Search

This work studies the allocation of bandwidth resources in wireless ad hoc networks. The highest-density clustering algorithm is presented to promote reuse of the spatial channel and a new slot allocation algorithm is proposed to achieve conflict-free scheduling for transmissions. Since the location-dependent contention is an important characteristic of ad hoc networks, in this paper we consider this feature of ad hoc networks to present a new cluster formation algorithm, by increasing the number of simultaneous links to enhance spatial channel reuse. Furthermore, because each cluster has its own scheduler and schedulers operate independently of each other, the transmissions may conflict among the clusters. In this paper, we classify the flows by the locations of their endpoints to prevent this problem. Finally, the proposed mechanism is implemented by simulation and the results reveal that the conflicts can be efficiently avoided without global information and the network throughput is improved without violating fairness. [ABSTRACT FROM AUTHOR]

The importance of multiuser detection for CDMA-based ad hoc network is addressed in this paper. Conventionally, the terminal in CDMA-based ad hoc network uses matched filter to receive packets, so the performance (e.g., throughput) of the network suffers from multi-access interference (MAI). Different from above scheme, in this paper, each terminal of the ad hoc network is equipped with an adaptive blind linear multiuser detector, so the ability of MAI-resistance is gained. Based on fully-connected network model and Log-distance path loss radio propagation model, the throughput of ad hoc network with multiuser detection is studied. Simulation results show that multiuser detection can remarkably enlarge the throughput of ad hoc network. [ABSTRACT FROM AUTHOR]

The viability of overlay multicasting has been established by previous research. However, in order to apply overlay multicast to Internet-scale distributed systems, such as the Grid and Peer-to-Peer systems, the issue of effectively enforcing fairness among peers so as to optimize overall performance remains as a challenge. This paper argues that simply applying a multiple-tree scheme does not provide sufficient fairness, in terms of performance. Instead, we believe that a better way to define fairness, for performance's sake, is to factor in peers' proportional contributions as it provides the opportunity to support many simultaneous multicasting sessions. This paper then presents a protocol, called FairOM (Fair Overlay Multicast), to enforce proportional contributions among peers in Internet-scale distributed systems. By exploiting the notion of staged spare capacity group and deploying a two-phase multicast forest construction process, FairOM enforces proportional contributions among peers, which enables more simultaneous multicasting sessions and alleviates potential hot-spots. The simulation results of a large multicast group with 1000 members show that FairOM achieves the goal of enforcing proportional contributions among peers and does not overwhelm the peers, including the multicast source. FairOM also achieves low delay penalty for peers and high path diversity. [ABSTRACT FROM AUTHOR]

Ad hoc networks became a hot topic recently, but the routing algorithm of anycast in the ad hoc networks has not yet been much explored. In this paper, we propose a mesh-based anycast routing algorithm (MARP) for ad hoc networks. The proposed routing model is robust and reliable, which can solve the unsteady topology problem in ad hoc networks. The future work is discussed at the end of this paper. [ABSTRACT FROM AUTHOR]

Many schemes had been used to reduce the performance (or speed) gap between processors and main memories; such as the cache memory is one of the most methods. In this paper, we issue the structure of shared cache, which is based on the multiprocessor architectures to reduce the memory latency time that is the one of major performance bottlenecks of modern processors. In this paper, we mix two schemes, sharing cache and multithreading, to implement this proposed multithreaded architecture with shared cache, to reduce the memory latency and, furthermore improve the processor performance. In this proposed multithreaded architecture, the shared cache is achieved in level-1 (L1) data cache. The L1 shared data cache is combination of cache clock in the single space address and a cache controller to solve the required data transmitting, data copies simultaneously, and reduce memory latency time. Keywords: Discrete processor architectures, cache coherency, multithreading, memory latency, shared cache, write-invalidate (WI), and cache block. [ABSTRACT FROM AUTHOR]

In fault-tolerant multistage interconnection design, the method of providing disjoint paths can tolerate faults, but it is complicated and hard to choose a collision-free path in disjoint paths networks. A disjoint paths network can concurrently send more identical packets from the source node to increase the arrival ratio, but the method might increase the collision ratio. In contrast, a dynamic rerouting method finds an alternative path that tolerates faults or prevents collisions. In this paper, we present methods of designing dynamic rerouting networks. This paper presents 1) three kinds of dynamic rerouting networks designed to tolerate faults and prevent collisions; 2) design schemes that enable a dynamic rerouting network to use destination tag routing to save hardware cost in switches for computing rerouting tags; and 3) simulation results of related dynamic rerouting networks to realize the factors which influence the arrival ratio including the fault tolerant capability and the number of rerouting hops. According to our proposed design schemes and according to our analysis and simulation results, a designer can choose an applicable dynamic rerouting network by using cost-efficient considerations. Keywords: Parallel computing, multistage interconnection network (MIN), dynamic rerouting, fault tolerance, collision, performance, destination tag routing. [ABSTRACT FROM AUTHOR]

