Adaptive Routing

In this paper, we present a new deadlock-free fault-tolerant adaptive routing algorithm for the 2D mesh NoC interconnections. The main contribution of this routing algorithm is that it allows both, routing of messages in the networks incorporating the regions not necessarily rectangular, and routing to all nodes which are not completely blocked by faulty nodes. The proposed routing algorithm is based on a modified turn model and well known XY algorithm. We detail the basic principle of this routing algorithm, prove its deadlock freeness, its feasibility and efficiency through the simulation results.

We introduce a load-balanced adaptive routing algorithm for torus networks, GOAL -Globally Oblivious Adaptive Locally -that provides high throughput on adversarial traffic patterns, matching or exceeding fully randomized routing and exceeding the worst-case performance of Chaos , RLB [14], and minimal routing [8] by more than 40%. GOAL also preserves locality to provide up to 4.6× the throughput of fully randomized routing [19] on local traffic. GOAL achieves global load balance by randomly choosing the direction to route in each dimension. Local load balance is then achieved by routing in the selected directions adaptively. We compare the throughput, latency, stability and hot-spot performance of GOAL to six previously published routing algorithms on six specific traffic patterns and 1,000 randomly generated permutations.

The number of individual RSD applications received by UNHCR offices worldwide nearly doubled from 1997 to 2001, while UNHCR's RSD operations have been criticized for failing to implement basic standards of procedural fairness. Yet, although there is some literature critiquing how UNHCR determines refugee status, there is little literature examining whether UNHCR should do so, and if it should, when, where, and under what conditions. UNHCR performance of RSD poses protection challenges because it is founded on a basic contradiction. On the one hand, government action is essential for effective refugee protection. On the other hand, UNHCR RSD is premised on at least partial government failure. Neither direct concern for protection from non-refoulement nor strict legal obligations completely explain UNHCR's current RSD activities. UNHCR's RSD activities seem best explained by what Goodwin-Gill has called 'negative responsibility', and hence can represent a risky shift of responsibility from governments to the UN. At the same time, in some circumstances UNHCR RSD substantially advances refugee rights. In order to match its actual mandate and resources, UNHCR should perform RSD when it can enhance the protection provided to refugees by governments, but the activity should be more limited and conditional than it is today. * Revised May 2004 and December 2005. This article stems in large part from my experience working to develop refugee legal aid and advocacy programs in Egypt and Lebanon from 2001 through 2003. For this opportunity, I am especially grateful to Samira Trad for her courage and determination, and to Liza Hazelton and Prof. Barbara Harrell-Bond for their wisdom and collaboration. The work and research which led to this article was funded by the Initiative for Public Interest Law at Yale, the Clara Belfield & Henry Bates Overseas Travel Fellowship at the University of Michigan Law School, and the American University in Cairo Forced Migration and Refugee Studies Program. Michael Alexander and Prof. James C. Hathaway provided useful comments on earlier drafts. The views expressed here are solely my own. 2 Michael Kagan outer fence. Some arrive early in the morning. Most are men, but there are some women and occasionally children. The crowd presses in toward openings in the fence without any clear order; on crowded days they sometimes push each other for position, elbows used for leverage. Every so often voices are raised. These peoplerefugees and asylum-seekers-come to UNHCR with a range of queries, petitions, and complaints. Some have just arrived and want to start their applications for refugee protection. Some have been accepted by UNHCR before, and want to be resettled. Rejected asylum-seekers look for someone to ask how to reopen their cases. Often, just a single person works for UNHCR at the fence, fielding questions from the crowd, trying to distinguish those who should be let into the office, while providing quick answers to others. UN staff often collect inquiries, slips of paper, and documents to take inside and return to the fence with official responses. The refugees and asylum-seekers at the gate often remain for hours, while in the summer the temperatures can reach over 40 degrees in the sun. This daily scene outside UNHCR offices, which I have personally witnessed in both Cairo and Beirut, is the most publicly visible link in an increasingly important but little studied part of refugee protection: the determination of refugee status by UNHCR. Refugee status determination (RSD) is the doorway to the protection and assistance that the international community provides to refugees. In dozens of countries, UNHCR acts as the gatekeeper. In this role, which was little noticed in academic and NGO literature until recently, the UN's refugee agency effectively decides among asylum-seekers who can be saved from deportation and in some cases released from detention, who can get humanitarian assistance, and often who can apply to resettle to third countries. Since the mid-1990s, scholarly and NGO literature has been critical of the way UNHCR performs RSD. In the seminal study on the subject, Michael Alexander argued that UNHCR's RSD systems had been left behind by the standards of fairness developed elsewhere. Other assessments have repeated similar criticism. 2 In September 2005, UNHCR for the first time published comprehensive procedural standards governing its RSD activities. At the same time, UNHCR RSD has steadily grown.

