Performance analysis of network topologies in agent-based open connectivity architecture for DSS

Zhang, Haolan; Leung, Clement H. C.; Raikundalia, Gitesh K.

doi:10.1109/aina.2006.266

Cited by 6 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have conducted a set of experiments to evaluate the topological performance of AOCD-based (hybrid) system (Zhang et al, 2006a). Figure 8 and Figure 9 show two snapshots of the AOCD topological experiments.…”

Section: Results Of the Aocd Topological Experimentsmentioning

confidence: 99%

“…In addition, the average success rates of the two topologies are 86.74% (centralised) and 95.45% (hybrid), respectively ( Figure 11). The experimental design and more detailed experimental analysis can be found in our previous work (Zhang, et al , 2006a). We noticed that for both centralised and hybrid topologies when the produce of the requestvolume/participated-agents increases, the success rate of processing the requests appears to decrease (Figure 12 and 13).…”

Section: Results Of the Aocd Topological Experimentsmentioning

confidence: 99%

“…It has been focusing on the architectural design of AOCD system, which provides a foundation for future AOCD research. The previous research involves: (1) Introducing the concept of Matrix-Agent connection, which has been proven efficient and effective compared with other decentralized or centralized frameworks (Wagner, 2003), (2) Experimental design of agent network topologies in AOCD-based systems (Zhang, et al, 2005;2006a). This paper is structured as follows; in the next section, we provide an example scenario to clarify the implementation of AOCD.…”

Section: Multi-agents Applications In Dssmentioning

confidence: 99%

See 2 more Smart Citations

Application of Multi-agent Technology to Information Systems: An Agent-based Design Architecture for Decision Support Systems

Zhang

2009

AJIS

View full text Add to dashboard Cite

One of the most difficult issues in building efficient Information Systems (IS) is the integration of these systems with the organization's other systems. This issue is particularly acute for Decision Support Systems (DSSs). To become more effective and efficient, a DSS must have an open structure to adapt to the dynamic environment. However, current IS, especially DSSs, tend to rely excessively on traditional System Development Life Cycle (SDLC) and this places limitations on current systems' infrastructures. The emergence of multi-agent technology addresses this issue and its applications to IS are becoming highly efficient. In this paper, we introduce a Matrix-Agent connection design, called Agent based Open Connectivity for Decision Support Systems (AOCD), which balances the manageability and flexibility in a system and maximizes system performance.

show abstract

Section: Results Of the Aocd Topological Experimentsmentioning

confidence: 99%

Section: Results Of the Aocd Topological Experimentsmentioning

confidence: 99%

Section: Multi-agents Applications In Dssmentioning

confidence: 99%

See 1 more Smart Citation

Application of Multi-agent Technology to Information Systems: An Agent-based Design Architecture for Decision Support Systems

Zhang

2009

AJIS

View full text Add to dashboard Cite

show abstract

“…From the review of literature, it is observed that many of Scientists and Engineers have used the UML in the networking field also. Zhang et al [10] computed the performance of the network topologies for agent based open connectivity architecture for the decision support system and they used the UML for computing the performance of network topologies. UML is also used for observing network performance by traffic reduction and loads are also shared for the distributed systems [11], [12].…”

Section: Related Workmentioning

confidence: 99%

Virtual Machine Allocation Policy in Cloud Computing Environment using CloudSim

Zaidi

Rampratap

2018

IJECE

View full text Add to dashboard Cite

Cloud computing has been widely accepted by the researchers for the web applications. During the past years, distributed computing replaced the centralized computing and finally turned towards the cloud computing. One can see lots of applications of cloud computing like online sale and purchase, social networking web pages, country wide virtual classes, digital libraries, sharing of pathological research labs, supercomputing and many more. Creating and allocating VMs to applications use virtualization concept. Resource allocates policies and load balancing polices play an important role in managing and allocating resources as per application request in a cloud computing environment. Cloud analyst is a GUI tool that simulates the cloud-computing environment. In the present work, the cloud servers are arranged through step network and a UML model for a minimization of energy consumption by processor, dynamic random access memory, hard disk, electrical components and mother board is developed. A well Unified Modeling Language is used for design of a class diagram. Response time and internet characteristics have been demonstrated and computed results are depicted in the form of tables and graphs using the cloud analyst simulation tool.

show abstract

“…Habib [16] has simulated the results for analysis of server placement for the execution of tasks under distributed environment. Zhang et al [17] have explained the performance analysis of network topology in agent based connectivity architecture for the decision support system.…”

Section: Introductionmentioning

confidence: 99%

Modifications in Lamport Algorithm for Distributed Computing System

Zaidi¹,

Saxena²

2012

IJCA

View full text Add to dashboard Cite

In the current scenario, distributed approach of computing is very popular over the centralized approach of computing due to faster execution of processes; cut off the execution time of processes and cost. In the year 1978, Lamport [6] has proposed an approach for synchronization of processes under distributed environment which has the limitations for reordering and executing the events of the processes by using time, ordering of events and clock conditions. The important limitation is that the algorithm does not cover the process execution in reflexive, symmetric and transitive manners when the unidirectional or bidirectional ring is appearing in the distributed network for executing the processes and sharing the common resources under distributed environment.The present work will focus on these aspects and processor can execute the events of processes either on its node called as computer system in the reflexive manner and if the current node is busy for other tasks then it can use the next promising node under the defined topology and can be executed by using symmetric property and if further second node is busy then events can be transmitted to next promising node and these are executed in the transitive manner and the output is transferred to the first node. These aspects are demonstrated by proposing a new kind of topology called as step topology in which numbers of computer systems are attached in the distributed network. Algorithms are designed for all these three cases by considering the definitions of process and thread. Since one computer system can interact with another computer system with message passing technique under distributed environment, therefore, message complexities in all these cases are also measured and compared with Lamport and other similar kinds of algorithms available for distributed computing system.

show abstract

Performance analysis of network topologies in agent-based open connectivity architecture for DSS

Cited by 6 publications

References 8 publications

Application of Multi-agent Technology to Information Systems: An Agent-based Design Architecture for Decision Support Systems

Application of Multi-agent Technology to Information Systems: An Agent-based Design Architecture for Decision Support Systems

Virtual Machine Allocation Policy in Cloud Computing Environment using CloudSim

Modifications in Lamport Algorithm for Distributed Computing System

Contact Info

Product

Resources

About