Sangsuree Vasupongayya

Design and Potential Performance of Goal-Oriented Job Scheduling Policies for Parallel Computer Workloads

To balance multiple scheduling performance requirements on parallel computer systems, traditional job schedulers use many parameters that can be configured to define job or queue priorities. Offering many parameters seems flexible, but in reality tuning the values for the parameters is highly challenging. To simplify the task of resource management, we propose goal-oriented policies, which allow system administrators to specify high-level performance objectives, rather than tuning low-level scheduling parameters. We study the design of goal-oriented policies, including (1) appropriate multi-objective models for specifying trade-offs between objectives, (2) efficient search algorithms for searching the best schedule at each scheduling decision point, and (3) appropriate performance measures to be optimized in the objectives with respect to two common performance requirements: preventing starvation and favoring shorter jobs. We compare goal-oriented policies with widely used backfill policies. Policies are evaluated by simulation using ten monthly workloads that ran on a Linux cluster (IA-64) from NCSA. Our results show that by automatically optimizing performance according to the given objectives through search, goal-oriented policies can simultaneously outperform FCFS-backfill and LXF-backfill, which are designed in favor of the maximum wait and average slowdown, respectively.

Search-based Job Scheduling for Parallel Computer Workloads

To balance performance goals and allow administrators to declaratively specify high-level performance goals, we apply complete search algorithms to design on-line job scheduling policies for workloads that run on parallel computer systems. We formulate a hierarchical two-level objective that contains two goals commonly placed on parallel computer systems: (1) minimizing the total excessive wait; (2) minimizing the average slowdown. Ten monthly workloads that ran on a Linux cluster (IA-64) from NCSA are used in our simulation of policies. A wide range of measures are used for performance evaluation, including the average slowdown, average wait, maximum wait, and new measures based on excessive wait. For the workloads studied, our results show that the best search-based scheduling policy (i.e., DDS/lxf/dynB) reported here simultaneously beats both FCFS-backfill and LXF-backfill, each roughly providing a lower bound on maximum wait and the average slowdown, respectively, among backfill policies

A novel personal health record system for handling emergency situations

Personal health record (PHR) becomes a popular research topic nowadays. Many research works have proposed several concepts in managing and organizing a PHR. However, there are several uncertain issues left such as the role of a PHR in emergency situations. In this paper, a solution to handle a PHR information management in emergency situations is proposed. Because a PHR is controlled by its owner, the critical challenge in handling the PHR in emergency situations is how emergency staffs can access PHR information, even when the PHR owner is unable to give his/her consent. The proposed scheme allows each PHR to be classified into several categories. Each category presents a different restriction. And, the emergency staffs can access each category according to the policy defined by the PHR owner. The threshold cryptosystem is adapted in this work to allow the selected set of PHR-owner-delegates to grant permission to the emergency staffs when the PHR owner is unconscious.

Multi-Objective Models for Scheduling Jobs on Parallel Computer Systems

This paper is concerned with the design of goal-oriented scheduling policies that deal with multiple goals on production parallel systems. Several objective models are compared, including two new models that allow an explicit specification of tradeoff among different goals and a hierarchical model studied in our previous paper. We focus on two performance goals commonly placed on production systems: starvation prevention and favoring shorter jobs. In this paper, we study how to best formulate high-level performance goals, in an attempt to provide guideline for defining the objectives

Using fingerprints to identify personal health record users in an emergency situation

Personal Health Records (PHRs) is a system that allows an individual to store and share his/her health related information with others. The PHR owner can control all accesses to his/her data stored on the PHR system. This work aims to propose a privacy-preserved identification scheme to be used in the PHR system during an emergency situation especially when the victim is unconscious. The fingerprint-based scheme under a Protected Biometric Template (PBT) concept is applied to identify the victim without compromising the privacy of the victim. The usability and security discussions show that the proposed scheme is practical under the current existing communication technology and environment.

Extending goal-oriented parallel computer job scheduling policies to heterogeneous systems

Several existing parallel computer systems partition their system resources or consist of systems from different geographical locations. This work is focusing on extending the original goal-oriented parallel computer job scheduling policies to cover such systems. The goal-oriented parallel computer job scheduling policies are proposed recently to handle conflicting objectives by utilizing a combinatorial search technique to find the most compromise schedule within a time limit. In this paper, some modifications to the original goal-oriented parallel computer job scheduling policy design are proposed and evaluated. The proposed policy is evaluated against basic priority backfilling techniques widely used in the field. Both homogeneous and heterogeneous parallel computer systems in terms of the computing power are evaluated. And, the design decision on the partition selection heuristic is also evaluated in this study. The experimental results show that the proposed policy produces good scheduling performances even when inaccurate runtime information is used.

Interactive examination management system

To handle several online examination settings, a web-based application test management software, namely interactive examination management system (iEMS), is proposed in this paper. The outstanding points of the proposed system are its good architecture designs, ease of uses, rich features, flexibilities and extensibilities. Seven standard types of questions are supported including multiple-choice, true/false, matching, ordering, fill-in the blank, short answer and essay questions. Except the essay questions, the iEMS can automatically grade the answers. Several design issues are discussed such as the graphic user interface, the special control character of the system and the flow of controls used in such systems. The student feedbacks on the iEMS are positive. That is, the simple graphic user interface is easy to learn; the interactive feature of the iEMS allows the students to get the results very fast; more tests can be given and automatically graded which results in a high attendant rate.

Distributed storage design for encrypted personal health record data

DSePHR is proposed in this work in order to manage the encrypted PHR data on a cloud storage. HBase and Hadoop are utilized in this work. The objective is to provide an API for any PHR system to upload/download the encrypted PHR data from a cloud storage. The DSePHR resolves the Namenode memory issues of HDFS when storing a lot of small files by classifying the encrypted PHR data into small and large files. The small files will be handled by HBase schema that is proposed in this work. The memory consumption and the processing time of the proposed DSePHR are evaluated using real data sets collected from various healthcare communities.

Two-layer ciphertext-policy attribute-based proxy re-encryption for supporting PHR delegation

Medical treatment sometimes requires a case forwarding to a doctor who has a specific expertise. Typically, an electronic medical record (EMS) of a patient can be passed to another doctor without asking the patient because EMS belongs to the healthcare organization. Personal health record (PHR), however, is different because PHR is owned by an individual (e.g., patient) and all accesses to the PHR is controlled by its owner. This work proposes a two-layer ciphertext-policy attribute-based proxy re-encryption scheme (2-layer CP-AB-PRE) for the PHR delegation process. The inner layer policy belongs to the PHR owner while the outer layer policy belongs to the doctors or experts that might want to delegate the PHR to other doctors or experts. This way, the PHR can be delegated to others while the PHR owner still has the control on his/her data. The evaluation results on the size of the resulting ciphertext PHR produced by the proposed method, are shown. The security issues of the proposed method are also discussed.

Personal Health Assistant on Android Mobile Device: Sleeping, Nutrition and Exercise

Good health can be achieved by maintaining good behaviors such as a good night sleep, enough exercise and good nutrition. However, the competitive environment nowadays prevents such good behaviors. Thus, this work aims to develop an application on mobile devices that is able to (1) record the daily sleeping, exercise and nutrition information, (2) analyze the collected information in order to provide a notification or an alarm, and (3) present the analyzed results in a simple and easy to understand format. The proposed application can collect data from other application and from the users. A set of simple data analysis methods is performed on the collected data in order to provide a personal health advice based on the user pre-defined preferences.