This paper introduces AntNet, a new routing algorithm for telecommunication networks. AntNet is an adaptive, distributed, mobile-agents-based algorithm which was inspired by recent work on the ant colony metaphor. We apply AntNet in a datagram network and compare it with both static and adaptive state-of-the-art routing algorithms. We ran experiments for various paradigmatic temporal and spatial traffic distributions. AntNet showed both very good performances and robustness under all the experimental conditions with respect to its competitors.

Evolving technology and increasing pin-bandwidth motivate the use of high-radix routers to reduce the diameter, latency, and cost of interconnection networks. High-radix networks, however, require longer cables than their low-radix counterparts. Because cables dominate network cost, the number of cables, and particularly the number of long, global cables should be minimized to realize an efficient network. In this paper, we introduce the dragonfly topology which uses a group of high-radix routers as a virtual router to increase the effective radix of the network. With this organization, each minimally routed packet traverses at most one global channel. By reducing global channels, a dragonfly reduces cost by 20% compared to a flattened butterfly and by 52% compared to a folded Clos network in configurations with ≥ 16K nodes. We also introduce two new variants of global adaptive routing that enable load-balanced routing in the dragonfly. Each router in a dragonfly must make an adaptive routing decision based on the state of a global channel connected to a different router. Because of the indirect nature of this routing decision, conventional adaptive routing algorithms give degraded performance. We introduce the use of selective virtual-channel discrimination and the use of credit round-trip latency to both sense and signal channel congestion. The combination of these two methods gives throughput and latency that approaches that of an ideal adaptive routing algorithm.

Abstract The intensive and continuous use of high-performance computing systems for executing computationally intensive applications, coupled with the large number of elements that make them up, dramatically increase the likelihood of failures during their operation. Clearly, network faults have an extremely high impact because most routing algorithms are not designed to tolerate faults. In such algorithms, just a single fault may lead to deadlocked configurations thus preventing the correct finalization of applications. This paper ...

The artificial neural net development has had something of a renaissance in the last decade with an impressive range of application areas. From the viewpoint of telecommunication networks and systems, an increasing number of studies can be observed in recent literature dealing with proposed applications of neural nets in telecommunication environments, such as connection admission control in broadband networks, the control of high-speed interconnection networks, channel allocation in cellular mobile systems, adaptive routing, etc. These proposed applications largely use three main neural net classes: feed-forward nets with backpropagation learning, Hopfield feedback nets, and selforganising neural nets. In this paper, we first give an overview of neural net classes and their main properties, and then present a review of applications in telecommunication systems, where attention is devoted to numerical aspects such as the convergence property and learning speed of the proposed neural nets.

We present HORNET, a parallel, highly configurable, cycle-level multicore simulator based on an ingress-queued wormhole router NoC architecture. The parallel simulation engine offers cycle-accurate as well as periodic synchronization; while preserving functional accuracy, this permits tradeoffs between perfect timing accuracy and high speed with very good accuracy. When run on 6 separate physical cores on a single die, speedups can exceed a factor of over 5, and when run on a two-die 12-core system with 2-way hyperthreading, speedups exceed 11×.

Unicast_V is a progressive, misrouting algorithm for packet or virtual cut-through networks. A progressive protocol forwards a message at an intermediate node if a nonfaulty profitable link is available and waits, deroutes, or aborts otherwise. A misrouting protocol uses both profitable and nonprofitable links at each node; thus, a message can move farther away from its destination at some steps. Unicast_V is simple for hardware implementation, requires a very small message overhead, and makes routing decisions by local failure information only. However, it is claimed to be partially adaptive and to be able to tolerate static faults in hypercubes only. In this paper, we uncover some new features of Unicast_V: 1) It is fully-adaptive, 2) it also applies to meshes and tori, and 3) it can tolerate dynamic faults by careful implementation. In addition, we also provide bounds on the performance of the algorithm.

