Search

Abstract: TCP (Transmission Control Protocol) is one of the protocols which are widely used in Internet environments. This paper presents an analytical model developed using the stochastic reward net (SRN) modeling technique for the TCP flow behavior in WLANs. The purpose of developing an analytical model is the evaluation of stationary TCP flow behavior. In this paper, we focus the attention on the TCP variant called TCP Reno which is implemented by most operating systems. The performance of TCP Reno is investigated through the SRN model. The model captures aspects such as congestion window (cwd) evolution, slow start and congestion avoidance phases, TCP packet transmissions, management of packet losses due to time-out, and due to generation of triple duplicate acknowledgements. The performance metrics such as throughput and delay of the TCP traffic are obtained using the SRN model. On the basis of these performance measures, the existing unfairness between the downstream and upstream flow at the AP in WLANs is also shown. The proposed analytical model is validated via simulation. [ABSTRACT FROM AUTHOR]

Abstract: With increasing number of cores, the communication latency of Network-on-Chip becomes a dominant problem due to complex operations per node. In this paper, we try to reduce communication latency by proposing single-cycle router architecture with wing channel, which forwards the incoming packets to free ports immediately with the inspection of switch allocation results. Also, the incoming packets granted with wing channel can fill in the time-slots of crossbar switch and reduce the contentions with subsequent ones, thereby pushing throughput effectively. We design the proposed router using 65nm CMOS process, and the results show that it supports different routing schemes and outperforms express virtual channel, prediction and Kumar’s single-cycle ones in terms of latency and throughput. When compared to the speculative router, it provides 45.7% latency reduction and 14.0% throughput improvement. Moreover, we show that the proposed design incurs a modest area overhead of 8.1% but the power consumption is saved by 7.8% due to less arbitration activities. [Copyright &y& Elsevier]

Abstract: The input buffers of the current packet-switched Network-on-Chip (NoC) architectures consume a significant portion of the total power of the interconnection network. Reducing the size of input buffers would result in degraded performance, while eliminating all buffers would result in increased power at high network load. In this article, we propose DXbar: an innovative dual-crossbar design. By combining the advantages of buffered and bufferless networks, we achieve at least 20% performance improvement in terms of throughput and latency, and at least 20% power saving over buffered networks with virtual channels. Furthermore, DXbar can outperform current bufferless networks with deflecting and dropping protocols while consuming at most half of the power. [Copyright &y& Elsevier]

Abstract: This paper presents a design methodology for IP networks under end-to-end Quality-of-Service (QoS) constraints. Particularly, we consider a more realistic problem formulation in which the link capacities of a general-topology packet network are discrete variables. This Discrete Capacity Assignment (DCA) problem can be classified as a constrained combinatorial optimization problem. A refined TCP/IP traffic modeling technique is also considered in order to estimate performance metrics for networks loaded by realistic traffic patterns. We propose a discrete variable Particle Swarm Optimization (PSO) procedure to find solutions for the problem. A simple approach called Bottleneck Link Heuristic (BLH) is also proposed to obtain admissible solutions in a fast way. The PSO performance, compared to that one of an exhaustive search (ES) procedure, suggests that the PSO algorithm provides a quite efficient approach to obtain (near) optimal solutions with small computational effort. [Copyright &y& Elsevier]

Abstract: Traditionally, congestion control in packet networks is performed by reducing the transmission rate when congestion is detected, in order to cut down the traffic that overwhelms the capacity of the network. However, if the bottleneck is a wireless link, congestion is often cumulated because of retransmissions derived from bit errors. In this case, it might be beneficial to allow delivery of partly corrupted packets up to the application layer instead of reducing the transmission rate. This would decrease the number of retransmissions in the link layer and therefore relieve congestion, but at the cost of bit errors appearing in the packet payload. In this paper, we study a congestion control mechanism for streaming applications that combines traditional congestion control with selective link layer partial checksumming allowing bit errors in the less sensitive parts of data. We have compared the performance of the proposed mechanism against traditional congestion control with a simulation study. The results show that the proposed approach can improve the overall performance both by increasing the throughput over the wireless and improving the video quality in terms of peak signal-to-noise ratio (PSNR) by up to 8dB, depending on the error conditions and the content. [Copyright &y& Elsevier]

Abstract: This paper proposes a novel Network-on-Chip architecture that not only enhances network transmission performance while maintaining a feasible implementation cost, but also provides a power-efficient solution for interconnection network scenarios. Diagonally-linked mesh NoC that uses wormhole packet switching technique implements a high-performance NoC platform to meet both cost and power consumption requirements. The proposed architecture uses an adaptive quasi-minimal routing algorithm so that it can improve average latency and saturation traffic load owing to its flexibility and adaptiveness. Based on these features, a congestion-aware routing algorithm is proposed to balance traffic load so as to alleviate congestion caused by high throughput network activities. Simulation results show that saturation load is improved dramatically for various traffic patterns. Implementation results also show that employing diagonal links is a more area-efficient method for improving network performance than using large buffers. It is shown that congestion-aware router requires negligible cost overhead but provides better throughput. Finally, simulation results also reveal that power consumption in the proposed architecture outperforms traditional mesh networks. [Copyright &y& Elsevier]

Abstract: This paper proposes multi-hop scheduling algorithms for the All-to-All Broadcast (AAB) problem in Wavelength Division Multiplexed (WDM) optical star networks. The multi-hop AAB problem can be split into two subproblems: Logical Topologies Construction (LTC) problem, and Transmission Scheduling (TS) problem. For improving the efficiency of multi-hop scheduling, we focus on a new multi-hop transmission model and transfer the LTC problem to a special case of the Round Robin Tournament (RRT) problem. In the proposed logical topologies, our multi-hop scheduling algorithms can easily overlap the tuning latency and reduce the number of tuning operations on each node. We compare our results with previous research in terms of schedule length. Overall results indicate that our multi-hop scheduling algorithms have better performance than previous algorithms. [ABSTRACT FROM AUTHOR]

