Policy Adjuster-driven Grid Workflow Management for Collaborative Heart Disease Identification System

Abstract

Abstract: This paper proposes a policy adjuster-driven Grid workflow management system for collaborative healthcare platform, which supports collaborative heart disease diagnosis applications. To select policies according to service level agreement of users and dynamic resource status, we devised a policy adjuster to handle workflow management polices and resource management policies using policy decision scheme. We implemented this new architecture with workflow management functions based on policy quorum based resource management system for providing poincare geometry-characterized ECG analysis and virtual heart simulation service. To evaluate our proposed system, we executed a heart disease identification application in our system and compared the performance to that of the general workflow system and PQRM system under different types of SLA. Keywords: Grid Worfklow, Collaborative Healthcare Platform, SLA, Policy Adjuster 1. Introduction There have been many attempts to create healthcare system or platform by combining the existing medical service with IT such as sensor and communication technology. In other words, the general health clinical data and information are exchanged electronically, and the patient, doctor, hospital and laboratories can be connected through communication network to perform medical practices. Such healthcare system is enabled and supported by IT, yet the core technology will be high-speed information exchange technology and high performance computing technology in distributed environment. Grid technology can meet these requirements by bringing heterogeneous resources together and allocating them efficiently to applications. Medical applications are no longer restricted to one medical institute. Some collaborated applications like heart disease simulator, an instance of workflow jobs, require several resources work together. So the healthcare platform requires collaborative job scheduling function based on resource status which is the core part of Grid resource management system [2][3]. However, the complexity of resource management for QoS guarantee in Grid significantly increases as the grid computing grows. One of the promising approaches trying to solve this problem is policy based resource management system [2] that is suitable to the complex management environments. To manage resource in Grid, it is required to have a sort of grid resource broker and scheduler that manage resources and jobs in the virtual Grid environment. Authors in [3] suggested policy-based resource management system (PQRM) architecture by consideration of Grid Service Level Agreement (SLA) and abstract architecture of grid resource management. In medical healthcare environment, beside most of single-program applications, there exist many applications which require co-process of many programs following a strict processing order. Since these applications are executed on Grid, they are called Grid workflows. Current Grid resource management systems do not consider complexity of collaborative medical applications and service level guarantee at workflow level. In this paper, we propose Grid workflow-driven healthcare platform for collaborative applications. In the sense of optimum management, PQRM [5] provides optimum resource quorum for applications, so we develop workflow-Integrated PQRM as one instance for this workflow-driven healthcare platform. PQRM’s available resource quorum is optimum resource set in resource management point of view and our workflow-driven system can provide optimum resource set in workflow management point of view. Two management philosophies require a policy decision scheme to adjust based on user’s SLA. We evaluate the proposed workflow-driven healthcare platform by measuring the completion time of collaborative heart disease simulator under different types of user SLA. DOI : 10.3745/JIPS.2008.4.3.103