Efficient and deadlock-free routing is critical to the performance of networks-on-chip. In this paper we present an approach that can be coupled to any adaptive routing algorithm to improve the performance with a minimal overhead on area and energy consumption. The proposed approach introduces the concept of Neighbors-on-Path to exploit the situations of indecision occurring when the routing function returns several admissible output channels. A selection strategy is developed with the aim to choose the channel that will allow the packet to be routed to its destination along a path that is as free as possible of congested nodes. Performance evaluation is carried out by using a flit-accurate simulator on traffic scenarios generated by both synthetic and real applications. Results obtained show how the proposed selection policy applied to the Odd-Even routing algorithm outperforms other deterministic and adaptive routing algorithms both in average delay and energy consumption.

In the past few years there has been a lot of research on the application of swarm intelligence to the problem of adaptive routing in telecommunications networks. A large number of algorithms have been proposed for different types of networks, including wired networks and wireless ad hoc networks. In this paper we give an overview of this research area. We address both the principles underlying the research and the practical applications that have been proposed. We start by giving a detailed description of the challenges in this problem domain, and we investigate how swarm intelligence can be used to address them. We identify typical building blocks of swarm intelligence systems and we show how they are used to solve routing problems. Then, we present Ant Colony Routing, a general framework in which most swarm intelligence routing algorithms can be placed. After that, we give an extensive overview of existing algorithms, discussing for each of them their contributions and their relative place in this research area. We conclude with an overview of future research directions that we consider important for the further development of this field.

Networks of workstations (NOWs) are becoming increasingly popular as a cost-effective alternative to parallel computers. Typically, these networks connect processors using irregular topologies, providing the wiring flexibility, scalability, and incremental expansion capability required in this environment. Similar to the evolution of parallel computers, NOWs are also evolving from distributed memory to shared memory programming model. However, physical distances between processors are longer in NOWs than in tightly-coupled distributed shared-memory multiprocessors (DSMs), leading to higher message latency and lower network bandwidth. Therefore, the network may be a bottleneck when executing some parallel applications in a NOW supporting a shared-memory programming paradigm.

An efficient routing algorithm is important for large on-chip networks [network-on-chip (NoC)] to provide the required communication performance to applications. Implementing NoC using table-based switches provide many advantages, including possibility of changing routing algorithms and fault tolerance, due to the option of table reconfigurations. However, table-based switches have been considered unsuitable for NoCs due to their perceived high area and power consumption. In this paper, we describe the region-based routing (RBR) mechanism which groups destinations into network regions allowing an efficient implementation with logic blocks. RBR can also be viewed as a mechanism to reduce the number of entries in routing tables. RBR is general and can be used in conjunction with any adaptive routing algorithm. In particular, we have evaluated the proposed scheme in conjunction with a general routing algorithm, namely segment-based routing (SR) and an Application Specific Routing Algorithm (APSRA) using regular and irregular mesh topologies. Our study shows that the number of entries in the table is significantly reduced, especially for large networks. Evaluation results show that RBR requires only four regions to support several routing algorithms in a 2-D mesh with no performance degradation. Considering link failures, our results indicate that RBR combined with SR is able to tolerate up to 7 link failures in an 8 8 mesh. RBR also reduces area and power dissipation of an equivalent table-based implementation by factors of 8 and 10, respectively. Moreover, the degradation in performance of the network is insignificant when using APSRA combined with RBR.

... Adaptive Routing in Networks-on-Chip Giuseppe Ascia, Vincenzo Catania, Maurizio Palesi, Member, IEEE Computer Society, and Davide Patti, Member, IEEE Computer Society ... 4. In particular, for each direction d 2 fN orth; South; East; W estg, we indicate ...