Abstract: Circumventing the speed bottleneck of electronic switching, novel switching approaches like optical burst switching (OBS) and optical packet switching (OPS) handle the switching of bursts (or packets) in backbone nodes optically, and include a set of fiber delay lines (FDLs) for optical buffering. While previous work acknowledges the performance difference between optical FDL buffers and electronic RAM buffers, the important role of synchronization herein has received little attention to date. Addressing this, we developed a single-wavelength FDL model that allows to capture the interplay between FDL buffer performance, burst size distribution and synchronization. Relying on generating functions, we constructed a discrete-time queueing model with batch arrivals that is valid for general burst and batch size distribution, and allows to quantify how synchronization impacts performance. This paper presents our model and compares its output for different synchronization levels. Whether or not buffer performance benefits from synchronization, turns out to depend strongly on the burst size distribution. [ABSTRACT FROM AUTHOR]

Abstract: We propose a new system of a packet of quantum bits generation using a soliton pulse within a microring resonator. A quantum gate can be formed by using a polarization control unit incorporating into the system. The random signal and idler pairs can be formed within the photon correlation bandwidth, which can be generated, and randomly form the packet quantum bits, i.e. quantum packet switching. Each random code (logic) can be performed by combining the signal and idler of each entangled photon pair via the quantum gate. Results obtained have shown that the packet of quantum logic bits can be generated using the entangled photon pairs generated by the proposed system. [ABSTRACT FROM AUTHOR]

Abstract: TCP performance over bufferless Optical Burst Switched (OBS) networks could be significantly degraded due to the misinterpretation of network congestion status (referred to as false congestion detection). It has been reported that burst retransmission in the OBS domain can improve the TCP throughput by hiding burst loss events from the upper TCP layer, which can effectively reduce the congestion window fluctuation at the expense of introducing additional delay. However, the additional delay may cause performance degradation for delay-based TCP implementations that are sensitive to packet round trip time in estimating the network congestion status. In this paper, a novel implementation of TCP Vegas that adopts a threshold-based mechanism is proposed for identifying the network congestion status in OBS networks. Analytical models are developed to evaluate the throughput of conventional TCP Vegas and threshold-based Vegas over OBS networks with burst retransmission. Simulation is conducted to validate the analytical model and to compare threshold-based Vegas with a number of legacy TCP implementations, such as TCP Sack and TCP Reno. The analytical model can be used to obtain a proper threshold value that results in an optimal steady state TCP throughput. [Copyright &y& Elsevier]

Abstract: In this paper, we investigate the low coverage problem of efficient broadcast protocols in wireless ad hoc networks with realistic physical layer models. To minimize energy consumption, efficient protocols aim to select small set of forward nodes and minimum transmission radii. In ideal physical layer model, nodes within forward nodes’ transmission ranges can definitely receive packets; therefore energy efficient protocols can guarantee full coverage for broadcasting. However, in networks with a realistic physical layer, nodes can only receive packets with probability. We present an analytical model to show that the transmission radii used for nodes can be used to establish a tradeoff between minimizing energy consumption and ensuring network coverage. We then propose a mechanism called redundant radius, which involves using two transmission radii, to form a buffer zone that guarantees the availability of logical links in the physical network, one for broadcast tree calculation and the other for actual data transmission. With this mechanism, we extend well-known centralized protocols, BIP and DBIP, and corresponding localized protocols, LBIP and LDBIP. The effectiveness of the proposed scheme in improving network coverage is validated analytically and by simulation. [Copyright &y& Elsevier]

Abstract: We propose a new design of the secure packet switching device using the nonlinear behaviors of soliton in a micro ring resonator, where the nonlinear penalty of light traveling in the device becomes beneficial. The chaotic signals are generated by a Kerr effects nonlinear type of the input soliton pulse in a micro ring resonator, where the control input power can be used to specify the output filtering signals. Some device parameters are chosen and simulated using the proposed model. The potential of using such a device for communication security is performed and discussed. For instance, the packet switching of the chaotic encoding data increases from the chaotic signal encoding of 100bits−1. Results obtained have shown the potential of using such a proposed device for the tunable bandpass and band-stop filters, in which packet switching data can be performed and secured. [Copyright &y& Elsevier]

Abstract: In this paper, we investigate the performance of optical burst switched networks for erbium-doped fiber amplifiers (EDFAs) and semiconductor optical amplifiers (SOAs). We show that EDFAs are more suitable for burst switching as compared to SOAs. We further investigate the burst length for 18, 24.6 and 55km optical switched network. It is observed that burst length should neither be very small nor very large. If the burst length is small, throughput will be less, and if the burst length is very large, delay will be very large. This is due to higher wait times incurred when packets are formed into larger bursts causing additional overall delay. It is observed that performance decreases up to a small burst length of 1500μs, which is the minimum burst length required for the creation of the burst. Once this burst is created, there is significant improvement in the quality factor up to 3000μs. After this burst length, the performance again degrades. Hence the burst length can be optimized for the best quality factor in optical burst switched networks. We further show that by increasing EDFA gain, the quality deteriorates as increasing the EDFA gain results in increased levels of additive phase noise, which can further induce nonlinearities. [Copyright &y& Elsevier]

