This study was conducted in a first year university course in computer programming. We investigated how the use of a digital assessment tool, consisting of quantitative weighting and which simultaneously generate qualitative formative feedback, improves the quality of the assessment and not least supports the students' further learning. Analysis of quantitative data generated by the digital system, as well as qualitative data from involved parties, shows clear improvements in validity and reliability in assessment. All students received automated feedback on their exam. In this paper, we show how the use if the tool contributed to students' learning and academical development. Furthermore, we present the process of developing this system for evaluation and automatic feedback, and conclude with results seen from teachers, reviewers and students' perspectives.

The expected influx of Internet of Things (IoT) in 5G will provide new opportunities for uplink traffic offloading. In general, base stations with proximity require lower transmission power of the IoT device (IoTD), thus saving energy consumption as spectral efficiency (SE) of the transmissions increase. By letting IoTDs send to base stations with better link conditions the IoTDs' battery lifetime is prolonged. In this paper, we present a many-to-many offloading scheme for uplink traffic. The scheme works when link conditions are private information and gives incentives to all involved players to participate. We believe this approach is better suited for the expected complex ecosystem of 5G base station cells. The sensitivity analyses show that there is a limited gain by requiring that the link conditions are public knowledge. Further, the suggested market optimizes the SE for all involved players. Numerical results show that the IoTDs can on average increase their SE with 25% and their spectral energy efficiency with 40%. The networks which are offloaded to and from can both expect an increase in the SE of 1%-6%. Sensitivity analyses show that the market equilibrium's benefits are robust as they stay positive for a range of different network configurations. Also, the work proves that market equilibrium is stable and unique. To derive the equilibrium, two approaches are presented, a closed form solution and a distributed algorithm, that both are solvable in polynomial time.

DiffServ was designed to implement service provider quality of service (QoS) policies, where routers change and react upon the DiffServ Code Point (DSCP) in the IP header. However, nowadays, applications are beginning to directly set the DSCP themselves, in the hope that this will yield a more appropriate service for their respective video, audio and data streams. WebRTC is a prime example of such an application. We present measurements, for both IPv4 and IPv6, of what happens to DSCP values along Internet paths after an end system has set them without any prior agreement between a customer and a service provider. We find that the DSCP is often changed or zeroed along the path, but detrimental effects from using the DSCP are extremely rare; moreover, DSCP values sometimes remain intact (potentially having an effect on traffic) for several AS hops. This positive result motivates an analysis of the potential latency impact from such DSCP usage, for which we present the first measurement results. We find that routers at approximately 3% of more than 100,000 links differentiate between the WebRTC DSCP values (EF, AF42 and CS1) and consistently reduce delay in comparison with probes carrying a zero value (CS0) under congestion. In contrast, routers at around 2% of these links increase the delay by a comparable amount under congestion, uniformly for EF, AF42 and CS1.

Concerns have been raised regarding the economical viability for each operator to have a full regional 5G coverage. A possible solution is to have traffic offloaded to competitors. In this work we present a new scheme for optimal offloading in a stochastic environment. This is more in line with the conditions 5G base stations will face with changing link and traffic conditions. The problem is formulated as a Stackelberg game, and the players' utility functions are derived though queuing models. Numerical results illustrate that our scheme provides a global optimal resource allocation up to a threshold. The threshold is a function of the traffic load and the number of offloading candidates. Beyond the threshold players still have incentives to participate, but the market equilibrium is not globally optimal.

Communication between two Internet hosts using parallel connections may result in unwanted interference between the connections. In this dissertation, we propose a sender-side solution to address this problem by letting the congestion controllers of the different connections collaborate, correctly taking congestion control logic into account. Real-life experiments and simulations show that our solution works for a wide variety of congestion control mechanisms, provides great flexibility when allocating application traffic to the connections, and results in lower queuing delay and less packet loss.