Efficient and deadlock-free routing is critical to the performance of networks-on-chip. In this paper we present an approach that can be coupled to any adaptive routing algorithm to improve the performance with a minimal overhead on area and energy consumption. The proposed approach introduces the concept of Neighbors-on-Path to exploit the situations of indecision occurring when the routing function returns several admissible output channels. A selection strategy is developed with the aim to choose the channel that will allow the packet to be routed to its destination along a path that is as free as possible of congested nodes. Performance evaluation is carried out by using a flit-accurate simulator on traffic scenarios generated by both synthetic and real applications. Results obtained show how the proposed selection policy applied to the Odd-Even routing algorithm outperforms other deterministic and adaptive routing algorithms both in average delay and energy consumption.

Most commercial routers designed for networks of workstations (NOWs) implement wormhole switching. However wormhole switching is not well suited for NOWs. The long wires required in this environment lead to large buffers to prevent buffer overflow during flow control signaling. Moreover, wire length is limited by buffer size. Virtual cut-through (VCT) achieves a higher throughput than wormhole switching. Moreover, the traditional disadvantages of VCT switching, as buffer requirements and packetizing overhead, disappear in NOWs. In this paper, we show that VCT routers can be simpler than wormhole ones, while still achieving the advantages of using virtual channels and adaptive routing. We also propose a fully adaptive routing algorithm for VCT switching in NOWs. Moreover, we show that VCT routers outperform wormhole routers in a NOW environment at a lower cost

In ant societies, and, more in general, in insect societies, the activities of the individuals, as well as of the society as a whole, are not regulated by any explicit form of centralized control. On the other hand, adaptive and robust behaviors transcending the behavioral repertoire of the single individual can be easily observed at society level. These complex global behaviors are the result of self-organizing dynamics driven by local interactions and communications among a number of relatively simple individuals. The simultaneous presence of these and other fascinating and unique characteristics have made ant societies an attractive and inspiring model for building new algorithms and new multi-agent systems. In the last decade, ant societies have been taken as a reference for an ever growing body of scientific work, mostly in the fields of robotics, operations research, and telecommunications.

We introduce a load-balanced adaptive routing algorithm for torus networks, GOAL -Globally Oblivious Adaptive Locally -that provides high throughput on adversarial traffic patterns, matching or exceeding fully randomized routing and exceeding the worst-case performance of Chaos , RLB [14], and minimal routing [8] by more than 40%. GOAL also preserves locality to provide up to 4.6× the throughput of fully randomized routing [19] on local traffic. GOAL achieves global load balance by randomly choosing the direction to route in each dimension. Local load balance is then achieved by routing in the selected directions adaptively. We compare the throughput, latency, stability and hot-spot performance of GOAL to six previously published routing algorithms on six specific traffic patterns and 1,000 randomly generated permutations.

The trend towards increasing the number of processor cores and cache capacity in future Chip-Multiprocessors (CMPs), will require scalable packet-switched interconnection networks adapted to the restrictions imposed by the CMP environment. This paper presents an innovative router design, which successfully addresses CMP cost/performance constraints. The router structure is based on two independent rings, which force packets to circulate either clockwise or anti-clockwise, traveling through every port of the router. It uses a completely decentralized scheduling scheme, which allows the design to: (1) take advantage of wide links, (2) reduce Head of Line blocking, (3) use adaptive routing, (4) be topology agnostic, (5) scale with network degree, and (6) have reasonable power consumption and implementation cost. A thorough comparative performance analysis against competitive conventional routers shows an advantage for our proposal of up to 50 % in terms of raw performance and nearly 60 % in terms of energy-delay product.

An important open problem in wormhole routing has been to find a necessary and sufficient condition for deadlock-free adaptive routing. Recently, Duato has solved this problem for a restricted class of adaptive routing algorithms. In this paper, a necessary and sufficient condition is proposed that can be used for any adaptive or nonadaptive routing algorithm for wormhole routing, as long as only local information is required for routing. The underlying proof technique introduces a new type of dependency graph, the channel waiting graph, which omits most channel dependencies that cannot be used to create a deadlock configuration. The necessary and sufficient condition can be applied in a straightforward manner to most routing algorithms. This is illustrated by proving deadlock freedom for a partially adaptive nonminimal mesh routing algorithm that does not require virtual channels and a fully adaptive minimal hypercube routing algorithm with two virtual channels per physical channel. Both routing algorithms are more adaptive than any previously proposed routing algorithm with similar virtual channel requirements.