Abstract: We propose a new design of secured packet switching generated by using nonlinear behaviors of light in a micro ring resonator. The use of chaotic signals generated by the micro ring resonator to form the filtering and packet switching characteristics is described, where the high-capacity and security switching using such form is presented. The key advantage is that the high capacity of communication data can be secured in the transmission link, where the nonlinear penalty of light traveling in the device is beneficial. For instance, the required information can be transmitted and retrieved by using the proposed packet switching scheme. In principle, the chaotic signals are generated by a Kerr effects nonlinear type of light in a micro ring resonator, where the control input power can be specified by the required output filtering signals. The ring radii used range between 10 and 20μm, κ=0.0225, α=0.5dB and n 2=2.2×10−15 m2/W. Simulation results obtained have been described based on the practical device parameters. Three forms of the applications have been simulated, the potential of using for the tunable band pass and band stop filters, in which high-capacity packet switching data can be performed, and the fs switching time is plausible. [Copyright &y& Elsevier]

Abstract: The burstiness of video traffic in future wired and wireless networks makes dynamic management of network resources more critical. This helps to meet stringent delay and loss requirements of video traffic and improves its Quality of Service (QoS). Since buffer management in queueing system plays an important role towards effective control of QoS for various types of applications, we have focused on its dynamic management. In this paper, we have proposed ADPBS scheme for priority queueing system. The performance of this scheme is analyzed with MPEG-4 encoded video sequence as input to the ADPBS queue. The simulation is carried out in MATLAB for various combinations of threshold control parameters, different traffic load and input traffic mix variations. The results of simulations indicate that dynamically controlled threshold in ADPBS contributes to significant reduction of packet loss of different priority classes as compared with static partial buffer sharing queue and first in first out queue based on threshold control parameters and the traffic type. [Copyright &y& Elsevier]

Abstract: This paper proposes a novel method to study the modelling problem of a networked control system. We first identify the minimum packet drop sequences for a given plant or controller using the dynamics of the plant or controller. Then we represent these minimum packet drop sequences as states of a Markov chain. The state transition of the Markov chain is triggered at each packet transmission. Finally, this new modelling technique is demonstrated using the most commonly employed PID controller. [Copyright &y& Elsevier]

Abstract: A novel scheme of time-stacked optical code label based on optical code division multiple (OCDM) technique for optical packet switching network is proposed, in which two-dimensional wavelength–time OCDM code is used as the optical label. Packet loss rate and system characteristic based on the proposed scheme are studied. Results show that less packet loss rate of proposed scheme can be achieved as compared with that of one-dimension time-stacked optical code label system. [Copyright &y& Elsevier]

Abstract: This paper considers a batch arrival retrial queue with general retrial times under a modified vacation policy. Any arriving batch finding the server busy or on vacation enters an orbit. Otherwise, one customer from the arriving batch obtains the service immediately while the rest join the orbit. If the orbit is empty, the server takes at most vacations repeatedly until at least one customer appears in the orbit upon returning from a vacation. If the orbit is nonempty when the server returns from a vacation, the server waits idly for customers from the orbit or new arrivals. On the other hand, if no customers are recorded in the orbit at the end of the th vacation, the server waits for new customers to arrive. This retrial system has potential applications in packet-switched networks. By applying the supplementary variable technique, some important system characteristics are derived. The results presented in the paper may be useful for network system designers and software system engineers. [Copyright &y& Elsevier]

Abstract: In this paper, an optically controlled loop buffer is proposed and experimentally demonstrated. It utilizes a semiconductor optical amplifier (SOA) based loop mirror as a fast switch to realize the writing and reading of packets within this buffer and a circulator based optical reflector to achieve internal re-circulations. By adding fibers with different lengths between the loop mirror and the circulator, variable delay time per circulations can be obtained. We also demonstrate the performance of the 2.5 and 10Gb/s data packets in this buffer structure, as well as the influence of the two different control signal formats on the packet signal degradation during buffering. This loop buffer has the merits of low cost and improved performance compared to other similar loop buffer structures. According to the obtained results, the achieved number of circulations is greatly increased. [Copyright &y& Elsevier]

Abstract: non-preemptive priority queue with bulk arrivals has already been analysed in many papers. Two problems are known in this area: first, when the number of priorities is greater than 2, the analysis for priority processes is obviously very difficult to handle. Therefore, the earlier work on the subject was restricted mostly to two priority classes; and second, although analytically explicit results are available, they require sophisticated closed-form expressions of the mean queue length. One particular bulk size distribution – the GE distribution – is motivated by an ME (Maximum Entropy) formulation for the behavior of a G/G/1 queue. The choice of a GE distribution is motivated by the fact that measurements of actual inter-arrival traffic or service times may be generally limited and so only few parameters, such as mean and variance, can be computed reliably. Thus this paper we can obtain very simple and analytic closed-form expression for the mean queue length of a GE/G/1 priority queue and a significant increase in performance evaluation has been achieved. We present the four-class priority queues, performance analysis and simulation of the LER (Label Edge Router) system in the ATM-based MPLS (Multiprotocol Label Switching) network. We wish to obtain the boundary conditions of the mean queue lengths and the mean queueing delays for each priority class, since this metric is one of the most important in performance evaluation parameters for improving QoS and system performance of the LER system in ATM-based MPLS network. A significant numerical example is presented and discussed as well. In order to obtain optimizing the performance analysis for EF flow, AF 1 flow, AF 2 flow and BE flow, the optimum ratios of COV (Coefficient of Variation) can be found via many numerical experiments carried out by the authors for queueing network model with HOL (Head of Line) priority rules. However, the ratios of COV value constraints exist. Furthermore, we find that each service class gradually begins to deteriorate when SQVs (Squared Coefficient of Variations), , and traffic intensity is greater than 0.95. We also find the values of maximum allowed burst size for EF flow and AF 1 flow and perform necessary policing actions on EF flow and AF 1 flow at the boundary node of the network. Finally, the four-class GE/G/1 priority queues and performance analysis of the LER system are shown accurate and robust after the comparison between theoretical evaluates and computer simulation results. [Copyright &y& Elsevier]