Message Passing Interface (MPI) Collective Communication Functions (MCCF) are usually implemented in programming libraries utilizing invariable algorithms. Not always do such algorithms yield the best performance with all kinds of applications and over all execution environments. In this paper, we present, simulate, analytically model, verify and analyze reconfigurable MCCF that present variable structures and behaviors, in order to provide optimized configurations, flexibility and performance. In this paper we propose and present a set of optimized reconfigurable MCCF, which add flexibility and high performance to collective communications. We simulate, analytically model, verify and analyze the proposed functions, and compare them with invariable implementations. Our results show that reconfiguration at the algorithm level really yields flexibility and performance gains in MCCF. [ABSTRACT FROM AUTHOR]

Mining association rules from multi-stream data has received a lot of attention to the data mining community. It is quite effective and useful to discover such rules. However, it is a very time consuming and expensive task to mine the rules from these kinds of time ordered real valued continuous data sets with high dimensionality when they are enormous in size. This strongly motivates the need of efficient parallel processing techniques and algorithms. In this paper, we use parallel processing to discover dependency from the large amount of time series multi-stream data. We apply two parallel programming techniques (OpenMP and MPI) to implement this. The experimental results conducted in multiprocessor systems show the effectiveness of MPI over OpenMp. [ABSTRACT FROM AUTHOR]

Scientific collaboration has emerged as an important tool for getting forefront research results by interoperating geographically distributed scientific equipment to solve complicated scientific problems. Grid technologies offer effective strategies to achieve this ambitious goal. However, more capabilities are required in the context of Equipment Grid due to the complexity of collaboration between equipment resources. In this paper an interesting equipment interoperation chain model is proposed. Equipment resources are organized into equipment pools, based on which the interoperation chain of equipment is built. The performance is discussed by means of several theoretical tools like Petri Net and π-Calculus from the different viewpoint of users. The structure of interoperation chain is proven highly efficient and feasible. Finally we analyze the prospective direction and challenges in this field. [ABSTRACT FROM AUTHOR]

Route caching strategy is an important on-demand routing protocol for mobile ad hoc networks. On-demand routing protocol for mobile ad hoc networks utilizes route caching in different forms to reduce overheads, peer-to-peer delay. This paper presents a variation in view compared to DSR and HER, to minimize cache staleness, partitions and enhance reliability of service. The variation is with respect to identification of route and cache validation of errors using different techniques namely Update Route Caching (URC), Temporal Cache Validation (TCV), Negative Cache Validation (NCV) and Combined Cache Validation (CCV). The proposed method refreshes cache more often than the DSR and HER thereby initiating route requests earlier, when a route still being used is broken, thus reducing peer to peer delay to transmit packets. The results of GloMoSim simulator validates higher cache hit percentage and reliable delivery of packets in the technique Combined Cache Validation (CCV) when in comparison to DSR and HER [ABSTRACT FROM AUTHOR]

The use of periodic invalidation reports (IRs), has been shown to be a useful technique for conserving wireless bandwidth and battery power. However, IR-based schemes have some drawbacks, such as long query delay and low client caching availability, even if the clients have sufficient local cache capacity. In this paper, we propose an efficient cache access protocol to address these problems. Instead of passively waiting, the clients use the local cache actively. Using our protocol, we can remove the "false alarm" that causes unnecessary delay. Based on our threshold-based scheme, the proposed protocol can optimize response time with little loss of data currency. Our simulation results are carried out to evaluate the proposed methodology. Compared to previous IR-based schemes, our scheme can reduce the response time significantly with a very little loss of data currency. [ABSTRACT FROM AUTHOR]

The Internet is replacing the traditional telephone network as the ubiquitous network infrastructure. Internet customers are increasing at an exponential rate and will continue to increase in the near future. With the proliferation of mobile communication technologies and wireless personal devices, the demand for mobile communications has grown exponentially over the last decade and is expected to grow even more in the near future. This paper proposes a new bandwidth allocation scheme that guarantees the time independent fairness and fault tolerance in the heterogeneous mobile communication services. It will hold some calls in the second buffer rather than directly discarding it when the residual bandwidth is insufficient. A multimedia call that satisfies all connection requirements has precedence over other calls. [ABSTRACT FROM AUTHOR]

