optical splitters in a hybrid network architecture for faster and simpler delivery of multicast traffic flows. An application-driven control plane manages the integrated optical and electronic switched traffic routing in the data plane layer. The control plane includes a resource allocation algorithm to optimally assign optical splitters to the flows. The hardware architecture is built on a hybrid network with both Electronic Packet Switching (EPS) and Optical Circuit Switching (OCS) networks to aggregate Top-of-Rack switches. The OCS is also the connectivity substrate of splitters to the optical network. The optical multicast system implementation requires only commodity optical components. We built a prototype and developed a simulation environment to evaluate the performance of the system for bulk multicasting. Experimental and numerical results show simultaneous delivery of multicast flows to all receivers with steady throughput. Compared to IP multicast that is the electronic counterpart, optical multicast performs with less protocol complexity and reduced energy consumption. Compared to peer-to-peer multicast methods, it achieves at minimum an order of magnitude higher throughput for flows under 250 MB with significantly less connection overheads. Furthermore, for delivering 20 TB of data containing only 15% multicast flows, it reduces the total delivery energy consumption by 50% and improves latency by 55% compared to a data center with a sole non-blocking EPS network.

무선 IP 네트워크에서 전용선 모뎀 사용가능성 검증

A leased line modem usability was evaluated and investigated in the wireless internet protocol(IP) network. The signal of the modem in the circuit switching network was translated to IP packet by using several voice codecs (PCM, G.711A, G.711μ, and etc.) and transmitted through the wireless IP network. The wireless IP network was simulated by the Tactical information and communication network Modeling and simulation Software(TMS). The performance and usability of the leased line modem are simulated using the system-in-the-loop(SITL) function of TMS with respect to packet delay, jitter, packet discard ratio, codecs, and wireless link BER.

Archon: A Function Programmable Optical Interconnect Architecture for Transparent Intra and Inter Data Center SDM/TDM/WDM Networking

This paper reports all-optical, function programmable, transparent, intra- and inter-data center networking (DCN) using space and time-division multiplexing (SDM/TDM) within data centers and wavelength division multiplexing (WDM) between data centers. A multielement fiber is used for SDM transmission to provide a large quantity of optical links between the top-of-racks (ToRs) and the function programmable cluster switch. Beam-steering large-port-count fiber switches, used as central cluster switches and intercluster switch, provide a single hop optical circuit switching solution, and also enable network function programmability for DCN to support variable traffic patterns and different network functions. A TDM switch as a plug-in function provides intra-cluster communication with variable capacity and low latency. The flat-structured intra data center architecture, with a circuit-switched SDM and TDM hybrid network enables scalable, large-capacity and low-latency DCN communication. In addition, all-optical ToR-to-ToR inter-DCN is realized through metro/core networks. A highly-nonlinear fiber based all-optical SDM-to-WDM converter transfers three SDM signals to three-carrier spectral superchannel signals, which are transmitted to the destination DCN, through the metro/core networks. The all-optical ToR-ToR cross-DCN connections enable the geographically distributed DCNs to appear as one big data center.

Study and Development of Next-Generation Optical Networks

Next-generation optical networks are expected to provide tremendous capacity in order to support upcoming traffic increases. Many technologies are currently being developed for optical transport networks in order to increase throughput, improve energy efficiency and simplify network deployment. The most important problem in current optical networks is transmission of Internet protocol (IP) traffic. Regardless of the tremendous throughput with optical fibers, switching nodes still limit overall network performance. Recently, optical burst switching technology has been developed to overcome this problem. Optical burst switching combines the advantages of both circuit switching and packet switching networks and provides good performance in terms of packet data transmission. Even though optical burst switching networks provide a good mechanism for IP traffic transmission, overall performance is still limited because of access networks. Existing passive optical networks based on Ethernet technology are not fully compatible with optical burst switching, which results in bottlenecks on the border between transport and access networks. In this paper, we present a new method of optical wavelength time-division multiple access (OWTDMA) for passive optical networks. The proposed approach can provide outstanding scalability of network resources and can increase throughput of the optical access network. In addition, we propose implementation of OWTDMA in edge nodes of optical burst switching networks to eliminate bottlenecks between transport and access networks. Simulation results prove the advantage of our proposed approach.

