BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260522T150153Z
LOCATION:D173
DTSTART;TZID=America/Chicago:20181111T090000
DTEND;TZID=America/Chicago:20181111T173000
UID:submissions.supercomputing.org_SC18_sess163@linklings.com
SUMMARY:WORKS 2018: 13th Workshop on Workflows in Support of Large-Scale
DESCRIPTION:WRENCH: A Framework for Simulating Workflow Management Systems
 \n\nScientific workflows are used routinely in numerous scientific domains
 , and Workflow Management Systems (WMSs) have been developed to orchestrat
 e and optimize workflow executions on distributed platforms.  WMSs are com
 plex software systems that interact with complex software infrastructures.
  Most WM...\n\n\nHenri Casanova and Suraj Pandey (University of Hawaii at 
 Manoa); James Oeth (University of Southern California); Ryan Tanaka (Unive
 rsity of Hawaii at Manoa); Frédéric Suter (IN2P3 Computing Center, Nationa
 l Center for Scientific Research (CNRS)); and Rafael Ferreira da Silva (Un
 iversity of Southern California)\n---------------------\nEnergy-Aware Work
 flow Scheduling and Optimization in Clouds Using Bat Algorithm\n\nWith the
  ever-increasing deployment of data centers and computer networks around t
 he world, cloud computing has emerged as one of the most important paradig
 ms for large-scale data-intensive applications. However, these cloud envir
 onments face many challenges including energy consumption, execution t...\
 n\n\nYi Gu and Chandu Budati (Middle Tennessee State University)\n--------
 -------------\nLOS: Level Order Sampling for Task Graph Scheduling on Hete
 rogeneous Resources\n\nList scheduling is an approach to task graph schedu
 ling that has been shown to work well for scheduling tasks with data depen
 dencies on heterogeneous resources. Key to the performance of a list sched
 uling heuristic is its method to prioritize the tasks, and various ranking
  schemes have been proposed...\n\n\nCarl Witt (Humboldt University of Berl
 in); Sam Wheating (University of Victoria, British Columbia); and Ulf Lese
 r (Humboldt University of Berlin)\n---------------------\nDynamic Distribu
 ted Orchestration of Node-RED IOT Workflows Using a Vector Symbolic Archit
 ecture\n\nThere are a large number of workflow systems designed to work in
  various scientific domains, including support for the Internet of Things 
 (IoT).  One such workflow system is Node-RED, which is designed to bring w
 orkflow-based programming to IoT. However, the majority of scientific work
 flow systems, ...\n\n\nChristopher Simpkin, Ian J. Taylor, and Daniel Harb
 orne (Cardiff University); Graham Bent (IBM Research, UK); Alun Preece (Ca
 rdiff University); and Raghu K. Ganti (IBM Research)\n--------------------
 -\nPlanner: Cost-efficient Execution Plans Placement for Uniform Stream An
 alytics on Edge and Cloud\n\nStream processing applications handle unbound
 ed and continuous flows of data items which are generated from multiple ge
 ographically distributed sources. Two approaches are commonly used for pro
 cessing: cloud-based analytics and edge analytics. The first one routes th
 e whole data set to the Cloud, in...\n\n\nLaurent Prosperi (ENS Paris-Sacl
 ay); Alexandru Costan and Pedro Silva (IRISA, INSA Rennes); and Gabriel An
 toniu (French Institute for Research in Computer Science and Automation (I
 NRIA))\n---------------------\nKeynote\n\nIlkay Altintas (San Diego Superc
 omputer Center)\n---------------------\nFlux: Overcoming Scheduling Challe
 nges for Exascale Workflows\n\nMany emerging scientific workflows that tar
 get high-end HPC systems require complex interplay with the resource and j
 ob management software~(RJMS).  However, portable, efficient and easy-to-u
 se scheduling and execution of these workflows is still an unsolved proble
 m.  We present Flux, a novel, hiera...\n\n\nDong H. Ahn, Ned Bass, Albert 
 Chu, Jim Garlick, Mark Grondona, Stephen Herbein, Joseph Koning, Tapasya P
 atki, Thomas R. W. Scogland, and Becky Springmeyer (Lawrence Livermore Nat
 ional Laboratory) and Michela Taufer (University of Tennessee)\n----------
 -----------\nIntroduction - WORKS 2018: 13th Workshop on Workflows in Supp
 ort of Large-Scale Science\n\nData Intensive Workflows (aka scientific wor