The paper presents the calibration and application of a simulation-based dynamic traffic assignment (DTA) model on a portion of the City of Calgary road network in Alberta, Canada. The DTA model iteratively re-assigns flow to paths using the Method of Successive Averages (MSA), based on travel times obtained with a traffic simulation model. The original sub-network extracted from a regional planning model, was enriched by greatly increasing the number of zones. The DTA origin-destination (O-D) matrix was estimated from an extensive database of turning movement counts via a trip generation/distribution model and a matrix adjustment algorithm. The network topology was enhanced by the addition of an interchange and a more precise representation of arterial intersections, including traffic signal control plans. A set of one-hour turning counts was used to calibrate the DTA model by adjusting local parameters such as gap-acceptance values, as well as global parameters such as average vehicle length. The final model results were compared to an independent set of 15-minute turning-movement counts. The resulting R 2 values, which ranged from 0.91 to 0.96, lead to a high degree of confidence in the model results.

InfiniBand networks are aimed to fulfill increasing communication demand of parallel applications in High Performance Clusters. However, the dynamic behavior of communication load may cause bottlenecked link(s) which lead to message congestion. Congestion spreading increases latency and reduces network throughput causing important performance degradation. In this paper, we propose a congestion control technique for InfiniBand networks. Our proposal is based on an adaptive routing algorithm that performs a communication load balancing over several alternative paths. Congestion is controlled by avoiding sending communication-load excess through network congested area, while maintaining injection rate. Proposed mechanism uses the management model defined in InfiniBand specs, thus full compatibility is provided meanwhile congestion control is addressed.

As the size of parallel computers increases, as well as the number of sources per router node, congestion inside the interconnection network rises significantly. In such systems, packet injection must be restricted in order to prevent throughput degradation at high loads. This work evaluates three congestion control mechanisms on adaptive cut-through torus networks under various synthetic traffic patterns.

We make use of the existence of cell-disjoint paths in the 3D grid topology to design a new highly reliable adaptive geographic routing protocol called Grid-based Adaptive Routing Protocol (GARP) for Underwater Wireless Sensor Networks. In GARP, the underwater environment is viewed as a virtual 3D grid of cells. A packet is forwarded following a pre-constructed routing path from a node in a grid cell to a node in a neighbouring grid cell repeatedly until the destination sink node is reached. When a selected routing path becomes unavailable, GARP adapts to the condition by switching to an alternative path making use of the existing cell-disjoint paths. Since the protocol uses pre-constructed routing paths, it avoids path establishment and path maintenance overheads. Analytical performance evaluation results for GARP are obtained showing its high reliability. In tested cases, the delivery ratio has approached 100% when the network density has reached a minimum number of sensor nodes per grid cell.

This paper presents the method of estimating of congestions in a partial mesh communication network comprises of many nodes such as the internet. The objectives are to characterize and model the non-stationary packet arrival process and to apply the model in adaptive routing algorithms. To achieve this, Bayesian estimation algorithms are implemented and used to determine the congestion of packet-queues in a prescribed interval time. The model is implemented in a state-space formation for estimating the arrival rate and occupancy at a network node. Bayesian method is used to predict the optimal size of the state vector in the proposed model with the aim to eliminate congestion through application of suitable adaptive routing algorithm.

We present HORNET, a parallel, highly configurable, cycle-level multicore simulator based on an ingress-queued wormhole router network-on-chip (NoC) architecture. The parallel simulation engine offers cycle-accurate as well as periodic synchronization; while preserving functional accuracy, this permits tradeoffs between perfect timing accuracy and high speed with very good accuracy. When run on six separate physical cores on a single die, speedups can exceed a factor of over 5, and when run on a two-die 12-core system with 2-way hyperthreading, speedups exceed 12×. Most hardware parameters are configurable, including memory hierarchy, interconnect geometry, bandwidth, crossbar dimensions, parameters driving power, and thermal effects. A highly parametrized table-based NoC design allows a variety of routing and virtual channel allocation algorithms out of the box, ranging from simple dimension-ordered routing to complex Valiant, ROMM, O1Turn or PROM schemes, BSOR, and adaptive routing. HORNET can run in network-only mode using synthetic traffic or traces, or directly emulate a MIPS-based multicore. HORNET is freely available under the open-source MIT license at http://csg.csail.mit.edu/hornet/.