Due to their environment friendliness, electric vehicles (EVs) are anticipated to form a considerable fraction of vehicles for transportation in smart cities. It is essential to design an electricity charging scheme that takes the utilities of both the charging stations and the EVs into consideration. However, the self-interested nature of the EVs together with the information asymmetry between the energy demand and supply sides makes the design a significant challenge. In this paper, we propose a queuing network-based model to characterize the charging process of the multiple EVs in a renewable energy-aided charging station. Based on the model, we adopt a contract theoretic approach to design an optimal charging policy in an information asymmetry scenario. Furthermore, we propose the new contract-based charging rate assignment and admission control schemes that maximize the utility of the charging station under certain charging constraints. To derive the optimal contract, we present a two-step iterative algorithm and prove its convergence. We evaluate the proposed schemes based on the IEEE 69-bus distribution test system. Results indicate that the contract-based charging schemes can effectively benefit both the charging stations and the EVs and concurrently improve the load level of the smart grid.

RINA, the Recursive InterNetwork Architecture, is a novel “back to basics” type approach to networking. The recursive nature of RINA calls for radically different approaches to how networking is performed. It shows great potential in many aspects, e.g. by simplifying management and providing better security. However, RINA has not been explored for congestion control yet. In this paper, we take first steps to investigate how congestion control can be performed in RINA, and demonstrate that it can be very efficient because it is applied close to where the problem happens, and through its recursive architecture, interesting effects can be achieved. We also show how easily congestion control can be combined with routing, enabling a straightforward implementation of in-network resource pooling.

Demand response management (DRM) is envisaged to play a key role in the smart grid operation, which requires reliable communications between power providers and consumers. To reduce communication cost, the cognitive radio technique is proposed to transmit the meter data from consumers to the control center. Unlike most existing studies on cognitive enabled smart grid, where only individual spectrum sensing is considered, in this paper, both cooperative spectrum sensing and harvested renewable energy are incorporated. The tradeoff between spectrum sensing cost and the DRM management gain makes the optimization of cooperation scheme a challenging research problem. To solve the problem, we analytically study the degradation of communication reliability of the renewable energy supplied consumers who attend the cooperative sensing as well as the DRM gain obtained by the communication improvement. Further, the optimization problem of selecting the number of cooperative consumers is formulated. We prove that there exists a unique optimal cooperative number under some constraints and propose an efficient searching algorithm. Numerical results are presented to validate our theoretical analysis.

Due to the ever-increasing use of electric vehicles (EVs) and renewable energy sources, the charging station with renewable energy supply is made as one promising energy solution. Moreover, grouping vehicles into platoons could greatly improve road capacity and reduce energy consumption. These tendencies urgently demand a theoretical performance analysis framework of the EV platoons charging at renewable energy supplied stations. In this paper, we present such a framework based on a queuing network model. In this model, the fluctuation of the renewable energy, the uncertainty of the EV platoons arrival, the variation of the charging price, and the serving capacity limitation of the charging station are taken into account. The steady-state distribution of the queuing system have been presented based on the equilibrium equations. Then, various performance metrics of the charging system together with the charging gain of EVs have been proposed. The queuing network model, validated by the simulation results, can be used in the planning of practical charging stations and the charging scheduling of EV platoons.

Explicit Congestion Notification (ECN) lets a bottleneck's Active Queue Management (AQM) mechanism inform an endpoint about congestion without having to drop a packet. A recently proposed sender-side modification called Alternative Backoff with ECN (ABE) enables reduced latency while maintaining good utilization with ECN. However, under certain circumstances ABE can produce a degree of unfair behavior between ABE-enabled TCP senders and conventional TCP senders. We propose specific guidance for configuring bottleneck AQMs to assist in fairness between ABE-enabled and conventional TCP flows. We evaluate our proposal using RED, then describe how it can be applied to other AQM mechanisms and incrementally introduced into the Internet.

Datacenter transport has attracted much recent interest, however, most proposed improvements require changing the datacenter fabric, which hinders their applicability and deployability over commodity hardware. In this paper, we present a novel congestion controller, Logistic Growth Control (LGC), for datacenters which does not require changes to the datacenter fabric. LGC uses a similar ECN marking as in DCTCP, but adapts to congestion using the logistic growth function. This function has been proven to have nice characteristics including stability, convergence, fairness, and scalability, which are very appealing for congestion control. As a result, our LGC mechanism operates in the datacenter network in a more stable and fair manner, leading to less queuing and latency. LGC also behaves better than DCTCP, and it converges to the fair share of the bottleneck link capacity irrespective of the Round-Trip-Time (RTT). We discuss the stability and fairness of LGC using a fluid model, and show its performance improvement with simulations.