Abstract: In active networks, the Execution Environment in an active node executes user codes to tailor the processing of packets to application needs. However, the existing implementation of a software-based active node has a dilemma of only using the user mode Execution Environment or, alternatively, only using the kernel mode Execution Environment because neither mode of the Execution Environments meets application needs. The dilemma stems from the choice between high overheads of a user mode Execution Environment and poor services of a kernel mode Execution Environment in executing user codes. In this paper, we propose the Dual-Mode Execution Environment to overcome this dilemma, i.e. arguing for the necessity of an Execution Environment that supports dual modes. Currently, we develop and make the Lifetime-Sensitive Quantity-based Policy the workload adjustment policy in the Dual-Mode Execution Environment. We implement the prototype in Windows 2000. We conduct experiments to compare the prototype with active nodes that uses either the user mode Execution Environment or the kernel mode Execution Environment. We prove that the prototype meets application needs and outperforms the compared active nodes. [Copyright &y& Elsevier]

Abstract: When using wireless sensor networks for real-time event alarming, it is critical to ensure event notification in a timely manner. Additionally, it is extremely important to ensure the alarms generated by the sensors propagate securely through the network to the sink. Another important factor to consider is energy, as it is a limited resource in wireless sensor networks. Accordingly, maximizing network lifetime is always an optimization goal. To address the aforementioned concerns, in this paper we present the Authentic Delay Bounded Event Detection System (ADBEDS). ADBEDS works in rounds, and in each round an event detection tree is responsible for simultaneously detecting events, routing packets to a gateway node, and detecting injection of false packets. The ADBEDS can support k-watching composite events to allow event detection in a redundant manner. Additionally, the corresponding event alarm can be delivered within a user-specified bounded delay. The use of energy-based keying allows smaller, more efficient keys as input to security mechanisms, allowing further reduction in energy consumption of the ADBEDS. We evaluate the energy efficiency and reliability of ADBEDS using theoretical analysis and simulation. [Copyright &y& Elsevier]

Abstract: This paper introduces a game theoretic method, called forwarding dilemma game (FDG), which controls routing overhead in dense multi-hop wireless ad hoc networks. The players of the game are the wireless nodes with set of strategies {Forward, Not forward}. The game is played whenever an arbitrary node in the network receives a flooding packet. In FDG, every player needs to know the number of players of the game. That is why a neighbor discovery protocol (NDP) is introduced. In order for NDP to function, a field is attached to the flooding packets (routing overhead packets). The mixed strategy Nash equilibrium is used as a solution for the FDG. This provides the probability that the flooding packet would be forwarded by the receiver node. FDG with NDP is implemented in AODV protocol in Network Simulator NS-2 to verify its performance with simulations. FDG with NDP improves performance of the AODV compared to the same network with only AODV protocol in moderate and high node densities. FDG can be applied to any routing protocol that uses flooding in the route discovery phase. [Copyright &y& Elsevier]

Abstract: In this paper, we study the problem of searching for a node or a piece of data in an ad hoc network using random packet forwarding. In particular, we examine three different methods. The first is a random direction forwarding scheme where the query packet is forwarded along a randomly chosen direction (following an approximate straight line) till it either hits the destination node (the target) or the boundary. It bounces off the boundary in the latter case and the process continues till the target is found. In the second approach, in addition to query packet traversing the network, the target releases an advertisement packet that propagates along a randomly chosen direction so that all nodes visited by the advertisement packet obtain and store the target location information. In the third method the query packet is assumed to follow a random walk type of forwarding. Our primary interest is in comparing the average hitting time under these methods and the memory required to store location information. In particular, we show that under the random direction forwarding the target hitting time is , where and denote the size/radii of the network and the target area, assumed to be circular in shape, respectively. The hitting time is with target advertisement, and under the random walk type of forwarding. We further show that the target advertisement method achieves mean hitting time on the same order as greedy forwarding schemes with less memory requirement. We compare this class of schemes with the family of Lévy walks and provide simulation results on their performance under more realistic settings. [Copyright &y& Elsevier]

Abstract: Active queue management (AQM) is a key congestion control scheme for reducing packet loss and improving network utilization in TCP/IP networks. This paper proposes a proportional–integral-derivative (PID) controller as an active queue manager for Internet routers. Due to the limitations of packet-dropping probability and the effects of propagation delays in TCP networks, the TCP AQM network was modeled as a time-delayed system with a saturated input. An improved genetic algorithm is employed to derive optimal or near optimal PID controller gains such that a performance index of integrated-absolute error (IAE) is minimized, and thereby a stable queue length, low packet loss, and high link utilization for TCP networks are guaranteed. The performance of the proposed control scheme is evaluated in various network scenarios via a series of numerical simulations. [Copyright &y& Elsevier]

