Deflection Routing Algorithm Research Articles

Contention avoidance scheme using machine learning inspired deflection routing approach in optical burst switched network

SummaryOptical transport has emerged as a candidate solution to cope with the rising data transmission challenges of enormously evolving data. In the bufferless environment, only the ingress node beholds the buffering to speed up the data transfer in the form of data bursts. However, such networks are prone to data contention issues that degrade the overall performance and eventually result in burst loss. The paper proposes a machine learning (ML) inspired deflection routing (DR) algorithm to overcome contention issues in optical burst switching (OBS) network. The contending burst is first evaluated and assigned the priority order as per the available bits. Based on the burst traffic analysis, support vector machine (SVM) kernels are trained to select an alternate route and redirected the bursts to a new output node. It has been observed that for 65% of cases, radial basis function (RBF) kernel demonstrated the best results among the three kernel functions. The work further shows that ML offers a wiser decision to avoid and overcome contention in the deflection of the route of the contenting bursts. Moreover, the proposed DR scheme has achieved the highest throughput and packet delivery ratio (PDR) with an average delay of 9.66 s using an OBS network deployed with 10 groups of nodes. When compared against the contention scenario and the existing work, the proposed DR outperformed the existing technique with a 4% to 11% margin.

Contention Avoidance Scheme Using Machine Learning Inspired Deflection Routing Algorithm in Optical Burst Switched Network

Contention Avoidance Scheme Using Machine Learning Inspired Deflection Routing Algorithm in Optical Burst Switched Network

Multi-hop Deflection Routing Algorithm Based on Reinforcement Learning for Energy-Harvesting Nanonetworks

Nanonetworks are composed of interacting nano-nodes, whose size ranges from several hundred cubic nanometers to several cubic micrometers. The extremely constrained computational resources of nano-nodes, the fluctuations in their energy caused by energy harvesting processes, and their very limited transmission range at Terahertz (THz)-band frequencies (0.1-10 THz), make the design of routing protocols in nanonetworks very challenging. A multi-hop deflection routing algorithm based on reinforcement learning (MDR-RL) is proposed in this paper to dynamically and efficiently explore the routing paths during packet transmissions. First, new routing and deflection tables are implemented in nano-nodes, so that nano-nodes can deflect packets to other neighbors when route entries in the routing table are invalid. Second, one forward updating scheme and two feedback updating schemes based on reinforcement learning are designed to update the tables, namely, on-policy and off-policy updating schemes. Finally, extensive simulations in networks simulator-3 are conducted to analyze the performance of MDR-RL using different updating policies, as well as to compare the performance with other machine learning routing algorithms based on Neural Networks and Decision Tree. The results show that the MDR-RL can increase the packet delivery ratio and number of delivered packets, and can decrease the packet average hop count.

Correction to: A controllable deflection routing and wavelength assignment algorithm in OBS networks

The article, A controllable deflection routing and wavelength assignment algorithm in OBS networks, written by Philani Khumalo, Bakhe Nleya, Andrew Mutsvangwa, was originally published electronically on the publisher’s Internet portal.

A controllable deflection routing and wavelength assignment algorithm in OBS networks

Heterogeneous IoT-enabled networks generally accommodate both jitter-tolerant traffic and jitter-intolerant traffic. Optical burst-switched backbone networks are handling the resultant volumes of such traffic by transmitting it in huge-size chunks called bursts. Because of the lack or limited buffering capabilities within the core network, contentions as well as congestion may frequently occur, thus affecting overall supportable quality of service (QoS). Both contention and congestion will be characterized by frequent burst losses, especially when traffic levels surge. The congestion is normally resolved by way of deflecting contending bursts to other less congested paths even though this may lead to differential delays incurred by bursts as they traverse the network. This will contribute to undesirable jitter that may ultimately compromise overall QoS. Noting that jitter is mostly caused by deflection routing which itself is a result of poor wavelength and routing assigning, in this paper we propose a controllable deflection routing scheme that allows the deflection of bursts to alternate paths only after controller buffer preset thresholds are surpassed. In this way, bursts intended for a common destination are always most likely to be routed on the same or least-cost path end-to-end. We describe the scheme and compare its performance to other existing approaches. Both analytical and simulation results overall show that the proposed scheme does lower both congestion and jitter, thus also improving throughput as well as avoiding congestion on deflection paths.