When multiple congestion controlled flows traverse the same network path, their resulting rate is usually an outcome of their competition at the bottleneck. The WebRTC / RTCWeb suite of standards for inter-browser communication is required to allow prioritization. This is addressed by our previously presented mechanism for coupled congestion control, called the Flow State Exchange (FSE). Here, we present our first simulation results using two mechanisms that have been proposed for IETF standardization: Google Congestion Control (GCC) and Network-Assisted Dynamic Adaptation (NADA). These two mechanisms exhibit aspects that allow us to use a simpler “passive” algorithm in our FSE. Passive coupling allows a less time-constrained request-response style of signaling between congestion control mechanisms and the FSE, which enables the FSE to run as a stand-alone management tool.

Cloud-enabled vehicular network is an emerging paradigm which utilizes cloud computing to enhance the performance of vehicular network. But some issues still need to be addressed and we focus on the pseudonym resources management, which is crucial for vehicles to guarantee location privacy. A new three-plane hierarchical architecture with software defined network technology is proposed to manage the pseudonym resources. We use two-sided matching theory to solve the pseudonym resources allocation problem among pseudonym pools in different roadside unit clouds. Numerical results show that our proposed approach optimizes the pseudonym resources utilization and also improves the privacy entropy of vehicles.

Vehicular social network (VSN) is envisioned to serve as an essential data sensing, exchanging and processing platform for the future Intelligent Transportation Systems. In this paper, we aim to address the location privacy issue in VSNs. In traditional pseudonym-based solutions, the privacy-preserving strength is mainly dependent on the number of vehicles meeting at the same occasion. We notice that an individual vehicle actually has many chances to meet several other vehicles. In most meeting occasions, there are only few vehicles appearing concurrently. Motivated by these observations, we propose a new privacy-preserving scheme, called MixGroup, which is capable of efficiently exploiting the sparse meeting opportunities for pseudonym changing. By integrating the group signature mechanism, MixGroup constructs extended pseudonym-changing regions, in which vehicles are allowed to successively exchange their pseudonyms. As a consequence, for the tracking adversary, the uncertainty of pseudonym mixture is accumulatively enlarged, and therefore location privacy preservation is considerably improved. We carry out simulations to verify the performance of MixGroup. Results indicate that MixGroup significantly outperforms the existing schemes. In addition, MixGroup is able to achieve favorable performance even in low traffic conditions.

Vehicle-to-grid (V2G) technology enables bidirectional energy flow between electric vehicles (EVs) and power grid, which provides flexible demand response management (DRM) for the reliability of smart grid. EV mobility is a unique and inherent feature of the V2G system. However, the inter-relationship between EV mobility and DRM is not obvious. In this paper, we focus on the exploration of EV mobility to impact DRM in V2G systems in smart grid. We first present a dynamic complex network model of V2G mobile energy networks, considering the fact that EVs travel across multiple districts, and hence EVs can be acting as energy transporters among different districts. We formulate the districts' DRM dynamics, which is coupled with each other through EV fleets. In addition, a complex network synchronization method is proposed to analyze the dynamic behavior in V2G mobile energy networks. Numerical results show that EVs mobility of symmetrical EV fleet is able to achieve synchronous stability of network and balance the power demand among different districts. This observation is also validated by simulation with real world data.

Multimedia crowdsourcing possesses a huge potential to actualize many new applications that are expected to yield tremendous benefits in diverse fields including environment monitoring, emergency rescues during natural catastrophes, online education, sports, and entertainment. Nonetheless, multimedia crowdsourcing unfolds new challenges such as big data acquisition and processing, more stringent quality of service requirements, and heterogeneity of crowdsensors. Consequently, incentive mechanisms specifically tailored to multimedia crowdsourcing applications need to be developed to fully utilize the potential of multimedia crowdsourcing. In this paper, we design an optimal incentive mechanism for the smartphone contributors to participate in a cloud-enabled multimedia crowdsourcing scheme. We establish a condition that determines whether the smartphones are eligible to participate, and provide a close form expression for the optimal duration of service from the contributors, for a given reward from the crowdsourcer. Consequently, we derive the conditions for existence of an optimal reward for the contributors from the crowdsourcer, and prove its uniqueness. We numerically illustrate the performance of our model considering logarithmic and linear cost functions for the cloud resources. The similarity of the results for different cost models corroborates the validity of our model and the results, whereas the difference in the magnitudes suggests that the strategy of the crowdsourcer as well as the strategies of the smartphone participants considerably depend on the cloud cost model.