A power consumption sensitivity analysis of circuit-switched versus packet-switched backbone networks

While telecommunication networks have historically been dominated by a circuit-switched paradigm, the last decades have seen a clear trend towards packet-switched networks. In this paper we evaluate how both paradigms (which have also been referred to as optical bypass and non-bypass, respectively) perform in optical backbone networks from a power consumption point of view, and whether the general agreement of circuit switching being more power-efficient holds. We consider artificially generated topologies of various sizes, mesh degrees and – not yet previously explored in this context – transport linerates. We cross-validate our findings with a number of realistic topologies.Our results show that circuit switching is preferable when the average node-to-node demands are higher than half the transport linerates. However, packet switching can become preferable when the traffic demands are lower than half the transport linerate. We find that an increase in the network node count does not consistently increase the energy savings of circuit switching over packet switching, but the savings are heavily influenced by the mesh degree and (to a minor extent) by the average link length. Our results are consistent for uniform traffic demands and realistic traffic demands.A key take-away message for other research on power saving solutions in backbone networks is that the ratio between the average demand and the demand bitrate has considerable effect on the overall efficiency, and should be taken into account.

An optical circuit switching network architecture and reconfiguration schemes for datacenter

The paper presents an optical circuit switching network architecture and its control and traffic scheduling schemes. This optical switch network is built on a 32×32 AWG and fast wavelength tunable transmitters and is able to support up to 128 interface ports. The feasibility of the architecture is verified through an experimental study. The traffic scheduling scheme takes into account the transmitter wavelength tuning time so as to avoid frequent connection reconfiguration. The simulation results show that fast connection reconfiguration speed and efficient traffic scheduling scheme enable optical circuit switching network to deliver high transmission bandwidth and low packet delay performance in datacenter network.

A Throughput-Optimized Optical Network for Data-Intensive Computing

Data-intensive computing increasingly involves operations at the scale of an entire computing system, requiring quick and efficient processing of massive datasets. In this article, the authors present a circuit-switched network architecture, together with requisite optical-switch and burst-mode transceiver technology, designed to support demanding graph algorithms in a distributed-memory system. The proposed optical network, configured as multiple planes of high-radix wavelength-division-multiplexed (WDM) switches, offers tremendous path diversity and is designed to deliver up to 10 terabytes per second of node bandwidth and predictable performance under heavy load with latencies well under a microsecond. With the optical core switch, the authors overcome pin-count and power-dissipation limitations of electrical networks with comparable bandwidth. To achieve this, they are developing new hardware, including nanosecond-scale silicon photonic switches with flip-chip-attached optical amplifiers, low-power parallel WDM transceivers operating at about 20-Gbps per channel, with burst-mode clock and data recovery circuits in advanced CMOS for link retraining in tens of nanoseconds. Network simulations predict that the proposed system could achieve graph performance on par with today's leading supercomputers, and its limited power consumption would result in several orders of magnitude of efficiency improvements that could allow the system to fit within a few racks.

Methods for Mitigating IP Network Packet Loss in Realtime Audio Streaming Applications

Increasingly Internet protocol (IP)-based networks are being used for transport of realtime broadcast quality audio. IP networks provide clear benefits of cost and flexibility over circuit-switched networks. However, IP networks can have impairments that must be mitigated in order to realize the quality of service that broadcasters are accustomed to with circuit-switched networks. Among these impairments, packet loss poses the toughest challenge. In many non-realtime applications, transport protocols such as transmission control protocol (TCP) or reliable user datagram protocol (UDP) can be used to retransmit lost packets. However, for realtime media streaming applications that are delay-sensitive and where multicasting is used, such protocols cannot be used. Therefore, techniques used for packet loss mitigation have to minimize delay and work in unidirectional network paths. The challenge faced as we encounter different packet loss patterns in real networks is that the effectiveness of the mitigation techniques depends upon the model these packet losses follow. This paper first shows how packet losses in real networks can be modeled. The results of the effectiveness of different mitigation techniques are then shown, using these models and how they can be cascaded to provide for a scalable method to mitigate varying levels of packet loss.