Designing an efficient routing algorithm for LEO satellite constellations is crucial for optimizing IP over Satellite (IPoS) network resources. Since there could be many shortest paths between two satellites, an efficient routing algorithm should provide better utilization of these paths. For this purpose, we propose a Priority-based Adaptive Routing (PAR) technique, which distributedly sets the shortest path through a destination. In this technique, a direction decision is made at each hop by a priority mechanism, depending on the past utilization and buffering information about the links. We further make some enhancements on PAR, and propose ePAR algorithm that also accounts for the contentions between packets with different source-destination pairs. We explore the performances of PAR and ePAR algorithms based on an extensive set of simulations, and compared their performances with static and adaptive routing techniques as a reference. Obtained results show that while the proposed PAR algorithm is promising for use in LEO satellite networks, ePAR algorithm may be more suitable for MEO satellite networks.

In this paper, the problem of real-time channel establishment in point-to-point connected networks using packet-switched store-andforward routing is considered. Each message is associated with a real-time channel, which is an abstraction used to represent a source to destination connection. An offline real-time channel establishment algorithm that produces a feasible orderin,g, where all channels meet their deadline guarantees is presented. When scheduling a new channel, we allow partial reordering of previously scheduled channels, thereby increasing the size of the feasible set of channels compared to other methods. Alternative minimal routing paths when a channel cannot be scheduled on a path are also analyzed. Simulations show that our algorithm results in reducing the number of unschedulable messages compared to other existing algorithms. For the 2D mesh, the percentage of failed messages using our algorithm drops by as much as 65.69% compared to a previous algorithm [I]. Allowing offline adaptive paths results in reducing the percentage of failed messages for all methods and topologies examined, compared to non-adaptive routing. 0 1998 Elsevier Science B.V.

ABSTRACT This paper targets the problem of efficient software component deployment in distributed networked services. We approach the problem from a model-based service development aspect and propose a solution based on novel methods applied in network management. The swarm intelligence-based deployment logic we have developed uses service models that are defined in UML 2.0. These service models are embellished to contain the non-functional requirements against the implementation of the service that are necessary to solve the component deployment problem and to obtain a deployment mapping. The result of the heuristic optimisation procedure is mappings between the components and the resources provided by the execution environment the service is deployed into. In this work, the deployment is viewed from the perspective of the service provider and our algorithm possesses significant potential in providing adaptation support for services in various changing environments.

Nature-inspired routing protocols are becoming an active area of research. Researchers in the community follow a well known engineering philosophy: inspire, abstract, design, develop and validate. As a consequence, the protocols are designed on the basis of heuristics and then their performance is evaluated in a network simulator. To the best of our knowledge, virtually no attention has been paid in developing a formal framework that provides an analytical insight into the behavior and performance of such algorithms. The lack of formal treatment of Nature-inspired routing protocols is often criticized in the networking community. In this paper we propose a formal framework that helps in analyzing a Nature-inspired routing protocol, BeeHive. We have verified the correctness of our model by comparing its estimated values with the results obtained from extensive network simulations. An important outcome of the work is that the estimated and measured values only differ by a small deviation. We believe that this work will be instrumental for Nature-inspired Telecommunications.

We introduce a load-balanced adaptive routing algorithm for torus networks, GOAL -Globally Oblivious Adaptive Locally -that provides high throughput on adversarial traffic patterns, matching or exceeding fully randomized routing and exceeding the worst-case performance of Chaos , RLB [14], and minimal routing [8] by more than 40%. GOAL also preserves locality to provide up to 4.6× the throughput of fully randomized routing [19] on local traffic. GOAL achieves global load balance by randomly choosing the direction to route in each dimension. Local load balance is then achieved by routing in the selected directions adaptively. We compare the throughput, latency, stability and hot-spot performance of GOAL to six previously published routing algorithms on six specific traffic patterns and 1,000 randomly generated permutations.