A Micro-buffered Router Architecture and Deflection Routing Algorithm for Vertically Partially Connected 3D NoC

Due to the problem of high hardware cost and low yield of the TSV in 3D NoC, the vertically partially connected 3D NoC with limit number of TSV has been researched widely. With respect to little research on micro-buffered router which is suitable for this topology and can further reduce hardware cost, a micro buffered router in vertically partially connected 3D NoC is proposed. This router is the 3D extension of MinBD and modifies side-buffer design in MinBD at the same time. Then a deflection routing algorithm based on this router is proposed. The productive output ports of the intra-layer communication packet are calculated according to the direction of destination node and the productive output ports of the inter-layer communication packet are calculated according to the distribution of TSV in current layer. The experimental results show that the network performance of our router is better than reference micro buffered routers’, while even is similar to traditional buffered routers in low and medium network traffic environment.

OPS/Agile-OCS Data Center Network With Flow Management

Modeling and performance analysis of a data center network (DCN) combining optical packet switching (OPS) and agile optical circuit switching (OCS) in a unified platform are presented. Hybrid optoelectronic packet routers which combine optical switching fabric and electronic buffers are used, supporting 100 Gbit/s (25 Gbit/s × 4 wavelengths) optical packets. OCS transmission is implemented by a novel “express path,” (ExP) an instant wavelength path on demand, which enables certain flows following the ExP with no packet contention, whereas ordinary OPS packets are switched with a deflection routing algorithm and buffering for contention resolution. This architecture can support OCS for large and reliability-sensitive data transferring and OPS for latency-sensitive applications. The performance of the network is investigated via numerical simulations of top-of-rack switch (ToR)-to-ToR traffic in an N-dimensional (up to 4096 node) torus topology. We have made the following observations: 1) torus topology results in high throughput and can be scaled out by increasing the dimension; 2) contention resolution between OPS and agile OCS is needed and our proposed strategies enhance the overall performance; and 3) in a lightly to moderately loaded case of OPS traffic, more than 100 ExPs can be supported simultaneously with acceptable affect on OPS.

Efficient routing on small complex networks without buffers

In this paper, we are exploring strategies for the reduction of the congestion in the complex networks. The nodes without buffers are considered, so, if the congestion occurs, the information packets will be dropped. The focus is on the efficient routing. The routing strategies are compared using two generic models, i.e., Barabàsi–Albert scale-free network and scale-free network on lattice, and the academic router networks of the Netherlands and France. We propose a dynamic deflection routing algorithm which automatically extends path of the packet before it arrives at congested node. The simulation results indicate that the dynamic routing strategy can further reduce the number of dropped packets in a combination with the efficient path routing proposed by Yan et al. [5].

Addressing Transient and Permanent Faults in NoC With Efficient Fault-Tolerant Deflection Router

Continuing decrease in the feature size of integrated circuits leads to increases in susceptibility to transient and permanent faults. This paper proposes a fault-tolerant solution for a bufferless network-on-chip, including an on-line fault-diagnosis mechanism to detect both transient and permanent faults, a hybrid automatic repeat request, and forward error correction link-level error control scheme to handle transient faults and a reinforcement-learning-based fault-tolerant deflection routing (FTDR) algorithm to tolerate permanent faults without deadlock and livelock. A hierarchical-routing-table-based algorithm (FTDR-H) is also presented to reduce the area overhead of the FTDR router. Synthesized results show that, compared with the FTDR router, the FTDR-H router can reduce the area by 27% in an 88 network. Simulation results demonstrate that under synthetic workloads, in the presence of permanent link faults, the throughput of an 8 8 network with FTDR and FTDR-H algorithms are 14% and 23% higher on average than that with the fault-on-neighbor (FoN) aware deflection routing algorithm and the cost-based deflection routing algorithm, respectively. Under real application workloads, the FTDR-H algorithm achieves 20% less hop counts on average than that of the FoN algorithm. For transient faults, the performance of the FTDR router can achieve graceful degradation even at a high fault rate. We also implement the fault-tolerant deflection router which can achieve 400 MHz in TSMC 65-nm technology.