In this paper, we proposed a new QoS framework with Distributed Adaptive Resource Management(DARM). DARM provides end-to-end QoS guarantees to individual flows with minimal overhead, while keeping the scalability characteristic of DiffServ. In DARM, per-flow admission control and resource reservation, in conjunction with a novel IPv6 flow label mechanism, can be processed instantaneously in a fully distributed and independent manner at edge of network without hop-by-hop signaling. In addition, DARM is capable of reconfiguring network resource adaptively according to dynamically changing of traffic load. Through extensive simulations, the results clearly exhibit that DARM has a better overall performance comparing to the IntServ and DiffServ. [ABSTRACT FROM AUTHOR]

Next-generation network (NGN) is a new concept and becoming more and more important for future telecommunication networks. This paper illustrates five function layers of NGN architecture and discusses some end-to-end QoS (quality of service) issues for NGN (called NGNQoS). The five function layers are: (1) Application Layer that supports SIP protocol; (2) Network Control Layer that aims at overcoming the bottleneck problems at edge nodes or servers for end-to-end admission control; (3) Adaptation Layer that supports different network configurations and network mobility; (4) Network Transmission Layer that provides end-to-end QoS control for real-time communications through integrating Differentiated Service (DiffServ) and Multi-Protocol Label Switching (MPLS) and (5) Management Layer that provides Web-based GUI browser for data presentation, monitoring, modification and decision making in NGN. [ABSTRACT FROM AUTHOR]

Managing distributed ontologies is a challenging issue in the Semantic Web area. Different to most current distributed ontologies management researches, which focus on ontologies maintenance, evolutions, and versioning, this paper proposes a new distributed ontologies management framework based on the function-oriented perspective, and its goal is to bring multiple distributed ontologies together to provide more powerful capabilities. Ontology mapping is the key factor for manage distributed ontologies. This management framework also proposes a novel approach to eliminate the redundancies and errors of mappings in distributed ontologies. [ABSTRACT FROM AUTHOR]

With the frequent changes in recent business and scientific environment, more efficient and effective workflow infrastructure is required. Besides, with increasing emphasis on Service-oriented architecture, service composition becomes a hot topic in workflow research. This paper proposes a novel approach of using ECA rules to realize the workflow modeling and implementation for service composition. First of all, the concept and formalization of ECA rule-based Workflow is presented. Second, an automatic event composition algorithm is developed to ensure the correctness and validness of service composition at design time. Finally, the proposed ECA rule-based approach for service composition is illustrated through a prototype system. [ABSTRACT FROM AUTHOR]

Multicast mobility management poses a great challenge in mobile Internet. This paper proposes a novel multicast mobility management algorithm using our proposed RingNet hierarchy, which takes advantage of our designed four states for mobility management: Not-in-the-group, PassiveReservation, QuasiReservation, and ActiveReservation, and two kinds of ranges which are closely related to a Mobile Host (MH) 's attached device called the Access Proxy (AP): TransmissionRange and ReservationRange. By judging the state of the AP and the distance between the AP and its attaching MH, operations of mobility management can be implemented. The introduction of prediction algorithm greatly decreases the blindness of resource reservation, and avoids the unnecessary waste of bandwidth. Furthermore, the introduction of resource reservation makes the smooth handoff highly probable. [ABSTRACT FROM AUTHOR]

In this paper, we first present a simple and effective path capacity predicting method to model the complex interaction between medium access mechanism and routing scheme. Based on the predicting model, an end-to-end cross-layer flow control architecture is proposed. The key issues about flowing control are discussed deeply. As we designed, whenever the path length changes, the applications adaptively modify their sending rate with the pre-computed optimal value. Simulation evaluation has demonstrated that this technique can greatly improve the performance of end-to-end transmission in ad hoc network: the throughput of the long path is improved by up to 40%. [ABSTRACT FROM AUTHOR]

The long-tailed distribution characterizes many properties of Internet traffic. The property is often modeled by Lognormal distribution, Weibull or Pareto distribution theoretically. However, it hinders us in traffic analysis and evaluation studies directly from these models due to their complex representations and theoretical properties. This paper proposes a Hyper-Erlang Model (Mixed Erlang distribution) for such long-tailed network traffic approximation. It fits network traffic with long-tailed characteristic into a mixed Erlang distribution directly to facilitate our further analysis. Compared with the well-known hyperexponential based method, the mixed Erlang model is more accurate in fitting the tail behavior and also computationally efficient. [ABSTRACT FROM AUTHOR]