Abstract: In mobile ad hoc networks (MANETs), flooding is a required message dissemination technique for network-wide broadcast. The conventional blind flooding algorithm causes broadcast storm problem, a high number of unnecessary packet rebroadcasts thus resulting in high contention and packet collisions. This paper proposes a new probabilistic approach that dynamically fine-tunes the rebroadcasting probability of a node for routing request packets (RREQs) according to the number of neighbour nodes. We evaluate the performance of the proposed approach for the ad hoc on demand distance vector (AODV) routing protocol and compared against the blind flooding, fixed probabilistic and adjusted probabilistic flooding [L.M.M.M. Bani-Yassein, M. Ould-Khaoua et al., Performance analysis of adjusted probabilistic broadcasting in mobile ad hoc networks, International Journal of Wireless Information Networks 13(2) (2006) 127–140; M.B. Yassein, M.O. Khaoua et al., Improving route discovery in on-demand routing protocols using local topology information in MANETs, Proceedings of the ACM international workshop on Performance Monitoring, Measurement, and Evaluation of Heterogeneous Wireless and Wired Networks, Terromolinos, Spain, ACM Press, 2006, pp. 95–99.] approaches. The simulation results show that our proposed approach demonstrates better performance than blind flooding, fixed probabilistic and adjusted flooding approaches. [Copyright &y& Elsevier]

Abstract: This paper presents a study of feasibility of different existing methodologies linked to field’s data acquisition from remote meteorological stations. The data transmission serves to collect field’s meteorological information, such as temperature, humidity and radiation. In our study the experimental data is registered in a weather station located about 100km from the University of Almeria. Various existing techniques are studied, especially Radio, GSM (global system of mobile communication) and GPRS (general packet radio service). In the result of these studies has been designed a system of field’s data acquisition (herein referred as Meteologger) which we are going to present in this paper. The system is based on an ATmega 16 microcontroller, which scans 8 sensors together at any programmable intervals. This paper presents the study of the mentioned project, application and some main characteristics of the prototype system and its program. We attempt to implement the system, and subsequently present the performance of tests regarding the mentioned system. To verify its functioning some comparison of this measurement system with two others commercial data-acquisition system (Campbell and Hobo H8) has been carried out. [Copyright &y& Elsevier]

Abstract: An all-optical differential group delay (DGD) monitor for packet-switched networks is proposed. The monitoring approach consists of an integrated active Mach–Zehnder interferometer acting as a logic XOR gate. According to the estimated DGD value, a latching switch is employed to route the input packets “on-the-fly”. The simulation results show a successful operation which has been confirmed with the experimental validation of the XOR-based monitoring subsystem. [Copyright &y& Elsevier]

Abstract: Dynamic Resource Allocation (DRA) algorithms set up different connections over the same resources and perform a scheduling policy to distribute the resources usage. Recently, intelligent DRA techniques based on Hopfield Neural Networks computational methods have been proposed, showing their potential for solving this kind of complex optimization problems. However, the initial algorithms suffer from severe instability problems impacting performance. This paper addresses these specific limitations stressing the proper neuron dynamics and proposing an efficient energy formulation and an optimum calculation of the weighting coefficients. These changes result in a maximum resource utilization together with an optimized neural network convergence. [Copyright &y& Elsevier]

Abstract: Metropolitan Area Networks (MANs) are considered one of the best arenas for an early introduction of optical packet switching technologies. However, there is still no clear definition of how these technologies should be exploited in the design of innovative MANs. In this paper we consider different architectures that have been studied in the framework of the European Network of Excellence e-Photon/ONe and analyze their advantages and limitations. The main contribution of this work is the proposal of an analytical framework to compare these architectures in terms of resource demand when dimensioning them for a given traffic matrix and, from this analysis, discuss issues and trade-offs arising in the design of optical packet MANs. [Copyright &y& Elsevier]

Abstract: Multi-wavelength optical networks make extensive use of erbium-doped optical amplifiers (EDFAs) to offset the effects of fiber attenuation and signal power splitting. As optical networking moves towards burst and packet switching, the effects of changes of optical power levels on one wavelength, or channel, can have an impact on the behavior of other wavelengths passing through the same amplifier and impair network performance. We have observed in our simulations of EDFA operation that both the amplitude and duration of EDFA transients will decrease when gradual changes are made to the input power of the EDFA. It was also verified in [D.H. Richards, J.L. Jackel, M.A. Ali, A theoretical investigation of dynamic all-optical automatic gain control in multichannel EDFA’s and EDFA cascades, J. Select. Top. Quantum Electron. 3 (4) (1997)] that the switching time of the channel dropping operation can influence the amplitude and duration of EDFA transients. We show that this effect can be exploited to successfully suppress EDFA transients by power shaping. Our approach is to increase/decrease the power of an added/dropped channel gradually, rather than abruptly. Power shaping can be implemented by adapting existing link layer protocols. It is general and can be applied to amplifiers using different technologies, including EDFAs, solid state and Raman amplifiers. [Copyright &y& Elsevier]

Abstract: The stationary nature of nodes in a mesh network has shifted the main design goal of routing protocols from maintaining connectivity between source and destination nodes to finding high-throughput paths between them. Numerous link-quality-based routing metrics have been proposed for choosing high-throughput routing paths in recent years. In this paper, we study routing metrics for high-throughput tree or mesh construction in multicast protocols. We show that there is a fundamental difference between unicast and multicast routing in how data packets are transmitted at the link layer, and accordingly how the routing metrics for unicast routing should be adapted for high-throughput multicast routing. We propose a low-overhead adaptive online algorithm to incorporate link-quality metrics to a representative multicast routing protocol. We then study the performance improvement achieved by using different link-quality-based routing metrics via extensive simulation and experiments on a mesh-network testbed, using ODMRP as a representative multicast protocol. Our extensive simulation studies show that: (1) ODMRP equipped with any of the link-quality-based routing metrics can achieve higher throughput than the original ODMRP. In particular, under a tree topology, on average, ODMRP enhanced with link-quality routing metrics achieve up to 34% higher throughput than the original ODMRP under low multicast sending rate; (2) the improvement reduces to 21% under high multicast sending rate due to higher interference experienced by the data packets from the probe packets; (3) heavily penalizing lossy links is an effective way in the link-quality metric design to avoid low-throughput paths; and (4) the path redundancy from a mesh data dissemination topology in mesh-based multicast protocols provides another degree of robustness to link characteristics and reduces the additional throughput gain achieved by using link-quality-based routing metrics. Finally, our experiments on an eight-node testbed show that on average, ODMRP using SPP and PP achieves 14% and 17% higher throughput over ODMRP, respectively, validating the simulation results. [Copyright &y& Elsevier]