Mobile cloud computing is a promising technology for pervasive healthcare, which guarantees real-time health monitoring and electronic medical records sharing in different environments. In this paper, we present a hierarchical mobile cloud computing framework with three layers for pervasive healthcare. The scalable and hierarchical mobile cloud framework can be used to disperse the global storage and management load. We also study the social characteristics among patients and divide the patients into different social groups for privacy protection. A secure electronic medical records sharing scheme and a real-time health information transmission scheme are proposed. The security analysis shows that our schemes not only provide secure communication but also protect privacy of the patients.

In this paper we investigate single-hop multicast transmission in which randomly located multiple transmitters multicast packets to a cluster of receivers. Packet retransmission is known as a promising mechanism for improving the transmission reliability. Our focus is on evaluating (i) the minimum required delay (retransmission attempts), τ*, for establishing an outage-free multicast, where a transmitted packet is successfully decoded by entire nodes in the cluster, and (ii) Multicast Progress Radius (MPR) for a given delay constraint. MPR indicates how far, on average, a packet can successfully progress in a cluster without outage while the retransmission delay is restricted. Assuming general fading distribution, we derive closed-form expressions for the cumulative distribution function of τ*, and MPR. By simulations we confirmed our analysis and studied the impact of several system parameters on the MPR. Based on results of this paper we conclude that outage-free multicast requires a very large number of retransmission attempts, thus not practically achievable only based on retransmission.

With the aid of advanced Information and Communication Technologies (ICT), Vehicle-to-Grid (V2G) networks will play an important role in supporting and enhancing the distributed electricity supply in the next generation power grid-smart grid. In order to ensure stability of the power grid and satisfy the Quality of Energy (QoE) requirements of Electric Vehicles (EVs), this paper proposes a two-level group bidding mechanism for the electric energy trade between the grid and EVs. Trading information between the grid and EVs is exchanged through communication networks. EVs acted as mobile energy storage are organized to form an electricity feedback group by aggregators. The grid aims at minimizing the cost of given electricity demand while EVs expect to maximize their profits. A quantity based feedback electricity unit pricing scheme is proposed to incentivize the participation of EVs in V2G networks. Moreover, Vickrey-Clarke-Groves (VCG) auction-based algorithms are designed to implement our proposed mechanisms. Simulation results indicate that our mechanism is able to reduce the cost of the grid while offer EVs significant incentives to participate in the V2G power market.

In future, a massive number of devices are expected to communicate for pervasive monitoring and measurement, industrial automation, and home/building energy management. Nevertheless, such Machine-to-Machine (M2M) communications are prone to failure due to depletion of machines energy if the communication system is not designed properly. A key step in building energy-efficient protocols for large-scale M2M communications is to assess, model or characterize a network energy consumption profile. To meet this need, we develop a theoretical and numerical framework to evaluate the cumulative distribution function (CDF) of the total energy consumption by fully exploiting the properties of stochastic geometry. Unlike the other existing approaches, we model the transmission energy as a function of transmission power, packet size, and link affordable capacity that is a logarithmic function of experienced Signal to Interference plus Noise Ratio (SINR). Since it is very difficult, if not impossible, to derive a closed-form expression for the CDF, we derive numerically computable first- and second-order moments of energy consumption. Applying these moments we then propose Log-normal and Log-logistic distributions to approximate the CDF. Our simulation results show that Log-logistic almost precisely approximates the exact CDF.

