Figure 1 - uploaded by Lakhwinder Kaur
Content may be subject to copyright.
Source publication
The design of a suitable interconnection network for inter-processor communication is one of the key issues of the system performance. The reliability of these networks and their ability to continue operating despite failures are major concerns in determining the overall system performance. In this paper a new irregular network IABN has been propos...
Similar publications
For parallel computation, various multistage interconnection networks have been discussed in the literature. But these networks always required further improvement in reliability and fault-tolerance. Fault-tolerance of the network can be achieved by increasing the number of disjoint paths as a result reliability of the interconnection networks also...
Citations
... Enhancing the dependability of MINs, i.e., its ability to provide a trusted service [3], is of great importance in order to maintain high system performance. Therefore, redundant switching elements are used to ensure that the network is able to provide the required switching even after the failure of some of these elements [1,21]. Thus, multiple-path MINs are used to increase the fault tolerance and hence the network reliability. ...
Designing dependable multiprocessor systems requires reliable interconnection networks. Multistage interconnection networks (MINs), including shuffle-exchange networks (SENs), are widely used to establish the desired connection. The failure of these networks can degrade the overall system performance, which may lead to significant losses. In this paper, we propose to formally model and analyze the dynamic dependability aspects of SENs using a combination of dynamic fault trees (DFTs) and dynamic reliability block diagrams (DRBDs) based on higher-order logic (HOL) theorem proving. We propose to integrate these two modeling approaches for efficiently handling the considered formal dependability analysis by leveraging upon the advantages of each method. The soundness of this integration is provided through a formal proof of equivalence between the DFT and DRBD algebras. We utilize the proposed framework to provide the formal DFT and DRBD analyses of three common measures of SENs, namely: terminal, broadcast and network reliability. The proposed approach allowed us to verify generic expressions of probability of failure and reliability of these systems, which can be instantiated with any number of system components and time-to-failure functions.
... Enhancing the reliability of MINs is of great importance in order to maintain high system performance. Therefore, redundant switching elements are used to ensure that the network is able to provide the required switching even after the failure of some of these elements [7,8]. Multiple-path MINs are used to increase the fault tolerance and hence the network reliability. ...
Dynamic dependability models, such as dynamic fault trees (DFTs) and dynamic reliability block diagrams (DRBDs), are introduced to overcome the modeling limitations of traditional models. Recently, higher-order logic (HOL) formalizations of both models have been conducted, which allow the analysis of these models formally, within a theorem prover. In this report, we provide the formal dynamic dependability analysis of shuffle-exchange networks, which are multistage interconnection networks that are commonly used in multiprocessor systems. We use DFTs and DRBDs to model the terminal, broadcast and network reliability with dynamic spare gates and constructs in several generic versions. We verify generic expressions of probability of failure and reliability of these systems, which can be instantiated with any number of system components and failure rates to reason about the failure behavior of these networks.
... In this paper, we shall focus on Artificial Intelligence for the purpose of steady state security assessment and rapid contingency evaluation [4]. For reliability analysis of fault-tolerant multistage interconnection networks an irregular augmented baseline network (IABN) is designed from regular augmented baseline network (ABN) [5]. In the past, the electric power industry around the world operated in a vertically integrated environment. ...
... The irregular augmented baseline network (IABN) provides an irregular multipath network with limited fault tolerance [54]. From the results, IABN provides much better fault tolerance and reliability. ...
Interconnection networks provide communication among processors, memory modules, and other devices in parallel computer systems. The number of stages, interconnection topology, and the types of SE used in the network configuration differentiate each interconnection network. As an illustration, there are numerous aspects that are important in the development of interconnection networks. Reliability can be considered as an important factor to measure the performance in the network. The reliability for interconnection network depends on the reliability of its components. In this paper, we examine the various topologies of interconnection, communication protocol, and discuss reliability issues related to interconnection network.
... Multistage interconnection networks are commonly recommended as connections in multiprocessor system or network switches 3 . MINs are acknowledged as being an economical solution offering programmable data paths among functional modules in multiprocessor systems 4 . These networks are typically employed with simple modular switches, consist of two input and two output switching elements 5 . ...
... MINs consist of layers of switching element connected together in predefined topology providing the connectivity between input and output. MIN commonly used in circuit switching and packet switching networks 4 . The interconnection design, number of stages, and the type of switching element used in the network configuration differentiate each MIN 2,3,4 . ...
Shuffle-exchange networks (SENs) have been generally considered as a convenient interconnection systems due to the size of their switching elements (SEs) and simple configuration. Evaluation of reliability performance has been attempted by researchers in the past. This paper is a depth study of reliability evaluation in shuffle exchange network. We propose a SEN with minus one stage (SEN-) and compared with three other types of SEN. The measurement includes three parameters; terminal, broadcast and network reliability.