Abstract: We propose a novel 2×2 wavelength-convertible optical switch based on dual-pump fiber parametric devices: one is driven by linearly parallel pumps, and the other one by perpendicular pumps. Theoretical analysis is made on the polarization effects on the switching performance of the two devices. The result predicts that two incident signals which are positioned symmetrically with respect to one pump can be switched independently, with judicious combinations of the relative pump-signal polarization states. Simulations performed in OptiSystem show that the scheme can achieve crosstalk-free packet switching with acceptable extinction ratios for both signals. Besides, future applications of this novel scheme in high-speed switching nodes are discussed. [Copyright &y& Elsevier]

Abstract: This paper proposes an all-optical label processing scheme that uses the multiple optical orthogonal codes sequences (MOOCS)-based optical label for optical packet switching (OPS) (MOOCS–OPS) networks. In this scheme, each MOOCS is a permutation or combination of the multiple optical orthogonal codes (MOOC) selected from the multiple-groups optical orthogonal codes (MGOOC). Following a comparison of different optical label processing (OLP) schemes, the principles of MOOCS–OPS network are given and analyzed. Firstly, theoretical analyses are used to prove that MOOCS is able to greatly enlarge the number of available optical labels when compared to the previous single optical orthogonal code (SOOC) for OPS (SOOC–OPS) network. Then, the key units of the MOOCS-based optical label packets, including optical packet generation, optical label erasing, optical label extraction and optical label rewriting etc., are given and studied. These results are used to verify that the proposed MOOCS–OPS scheme is feasible. [Copyright &y& Elsevier]

Abstract: This paper presents the architecture of a Wavelength Division Multiplexing (WDM) optical packet network, called WONDER, that was designed and prototyped in the PhotonLab at Politecnico di Torino, Italy. The design and implementation of the WONDER network aim to assess the effectiveness of optical technologies with respect to electronic ones, trying to identify an optimal mix of the two technologies. The architecture shows interesting resilience properties that enable the design of fast fault-recovery schemes. In this paper, we present the physical topology and node structure of the prototype, and discuss the implementation and performance of a fault-recovery algorithm. [Copyright &y& Elsevier]

Abstract: This paper presents an analysis of the energy consumption in a number of optical switch fabric architectures for optical packet-switched applications and compares them to electronic switch fabrics. Optical packet switching does not appear to offer any substantial power consumption advantages over electronic packet switching. Therefore, there is no compelling case for optical packet switching. [Copyright &y& Elsevier]

Abstract: In this paper, we propose the optical multicast-capable packet switch network based upon OC-label switching, which can enhance scalability in the number of multicast members because this approach can combine the wavelength with the optical code as the labels. The optical implementation features two key components. Firstly, a multiport encoder and a decoder are newly introduced, which allows one to generate and process the optical-code labels simultaneously, thus ensuring a good scalability. Secondly, an optical multicast-capable matrix switch which is composed of 1×2 TO-SWs enables the dynamical updating of the multicast forwarding table. Finally, this multicast-capable optical packet switched network is experimentally demonstrated. [Copyright &y& Elsevier]

Abstract: We describe the practical and fundamental limitations of the more prominent optical buffering approaches. The architectural implementation and needs of an optical packet switch are used as a foundation for the study. We also present initial results for a buffered, all-optical, 40 Gb/s packet switch. [Copyright &y& Elsevier]

Abstract: We consider the use of random linear network coding in lossy packet networks. In particular, we consider the following simple strategy: nodes store the packets that they receive and, whenever they have a transmission opportunity, they send out coded packets formed from random linear combinations of stored packets. In such a strategy, intermediate nodes perform additional coding yet do not decode nor wait for a block of packets before sending out coded packets. Moreover, all coding and decoding operations have polynomial complexity. We show that, provided packet headers can be used to carry an amount of side-information that grows arbitrarily large (but independently of payload size), random linear network coding achieves packet-level capacity for both single unicast and single multicast connections and for both wireline and wireless networks. This result holds as long as packets received on links arrive according to processes that have average rates. Thus packet losses on links may exhibit correlations in time or with losses on other links. In the special case of Poisson traffic with i.i.d. losses, we give error exponents that quantify the rate of decay of the probability of error with coding delay. Our analysis of random linear network coding shows not only that it achieves packet-level capacity, but also that the propagation of packets carrying “innovative” information follows the propagation of jobs through a queueing network, thus implying that fluid flow models yield good approximations. [Copyright &y& Elsevier]