Providing direct communications among a rapidly growing number of wireless devices within the coverage area of a cellular system is an attractive way of exploiting the proximity among them to enhance coverage and spectral and energy efficiency. However, such device-to-device (D2D) communications create a new type of interference in cellular systems, calling for rigorous system analysis and design to both protect mobile users (MUs) and guarantee the connectivity of devices. Motivated by the potential advantages of cognitive radio (CR) technology in detecting and exploiting underutilized spectrum, we investigate CR-assisted D2D communications in a cellular network as a viable solution for D2D communications, in which devices access the network with mixed overlay-underlay spectrum sharing. Our comprehensive analysis reveals several engineering insights useful to system design. We first derive bounds of pivotal performance metrics. For a given collision probability constraint, as the prime spectrum-sharing criterion, we also derive the maximum allowable density of devices. This captures the density of MUs and that of active macro base stations. Limited in spatial density, devices may not have connectivity among them. Nevertheless, it is shown that for the derived maximum allowable density, one should judiciously push a portion of devices into receiving mode in order to preserve the connectivity and to keep the isolation probability low. Furthermore, upper bounds on the cellular coverage probability are obtained incorporating load-based power allocation for both path-loss and fading-based cell association mechanisms, which are fairly accurate and consistent with our in-depth simulation results. Finally, implementation issues are discussed.

Vehicle-to-grid (V2G) system with efficient demand response management (DRM) is critical to solve the problem of supplying electricity by utilizing surplus electricity available at electric vehicles (EVs). An incentivized DRM approach is studied to reduce the system cost and maintain the system stability. EVs are motivated with dynamic pricing determined by the group-selling-based auction. In the proposed approach, a number of aggregators sit on the first-level auction responsible to communicate with a group of EVs. EVs as bidders consider quality of energy (QoE) requirements, and report interests and decisions on the bidding process coordinated by the associated aggregator. Auction winners are determined based on the bidding prices and the amount of electricity sold by the EV bidders. We investigate the impact of the proposed mechanism on the system performance with maximum feedback power constraints of aggregators. The designed mechanism is proven to have essential economic properties. Simulation results indicate that the proposed mechanism can reduce the system cost and offer EVs significant incentives to participate in the V2G DRM operation.

The goal of Rate Adaptation (RA) mechanisms in 802.11 WLANs is to provide optimum system throughput under varying channel conditions (e.g. in presence of noise) by carrying out run-time prediction and selection of the most appropriate bit-rate. The cross-layer interaction of TCP, as the major transport protocol in the Internet, with different RA mechanisms and DCF is yet to be thoroughly investigated. Previously reported efforts A) have never included real-life measurements of uplink TCP traffic; B) lack a practical view because they do not consider the RA mechanisms commonly deployed in today's off-the-shelf 802.11 devices; C) miss the study of RA mechanisms in low-noise environments. This paper covers all the above shortages, by conducting real-life measurements in two different test-beds (NDlab and Emulab) alongside with simulations, to study the performance of TCP coupled with different commonly deployed RA mechanisms. Our measurements reveal that 1) most conventional RA mechanisms are unable to distinguish frame errors due to collisions from channel noise/interference, and will respond to them negatively to some extent; 2) different than downlink TCP, uplink TCP can be adversely affected by collision-triggered rate downshifts that some RA schemes exhibit even under perfect channel conditions or in low-noise environments; 3) the relatively recent Minstrel RA mechanism can counter this negative uplink behavior well, yielding almost equal performance as in the downlink case.

The Internet-wide deployment of new transport protocols such as the Stream Control Transmission Protocol (SCTP) is a difficult matter. While SCTP could be beneficial in many cases, it is still a major challenge to enable applications to use the new protocol. We believe that its deployment could be significantly accelerated by introducing an intermediate step: transparent usage below TCP, such that TCP-based applications automatically obtain a benefit. We have implemented a Linux based TCP-SCTP mapping tool that exploits SCTP's multi-streaming feature, and carried out measurements which show that such an approach can significantly improve the performance of TCP applications. However, and perhaps more importantly, we also encountered difficulties, which lead us to make some concrete recommendations regarding future research and the implementation and specification of SCTP itself.

Congestion control in transport protocols can be performed implicit when packets are lost, or explicit with feedback from the network. In this paper we compare some aspects of implicit and explicit congestion control using a variant of CUBIC with Quick-Start, called CUBIQ. We compare CUBIQ with regular TCP, XCP and CUBIC, and find that CUBIQ performs as well as XCP in most cases, and much better than XCP when XCP is hampered by small buffers in large BDP-networks. These results indicate that the feedback provided by Quick-Start may be enough for a sender when it needs to find the right transmission rate, also in the initial phase of a communication.