Scalability Analysis of Memory Consistency Models in NoC-Based Distributed Shared Memory SoCs

We analyze the scalability of six memory consistency models in network-on-chip (NoC)-based distributed shared memory multicore systems: 1) protected release consistency (PRC); 2) release consistency (RC); 3) weak consistency (WC); 4) partial store ordering (PSO); 5) total store ordering (TSO); and 6) sequential consistency (SC). Their realizations are based on a transaction counter and an address-stack-based approach. The scalability analysis is based on different workloads mapped on various sizes of networks using different problem sizes. For the experiments, we use Nostrum NoC-based configurable multicore platform with a 2-D mesh topology and a deflection routing algorithm. Under the synthetic workloads, the average execution time for the PRC, RC, WC, PSO, and TSO models in the 8 $\,\times\,$ 8 network (64-cores) is reduced by 32.3%, 28.3%, 20.1%, 13.8%, and 9.9% over the SC model, respectively. For the application workloads, as the network size grows, the average execution time under these relaxed memory models decreases with respect to the SC model depending on the application and its match to the architecture. The performance improvement of the PRC and RC models over the SC model tends to be higher than 50% as observed in the experiments, when the system is further scaled up. The area cost in the network interface for the relaxed memory models is increased by less than 4% over the SC model.

Improve Packet Delivery Ratio Using Extended Deflection Routing Algorithm in Optical Burst Switching Network

In order to ensure the quality of service in the optical burst switching network and solve the control problem of the deflection algorithm, this paper proposes extended deflection routing algorithm that based on priority and adjustable parameters. The algorithm detects the function of packet loss rate by increasing the deflection conditions to control the deflection of conflict burst packet, and find the best deflection routing from the sense of adjustable packet loss rate and deflection’s path length. When a conflict occurs, if satisfying the conditions, we deflect it, otherwise put it away, thus ensuring the network load balancing. Finally, the results of the simulation show that the algorithm can effectively reduce the packet loss rate of the entire network, choose the best deflection path, and to a certain extent reduce the end to end transmission delay effectively, reduce pressure of the offset time to guarantee quality of service for deflection burst, thus improve the performance of overall network. The proposed algorithm is effective.

OBS网络中一种基于优先级和门限的偏射路由算法

In order to solve the problem in deflection control of deflection algorithm,a deflection routing algorithm based on priority and burst loss threshold in OBS networks is proposed.It drops some high priority deflected bursts to provide QoS for low priority non-deflected bursts.When competition occurs,in order to protect high priority burst,low priority bursts are segmented and deflected.Then,the node uses threshold check function to decide whether to drop or to preempt the resource of low priority non-deflected bursts on deflected route.Simulation results show that although the proposed algorithm increase a little delay,it can efficiently prevent deflected burst from contending with non-deflected burst on deflected route,and reduce packet loss probability of entire networks and protect the integrity of some high priority bursts.As a result,the scheme can efficiently improve the performance of OBS networks.

High-performance self-routing algorithm for multiprocessor systems with shuffle interconnections

This paper proposes a routing algorithm for the interconnection of multiple processors based on the shortest-path and deflection-routing principles. The routing algorithm, named SPDRA (Shortest Path and Deflection Routing Algorithm), is applied to multiprocessor systems with a single-stage shuffle physical topology. SPDRA is general-purpose, as opposed to the majority of routing algorithms for multiprocessor systems which are optimized for particular traffic patterns generated by a restricted class of parallel algorithms. The general-purpose nature of SPDRA allows perfomance comparisons with a wide class of routing algorithms for multiprocessor systems that, similar to the single-stage shuffle physical topology, have a fixed node-to-processor ratio. The paper compares SPDRA with hypercube algorithms for bidimensional meshes and torus physical topologies, routing algorithms for hierarchical tridimensional tori, and algorithms for routing permutations in shuffle networks, which constitute the most widely accepted approaches for multiprocessor interconnection. SPDRA exhibits a performance advantage for a broad range of network sizes and, in general, the performance advantage grows as the number of processors increases. However, this paper compares the SPDRA algorithm against a limited set of multiprocessor systems and does not demonstrate a general superiority of SPDRA over all systems with a fixed node-to-processor ratio and, especially, with a growing node-to-processor ratio, such as multistage networks.