Abstract: In Mobile Ad Hoc Networks (MANETs), nodes depend upon each other for routing and forwarding packets. However, nodes belonging to independent authorities in MANETs may behave selfishly and may not forward packets to save battery and other resources. To stimulate cooperation, nodes are rewarded for their forwarding service. Since nodes spend different cost to forward packets, it is desirable to reimburse nodes according to their cost so that nodes get incentive while the least total payment is charged to the sender. However, to maximize their utility, nodes may tell lie about their cost. This poses the requirement of truthful protocols, which maximizes the utility of nodes only when they declare their true cost. Anderegg and Eidenbenz recently proposed a truthful routing protocol, named ad hoc-VCG. This protocol incurs the route discovery overhead of , where is the number of nodes in the network. This routing overhead is likely to become prohibitively large as the network size grows. Moreover, it leads to low network performance due to congestion and interference. We present a low-overhead truthful routing protocol for route discovery in MANETs with selfish nodes by applying mechanism design. The protocol, named LOTTO (Low Overhead Truthful rouTing prOtocol), finds a least cost path for data forwarding with a lower routing overhead of . We conduct an extensive simulation study to evaluate the performance of our protocol and compare it with ad hoc-VCG. Simulation results show that our protocol provides a much higher packet delivery ratio, generates much lower overhead and has much lower end-to-end delay. [Copyright &y& Elsevier]

In this work, we study the impact of the dynamic changing of the network link capacities on the stability properties of packet-switched networks. Especially, we consider the Adversarial, Quasi-Static Queuing Theory model, where each link capacity may take on only two possible (integer) values, namely 1 and under a-adversary. We obtain the following results: [•] Allowing such dynamic changes to the link capacities of a network with just ten nodes that uses the LIS (Longest-in-System) protocol for contention–resolution results in instability at rates and for large enough values of . [•] The combination of dynamically changing link capacities with compositions of contention–resolution protocols on network queues suffices for similar instability bounds: The composition of LIS with any of SIS (Shortest-in-System), NTS (Nearest-to-Source), and FTG (Furthest-to-Go) protocols is unstable at rates for large enough values of . [•] The instability bound of the network subgraphs that are forbidden for stability is affected by the dynamic changes to the link capacities: we present improved instability bounds for all the directed subgraphs that were known to be forbidden for stability on networks running a certain greedy protocol. [Copyright &y& Elsevier]

Abstract: In this paper a sequential binary Hopfield network architecture to solve crossbar switch problems (CSP) is proposed. It is shown that the sequential Hopfield algorithm''s performance on the CSP depends on the neurons’ updating ordering, and also an optimal ordering for the CSP is proposed. Our sequential binary Hopfield network has been applied to the resolution of large and very large CSP instances, obtaining optimal solutions within less steps than previous approaches to this problem. [Copyright &y& Elsevier]

Abstract: We present an efficient routing approach for delivering packets in complex networks. On delivering a message from a node to a destination, a node forwards the message to a neighbor by estimating the waiting time along the shortest path from each of its neighbors to the destination. This projected waiting time is dynamical in nature and the path through which a message is delivered would be adapted to the distribution of messages in the network. Implementing the approach on scale-free networks, we show that the present approach performs better than the shortest-path approach and another approach that takes into account of the waiting time only at the neighboring nodes. Key features in numerical results are explained by a mean field theory. The approach has the merit that messages are distributed among the nodes according to the capabilities of the nodes in handling messages. [Copyright &y& Elsevier]

Abstract: Given a graph , the problem is to determine an acyclic orientation of which minimizes the maximal number of changes of orientation along any shortest path in . The corresponding value is called the rank of the graph . The motivation for this graph theoretical problem comes from the design of deadlock-free packet routing protocols [G. Tel, Deadlock-free packet switching networks, in: Introduction to Distributed Algorithms, Cambridge University Press, Cambridge, UK, 1994 (Chapter 5)]. This acyclic orientation covering problem on the shortest path systems has been studied in [J.-C. Bermond, M. Di Ianni, M. Flammini, S. Perennes, Acyclic orientations for deadlock prevention in interconnection networks, in: 23rd International Workshop on Graph-Theoretic Concepts in Computer Science (WG), in: Lecture Notes in Computer Science, vol. 1335, Springer-Verlag, 1997, pp. 52–64] where it was shown that the general problem of determining the rank is NP-complete and some upper and lower bounds on the rank were presented for particular topologies, such as grids, tori and hypercubes. The main unresolved problem stated in [J.-C. Bermond, M. Di Ianni, M. Flammini, S. Perennes, Acyclic orientations for deadlock prevention in interconnection networks, in: 23rd International Workshop on Graph-Theoretic Concepts in Computer Science (WG), in: Lecture Notes in Computer Science, vol. 1335, Springer-Verlag, 1997, pp. 52–64] was to determine the rank values for other well-known interconnection networks and also for more general classes of graphs. In this paper we give a general lower bound argument for the rank problem and apply it to the class of involution-generated Cayley graphs which among others include hypercubes, star graphs, pancake graphs and transposition-tree based graphs [S.B. Akers, B. Krishnamurthy, A group-theoretic model for symmetric interconnection networks, IEEE Transactions on Computers 38 (4) (1989) 555–565]. We also present a large class of graphs with constant rank. This class of graphs is defined as the layered cross product [S. Even, A. Litman, Layered cross product—A technique to construct interconnection networks, Networks 29 (1997) 219–223] of layered trees and series–parallel graphs and includes among others butterflies, Beneš networks, fat-trees and meshes of trees. For some special topologies, improved lower bounds on the rank are also presented. We consider some of the modified versions of the rank problem as well. [Copyright &y& Elsevier]

Abstract: System performance of Gigabit network hosts can be severely degraded due to interrupt overhead caused by heavy incoming traffic. One of the most popular solutions to mitigate such overhead is interrupt coalescing in which a single interrupt is generated for multiple incoming packets. This is opposed to normal interruption in which an interrupt is generated for every incoming packet. In this paper we investigate the performance of interrupt coalescing analytically and compare it with that of normal interruption. We consider two types of coalescing (viz. count-based and time-based). The system performance is studied in terms of throughput, CPU availability for user applications, latency and packet loss. [Copyright &y& Elsevier]