Next-generation satellite networks are expected to provide a variety of applications with diverse performance requirements, which will call for the development of adaptive routing procedures supporting different levels of services. In this paper, we propose traffic class dependent (TCD) routing, which has the potential to differentiate between traffic classes using different optimization criteria in route calculation. The performance of TCD routing is evaluated for different traffic scenarios using an empirical traffic source model derived from the real backbone Internet traffic trace and compared with results obtained with equivalent Poisson traffic as a reference point. In addition, TCD routing is compared with a simple single service routing procedure, which does not make any distinction between traffic classes. Performance analysis, in terms of average packet delay, normalized data throughput, and normalized link load, reveals improved routing resulting from traffic class differentiation, regardless of the traffic scenario considered. The performance measures based of aggregate traffic flow show no significant difference between routing of empirical and equivalent Poisson traffic.

First-in-First-out (FIFO) is the most widely used scheduling protocol in packet switching network. In fact, it is one of the simplest queuing policies used to provide best effort services in packet-switched network. However, the performance of FIFO is really crucial when it related to stability i.e. question of whether there is a bound on the total size of packets in the network at all times. In this study, our primary objective is to find the optimum packet size of voice packet when using FIFO adversarial network and FIFO M/M/1 network. Our new approach is based on adversarial generation of packets so that positive results are more robust in that they do not depend on particular probabilistic assumptions about the input sequences.

With increase in concern for reliability in the current and next generation of multiprocessors system-on-chip (MP-SoCs), multi-computers, cluster computers, and peer-to-peer communication networks, fault-tolerance has become an integral part of these systems. One of the fundamental issues regarding fault-tolerance is how to efficiently route a faulty network where each component is associated with some probability of failure. Adaptive fault-tolerant routing algorithms have been frequently suggested in the literature as means of ...

Routing efficiency is one of the challenges offered by Mobile Ad-hoc Networks (MANETs). This paper proposes a novel routing technique called Adaptive Link-Weight (ALW) routing protocol. ALW adaptively selects an optimum route on the basis of available bandwidth, low delay and long route lifetime. The technique adapts a cross-layer framework where the ALW is integrated with application and physical layer. The proposed design allows applications to convey preferences to the ALW protocol to override the default path selection mechanism. The results confirm improvement over AODV in terms of network load, route discovery time and link reliability.

This paper proposes a new method for designing adaptive routing algorithms for 3D networks-on-chip (NoCs). This method is based on extending the existing 2D turn model adaptive routing to a 3D scenario. A 3-D plane-balanced approach with maximal degree of adaptiveness is achieved by applying a well-defined set of rules for different strata of the 3D NoC. The proposed method is applicable to any of the turn models. In this paper, we employ odd-even turn model as a basis for introducing the proposed strategy. Experimental results show that the new 3D odd-even can achieve up to 23.8% improvement in throughput over conventional odd-even approach. The improvement is consistent for different traffic types. The proposed method enables a new avenue to explore adaptive approaches for future large-scale 3D integration.

Networks of workstations (NOWs) are becoming increasingly popular as an alternative to parallel computers. Typically, these networks present irregular topologies, providing the wiring flexibility, scalability, and incremental expansion capability required in this environment. Similar to the evolution of parallel computers, NOWs are also evolving from distributed memory to shared memory. However distances between processors are longer in NOWs, leading to

Reinforcement - Learning methods are widely used in routing problems. These methods interact with the network changes, so are called Adaptive routing methods. Q - Learning algorithms has some quantities which are labeled Q, and are known as headers in routing methods which apply this algorithm. As a result, if we add forward exploration to backward One, their header will

Several analytical models of fully adaptive routing have recently been proposed for k-ary n-cubes and hypercube networks under the uniform traffic pattern. Although, hypercube is a special case of k-ary n-cubes topology, the modeling approach for hypercube is more accurate than kary n-cubes due to its simpler structure. This paper proposes a general analytical model to predict message latency in wormhole-routed k-ary n-cubes with fully adaptive routing that uses a similar modeling approach to hypercube. The analysis focuses Duato's fully adaptive routing algorithm [12], which is widely accepted as the most general algorithm for achieving adaptivity in wormhole-routed networks while allowing for an efficient router implementation. The proposed model is general enough that it can be used for hypercube and other fully adaptive routing algorithms.