Information-centric networking: The evolution from circuits to packets to content

Today’s information-centric networks (ICNs) represent a 100-year evolution of communication networks from circuit-switched networks to packet-switched networks to ICNs, sharing common features with both of these earlier network architectures, but having many unique characteristics of its own. We describe and survey ongoing research and identify challenges in the modeling, design and analysis of information-centric networks and protocols. We discuss performance modeling frameworks and challenges for ICNs, with a particular focus on content flowing through a network of caches, drawing analogies and distinctions from past research in both circuit-switched and packet-switched networks. We also survey the challenges and recent research results associated with finding content in a network of caches and managing the content in those caches. The challenges posed by mobility (of both the end users accessing content as well as content itself) are also discussed.

Flow Deviation: 40 years of incremental flows for packets, waves, cars and tunnels

It was about 40years ago that the ARPANET had surpassed 40 nodes and was rapidly growing at the rate of one node per month. The first government and commercial P/S networks were emerging. Designing an efficient topology and flow assignment strategy that could meet the requirements at lowest costs was essential in order to outperform the competition represented by circuit-switched or private-line networks. The challenge was to solve a combined flow and capacity assignment problem. Researchers at UCLA, under Len Kleinrock’s leadership and DARPA support, developed a method based on multicommodity flow and non-linear programming principles called the Flow Deviation (FD) algorithm. The key underlying technique was to “deviate flows” on incrementally improving paths until the optimum was reached. In the early days, the FD algorithm was used to design and “upgrade” the growing ARPANET topology. After the ARPANET topology became stable, the FD algorithm took on a life of its own as an intuitive, efficient method to solve a variety of network flow problems in different domains, from ARPANET packets to WDM wavelengths, urban traffic cars and SDN tunnels, as reflected in the over 500 citations.This paper reviews the key concepts and features of the FD algorithm as published in 1973, traces the various problems and scenarios to which it has been applied (most recently, vehicular traffic management) and discusses the possible use of FD in today’s SDN tunnel allocation.

Hybrid circuit-switched network for on-chip communication in large-scale chip-multiprocessors

Large-scale chip-multiprocessors (CMPs) need a scalable communication structure characterized by low cost, low power, and high performance to meet their on-chip communication requirements. This paper presents a hybrid circuit-switched (HCS) network for on-chip communication in the large-scale CMPs. The HCS network, which is Advanced Microcontroller Bus Architecture (AMBA) compatible, is composed of bufferless switches, pipeline channels, and network interfaces. Furthermore, packets are transferred in a hybrid transmission scheme. If a message has only one packet, the transmission scheme for this message is packet switching. Conversely, if a message contains multiple packets, the transmission scheme for this message is circuit switching. We evaluate HCS networks with different channel depths and then compare the HCS network with the Stanford elastic buffer (EB) network. Our results show that the HCS network with two-depth channel requires 83% less power and occupies 32% less area compared with the EB network. Furthermore, under maximum frequency and single traffic, the HCS network with two-depth channel provides 37% lower zero-load latency, 390% higher maximum throughput per unit power, and 19% higher maximum throughput per unit area compared with the EB network.

Performance Analysis of Circuit Switched Multi-Service Multi-Rate Networks With Alternative Routing

We consider a circuit-switched multiservice network with non-hierarchical alternative routing and trunk reservation. Based on the fundamental concept of overflow priority classification approximation (OPCA), we develop two approximations for the estimation of the blocking probability: OPCA and service-based OPCA. We also apply the classical Erlang fixed-point approximation (EFPA) for the estimation of the blocking probability in the network and propose the more conservative max (EFPA, service-based OPCA) as a reasonably accurate evaluation. We compare the approximations with simulation results and discuss the accuracy of the blocking probabilities for the various traffic classes under different system parameter values such as service rates, bandwidth requirements, number of channels per trunk, maximum allowable number of alternative paths and trunk reservation. We also discuss the robustness of the approximations to the shape of the holding time distribution and their performances under asymmetrical cases. We illustrate that when the approximations are used for network dimensioning, their error is acceptable. We further demonstrate that the approximations can be applied in large networks such as the CORONET.

Deployment of the Content-Based Switching Network

In this paper, we propose a hybrid network architecture, called Content-based Switching Network (CSN), and its signaling scheme, which addresses the issues inherent to conventional hybrid networks which implement a horizontal separation over the entire network (from edge to edge). We will show how CSN nodes can flexibly choose their switching paradigm (store-and-forward, optical bypass, electrical bypass) during a path establishment. Contents being transferred in one piece from end-to-end, the concept of packet can be eluded in our network, and, in particular, the user is able to avoid complicated transport layer functions, like TCP, if they are not essential. In CSN, very large contents have a special status, since they cannot be store-and-forwarded. We will show how the resource management has been designed in order to deal with such contents. A section is dedicated to deployment and feasibility issues. Simulation results will show that CSN can successfully transfer contents at 1 Gbps and 10 Gbps, the maximum speed being limited by the state-of-the-art device technologies when buffering is required (memory speed), while no major limit is observed in the case of all-optical transfers other than the optical fiber speed. Other results concern the deployment of CSN from an unclean slate approach. They will show how beneficial can be the deployment of CSN from an Optical Circuit Switching network.

Blocking Probability Analysis of Circuit-Switched Networks With Long-Lived and Short-Lived Connections

We consider a circuit-switched network with nonhierarchical alternate routing and trunk reservation involving two types of connections that are modeled as long-lived and short-lived calls. The long-lived calls can be reserved well in advance, and the short-lived calls are provided on demand. Therefore, we assume that the long-lived calls have strict priority over the short-lived ones. We develop approximations for the estimation of the blocking probability based on the quasi-stationary approach in two ways. One uses the Erlang fixed-point approximation (EFPA), and the other uses the overflow priority classification approximation (OPCA). We compare the results of the approximations with simulation results and discuss the accuracy of the approximations under different system parameters, such as ratio of offered load, number of links per trunk, maximum allowable number of deflections, and trunk reservation. We also discuss the robustness of the quasi-stationary approximation to the ratio of the mean holding times of the long-lived and short-lived calls as well as that of EFPA and OPCA to the shape of the holding time distribution. Finally, we demonstrate that OPCA can be applied to a large network such as the Coronet.

Web-based communications [Guest editorial

Communication is an intensely social activity. Not only do human beings engage in it, but all manner of species depend on communicating intent and information with each other. However, human beings are unique in that we have evolved communications to travel over very long distances. Technology has helped us, from communicating our thoughts on a written medium (papyrus, first manufactured in Egypt as far back as the third millenium BC) to scattering our voice and the written word through ether and light fibers. This, in turn, has enabled us to build special networks optimized for communications. Currently, we are in the throes of a monumental migration in the means of communications, as the incumbent technology (circuit-switched networks that formed the backbone of the public switched telephone network) gives way to a new contender (packet-switched network, or the Internet) [1]. Today, the Internet is the dominant technology over which we communicate our voices, our words, and our images.

An Energy-Efficient Optically Connected Memory Module for Hybrid Packet- and Circuit-Switched Optical Networks

Demands on future data centers and high-performance computing systems will require processor-memory interconnects with greater performance and flexibility than can be provided by existing electronic interconnects. The bandwidth density and bit-rate transparency offered by optical systems are uniquely suited to address these challenges facing memory interconnects. We, thus, investigate a hybrid packet- and circuit-switched optical interconnection network linking microprocessors with their associated main memory, which can simultaneously reduce memory access latency and improve energy efficiency performance. This novel hybrid approach allows low-bandwidth memory control data and small memory transactions to be efficiently transmitted as wavelength-striped optical packets, while long bursts of memory accesses are optically circuit switched. In this study, we experimentally demonstrate an optically connected memory system in which a microprocessor accesses multiple 80-Gb/s memory modules all-optically across a hybrid packet- and circuit- switched optical network. Error-free communication between the microprocessor and main memory is confirmed (bit-error rates less than 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-12</sup> ) with the optical network providing low-memory access latencies. The overall memory system reduces energy consumption by 28%.

A distributed framework for energy-efficient lightpaths in computational grids

Over the past decade, the ever-increasing energy demands of IT infrastructures have posed significant challenges for the research community in terms of reducing their total power consumption and minimizing their environmental impact. Optical communication networks are envisioned to be promising candidates to help preventing this problem affecting the Internet backbone, as well as for distributed applications such as computational grids. In this paper, we propose an adaptive and distributed scheme for the establishment of energy-efficient lightpaths in computational grids. The grid is deployed over an optical circuit-switched backbone network, defining an optical grid network. Each node of the backbone network maintains two different dynamic thresholds values and estimates the changes in network performance by evaluating the moving average of the total wavelength channel occupancy on all its input/output links. The nodes have the ability of reducing the energy consumption by entering into an Energy Saving Mode ESM on the basis of a comparison between their channel occupancy and the thresholds. Furthermore, we extend our framework by allowing the thresholds to be dynamically adapted depending on the network performance in terms of blocking probability. We show that the proposed method achieves considerable energy savings when compared to a normal energy-unaware operational mode and still allows to maintain an acceptable level of network performance in terms of blocking probability and end-to-end delay. Numerical results are obtained with a Java event-driven simulator of two different optical network topologies.

Network Energy Efficiency Gains Through Coordinated Cross-Layer Aggregation and Bypass

With the continuous growth of traffic in Internet Protocol (IP) networks, the issue of energy consumption in these networks has been growing in importance. &#x201C;Next-generation networks&#x201D; have been predicted as having a potential to reduce energy consumption of packet switched IP networks; however, these predictions have generally not been quantified. This paper provides a demonstration of how these energy savings could be achieved, through architectures including the appropriate application of both circuit switching and packet switching network layers. In this paper, we show that energy savings of around 70&#x0025; could be achieved through a coordinated cross-layer aggregation and bypass process which can be conveniently implemented by network technologies such as automatically switched optical networks, and generalized multi-protocol label switching, compared to a network using full IP routing at each node.

Exploiting packet size in uncertain nonlinear networked control systems

This paper addresses the problem of stabilizing uncertain nonlinear plants over a shared limited-bandwidth packet-switching network. While conventional control loops are designed to work with circuit-switching networks, where dedicated communication channels provide almost constant bit rate and delay, many networks, such as Ethernet, organize data transmission in packets, carrying larger amounts of information at less predictable rates. We adopt a model-based approach to remotely compute a predictive control signal on a suitable time horizon. By exploiting the inherent packets payload, this technique effectively reduces the bandwidth required to guarantee stability. Communications are assumed to be ruled by a rather general protocol model, which encompasses many protocols used in practice. An explicit bound on the combined effects of the maximum time between consecutive accesses to each node (MATI) and the transmission and processing delays (MAD), for both measurements and control packets, is provided as a function of the basin of attraction and the model accuracy. Our control strategy is shown to be robust with respect to sector-bounded uncertainties in the plant model. Sampling of the control signal is also explicitly taken into account. A case study is presented which enlightens the great improvements induced by the packet-based control strategy over methods that send a single control value in each packet.