Abstract: In an open shortest path first (OSPF) based best effort network, when a packet experiences congestion, the routing subsystem cannot send it through an alternate path. Thus, it fails to provide desired quality of service (QoS) during congestion. In order to provide QoS we have reported three different load sensitive routing (LSR) protocols in [A. Sahoo, An OSPF based load-sensitive QoS routing algorithm using alternate paths, in: IEEE International Conference on Computer Communication Networks, October 2002; A. Tiwari, A. Sahoo, Providing QoS support in OSPF based best effort network, in: IEEE International Conference on Networks, November 2005; A. Tiwari, A. Sahoo, A local coefficient based load sensitive routing protocol for providing QoS, in: IEEE International Conference on Parallel and Distributed Systems, July 2006]. The LSR protocol forwards packets through alternate paths in case of congestion. The number of alternate paths at any node depends on the value of operating parameter or coefficient used for alternate path calculation. Though the basic protocol in these cases was the same, the methods of choosing operating parameter were different. We referred to these three methods as LSR [A. Sahoo, An OSPF based load-sensitive QoS routing algorithm using alternate paths, in: IEEE International Conference on Computer Communication Networks, October 2002], E-LSR [A. Tiwari, A. Sahoo, Providing QoS support in OSPF based best effort network, in: IEEE International Conference on Networks, November 2005] and L-LSR [A. Tiwari, A. Sahoo, A local coefficient based load sensitive routing protocol for providing QoS, in: IEEE International Conference on Parallel and Distributed Systems, July 2006] coefficient methods. In this paper, we present the LSR protocol along with the three coefficient calculation methods pointing out the reason for going from one method to the next. The main strength of our LSR protocol is that it provides loop free alternate paths in the event of congestion and can interwork with routers running vanilla OSPF protocol. We show through simulation that the LSR protocol based on any of the three different coefficient calculation methods performs much better than OSPF and that out of the three methods proposed by us, L-LSR performs the best. [Copyright &y& Elsevier]

Abstract: In this paper, we present an orthogonal labelling scheme using inverted return-to-zero (IRZ) as payload and differential-phase-shift-keying (DPSK) as label. Transmission performances of orthogonal labelling with 40Gb/s IRZ payload and 10Gb/s label are evaluated. Simulation results show that orthogonal labelling using IRZ as payload exhibits a much larger extinction ratio margin than that of using return-to-zero (RZ) as payload. The asynchronous effect between payload and label on the transmission performances of orthogonal labelling using IRZ and RZ as payload is evaluated. Simulation results show that the degradation of asynchronous orthogonal labelling using IRZ as payload is relatively worse than that of using RZ as payload. The impact of optical filter bandwidth before receivers is also investigated. Results show that the receiver sensitivities of label for IRZ/DPSK and payloads for both IRZ/DPSK and RZ/DPSK are degraded with the reduction of the filter bandwidth, while the label of RZ/DPSK exhibits an opposite trend. [Copyright &y& Elsevier]

Abstract: The use of a Pump-Suppressed Four Wave Mixing PS-FWM wavelength converter in a wavelength conversion and selection switching scheme is examined and demonstrated. The scheme requires a single 2×1 Mach Zenhder Interferometer (MZI) and offers substantial pump suppression and efficiency improvement in terms of optical signal-to-noise ratio. Performance measurements on the combination of PS-FWM wavelength converter with an Arrayed Waveguide Grating (AWG) for passive routing, shows the potentially successful use of the scheme in an ultra-fast wavelength routed optical packet switching scheme where the use of optical filters for the separation of the converted signal from the pump is avoided. [Copyright &y& Elsevier]

Abstract: In this paper, we discuss different signaling techniques for optical burst-switched networks. We develop a generalized signaling framework for optical burst-switched networks, which provides guidelines about the performance of each signaling technique based on the different parameters in the framework. The two commonly used signaling techniques in optical burst switching are two-way based tell-and-wait (TAW) and one-way based just-enough-time (JET). TAW suffers from high end-to-end packet delay, while JET suffers from high packet loss. There is no signaling technique that offers flexibility in terms of both loss and delay. We propose a hybrid signaling technique called intermediate-node-initiated (INI) signaling for optical burst-switched networks. INI can provide different levels of loss and delay characteristics based on end-user application requirements. The granularity of INI ranges between the one-way based and the two-way based signaling techniques. In INI reservation of channels is initiated at an intermediate node, known as the initiating node, in both forward and backward directions at the same time. We show that by appropriately selecting the initiating node, we can simulate both TAW and JET using the INI signaling technique. Through simulations, we shown that INI performs better than TAW in terms of average end-to-end packet delay and better than JET in terms of burst loss probability. We extend the INI signaling technique to provide QoS differentiation in the OBS core, differentiated INI (DINI), by carefully choosing different initiation nodes depending on delay and loss requirements of end-user applications. Through extensive simulations, we show that the DINI technique outperforms the existing offset-based QoS technique. [Copyright &y& Elsevier]

Abstract: We evaluate the performance of a novel technique to equalize power variation between optical bursts using feed-forward control of semiconductor optical amplifier gain. The technique enables large dynamic range power equalization of incoming optical bursts with up to 10dB power difference. Moreover, the technique can remove SOA-induced waveform distortion. We achieve more than 4dB sensitivity improvement with equalized burst power. [Copyright &y& Elsevier]