Performance of deflection routing algorithms in IP optical transport networks

This paper 1 Work partially supported by EU IST Network of Excellence e-Photon/ONe. A preliminary version of this paper has been presented at BROADNETS 2004 conference. 1 deals with optical packet switching in a full-IP transport network scenario. For the switching of IP packet flows different node architectures are considered that are based on current optical routing devices. The traffic performance of a mesh network is evaluated with the various node structures, assuming that nodes employ either shortest path routing or deflection routing to forward packets to the addressed destinations. The paper shows how the different node structures behave in terms of packet loss probability with different network configurations when the node parameters are varied.

A Study on Deflection Routing in Optical Burst-Switched Networks

A major concern in optical burst-switched networks is contention,which occurs when multiple bursts contend for the same link. While a deflection routing protocol is proposed as one of the contention resolution techniques,there has been no appropriate deflection routing algorithm to find an alternate route. In this paper, we formulate a deflection routing problem based on the burst blocking rate resulting from resource contention in an optical burst-switched network. This algorithm minimizes the contention on the alternate path with the minimum distance. Furthermore, in this paper, we develop an analytical model for the deflection routing time when deflection routing is performed to resolve contention. In this model, we investigate the expected deflection routing time considering that the burst could be dropped even with deflection routing due to another contention on the alternate path. Simulations are conducted to show that there is an improvement in terms of burst loss rate and network throughput.

Wait-free deflection routing of long messages

In order to obtain the lowest possible latency, routing algorithms should try to avoid a message waiting for resources (network links) blocked by other messages or multiplexing of more messages over one physical channel. This requirement becomes especially important in the case of long messages. The only type of protocols able to guarantee waiting free routing under heavy load are algorithms based on deflection (also called nonminimal adaptive or hot potato) routing. This paper deals with problems connected with the use of deflection algorithms. In contrast to the case of nonadaptive or partially (e.g., minimal) adaptive routing, it is very infrequent that an unrestricted deflection routing becomes deadlocked and, similarly, livelock is not a serious problem. On the other hand, there is another phenomenon, called a deflection jam, that limits throughput of deflection algorithms used to route long messages. It has been observed for many deflection heuristics, interconnection network topologies, and both virtual cut-through and wormhole routing. A deflection jam is a sudden and persistent saturation of a network which sometimes occur, after a very long period of undisturbed communication. This paper describes events that trigger this saturation which suggest ways to design improved and stable deflection routing algorithms.

Comparison of two recycle dilated banyan network with output buffers

Two dilated banyan networks with recirculation and deflection routing algorithm are proposed. Without input buffers, the proposed switching fabrics can fully reuse the routing capacity wasted in a pure dilated banyan network. An analytical model of two switching fabrics and a study of packet loss probability are presented.

Distributed Coordinated Deflection Routing Algorithms for High Speed Networks

The deflection routing problem for a high speed network is dealt with, where every packet must be associated with one output port at the instant of its arrival at a switching node. Conflicts occur whenever two or more should be sent through the same output port. The algorithm proposed to solve such situations coordinates locally optimal strategies, based on instantaneous information, via a mechanism to exchange information among the nodes. Such a coordination is performed by making each node pass some aggregate information, regarding the traffic 'congestion' in the downstream portion of the network, to its predecessors. The algorithm is first stated in its optimal version, which may require a significant computational overhead. For this reason, a suboptimal, but computationally efficient version of the algorithm is also introduced. Some simulation results are presented to compare the performance of both versions of the algorithm with those of other routing policies previously proposed in the literature.

Performance of dilated banyan network with recirculation

A dilated banyan network with recirculation and a deflection routing algorithm is proposed. In the proposed switch architecture, the routing capacity wasted in a pure dilated banyan network can be fully used. An analytical model of the switch and a study of its throughput and packet loss probability are also presented.