Mobile Agent Based Distributed Network Architecture with Map Reduce Programming Model

Abstract

In the recent years, the demand for data processing has been on the rise prompting researchers to investigate new ways of managing data. Our research delves into the emerging trends of data management methods, one of which is the agent based techniques and the active disk technology and also the use of Map-reduce functions in unstructured data management. Motivated by this new trend, our architecture employs mobile agents technology to develop an open source framework called SPADE to implement a simulation platform called SABSA. The architecture in this research compares the performance of four network storage architectures: Store and forward processes(SAF), Object Storage Devices(OSD), Mobile agent with a Domain Controller (DMC) enhanced with map-reduce function and Mobile agent with a Domain Controller and child DMC enhanced with Map-reduce (ABMR): both handling sorted and unsorted metadata. In order to accurately establish the performance improvements in the new hybrid agent based models and map-reduce functions, an analytic simulation model on which experiments based on the identified storage architectures were performed was developed and then analytical data and graphs were generated. The results indicated that all the agents based storage architectures minimize latencies by up to 45 % and reduce access time by up to 21% compared to SAF and OSD.

Distributed System Computation Model Based on Mobile Agent Development Platform

“…Mobile Agent platform is a brand-new DC model, and its superiority in computing massive data has been paid more and more attention [5]. Java language is very suitable for Agent programming, so many researchers choose Java language when designing Agent platform [6]. After years of development, the research on Agent theory and technology has made great progress and has become an important concept in current computer science.…”