Nowadays, the Internet architecture is complicated and IP addresses are limited in IPV4 context. Many users located behind different kinds of NATs or Firewalls can hardly get a public unique IP. So the hosts behind the NAT can not be accessed by the hosts behind the other NATs. Some P2P systems can partially solve such kind of problems, but unfortunately, these systems just focus the specific self-contained applications such as Skype and BitTorrent whose P2P architectures and NAT traversal mechanisms can not be re-used by other applications directly. In this paper we present a solution by setting up a Virtual Intranet Platform (VIP) which use the public DHT service -OpenDHT as the distributed address/port information rendezvous. Without changing the configuration of the NAT, all the network and distributed application service behind the NAT can make use of the VIP to communicate with the corresponding peer services outside the NAT. The performance of the bandwidth, data lost and delay problems are much better than the existing traditional C-S framework platforms, more general than specific P2P applications. The P2P Communication Platform for NAT Traversal-VIP, is robust and scalable because there are no single failure points in the platform, the structure is in distributed, and majority of the traffic data between two hosts behind the NAT can be transfer directly without relaying. [ABSTRACT FROM AUTHOR]

High availability in peer-to-peer DHTs requires data redundancy. This paper takes user download behavior into account to evaluate redundancy schemes in data storage and share systems. Furthermore, we propose a hybrid redundancy scheme of replication and erasure coding. Experiment results show that replication scheme saves more bandwidth than erasure coding scheme, although it requires more storage space, when average node availability is higher than 48%. Our hybrid scheme saves more maintenance bandwidth with acceptable redundancy factor. Keywords: Peer-to-Peer, Distributed Hash Table, Replication, Erasure Coding. [ABSTRACT FROM AUTHOR]

The current P2P application protocols are usually constructed over the application-level overlay network. However, because the users in the P2P systems always follow a very dynamic mode, the overlay network with poor performance will leads to the problem of connectivity—the departures of peers often break the network into plenty of small parts, and results in the resource islands. Although increasing the links between peers can enhance the performance of connectivity by information redundancy. But it will lead to the severe cost of maintenance. Then there is an urgent need to integrate the online peers as a "giant component" as large as possible, so that the resources online can be shared completely; at the same time to guarantee the cost of maintenance as little as possible. And due to the prevalence and significance of small world in reality and theory, in this paper we analyzed the correlation between the shortcuts density and the connectivity, as well as the impact of shortcuts density to robustness over the popular WS Small World model. At last, numerical simulation was done to confirm our analytic results. [ABSTRACT FROM AUTHOR]

Power conservation is a critical issue in mobile ad hoc networks, as the nodes are powered by batteries only. In this paper, according to the mobility of nodes, the power-aware dynamic adaptive replica allocation algorithm is proposed. In the power-aware dynamic adaptive replica allocation algorithm, based on the locality of data access, the replica allocation scheme is adjusted regularly in order to reduce the power consumption, and thus extend the survival time of network. The relation between mobility models and efficiency of power-aware dynamic adaptive replica allocation algorithm is studied. The results of performance evaluation show that the power-aware dynamic adaptive replica allocation algorithm can reduce the total power consumption of network greatly. [ABSTRACT FROM AUTHOR]

Call Admission Control (CAC) is crucial for assuring the quality of service (QoS) of communication in wireless cellular networks. In this paper, we propose a model, called Guard Channel Prediction Model (GCPM), for efficient call admission control satisfying the QoS requirements. A predictive value of the appropriate number of guard channels can be calculated based on this model by using statistical properties of new and handoff call arrival rates and mean call residency time, as well as the total capacity of a specific cell. Simulation studies are carried out to evaluate the performance in comparison with an existing adaptive algorithm under variable traffic loads and mobility patterns. Simulation results show that our proposed GCPM, using the static and fractional Guard Channel policy to process both types of incoming calls based on the predictive values, has gained better QoS with less blocking probabilities of both types of calls and meanwhile, larger network utilizations. Keywords: Call Admission Control, Guard Channel, Guard Channel Prediction Model (GCPM), Quality of Service (QoS), Wireless/Mobile Cellular Networks. [ABSTRACT FROM AUTHOR]

