International Journal of Computer Applications (0975 – 8887) Volume 40– No.1, February 2012 35 Multiagent Framework based Interactive Job Management for Grid Sneha Viral Mehta International Institute of Information Technology, Pune-57, India. ABSTRACT Grid , a hardware and software infrastructure that provides dependable, consistent, pervasive and inexpensive access to high end computational capabilities, with intelligent cooperative agents, enable the system to well-suited for many types of services and autonomously adapt to users computation needs as well as dynamically changing computing resource environments. Grid technologies need to be extended which includes graphical, interactive sessions known as Interactive Grids. Interactive Grids permit end-users to access and control a remote resource. The motive of this paper is to intricate the effectiveness of Grid computing by Interactive Agent based Job management. An agent based interactive job management system is developed to incorporate the concept of agent in the grid. Keywords Grid, Interactive Grid, MultiAgent, JMS 1. INTRODUCTION Grid Computing [1] is an active research area which promises to provide a flexible infrastructure for complex, dynamic and distributed resource sharing. Recent research on Grid has largely focused on issues of performance, scalability and standardization. Managing access to computing and data resources is a complex and time consuming task. As Grid computing matures, deciding which systems to use, where the data resides for a particular application domain, how to migrate the data to the point of computation (or vice versa), and data rates required to maintain a particular application “behavior” become significant. Traditional use of Grid Computing Systems has been for batch jobs in the scientific and academic computing. It is envisioned that the next generation Grid computing systems should support graphical interactive sessions [2]. Autonomy is used to describe the character of an agent. An agent can fulfill high-level tasks directly or through cooperation with other agents [3]. Agent and multi-agent technologies provide a promising approach to make Grid technologies and solutions based on Grid and Cluster technologies smarter, more flexible, and adaptable. Agents could play an important role in Grid Computing. Intelligent MultiAgent approaches are well-suited for many types of services. Intelligent cooperative agents enable the system to autonomously adapt to users computation needs as well as dynamically changing computing resource environments. Main objective of this paper is to elaborate the effectiveness of Grid computing by Interactive Agent based Job management. This special issue brings together fields of grid computing and multiagent technology together with providing interactivity to present their work on the applications of agent- based techniques and approaches in managing and allocating resources in grid computing environment. 2. RESEARCH METHODOLOGY Globus is a grid middleware, considered to be the de facto standard for grid computing. So, for practical experience of the grid computing it is best to start with Globus. 2.1 Designing MultiAgent Framework for Job Management using Globus Globus [4] is required to setup grid environment. In which one node has been chosen as a submission node, and the other two are container nodes. These container nodes are actually having the schedulers of OpenPBS, SGE and also condor can be used which creates heterogeneous environment for clusters. When the submission node submits jobs to the containers, then these jobs are scheduled to run on other nodes. All components and sub-systems in a grid environment can be represented as agents. Different agents communicate using Inter-agent Communication (ICL). Each agent collects relevant identification information, resource information, state information, etc. The multi-agent system-based grid architecture model highly abstracts the substance application. It can be divided into layers in logic. Communication between agents [5] and Grid nodes is shown in Figure 1.  Through Interface Agent user submits a job.  Each and every Agent communicates with controller agent which is the master agent.  Controller Agent through GRAM calls Info and Resource Allocation Agent to assign a suitable node and resources.  Resource database returns nodes itinerary to the Info Agent.  Job creating Agent assigns job-id and resources.  Each Agent begins a user process on an available node.  After the available node execution, the result is back to the sub-agents.  Sub-agents pass the result to their main master Agent or Controller Agent.  Controller Agent handles with all the back results and submits the ultimate result to the user through Interface Agent.