 kflows) are routinely used in most scientific disciplines today, especiall
 y in the context of parallel and distributed computing. Workflows provide 
 a systematic way of describing the analysis and rely on workflow managemen
 t systems to execute the complex a...\n\n\nSandra Gesing (University of No
 tre Dame) and Rafael Ferreira da Silva (University of Southern California)
 \n---------------------\nWorkshop Lunch (on your own)\n-------------------
 --\nDagOn*: Executing Direct Acyclic Graphs as Parallel Jobs on Anything\n
 \nThe democratization of computational resources, thanks to the advent of 
 public, private, and hybrid clouds, changed the rules in many science fiel
 ds. For decades, one of the effort of computer scientists and computer eng
 ineers was the development of tools able to simplify access to high-end co
 mputat...\n\n\nRaffaele Montella and Diana Di Luccio (Parthenope Universit
 y of Naples) and Sokol Kosta (Aalborg University, Copenhagen)\n-----------
 ----------\nWorkshop Morning Break\n---------------------\nWorkshop Aftern
 oon Break\n---------------------\nEnd-to-End Online Performance Data Captu
 re and Analysis for Scientific Workflows\n\nWith the increased prevalence 
 of employing workflows for scientific computing and a push toward exascale
  computing, it has become paramount that we are able to analyze characteri
 stics of scientific applications to better understand the impact on the un
 derlying infrastructure and vice-versa. Such ana...\n\n\nGeorge Papadimitr
 iou (University of Southern California), Cong Wang (Renaissance Computing 
 Institute (RenCI)), Karan Vahi and Rafael Ferreira da Silva (University of
  Southern California), Anirban Mandal (Renaissance Computing Institute (Re
 nCI)), Zhengchun Liu (Argonne National Laboratory), Rajiv Mayani and Mats 
 Rynge (University of Southern California), Mariam Kiran (Energy Sciences N
 etwork (ESnet)), Vickie E. Lynch (Oak Ridge National Laboratory), Rajkumar
  Kettimuthu (Argonne National Laboratory), Ewa Deelman (University of Sout
 hern California), Jeffrey S. Vetter (Oak Ridge National Laboratory), and I
 an T. Foster (Argonne National Laboratory)\n---------------------\nOptimiz
 ing the Throughput of Storm-Based Stream Processing in Clouds\n\nThere is 
 a rapidly growing need for processing large volumes of streaming data in r
 eal time in various big data applications. As one of the most commonly use
 d systems for streaming data processing, Apache Storm provides a workflow-
 based mechanism to execute directed acyclic graph (DAG)-structured to...\n
 \n\nHuiyan Cao and Chase Q. Wu (New Jersey Institute of Technology); Liang
  Bao (XiDian University); and Aiqin Hou (Northwest University, China)\n---
 ------------------\nWORKS 2018 Panel\n---------------------\nReduction of 
 Workflow Resource Consumption Using a Density-based Clustering Model\n\nOf
 ten times, a researcher running a scientific workflow will ask for orders 
 of magnitude too few or too many resources to run their workflow. If the r
 esource requisition is too small, the job may fail due to resource exhaust
 ion; if it is too large, resources will be wasted though job may succeed. 
 It...\n\n\nQimin Zhang (Chinese Academy of Sciences) and Nathaniel Kremer-
 Herman, Benjamin Tovar, and Douglas Thain (University of Notre Dame)\n----
 -----------------\nA Practical Roadmap for Provenance Capture and Data Ana
 lysis in Spark-Based Scientific Workflows\n\nWhenever high-performance com
 puting applications meet data-intensive scalable systems, an attractive ap
 proach is the use of Apache Spark for the management of scientific workflo
 ws. Spark provides several advantages such as being widely supported and g
 ranting efficient in-memory data management for l...\n\n\nThaylon Guedes (
 Fluminense Federal University, Fluminense Federal University, Brazil); Vit
 or Silva and Marta Mattoso (Federal University of Rio de Janeiro); and Mar
 cos Bedo and Daniel Oliveira (Fluminense Federal University, Fluminense Fe
 deral University, Brazil)\n\nTag: Reproducibility, Scientific Computing, S
 cientific Workflows, Workflows, HPC, Data Intensive\n\nRegistration Catego
 ry: Workshop Reg Pass
END:VEVENT
END:VCALENDAR