The way conventional Ethernet is used today differs in two aspects from how dedicated system area networks are used. Firstly, dedicated system area networks are lossless and only drop frames when bit errors occur, while conventional Ethernet drop frames whenever congestion occur. Secondly, these networks are either deadlock free or use mechanisms which avoids deadlock situations, while still using all available links. Ethernet avoids deadlocks by using a spanning tree protocol which turns any topology into a tree. A drawback of this approach is that we are left with a lot of unused links and thus wasting resources. In this paper we describe how to obtain a lossless deadlock free network with the best possible performance, while adhering to the current Ethernet standard and using off-the-shelf Ethernet equipment. We achieve this by introducing flow control in all network nodes and by taking control over the routing algorithm. Also, we use TCP to illustrate the effect of flow control on higher layer protocols. Through simulations we verify the following tree improvements. Firstly, the activation of flow control turns Ethernet into a lossless network. Secondly, taking control over the routing algorithm allows us to build any topology without the limitations of the spanning tree protocol. And thirdly, an overall improvement in throughput is achieved by combining these enhancements. [ABSTRACT FROM AUTHOR]

The goal of geocasting protocols is to deliver data packets to a group of nodes that are within a specified geographical area, i.e., the geocast region. In an ad hoc environment, there are numerous scenarios which benefit from geocast communication. In this paper, the network is divided into grids, we propose a new routing protocol for geocasting, which combines anycast and flood. The proposed protocol utilizes the location information to route messages in grid-by-grid manner. The routing path by using proposed protocol is the shortest route between hosts in grids. The grid structure is successfully used to eliminate redundant transmission of geocasting messages. The time complexity of route discovery and the routing overhead are reduced. [ABSTRACT FROM AUTHOR]

As an enhancement mechanism for the end-to-end congestion control, Active Queue Management (AQM) can keep smaller queuing delay and higher throughput by proposing fully dropping the packets at the intermediate nodes. comparing with RED algorithm, although PI controller for AQM designed by Hollot improves the stability, it seems other methods to design of robust controllers may lead to better results. Morover, the transient performance of PI controller is not perfect, such as the regulating time is so long. In order to overcome to this drawback, in this paper, a novel adaptive fuzzy logic based controller is designed for Active Queue Management (AQM) in TCP/AQM networks. From control point of view, it is rational to regard AQM as a typical regulation system. Recently many AQM algorithms have been proposed to address performance degradations of end-to-end congestion control. However, these AQM algorithms show weaknesses to detect and control congestion under dynamically changing network situations. A simulation study over a wide range of IP traffic conditions shows the effectiveness of the proposed controller in terms of the queue length dynamics, the packet loss rates, and the link utilization. [ABSTRACT FROM AUTHOR]

Because of the limited bandwidth, wireless communication in mobile environments is much more expensive than the communication cost in wired network. Thus, to save the cost of wireless communication, during the process of wireless Web page access, mobile unit usually prefetches some Web pages into its local cache and then disconnect itself from the network, so that updates are performed in its local cache and propagated back to Web server upon reconnection again. In this paper, after discussing the design rationale of a new Web page access mechanism, the performance of this mechanism is analyzed theoretically and experimentally. The results show that the efficiency of update propagation is improved and the burden of Web server is decreased. [ABSTRACT FROM AUTHOR]

This paper proposes a workflow management mechanism to address a neglected aspect of existing P2P computing platforms - the lack of support for various computational models. In the workflow management mechanism, a workflow description file is used to define the workflow diagram of the target application. We develop a prototype system, and evaluate it using a test program to demonstrate how the workflow management mechanism effectively works. [ABSTRACT FROM AUTHOR]

Today many current and emerging applications require support for on-line analysis of rapidly changing data streams. Limitations of traditional DBMSs in supporting streaming applications have been recognized, prompting research to augment existing technologies and build new systems to manage streaming data. Stream-oriented systems are inherently geographically distributed and because distribution offers scalable load management and higher availability, future stream processing systems will operate in a distributed fashion. Moreover, service-based approaches have gained considerable attention recently for supporting distributed application development in e-business and e-science. In this paper, we present our innovative work to build a large scale distributed query processing over streaming data, this system has been designed as a WSRF-compliant application built on top of standard Web services technologies. Our distributed data stream Queries are written and evaluated over distributed resources discovered and accessed using emerging the WS-Resource Framework specifications. The data stream query processor has been designed and implemented as a collection of cooperating services, using the facilities of the WSRF to dynamically discover, access and use computational resources to support query compilation and evaluation. [ABSTRACT FROM AUTHOR]