Cooperative spectrum sensing improves the reliability of detection. However, if the secondary users are selfish, they may not collaborate for sensing. In order to address this problem, Medium Access Control (MAC) protocols can be designed to enforce cooperation among secondary users for spectrum sensing. In this paper, we investigate this problem using game theoretical framework. We introduce the concept of correlated equilibrium for the cooperative spectrum sensing game among non-cooperative secondary users and formulate the optimization problem for the case where secondary users have heterogeneous traffic dynamics. We show that the correlated equilibrium improves the system utility, as compared to the mixed strategy Nash equilibrium. While maximizing system payoff is important, fairness is also equally important in systems with dissimilar users. In order to address fairness issue, we propose a new fair social welfare correlated equilibrium, which maximizes the system utility and ensures that the less well-off users do not starve. We employ a no-regret learning algorithm for distributed implementation of the correlated equilibrium. Finally, we propose a neighbourhood based learning algorithm and show that it achieves better performance than the no-regret algorithm.

Real time traffic such as voice and video have strict requirements on the acceptable end-to-end packet delay. When there are different types of traffic with different requirements on tolerable latency, priority based packet scheduling schemes are normally used in order to reduce the queuing delay for real time services. However, in cognitive radio networks, the time that the system spends on spectrum sensing adds further delay to the packet transmission. In this paper, we propose a new scheme to significantly reduce the overall packet delay, including the delay due to sensing for real time services in cognitive radio networks. We derive the expression for average packet delay for the proposed scheme and the simulation results match well with the analytical results. The numerical results show that the priority based scheduling scheme combined with our scheme substantially reduces the packet delay for real time applications.

Multi-topology routing is an increasingly popular IP network management concept that allows transport of different traffic types over disjoint network paths. The concept is of particular interest for implementation of IP fast reroute (IP FRR). The authors have previously proposed an IP FRR scheme based on multi-topology routing called Multiple Routing Configurations (MRC). MRC supports guaranteed, instantaneous recovery from any single link or node failure in biconnected networks as well as from many combined failures, provided sufficient bandwidth on the surviving links. Furthermore, in MRC different failures result in routing over different network topologies, which gives a good control of the traffic distribution in the networks after a failure

Recovery of traffic in connectionless pure IP networks has traditionally been handled by a full re-convergence of the network state. This process operates in a time scale that is not compatible with new real time and highly dependable services. Recently, schemes for fast local and proactive recovery in connectionless IP networks have been proposed. All these schemes are designed to guarantee recovery of the failure of one component. As IP protocols are used to carry more highly dependable services and new wireless infrastructures are approaching, guaranteed failure coverage of more than one failure becomes necessary. In this paper we present and evaluate a scheme that guarantees to handle any two concurrent failures in a network. We are not aware of any other schemes that addresses such guarantees. We evaluate and compare it with other known recovery schemes, and we show how it gives substantially better recovery success rates than the schemes designed for one fault tolerance, also for more than two failures.

In this article we investigate the effects of increased Control Packet lead Time (CPT) on the loss probability of bursts in an OBS network with deflection routing. In particular we investigate burst loss caused by bursts overtaking their control packets, and bursts losses caused by blocking. We have made a detailed discrete event simulation model of OBS networks and evaluated the performance of hot potato deflection when bursts are routed connectionless from ingress to egress. To our knowledge such detailed investigations into the effects of increased control packet lead time and causes of burst losses have never been performed before. We conclude that increased control packet lead time gives better performance, in particular for low loads. We also conclude that there might be a point of diminishing return, above which the increase in CPT does not decrease the burst loss enough to justify the larger burst latency.

This paper demonstrates that the algorithmic performance of end user programs may be greatly affected by the two or three level caching scheme of the processor, and we introduce a general but simple model that estimates this effect with good accuracy. Using 4 different processors and two simple tests, we demonstrate that a number of random reads and writes in an array can have a penalty factor of 40-70 compared to the exact same number of sequential array accesses. These effects from cache misses first occur when a randomly accessed array is larger than the L1 cache and even more so when the array does not fit in the much larger L2 cache. A similar but much smaller effect between sequential reads and writes in large arrays compared with smaller arrays is also reported. In the second part of this paper three versions of the well known Radix algorithm is used to demonstrate that the 'artificial' results from the first part definitely occur in practice. These versions use one, two and three digits, and hence one, two or three full passes to sort an array. For small arrays the two and three digit Radix algorithms of course are much slower than the one digit version, but for larger arrays the former outperform the latter. For comparison, the radix sorting execution times are compared to Quicksort and Flashsort, a different one-digit sorting algorithm, both of which are outperformed by the two and three digit Radix algorithms. Finally, a simple model based on the penalty of cache misses is introduced, and we use this model to explain the demonstrated differences in algorithmic efficiency.

