Improvements in computer and networking technologies over the past decades produced new type of collaborative computing environment called grid networks. Grid is a parallel and distributedcomputing network system tha...
详细信息
Improvements in computer and networking technologies over the past decades produced new type of collaborative computing environment called grid networks. Grid is a parallel and distributedcomputing network system that provides the ability to perform higher throughput computing by taking advantage of many computing resources available in the network. Therefore, to achieve a scalable and reliable grid network system, we need to efficiently distribute the load among the resources accessible on the network. In this paper, we present a distributed and scalable load- balancing framework for grid networks. The generated network system is self-organized and depends only on local information for load distribution and resource discovery. Simulation results show that the generated network system provides an effective, scalable, and reliable load-balancing scheme for the distributed resources accessible on grid networks.
To study the progress risk of IUR commissioned R&D project, this paper identifies progress risk source first, then forecasts the R&D time required in total by constructing GERT network model of R&D flow. I...
详细信息
To study the progress risk of IUR commissioned R&D project, this paper identifies progress risk source first, then forecasts the R&D time required in total by constructing GERT network model of R&D flow. In the quantitative analysis, the mason formula is used to compute the transfer function of the GERT, and the moment generating function is used to compute the probability distribution of the R&D time and costs. This analytical solution is used to describe the risk of the commissioned R&D project. An example is given to illuminate how to use this analytical algorithm in the end.
distributed applications are realized by cooperation of a group of multiple objects. An object multicasts a message to multiple destinations and sends in parallel multiple messages to multiple destinations, i.e. paral...
详细信息
ISBN:
(纸本)0769509517
distributed applications are realized by cooperation of a group of multiple objects. An object multicasts a message to multiple destinations and sends in parallel multiple messages to multiple destinations, i.e. parallel-cast. The object receives multiple messages in conjunctive and disjunctive receipt. We newly define a novel precedent relation of messages exchanged among objects in presence of multi- and parallel-cast and conjunctive- and disjunctive-receipt of messages.
It is very risky to improve the performance of network protocols without the assurance of its functional correctness, especially for protocols that with complicated and concurrent behaviors. However, in most of curren...
详细信息
ISBN:
(纸本)9781424474226;9780769540887
It is very risky to improve the performance of network protocols without the assurance of its functional correctness, especially for protocols that with complicated and concurrent behaviors. However, in most of current model based protocol engineering projects, two independent models are adopted for individual functional verification and performance analysis, which could not guarantee the performance model satisfying the functionality correctness, and usually cost more in protocol design and maintenance. In this paper, we propose a colored Petri nets (CP-nets) based method to integrate functional verification and performance analysis procedures, and focus on the BitTorrent protocol as a representative example to illustrate the practical effectiveness of our proposed methodology. That is, the functional CP-nets models of BitTorrent protocol are constructed and validated firstly, and then performance related temporal constrains are added into above models to form its performance CP-nets models for corresponding simulation based performance analysis. Because such closely related CP-nets models are utilized where every occurrence sequence in the performance model corresponds to an occurrence sequence in its functional model, it is guaranteed that both models satisfy the functionality requirements of protocol systems. Besides, model maintenance becomes more convenient.
A facility location problem deals with locating the best place for a group of facilities, among distinct demand points, minimizing a certain locational optimization function. In this paper, distributed, asynchronous, ...
详细信息
A facility location problem deals with locating the best place for a group of facilities, among distinct demand points, minimizing a certain locational optimization function. In this paper, distributed, asynchronous, and scalable algorithms are presented for solving a facility location problem known as continuous n-median problem (generalized Fermat-Weber problem) via multi-agent robotic systems. The algorithms are discussed both in continuous and discrete time domain, and their validity is proved. It is also shown that the solution of this facility location problem is the set of points that are the geometric medians of their corresponding Voronoi cells.
In this paper, we study the performance of the coordinated distributed scheduler in IEEE 802.16 mesh mode. In the coordinated distributed scheduler, the three-way handshaking procedure, which is used for data slot sch...
详细信息
ISBN:
(纸本)9781510804166
In this paper, we study the performance of the coordinated distributed scheduler in IEEE 802.16 mesh mode. In the coordinated distributed scheduler, the three-way handshaking procedure, which is used for data slot scheduling, is a vital important part of the network performance. In this paper, the three-way handshaking time is newly defined from the reasonable aspect of engineering practice, arguing that the waiting time, which is caused by failures in the competition for transmission opportunities before sending the first handshaking message, should be the first part of the three-way handshaking time. Meanwhile, the slot sending the last handshaking message is defined as the end of the three-way handshaking procedure. The handshaking messages are carried in DSCH messages, one kind of scheduling control messages which obtain transmission opportunities through mesh election competition procedure in coordinated distributed scheduler. Mesh election competition procedure has a significant effect on the three-way handshaking time, so the decisive parameters of mesh election competition procedure have a great influence on the three-way handshaking time. On such parameters, we provide and compare the simulation and analytical results of the three-way handshaking time defined in this paper with others.
In the literature, there exist connectivity-based distributed clustering methods called CDC (Connectivity-based distributed node Clustering scheme) and SDC (SCM-based distributed Clustering). CDC and SDC have mechanis...
详细信息
ISBN:
(纸本)9781467308670
In the literature, there exist connectivity-based distributed clustering methods called CDC (Connectivity-based distributed node Clustering scheme) and SDC (SCM-based distributed Clustering). CDC and SDC have mechanisms for maintaining clusters against nodes join and leave, but both methods do not assume frequent changes in the network topology. In this paper, we propose a lightweight distributed clustering method called SBDC (Schelling-Based distributed Clustering), which is inspired by Schelling's model -- a popular segregation model in sociology. We also evaluate the effectiveness of our proposed SBDC in environment with frequent changes in the network topology. Our simulation results show that SBDC outperforms CDC and SDC under frequent changes in the network topology caused by high node mobility.
Data security and availability for operational use are frequently seen as conflicting goals. Research on searchable encryption and homomorphic encryption are a start, but they typically build from encryption methods t...
详细信息
ISBN:
(纸本)9781467385800
Data security and availability for operational use are frequently seen as conflicting goals. Research on searchable encryption and homomorphic encryption are a start, but they typically build from encryption methods that, at best, provide protections based on problems assumed to be computationally hard. By contrast, data encoding methods such as secret sharing provide information-theoretic data protections. Archives that distribute data using secret sharing can provide data protections that are resilient to malicious insiders, compromised systems, and untrusted components. In this paper, we create the Serial Interpolation Filter, a method for storing and interacting with sets of data that are secured and distributed using secret sharing. We provide the ability to operate over set-oriented data distributed across multiple repositories without exposing the original data. Furthermore, we demonstrate the security of our method under various attacker models and provide protocol extensions to handle colluding attackers. The Serial Interpolation Filter provides information-theoretic protections from a single attacker and computationally hard protections from colluding attackers.
暂无评论