Autonomous Real-Time Navigation for Service Level Agreement in Distributed Information Service System

Abstract

In today's aggressive and competitive marketplace, there is substantial need for corporations to incorporate service level agreement (SLA) in their enterprise; and keep user differentiation with respect to information volume, response time, or system availability; to make their business more idiosyncratic. Faded information field (FIF) was proposed to deliver assurance in distributed information system but it does not fulfil requirement of user differentiation to attain heterogeneous service levels. Due to structural characteristics of FIF, SLA-based mobile agent navigation technology is proposed, which is composed of autonomous node, response time monitoring, local status notification between neighbor nodes, and finally the Pull-MA navigation decision based on locality statistics information. As a result, the requests are able to avoid local congestion zones without a centralized dispatcher or workload manager, leading to globally accomplishing the heterogeneous service level objectives of each user even in case of subsystem failure and ever-changing environment. The effectiveness of the proposed technology has been proved through simulation, and the results show that the navigation technology increases an average of 60% the service satisfaction ratio. Since proposed navigation of Pull-MA is highly dependent on value of maximum access time (MAT), MAT per node was simulated for different techniques. Moreover, response time of all nodes in the network was simulated and satisfaction ratio for various possible techniques, along with that proposed has been shown for comparison