With the help of distributed hash tables, the structured peer-to-peer system has a short routing path and good extensibility. However, the mismatch between the overlay and physical network is the barrier to build an effective peer-to-peer system in the large-scale environment. In this paper, we propose a generic approach to solve this problem, which is quite different from other protocol-dependent methods. We reserve the structure of system and break the coupling between the node and its identifier by swap operations. We also propose several policies to reduce the traffic overhead. The policies include adaptive probing and shadow scheme. The experiment shows that our approach can greatly reduce the average latency of overlay networks and the overhead is controllable. Keywords: peer-to-peer, overlay network, topology-aware, stretch. [ABSTRACT FROM AUTHOR]

Authentication protocols are essential for security in many systems. However, authentication protocols are error-prone and difficult to design. In pervasive computing, the inherent characteristics such as mobility and restricted resources make it even harder to design suitable authentication protocols. In this paper we propose an authentication protocol to solve an open problem in pervasive computing, that is secure use of public information utilities without accessing a trusted third party (TTP). Our solution not only provides authentication, but also establishes a secure communication channel between the user and the service provider without the participation of TTP. The authentication protocol can be built with any secure symmetric and asymmetric cryptographic algorithm. We show the protocol can resist passive and active attacks. We also discuss how the protocol can be extended to an applicable scheme with payment support. Keywords: Authentication, Pervasive Computing Security, Public Key Infrastructure, E-Commerce. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new method to enhance the fault-tolerance of the Content Addressable Network (CAN), which is known as a typical pure P2P system based on the notion of Distributed Hash Table (DHT). The basic idea of the proposed method is to introduce a redundancy to the management of index information distributed over the nodes in the network, by allowing each index to be assigned to several nodes, which was restricted to be one in the original CAN system. To keep the consistency among several copies of indices, we propose an efficient synchronization scheme based on the notion of labels assigned to each copy in a distinct manner. The performance of the proposed scheme is evaluated by simulation. The result of simulations indicates that the proposed scheme really enhances the fault-tolerance of the CAN system. Keywords: Peer-to-peer system, fault-tolerance, distributed hash table, content addressable network. [ABSTRACT FROM AUTHOR]

Recent researches on energy efficient coverage configuration in wireless sensor networks mainly address the goal of 100% or near 100% coverage preserving. However, we find that a small percentage of loss of coverage, which is acceptable in many applications, can result in dramatic increase in energy savings. Therefore, in this paper percentage coverage rather than complete coverage is selected as the design goal, and a location-based Percentage Coverage Configuration Protocol (PCCP) is developed to assure that the proportion of the sensing area after configuration to the original sensing area is no less than a desired percentage. Numerical testing results show that PCCP can not only guarantee the desired coverage percentage but also generate more energy efficient configuration in comparison with the existing schemes so that the system lifespan is extended significantly. [ABSTRACT FROM AUTHOR]

One of the most important issues on the sensor network with resource-limited sensor nodes is prolonging the network lifetime by effectively utilizing the limited node energy. The most representative mechanism to achieve a long-lived sensor network is the clustering mechanism which can be further classified into the single-hop mode and the multi-hop mode. In the single-hop mode, all sensor nodes in a cluster communicate directly with the cluster head (CH) via single hop, so the contention-less MAC protocol is preferred. In the multi-hop mode, sensor nodes communicate with the CH with the help of other intermediate nodes and the contention-less MAC protocol is not required. One of the most critical factors that impact on the performance of the existing multi-hop clustering mechanism (in which the cluster size is fixed to some value, so we call this the fixed-size mechanism) is the cluster size and, without the assumption on the uniform node distribution, finding out the best cluster size is intractable. Since sensor nodes in a real sensor network are distributed non-uniformly, the fixed-size mechanism may not work best for real sensor networks. Therefore, in this paper, we propose a new dynamic-size multi-hop clustering mechanism in which the cluster size is adjusted according to the information on the load and the residual energy of a CH and that of other nodes near to the CH. We show that our proposed scheme outperforms other clustering mechanisms by carrying out simulations. [ABSTRACT FROM AUTHOR]

