License Forecasting and Scheduling for HPC

Ahmed Burak Gulhan; Gulsum Gudukbay Akbulut; Amit Amritkar; Jack Sampson; Vasant Honovar; Adam Focht; Chuck Pavloski; Mahmut Kandemir

doi:10.1109/MASCOTS59514.2023.10387539

License Forecasting and Scheduling for HPC

Ahmed Burak Gulhan, Gulsum Gudukbay Akbulut, Amit Amritkar, Jack Sampson, Vasant Honovar, Adam Focht, Chuck Pavloski, Mahmut Kandemir

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This work focuses on forecasting future license usage for high-performance computing environments and using such predictions to improve the effectiveness of job scheduling. Specifically, we propose a model that carries out both short-term and long-term license usage forecasting and a method of using forecasts to improve job scheduling. Our long-term forecasting model achieves a Mean Absolute Percentage Error (MAPE) as low as 0.26 for a 12-month forecast of daily peak license usage. Our job scheduling experimental results also indicate that wasted work from jobs with insufficient licenses can be reduced by up to 92% without increasing the average license-using job completion times, during periods of high license usage, with our proposed license-aware scheduler.

Original language	English (US)
Title of host publication	Proceedings - 2023 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023
Publisher	IEEE Computer Society
ISBN (Electronic)	9798350319484
DOIs	https://doi.org/10.1109/MASCOTS59514.2023.10387539
State	Published - 2023
Event	31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023 - Stony Brook, United States Duration: Oct 16 2023 → Oct 18 2023

Publication series

Name	Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS
ISSN (Print)	1526-7539

Conference

Conference	31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023
Country/Territory	United States
City	Stony Brook
Period	10/16/23 → 10/18/23

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering
Computer Networks and Communications
Software
Modeling and Simulation

Access to Document

10.1109/MASCOTS59514.2023.10387539

Cite this

Gulhan, A. B., Akbulut, G. G., Amritkar, A., Sampson, J., Honovar, V., Focht, A., Pavloski, C., & Kandemir, M. (2023). License Forecasting and Scheduling for HPC. In Proceedings - 2023 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023 (Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS). IEEE Computer Society. https://doi.org/10.1109/MASCOTS59514.2023.10387539

Gulhan, Ahmed Burak ; Akbulut, Gulsum Gudukbay ; Amritkar, Amit et al. / License Forecasting and Scheduling for HPC. Proceedings - 2023 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023. IEEE Computer Society, 2023. (Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS).

@inproceedings{beb396a8392b41a695d01ab3168812e0,

title = "License Forecasting and Scheduling for HPC",

abstract = "This work focuses on forecasting future license usage for high-performance computing environments and using such predictions to improve the effectiveness of job scheduling. Specifically, we propose a model that carries out both short-term and long-term license usage forecasting and a method of using forecasts to improve job scheduling. Our long-term forecasting model achieves a Mean Absolute Percentage Error (MAPE) as low as 0.26 for a 12-month forecast of daily peak license usage. Our job scheduling experimental results also indicate that wasted work from jobs with insufficient licenses can be reduced by up to 92% without increasing the average license-using job completion times, during periods of high license usage, with our proposed license-aware scheduler.",

author = "Gulhan, {Ahmed Burak} and Akbulut, {Gulsum Gudukbay} and Amit Amritkar and Jack Sampson and Vasant Honovar and Adam Focht and Chuck Pavloski and Mahmut Kandemir",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023 ; Conference date: 16-10-2023 Through 18-10-2023",

year = "2023",

doi = "10.1109/MASCOTS59514.2023.10387539",

language = "English (US)",

series = "Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS",

publisher = "IEEE Computer Society",

booktitle = "Proceedings - 2023 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023",

address = "United States",

}

Gulhan, AB, Akbulut, GG, Amritkar, A, Sampson, J, Honovar, V, Focht, A, Pavloski, C & Kandemir, M 2023, License Forecasting and Scheduling for HPC. in Proceedings - 2023 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023. Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS, IEEE Computer Society, 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023, Stony Brook, United States, 10/16/23. https://doi.org/10.1109/MASCOTS59514.2023.10387539

License Forecasting and Scheduling for HPC. / Gulhan, Ahmed Burak; