Virtual Circuit Switching Research Articles

Stratosphere: A Fast Virtual Circuit Switch Layer for Data Center Network

The hierarchical structure of the data center network is more and more unsuitable for increasing east-west traffic from virtual machines. Reconfigurable circuit switching is utilized to reduce regional hotspots, which causes the problem of routing oscillation. We propose a stratospheric network of the data center, which combines virtual circuit switching and Tor switches. It acts as a supplement to tropospheric transmission across the hierarchical structure to alleviate global hotspots. The link of VCS (Virtual Circuit Switching) is divided into virtual channels by time division, and packets are sliced into cells to be transmitted at a specific time slot. Via the direct connection and the relaying of VCS modules, the stratospheric network could support not only the sharing of uplinks between Tor switches but also dynamical forwarding. Experiments of parameter servers demonstrate that it accelerates the transmission of data, which could provide a direct and fast path, especially for east-west traffic.

VCS: A method of in-order packet delivery for adaptive NoC routing

Adaptive routing proves its efficiency in sustaining higher network performance bypassing packets through alternate congestion-free minimal or non-minimal routes for a many-core on-chip communication system. It prevents the network from reaching an early saturation due to the stalling of packets in the priority-fixed shortest route for a longer period. However, routing packets adaptively to an alternate route instead of choosing the priority-fixed and shortest route may lead to an unintended state of delivering packets out-of-order sequence at the destination node that is not accepted by many message-passing systems. This ordering mismatch is due to allowing multiple alternate routes for packets of the same communication flow in adaptive mode. In such a case, a packet with a higher sequence number takes over another packet of the same communication flow having a lower sequence number. Storing and reordering all unordered packets of the same communication flow at the sink side becomes costlier due to the increasing area and power requirement. Ideally, the added memory size reaches to infinity for storing all unordered packets that belong to the same communication flow. In the proposed method, we guarantee delivery of all packets belongs to the same communication flow in an orderly manner under adaptive routing mode. In particular, we have proposed a flow-control policy based on a virtual circuit switch (VCS) method that exclusively won and reserve a virtual path for routing packets in an adaptive mode for each communication flow. To maximize network performance, we allow sharing of the reserved path among packets of different communication flows, routing under priority fix deterministic mode. The method saves need of having additional memory unit for storing all unordered packets while guaranteeing the packet’s ordering sequence at the destination end. An experiment conducted on two different size Mesh networks (8x8 and 12x12) under several synthetic traffic and benchmark application reveals that our virtual circuit switching (VCS) based proposed method offers a significant improvement over the state-of-the-art packet reordering method (ROR) and two similar type of research works. Our simulation based experimental result shows that method offers a 60% higher saturation point and 21% improvements (maximum) in throughput while offering a reduction of 60% in NoC area and 58% power value compared to the baseline reorder (ROR) method.

Energy routing algorithm based on OSPF protocol and virtual circuit switching mode in energy local area network

Energy routing algorithm based on OSPF protocol and virtual circuit switching mode in energy local area network

Energy Routing Algorithm Based on OSPF Protocol and Virtual Circuit Switching Mode in Energy Local Area Network

The advance management of the power supply to load such as in homes, offices, etc. and power from the source to central network in a smart grid system with lowest possible loss is considered here in this paper using the concept of energy internet. It also includes the complete details of power flow and control. In this paper, the efficiency of transmission is increased by using energy routers based on open shortest path first (OSPF) protocol, a new concept in the field of energy internet. By using energy local area network (e-LAN) concept, all the energy routers are connected by using OSPF protocols and virtual circuit concept theory. An algorithm is proposed for efficient power transmission and effective selection of sources to minimise the overall cost in the network.

A Graph Theory Based Energy Routing Algorithm in Energy Local Area Network

The energy Internet concept has been considered as a new development stage of the smart grid, which aims to increase the energy transmission efficiency and optimize the energy dispatching in time and space. Energy router is a core device in the energy Internet and it connects all the devices together into a net structure and manages power flows among them. The research work presented in this paper described the energy router's structure and function expectations from the network perspective, and improved the existing energy router design. Open shortest path first (OSPF) protocol and virtual circuit switching mode are referenced from the Internet in the energy local area network (e-LAN) design. This paper proposed a design of an energy routing algorithm based on graph theory in an e-LAN. A lowest cost routing selection algorithm is designed according to the features of power transmission, and a source selection and routing design algorithm is proposed for very heavy load conditions. Both algorithms have been verified by case analyses.

Novel virtual OCS in OPS data center networks

This paper considers a novel virtual optical circuit switching (VOCS) scheme for data center networks where short flows are transmitted via optical packet switching (OPS), while long flows with reliability requirement are transmitted via VOCS. VOCS preserves the advantage of optical circuit switching (OCS) for reliable communication, while it overcomes the disadvantage of OCS in terms of low link utilization. In the VOCS/OPS scheme, idle periods of the virtual circuits can be used by OPS, which thus enhances the overall performance. Simulations on a six-dimensional torus topology data center network with 4096 (=4$$^6$$6) nodes are conducted for the performance evaluation. We have observed that, compared to OCS, VOCS has much less adverse impact on the performance of OPS. Furthermore, quite a large number (i.e., 2048) of virtual circuits can be set up with little affect on the OPS performance.

A Low-Latency and Low-Power Hybrid Scheme for On-Chip Networks

Network-on-chip (NoC) has emerged as a vital factor that determines the performance and power consumption of many-core systems. This paper proposes a hybrid scheme for NoCs, which aims at obtaining low latency and low power consumption. In the presented hybrid scheme, a novel switching mechanism, called virtual circuit switching, is proposed to intermingle with circuit switching and packet switching. Flits traveling in virtual circuit switching can traverse the router with only one stage. In addition, multiple virtual circuit-switched (VCS) connections are allowed to share a common physical channel. Moreover, a path allocation algorithm is proposed in this paper to determine VCS connections and circuit-switched connections on a mesh-connected NoC, such that both communication latency and power are optimized. A set of synthetic and real traffic workloads are exploited to evaluate the effectiveness of the proposed hybrid scheme. The experimental results show that our proposed hybrid scheme can efficiently reduce the communication latency and power. For instance, for real traffic workloads, an average of 20.3% latency reduction and 33.2% power saving can be obtained when compared with the baseline NoC. Moreover, when compared with the NoC with virtual point-to-point connections (VIP), the proposed hybrid scheme can reduce the latency by 6.8% with the power decreasing by 11.3% averagely.

Minimization of Latency and Power for Network-on-Chip

Network-on-chip (NoC) has emerged as a imperative aspect that determines the performance and power consumption of many-core systems. This paper proposes a combination scheme for NoCs, which aims at gaining low latency and low power consumption. In the presented combination scheme, a peculiar switching mechanism, called virtual circuit switching, is proposed to interweave with circuit switching and packet switching. Flits traveling in virtual circuit switching can pass through the router with only one stage. In addition, multiple virtual circuit-switched (VCS) connections are granted to share a common physical channel. Moreover, a path allocation algorithm is used in this paper to determine VCS connections and circuit-switched connections on a mesh-connected NoC, such that both communication latency and power are optimized.

Modelling of virtual‐circuit switching nodes with multicast connections

AbstractThis paper presents an approximate calculation methodology of the occupancy distribution and the blocking probability in a virtual circuit switching node with multi‐rate unicast and multicast traffic streams. Particular traffic streams are generated by an infinite as well as by a finite population of traffic sources. The model enables calculations of any structure of the groups forming the outgoing directions of the node. Additionally, bandwidth reservation algorithms are also proposed in order to improve traffic characteristics of different traffic classes. The results of the analytical calculations have been compared with the simulation results of a switching node carrying multicast and unicast traffic streams. Copyright © 2007 John Wiley & Sons, Ltd.

Algorithms for Fault‐Tolerant Routing in Circuit‐Switched Networks

In this paper we consider the k edge‐disjoint paths problem (k‐EDP), a generalization of the well‐known edge‐disjoint paths problem. Given a graph $G=(V,E)$ and a set of terminal pairs (or requests) T, the problem is to find a maximum subset of the pairs in T for which it is possible to select paths such that each pair is connected by k edge‐disjoint paths and the paths for different pairs are mutually disjoint. To the best of our knowledge, no nontrivial result is known for this problem for $k>1$. To measure the performance of our algorithms we use the recently introduced flow number F of a graph. This parameter is known to fulfill $F=O(\Delta \alpha^{-1} \log n)$, where $\Delta$ is the maximum degree, $\alpha$ is the edge expansion of G, and n is the number of vertices in G. We show that a simple greedy online algorithm achieves a competitive ratio of $O(k^3 F)$ which naturally extends the best known bound of $O(F)$ for $k=1$ to higher k. To achieve this competitive ratio, we introduce a new method of converting a system of k disjoint paths into a system of k length‐bounded disjoint paths. We also show that any deterministic online algorithm has a competitive ratio of $\Omega(k F)$. In addition, we study the k disjoint flows problem (k‐DFP), which is a generalization of the previously studied unsplittable flow problem. The difference between the k‐DFP and the k‐EDP is that now we consider a graph with edge capacities and our requests are allowed to have arbitrary demands $d_i$. The aim is to find a subset of requests of maximum total demand for which it is possible to select flow paths such that all the capacity constraints are maintained and each selected request with demand $d_i$ is connected by k disjoint paths, each of flow value $d_i/k$. The k‐EDP and k‐DFP problems have important applications in fault‐tolerant (virtual) circuit switching, which plays a key role in optical networks.

Practical design methods for ATM systems

The basic service categories necessary for the information highway, namely, VLL (virtual leased line), VCS (virtual circuit switching), COPS (connection oriented packet switching), and CLPS (connectionless packet switching), have been proposed [9]. In this paper, we propose simplified practical design and control methods for the ATM systems to implement these categories of service. VLL may be realized by a cross-connecting technology of transmission systems. For VCS, the transmission speed is designed so as to satisfy the average call loss rate by applying a multidimensional traffic model. For COPS, using the call blocking probability as the call level QoS (quality of service), the maximum number of virtual channels (VCs) is designed to satisfy the QoS requirement. With the cell level QoS, the cell loss rate and mean cell delay, the transmission line speed and the buffer size are designed to satisfy the QoS requirement. In a system integrating COPS and CLPS, COPS is given nonpreemptive priority over CLPS, the latter being served on a best effort basis. In overload traffic conditions, a control method is proposed in which the number of assigned VCs is reduced so as to meet the cell level QoS requirement. © 2000 Scripta Technica, Electron Comm Jpn Pt 1, 83(10): 1–10, 2000

The /spl lambda/-scheduler: A multiwavelength scheduling switch

We propose a new multiwavelength almost all-optical switch architecture called the /spl lambda/-scheduler that uses wavelength division multiplexing (WDM) internally to fold the switch architecture in both the space and time domains to reduce the hardware complexity and to improve the signal characteristics through the switch. The /spl lambda/-scheduler preserves the packet order for a given input-output pair, is consistent with virtual circuit switching, and when combined with appropriate connection and flow control protocols, provides lossless communication for bursty (or nonconstant rate) traffic, provided the traffic satisfies certain smoothness properties. The /spl lambda/-scheduler uses novel scheduling and wavelength assignment algorithms, in conjunction with a series of feed-forward delay blocks, to avoid packet collisions within the switch or at the switch outputs. We present two implementations of the /spl lambda/-scheduler when the number of internal wavelengths k equal the number of inputs (and outputs) N to the switch. In the compressed /spl lambda/-scheduler, the N internal wavelengths are used to fold the architecture in the time domain, which reduces the total number of delay blocks for the switch by 2N log N. In the collapsed /spl lambda/-scheduler, the N internal wavelengths are used to fold the architecture in the space domain, which reduces the number of delay blocks and total fiber length used for delays by a factor of N. We examine the insertion loss for both /spl lambda/-scheduler implementations and discuss the trade-offs between the reduction in overall component count and the improvement in the signal characteristics.

A virtual circuit deflection protocol

We propose a communication protocol, called the virtual circuit deflection (VCD) protocol, which combines some of the individual characteristics of virtual circuit switching and deflection routing. An advantage of the VCD protocol over previous (datagram) deflection schemes is that deflections in the former occur on a per session basis (or a per subsession basis, if sessions need to be split to find adequate capacity on the outgoing links), while in the latter, they occur on a per packet basis. This makes packet resequencing at the destination considerably easier to accomplish in the VCD protocol than in datagram deflection schemes. The VCD protocol exploits the storage arising from the high bandwidth-delay product of optical fibers to provide lossless communication with little buffering at the switches and without the need for advance reservations. This makes it particularly suitable for networks that use optical switching, where buffers are expensive to implement with current optical technology. We present a simple implementation of the VCD protocol for such networks, which requires only limited buffering, accomplished through the use of a minimal number of optical delay lines. We also analyze the performance of the protocol for the Manhattan Street network topology by using new analytical models. In particular, we examine the effect of the traffic load and the network size on the throughput and the length of the paths followed by the sessions, and compare the analytical results obtained with corresponding simulation results. The results indicate that the VCD protocol is efficient under both light and heavy traffic conditions, especially when the link capacities are large compared to the basic rate of individual sessions, as is expected to be the case in future multigigabit networks.

Static and Dynamic Path Selection on Expander Graphs: A Random Walk Approach

This paper addresses the problem of virtual circuit switching in bounded degree expander graphs. We study the static and dynamic versions of this problem. Our solutions are based on the rapidly mixing properties of random walks on expander graphs. In the static version of the problem an algorithm is required to route a path between each of K pairs of vertices so that no edge is used by more than g paths. A natural approach to this problem is through a multicommodity flow reduction. However, we show that the random walk approach leads to significantly stronger-results than those recently obtained by Leighton w x and Rao Proc. of 9th International Parallel Processing Symposium, 1995 using the multicommodity flow setup. In the dynamic version of the problem connection requests are Ž continuously injected into the network. Once a connection is established it utilizes a path a . virtual circuit for a certain time until the communication terminates and the path is deleted. Again each edge in the network should not be used by more than g paths at once. The dynamic version is a better model for the practical use of communication networks. Our random walk approach gives a simple and fully distributed solution for this problem. We show that if the injection to the network and the duration of connection are both controlled by Poisson processes then our algorithm achieves a steady state utilization of the network which is similar to the utilization achieved in the static case situation. Q 1999 John Wiley & Sons, Inc. Random Struct. Alg., 14, 87]109, 1999 Correspondence to: A. Frieze *Supported in part by NSF Grants CCR-9225008 and CCR-9530974. Q 1999 John Wiley & Sons, Inc. CCC 1042-9832r99r010087-23 87 BRODER, FRIEZE, AND UPFAL 88

The "packing" and the "scheduling packet" switch architectures for almost all-optical lossless networks

This paper proposes two almost all-optical packet architectures, called the switch and the switch architecture, which when combined with appropriate wait-for-reservation or tell-and-go connection and how control protocols provide lossless communication for traffic that satisfies certain smoothness properties. Both architectures preserve the order of packets that use a given input-output pair, and are consistent with virtual circuit switching, The scheduling requires 2klogT+k/sup 2/ two-state elementary switches (or 2klogT+2klogk elementary switches, if a different version is used) where k is the number of inputs and T is a parameter that measures the allowed burstiness of the traffic. The packing requires very little processing of the packet header, and uses k/sup 2/logT+klogk two-state switches. We also examine the suitability of the proposed architectures for the design of circuit switched networks. We find that the scheduling combines low hardware cost with little processing requirements at the nodes, and is an attractive architecture for both packet-switched and circuit-switched high-speed networks.

Two Simulation Tools for Testing ATM Resource Allocation Strategies

Two event-driven simulation tools aimed at testing access control and routing mechanisms in an Asynchronous Transfer Mode (ATM) environment are presented. The first one is dedicated to the behavioural description of an ATM Virtual Circuit (VC) switch. The purpose is to test resource allocation and Call Admission Control (CAC) strategies, so only the relevant events for this objective are considered and some important functions (e.g., the switching element) for a complete description of an ATM switch are not explicitly modeled. The second simulator has been designed to test routing strategies for an ATM network. In such a case, a higher level of abstraction than in the previous one is necessary and, again, only the meaningful events to the aim are taken into account. Some resource allocation, CAC, and routing schemes are also reported, along with the description of the simulation tools. Several simulation results are discussed, in order to assess their performance.

A distributed media access protocol for packet radio networks and performance analysis. Part 1: Network capacity

AbstractA distributed time‐slot assignment protocol is developed for a mobile multi‐hop broadcast packet radio network, using time division multiple access channel access and virtual circuit switching. The protocol eliminates the single point failure mode of centralized network management and the delays of centralized processing. It is applicable to the user‐to‐user communications functions of such systems as the U. S. Army's enhanced position location and reporting system (EPLRS). The important functions of the distributed protocol, including time‐slot assignment, virtual circuit set‐up, and network synthesis, are identified, and implementing algorithms are presented and verified. The performance analysis of the protocol is divided into two parts. In this paper, Part 1 of the performance analysis, the capacity of a network using this protocol is studied and a tool is developed to design the network capacity by trading off among the network area, the transmission range, and the number of packet radio units. Since these results are not in closed form, numerical results provide insight into these parameters. In Part 2 the network set‐up time and network data rate are analysed and a hierarchical architecture for the distributed protocol is proposed and analysed.

An Open Architecture Corporate Electronic Publishing Platform

Corporate Electronic Publishing (CEP) encompasses more than the primitive capabilities of desktop publishing systems. It also includes networking and, in its optimal form, provides a platform for addressing a wide-ranging set of corporate documentation requirements. At AT&T Bell Laboratories we have evolved a platform for CEP consisting of AT&T's UNIX® operating system, the Datakit® virtual circuit switch, the Documenter's Workbench® and Graphics Workbench software, and the Adobe System, Inc. PostScript™ page description language. We cite real-life examples in which authors and printing facilities at geographically dispersed locations participated in cooperative efforts using the platform. We describe new work in progress that builds on this platform and addresses needs in illustration, photographic reproduction and plotting.

Starkeeper® Network Troubleshooter: An Expert System Product

StarKeeper network troubleshooter is a real-time interactive expert system that assists clerks, technicians, and network administrators with varying skill and experience levels in isolating and correcting faults in Datakit® virtual-circuit switch networks. The system interrogates and manipulates network components via a standard login to an existing element management system. Given a symptom description and minimal background information, the system can automatically isolate and correct network faults. It provides detailed corrective procedures in cases where human intervention is required. Feedback mechanisms let the system adapt to different networks and to individual operators.

A Transient Analysis of a Data Network with a Processor-Sharing Switch

This paper gives a simple, accurate, first-order asymptotic analysis of the transient behavior of a data network. The network is based on a switch, such as the Datakit® virtual circuit switch, which receives packetized traffic from many message sources of diverse classes and multiplexes the traffic over a trunk line. The network has a regulatory mechanism based on acknowledgments that produces a closed model. Assuming that the switch has a processor-sharing discipline, and assuming an asymptotic regime of high loading of the switch and high-capacity trunks, we derive the explicit, first-order transient behavior of the means of queue lengths — and hence response times. We then give a simple procedure for finding the time constants (eigenvalues) that govern the approach to steady state. Our numerical experiments show that the analysis is quite accurate.