Deep Learning Cascading Failure Prediction in a High Performance Computing System Eric Abreut1, Zhongbo Li2 1 Florida International University 2 The University.

Slides:



Advertisements
Similar presentations
Chapter 5: Introduction to Information Retrieval
Advertisements

A Flexible Workbench for Document Analysis and Text Mining NLDB’2004, Salford, June Gulla, Brasethvik and Kaada A Flexible Workbench for Document.
Architecture and Real Time Systems Lab University of Massachusetts, Amherst An Application Driven Reliability Measures and Evaluation Tool for Fault Tolerant.
Introduction & Overview CS4533 from Cooper & Torczon.
Introduction to Data Science Kamal Al Nasr, Matthew Hayes and Jean-Claude Pedjeu Computer Science and Mathematical Sciences College of Engineering Tennessee.
Software Development Unit 2 Databases What is a database? A collection of data organised in a manner that allows access, retrieval and use of that data.
The Evaluation and Development of an Efficient Cooling System for High Performance Computing Applications Raaghul Senthilkumar and Ronik Sheth CURENT,
Dermatology 2006 SNU Dermatolory Lab Bioinformatics for Genomic Medicine 2006 Dermatology Lab Yoonkyung Kim 0 Term Project Proposal Presentation 2006.
© Janice Regan, CMPT 128, Jan CMPT 128 Introduction to Computing Science for Engineering Students Creating a program.
An Approach to Test Autonomic Containers Ronald Stevens (IEEE Computer Society & ACM Student Member) August 1, 2006 REU Sponsored by NSF.
Chapter 1 Introduction Dr. Frank Lee. 1.1 Why Study Compiler? To write more efficient code in a high-level language To provide solid foundation in parsing.
General Programming Introduction to Computing Science and Programming I.
Internet Information Retrieval Sun Wu. Course Goal To learn the basic concepts and techniques of internet search engines –How to use and evaluate search.
Cohesion and Coupling CS 4311
Unit-1 Introduction Prepared by: Prof. Harish I Rathod
Secure Systems Research Group - FAU 1 Active Replication Pattern Ingrid Buckley Dept. of Computer Science and Engineering Florida Atlantic University Boca.
SEG3300 A&B W2004R.L. Probert1 COCOMO Models Ognian Kabranov.
Component 4: Introduction to Information and Computer Science Unit 6a Databases and SQL.
Creating a System to Test Single Photon Avalanche Diodes Alex Chan Young Scholars Program Farragut High School July, 16,2014 Knoxville, Tennessee.
High Efficiency Power Converters Using Gallium Nitride Transistors Marl Nakmali Mentors: Dr. Leon Tolbert Yutian Cui.
Introduction to Compilers. Related Area Programming languages Machine architecture Language theory Algorithms Data structures Operating systems Software.
Chapter 1 Introduction Major Data Structures in Compiler
Software Development Problem Analysis and Specification Design Implementation (Coding) Testing, Execution and Debugging Maintenance.
Information Retrieval CSE 8337 Spring 2007 Introduction/Overview Some Material for these slides obtained from: Modern Information Retrieval by Ricardo.
The Comparison of Approximations of Nonlinear Functions Combined with Harmonic Balance Method for Power System Oscillation Frequency Estimation Abigail.
Thermal Analysis and PCB Design for GaN Power Transistor
I n regulated power industry utility wants to do demand response. Designing a Model to Obtain Residents’ Response for the Financial Incentives in a Demand.
Optimization of EV Charging Shivam Patel Final Presentation 07/23/15 CURENT.
Modelling the NPCC System with 12.5% Wind Penetration
Neural Network Recognition of Frequency Disturbance Recorder Signals Stephen Tang REU Final Presentation July 22, 2014.
ICS312 Introduction to Compilers Set 23. What is a Compiler? A compiler is software (a program) that translates a high-level programming language to machine.
Computer Science & Engineering 2111 Database Objects 1 CSE 2111 Introduction to Database Management Systems.
A New Generation of Artificial Neural Networks.  Support Vector Machines (SVM) appeared in the early nineties in the COLT92 ACM Conference.  SVM have.
Signal Detection and How to Build an Audio Amplifier
Experience Report: System Log Analysis for Anomaly Detection
DDC 2223 SYSTEM SOFTWARE DDC2223 SYSTEM SOFTWARE.
Introduction to Computing Science and Programming I
Designing Cross-Language Information Retrieval System using various Techniques of Query Expansion and Indexing for Improved Performance  Hello everyone,
3D Animation of Power System Data
Multi-Layer Network Representation of the NTC Environment Lili Sun, Proof School Arijit Das, Computer Science Introduction The United States Army’s National.
Automatic Video Shot Detection from MPEG Bit Stream
Casey O’Leary – Washington State University
Map Reduce.
CISC 7120X Programming Languages and Compilers
Dynamic Transmission Network Behavior for DER Power Systems
Interleaved AC-DC CRM PFC Converter
Datamining : Refers to extracting or mining knowledge from large amounts of data Applications : Market Analysis Fraud Detection Customer Retention Production.
Jeremy Till1, Shutang You2, Yilu Liu2
Analog to Digital Conversion
Authors: Khaled Abdelsalam Mohamed Amr Kamel
Information Retrieval
OUTAGE MODELING: PQ BUS NUMERICAL ANALYSIS & RESULTS
MATHEMATICAL MODELING
Error Detection in the Frequency Monitoring Network (FNET)
3D Animation of Power System Data
Title of Poster Site Visit 2017 Introduction Results
Analog to Digital Converter
Spreadsheets, Modelling & Databases
Publication Output on the Topical Area of "Energy" and Real Estate (Education) Bob Martens.
CISC 7120X Programming Languages and Compilers
Introduction to Computer Science
Title of Poster Site Visit 2018 Introduction Results
1Peyton Spencer, 2Yang Liu, 2Dr. Kai Sun
A Comparison of Modulation Techniques for Three-Level Neutral-Point-Clamped Inverter Fed Motor Drives William Karls1, Ruirui Chen2, Dr Fred Wang2 1The.
Norbert Bigirimana1, Dr. Hantao Cui2, Dr. Kevin Tomsovic2
Examining Hurricane Irma with Twitter Data
Mason Strader1, Vivian Wang2
Sharifa Sharfeldden1, Peter Pham2, Dr. Daniel Costinett2
Mechanical Construction
BUILDING A BLOCKCHAIN USING PYTHON
Presentation transcript:

Deep Learning Cascading Failure Prediction in a High Performance Computing System Eric Abreut1, Zhongbo Li2 1 Florida International University 2 The University of Tennessee, Knoxville Introduction Results Test file loaded into program using 2 different error cases (NDdoGS and Wa) and 40 occurrences: Purpose: To apply deep learning methods to predict the cascading failure in High Performance Computing. The Titan can tolerate many different physical and cyber failures during daily operations. System log is kept of these errors including component information as well as the kind of error. Deep learning methods can help parse the logs and keep the essential information which includes the type of error as well as the amount of times it occurred. Console output of all the cases: Concept Sample of System Log: 2017-02-07 15:58:53 Node c5-2c2s4n1 DBE detected on GPU SerialNum 0323812023167 2017-02-08 12:33:07 Warmswap adding c7-4c2s0 2017-02-09 22:39:23 Node c8-7c2s0n3 DBE detected on GPU SerialNum 0323712044373 The results lined up with the information being parsed by the program using basic python functions. Remove timestamps, whitespaces, and ‘Node’, ‘Link’, and ‘Module’ IDs: Node DBE detected on GPU SerialNum Warmswap adding Future Steps Apply Pyspark library to replicate python code but add deep learning methods to facilitate the error calculation. Increase time complexity of program so that large file parsing becomes faster and much more efficient. Extract first letter of words and generate sentence in the specific line: NDdoGS Wa References Rajman, M., & Besançon, R. (1998). Text mining: Natural language techniques and text mining applications. In S. Spaccapietra, & F. Maryanski (Eds.), Data mining and reverse engineering: Searching for semantics. IFIP TC2 WG2.6 IFIP seventh conference on database semantics (DS-7) 7–10 october 1997, leysin, switzerland (pp. 50-64). Boston, MA: Springer US. Record amount of error occurrences: Error Type Occurrences NDdoGS 2 Wa 1 This work was supported primarily by the ERC Program of the National Science Foundation and DOE under NSF Award Number EEC-1041877. Other US government and industrial sponsors of CURENT research are also gratefully acknowledged.