The slow convergence of IGP routing protocols after a topology change has led to several proposals for proactive recovery schemes in IP networks. These proposals are limited to guaranteeing loop-free connectivity after a link or node failure, and do not take into account the resulting load distribution in the network. This can lead to congestion and packet drops. In this work, we show how a good load distribution can be achieved in pure IP networks immediately after a link failure, when multiple routing configurations (MRC) is used as a fast recovery mechanism. This paper is the first attempt to improve the load balancing when a proactive recovery scheme is used. Unlike load balancing methods used with normal IP rerouting, our method does not compromise on the routing performance in the failure free case. Our method is evaluated using simulations on several real and synthetically generated network topologies. The evaluation shows that our method yields good routing performance, making it feasible to use MRC to handle transient network failures.

Abstract — As the Internet takes an increasingly central role in our communications infrastructure, the slow convergence of routing protocols after a network failure becomes a growing problem. To assure fast recovery from link and node failures in IP networks, we present a new recovery scheme called Multiple Routing Configurations (MRC). MRC is based on keeping additional routing information in the routers, and allows packet forwarding to continue on an alternative output link immediately after the detection of a failure. Our proposed scheme guarantees recovery in all single failure scenarios, using a single mechanism to handle both link and node failures, and without knowing the root cause of the failure. MRC is strictly connectionless, and assumes only destination based hop-by-hop forwarding. It can be implemented with only minor changes to existing solutions. In this paper we present MRC, and analyze its performance with respect to scalability, backup path lengths, and load distribution after a failure. I.

Most existing methods for network recovery are often complex and seldom used by network administrators. In this paper we present a novel approach for global and local recovery named resilient routing layers (RRL). The method is supported by algorithms, but also simple enough for a network administrator to implement by hand for reasonably sized networks. The idea in our approach is that for each node in the network there is a topology subset called a "safe layer", which can handle any traffic affected by a fault in the node itself, or any of its links. We demonstrate that our approach performs well compared to other comparable methods in a wide range of different network topologies. Particularly, we demonstrate RRLs performance for what are assumed to be the weakest parameters for our method, i.e., backup-path lengths and state information overhead. We discuss implementation issues of RRL, and demonstrate its applicability to MPLS networks.

Resilient packet ring (RPR, IEEE std. 802.17-2004) is a recent networking standard developed by the IEEE LAN/MAN working group. RPR is an insertion buffer, dual ring technology, utilizing a back pressure based fairness algorithm to distribute bandwidth when congestion occurs. In its attempt to control a set of nodes' sending behavior over a congested link, the RPR fairness algorithm suffers from two severe performance deficiencies. The first concerns how the node closest to a congested link calculates a fair rate estimate, the second deficiency relates to the method used to distribute this fair rate estimate to nodes upstream from the congested node. In this paper, we analyze these deficiencies and propose improvements to resolve them.

Resilient packet ring (RPR) is a new standard, designated IEEE standard number 802.17, for MAN and WAN dual ring topologies. RPR uses the buffer insertion principle as a basis for its medium access control protocol. In this paper, we analyze parts of the aggressive mode of the RPR fairness protocol. We look at a congested node, and utilize control systems theory to analyze the stability of the associated fairness algorithm. In particular, we discuss how the settings of the two important parameters ageCoef and IpCoef influence the stability of an RPR-network. At the end of the paper we present simulated scenarios in order to illustrate our results.

We present a novel scheme for network recovery, named resilient routing layers (RRL). Our proposed scheme is based on calculating fully connected topology subsets, termed layers, which are used to forward traffic in case of a network failure. For the purpose of this work, the layers are created to protect against link failures only. RRL keeps pre-calculated backup routing information in the network stations. This allows local response to network failures, which gives recovery in the order of milliseconds. The main strengths of our approach are its flexibility, as it is independent of the network technology used, and its simplicity, as it offers the network operator a simple and coherent view of the resources available after a link failure. We also show that our scheme scales well for networks of several hundred nodes.