The current wireless sensor network designs are largely based on a layered approach. The suboptimality and inflexibility of this paradigm result in poor performance, due to constraints of power, communication, and computational capabilities. Key management plays an important role in wireless sensor networks, because it not only takes charge of securing link-layer communications between nodes, but also has great effects on other protocol layers, e.g. routing and IDS (Intrusion Detection System). However, no existing key management protocols have attached enough importance to cross-layering designs. In this paper, we propose a cross-layering key management scheme, which can provide other protocol layers with a nice trust-level metric. The trust-level metric is generated during the pairwise key establishment phase, and it varies as system conditions change. This metric describes the security level between two neighboring nodes and helps other protocol layers to make decisions. We also present simulations and analysis to show the superior characteristics of our scheme against both passive attacks and active attacks. [ABSTRACT FROM AUTHOR]

In this paper, we propose a distributed power-efficient data gathering and aggregation algorithm (DPEG), in which a node, according to its residual energy and the strength of signal received from its neighboring nodes, independently makes its decision to compete for becoming a cluster head. In addition, assume that the inter-cluster communication data is, in a multi-hop manner, sent to the designated node, which then sends the data gathered by the whole network to the base station. DPEG also proposes a simple approach to solve the cluster coverage problem. With the increase in node density, this approach lets sensor network lifetime be linear in the number of nodes. Our experimental results have proved that DPEG algorithm, in the best case, lets sensor network lifetime be respectively increased by 1800% and 300% as compared with another two data gathering and aggregation protocols— LEACH and PEGASIS. [ABSTRACT FROM AUTHOR]

In this paper, we introduce graph theory into transient stability analysis in power system. In the weighted graph, Vertex weight represents node's parallel computing workload and edge weight represents serial computing workload on the border of regions, which reflects the degree of parallelism of computing and improves speed-up ration of system. In order to reduce communication time wastage induced by CSMA protocol in TCP/IP based LAN, asynchronous message passing is used in our method. Simulation results show that it achieves better performance. [ABSTRACT FROM AUTHOR]

Service broker is a software component that maps user's request to proper services. By using the broker, users can access various services without any knowledge of the services. However, design of the service broker for GCE (Global Computing Environment) is quite difficult because a broker cannot cope with all the information of services which are spread over the world. Thus, we need to build new architectural foundations for global service brokering. In this paper, we propose a scalable broker system for GCE based on the federation of personalized brokers. In our broker system, every user can have a service broker. The broker maintains the information of services related to the user and exchanges the information with neighboring brokers if necessary. As a result, the broker can provide proper services to users faster and a burden of brokers can also be decreased. Experimental results show that the proposed service broker can reduce the average service discovery time and the average operation overhead of each broker comparing to other brokering architectures. [ABSTRACT FROM AUTHOR]

In this paper, a holistic approach to realize survivability of distributed information network systems for critical applications(DISCA) based on three basic states, processed, stored, and transmitted, of information (called a PST-based system model), is proposed and its evaluation method and some experiment results are given as an example of its application. A PST-based system model brings all three parts together and coordinates them through the services supported by them, in which whole system's survivability is embodied by system services and their interdependency relations. With this model, a multi-layer survivability framework based on the information states is formed and the complexity of a DISCA system in implementation and evaluation can be conquered in the most prevalent approach—"divide and conquer" approach. Keywords: DISCA, Survivability, Evaluation, PST-based model. [ABSTRACT FROM AUTHOR]

Simulation has been proved to be a practical approach for performance evaluation of mobile agents. However, the lack of a standard for the execution of mobile agents makes the semantics ambiguous. Thus, the simulation of mobile agents is not feasible or reasonable without an explicitly defined execution model of agents. In this paper, we propose an execution model of mobile agents called SMA. Based on the SMA model, the discrete event models describing the SMA agents and hosts, called SMA-DEVS, are presented using the modelling approach of DEVS and DSDE. We implement a simulation environment based on SMA-DEVS and test the environment with certain mobile agent-based algorithms. [ABSTRACT FROM AUTHOR]

This paper discusses a new approach that models the single node of general real-time wormhole networks, and analyzes this new model with queuing theory. Since the wormhole network's node is too complicated to analyze generally, a multi-vision solution is applied to analyzing the wormhole network's node. The wormhole network single-node model is decomposed into three sub-models, and each of them can be analyzed with queuing theory separately. Lastly, a simulation model is made with this solution, and several simulation results are presented to illustrate the performance of real-time wormhole scheduling in single-node. [ABSTRACT FROM AUTHOR]