... Shukla and Gadewar(2007) initiated a stochastic model for cell movement in a Knockout Switch and presented a probability based results on it. Agarwal and Kaur (2008) performed reliability analysis for fault-tolerance in multistage interconnection networks case. Shukla et al.(2007) utilized markov chain model as a tool for space-division switching in a computer network. ...
... Newby and Dagg (2002) proposed inspection and maintenance for stochastically deteriorating systems for average cost criteria with the help of markov chain model. Agarwal and Kaur (2008) discuss a reliability analysis of fault-tolerant multistage interconnection networks and develop a methodology for it. Medhi (1991) has given detail discussion on random movement in every aspect of real time situation through markov chain. ...
... Dorea, Cruz and Rojas (2004) discussed on an approximation results for nonhomogeneous Markov chains and develop some applications. Agarwal and Lakhwinder (2008) advocate reliability analysis of fault-tolerant multistage interconnection networks and discuss various aspects for it. Tiwari, Thakur and Shukla (2010) focused on cyber crime based analysis for multi-dimensional effect when two service providers are in comparative mode. ...
... 5 indicates that for increasing value of L 2 bounded area increases subject to the condition for prefixed input parameter. It also supports to table no 5. ...
In present scenario of research, network congestion is one of the most interesting area. Congestion in internet is a long-standing problem and in modern days internet service providers use congestion control and congestion avoidance techniques to avoid congestion collapse. Internet congestion appears when a large volume of data is being routed on low bandwidth lines or across networks that have high latency and cannot handle large volumes. Due to such heavy load on network, disconnectivity appears and internet traffic share of operators fluctuate. Naldi (2002) explored a model based on Internet Traffic Share problem between comparative operators mode. The basic idea of Naldi (2002) was extended by Thakur and Shukla (2010) in which disconnectivity factor was introduced and mathematical relationship of traffic share and network blocking probability with special reference for disconnectivity factor was examined. This relationship originates probability based quadratic function which has a definite bounded area. This area contains many network parameters and to assess various properties of internet traffic it is necessary to estimate. The aim of this paper is to develop an appropriate approach for estimation of such kind of bounded area by using Simpson 1/3 rule usually applied in numerical quadrature. It is found that probability of disconnectivity (i.e. S1 and S2) is directly proportional to bounded area. This study is an attempt to establish the relationship among internet traffic share status and network disconnectivity parameters. Graphical study is also performed to support for numerical facts.
... The bus network suffers from a performance bottleneck due to bus connection while to connect N input to N output with a crossbar N 2 switches are needed. Consequently, crossbar networks cannot be scaled to any arbitrary size [11,2,3]. MINs are better suited for various parallel computing and telecommunication applications because they provide efficient performance using a reasonable number of switches. ...
... An IN is very important for its continuous operation over a relatively long period of time. The basic idea for the fault-tolerance of the MIN is to create redundancy in the number of paths between each source-destination pair so that alternative paths can been used in case of faults [6,26,39,48,11,2,3]. ...
... Benefits of this method can be listed as follows: (1) It can increase reliability and fault-tolerance to some extent. (2) This approach increases costs exactly as a single switching stage does, therefore it slightly raises the cost and thus, is cost effective. (3) It is easy to be implemented. ...
... On the reliability analysis of network a useful contribution is by Shukla et al. [13] whereas Paxson [9] introduced some of their critical experiences while measuring the internet traffic. Shukla et al. [14], [15], [16], [17], [18], [19] and [20] presented different dimensions of Internet traffic sharing in the light of share loss analysis. Shukla et al. [21], [22], [23], [24], [25] and [26] have given some Markov Chain model applications in view to disconnectivity factor, multi marketing and crime based analysis. ...
Cyber crime is growing fast day-by-day through the spreading of Internet around the world. Many under-developed countries are using dial-up-setup network where a call is connected only after a little extra effort. Some identified cyber crimes are writing abusive letters, giving threats to other, sending unwanted mails, hacking secret data, phishing attack on websites etc. The Internet traffic growth has some positive correlation with the cyber crime as justified by the Markov Chain Model based analysis of authors to examine the interrelationship between traffic sharing and blocking probability. This analysis has been extended for two-call basis also and model based relations are derived. These relations are complicated in terms of mathematical structure. This paper presents least square based curve analysis for Markov Chain model based relationship between traffic sharing and network blocking. The earlier suggested complicated relationship has been simplified in the form of straight line showing a good fitting. The Coefficient of determination has been computed showing the high value towards unity. It proves that simplified linear relationships perform well as a thumb rule for expressing the complex relationship between traffic sharing and network blocking probability. .