Resilient packet ring (RPR, IEEE 802.17) is designed with a protection mechanism aiming at restoring traffic on the ring within 50 ms in case of a link or node failure. However, the total experienced disruption time often exceeds this if strict order delivery of packets is required, since a 40 ms (configurable from 10 ms to 100 ms) topology stabilisation timer is used to avoid packet reordering. In this article, we present three alternative ways to avoid packet reordering for strict order traffic in RPR networks. The three suggested methods are discussed analytically, and simulations are used to compare their performance. Our simulation results suggest that the new methods give up to 90% reduction in packet loss during a failure situation compared to the current RPR standard

Optical burst switching (OBS) is a much researched paradigm for the next generation optical Internet. We have made a detailed discrete event simulation model of OBS networks. Among other things our model includes self similar traffic sources, burst assembly with fixed and variable length bursts, burst scheduling, wavelength conversion and fiber delay lines. In this paper we simulate a large optical burst-switched backbone network using the COST 239 network topology that connects 11 European cities. The performance of this realistic network is investigated, mainly by varying the load and the number of channels (lambdas). We propose and evaluate a new method for the utilization of otherwise unused network capacity by very low priority traffic. Other interesting results include how total burst loss increase when high priority bursts are used.

Resilient packet ring (RPR) is currently being standardized by the Institute of Electrical and Electronics Engineers (IEEE), within the 802.17 working group. RPR is a dual ring based medium access protocol based on the "buffer insertion" principle. Instead of controlling the access to the ring using a circulating token, each station on the ring executes its part of a distributed fairness algorithm. The task of the fairness algorithm is to ensure that all stations gets their fair share of the bandwidth, when there is more demand than supply. This article discusses how the RPR fairness algorithm is able to divide the bandwidth fairly among contending stations as well as the requirements for this to work correctly. We discuss how and when the fairness algorithm fails to converge to a fair value, and what is needed in order to make it converge. Finally we show that the setting of the RPR IpCoef configuration parameter is of crucial importance for the convergence of the fairness algorithm as well as some guidelines for setting this correctly. To do this, we first present some analytical work, of which some were contributed to the RPR working group and is now incorporated in the standard. We explain our approach using an informal "proof by induction".

In this paper we argue that widely shared data are a more serious problem than previously recognized, and that furthermore, it is possible to provide transparent support that actually gives an advantage to accesses to widely shared data by exploiting their redundancy to improve accessibility.The GLOW extensions to cache coherence pmtocofs -previously proposed-provide such support for widely shared data by defining functionality in the network domain.However in their static form the GLOW extensions relied on the user to identify and expose widely shared data to the hardware.This approach suffers because: i) it requires modification of the programs, ii) it is not always possible to statically idenhfi the widely shared data, and iii) it is incompatible with cornmod@ hardware.To address these issues, we study three dynamic schemes to discover widely shared data at runtime.The first scheme is inspired by read-combining and is based on observing requests in the network switches -the GLOW agents.The agents intercept requests whose addresses have been observed recently.This scheme tracks closely the pegormance of the static GLOW while it always outpelfomrs ordinary congestion-based readcombining.In the second scheme, the memory directory discovers widely shared data by counting the number of reaa!s between writes.Information about the widely shared nature of data is distributed to the nodes which subsequently use special wide sharing requests to access them.Simulations confrm that this scheme works well when the widely shared nature of the data is persistent over time.The third and most significant scheme is based on predicting which load instructions are going to access widely shared data.Although the implementation of this scheme is not as straighrforwani in a commodity-parts environment, it outperforms all others. 1 Introduction Shared-memory multiprocessing is only attractive if it can support a programming paradigm and programming languages efficiently.Numerous studies have characterized the sharing patterns of programs that have been written for such multiprocessors [25], and it is generally believed that widely shared data occur infrequently and do not significantly affect performance.In this paper we argue that in fact widely shared data inherent in some parallel algorithms are a more serious problem than previously recognized, and that furthermore, it is possible to provide support that actually gives an advantage to widely shared data.The idea of read-combining [ 1 l] evolved because of the concern for network contention for widely shared data.Read-combining is highly dynamic, and reduces traffic in the network by recognizing