In this paper we approach the solution of large instances of the distribution design problem. The traditional approaches do not consider that the size of the instances can significantly reduce the efficiency of the solution process, which only involves a model of the problem and a solution algorithm. We propose a new approach that incorporates multiple models and algorithms and mechanisms for instance compression, for increasing the scalability of the solution process. In order to validate the approach we tested it on a new model of the replicated version of the distribution design problem which incorporates generalized database objects, and a method for instance compression that uses clustering techniques. The experimental results, utilizing typical Internet usage loads, show that our approach permits to reduce at least 65% the computational resources needed for solving large instances, without significantly reducing the quality of its solution. [ABSTRACT FROM AUTHOR]

Mining frequent closed itemsets provides complete and non-redundant result for the analysis of frequent pattern. Most of the previous studies adopted the FP-tree based conditional FP-tree generation and candidate itemsets generation-and-test approaches. However, those techniques are still costly, especially when there exists prolific and/or long itemsets. This paper redesigns FP-tree structure and proposes a novel algorithm based on it. This algorithm not only avoids building conditional FP-tree but also can get frequent closed itemsets directly without candidate itemsets generation. The experimental results show the advantage and improvement of these strategies. Keywords: data mining; association rule; frequent closed itemsets; stack. [ABSTRACT FROM AUTHOR]

Clustering is a widely used technique in data mining, now there exists many clustering algorithms, but most existing clustering algorithms either are limited to handle the single attribute or can handle both data types but are not efficient when clustering large data sets. Few algorithms can do both well. In this paper, we propose a clustering algorithm CFIKP that can handle large datasets with mixed type of attributes. We first use CF*-tree to pre-cluster datasets. After the dense regions are stored in leaf nodes, then we look every dense region as a single point and use an improved k-prototype to cluster such dense regions. Experiments show that the CFIKP algorithm is very efficient in clustering large datasets with mixed type of attributes. [ABSTRACT FROM AUTHOR]

Data streams are massive unbounded sequence of data elements continuously generated at a rapid rate. Consequently, it is challenge to find frequent items over data streams in a dynamic environment. In this paper, a new novel algorithm was proposed, which can capture frequent items with any length online continuously. Furthermore, several optimization techniques are devised to minimize processing time as well as main memory usage. Compared with related algorithm, it is more suitable for the mining of long frequent items. Finally, the proposed method is analyzed by a series of experiments and the results show that this algorithm owns significantly better performance than before. [ABSTRACT FROM AUTHOR]

The conventional computing grid has developed a service oriented computing architecture with a super-local, two commit scheduling strategy. This architecture is limited in modeling open systems with highly dynamic and autonomous computing resources due to its server-based computing model. The use of super-local scheduling strategy also limits the utilization of the computing resources. In this paper, we propose a multi-agent based grid computing infrastructure to tackle the above issues, while provide reasonable compatibility and interoperability with the conventional grid systems and clients. Compared with the existing grids, the new infrastructure is leveraged by the intelligent agents, and therefore is more efficient and flexible for open systems. [ABSTRACT FROM AUTHOR]

The ShanghaiGrid, as a Grid Computing Environment, is an information Grid to serve the public in the city, and all resources are regarded as Grid Services in the Open Grid Services Architecture (OGSA). The primary goal of the ShanghaiGrid is to build a generally shared information grid platform. Charging and accounting are an important part of the grid computing system in the ShanghaiGrid. This paper discusses an accounting services model and accounting life cycle that will be used in the ShanghaiGrid. We will analyze the charging and accounting process in detail based on this model and cycle. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the recent popular computing technique called Grid Computing, and use video conversion and 3D rendering applications to demonstrate this technology's effectiveness and high performance. We also report on developing a resource broker called Phantom that runs on our grid computing testbed and whose main function is querying nodes in grid computing environments and showing their system information to aid in selecting the best nodes for job assignments to have the jobs executed in the least amount of time. Keywords: Grid computing, Resource broker, Job submission, Video conversion, 3D rendering. [ABSTRACT FROM AUTHOR]

With the dramatic development of grid technologies, performance analysis and prediction of grid systems is increasingly significant to develop a variety of new grid technologies. The VEGA grid, a new grid infrastructure developed by Institute of Computing Technology, CAS, views a grid as a distributed computer system. In this paper, we propose some new metrics to evaluate the performance of it. Moreover, we apply queueing system models to model the VEGA grid and predict the performance of it in terms of the mean queue length and mean service time, especially, in the equilibrium state. Hence, a real application, the Air booking service, is deployed on the VEGA grid as a benchmark to measure the performance via latency and throughput. Finally, we point out this method can be used on other homogeneous grid systems. [ABSTRACT FROM AUTHOR]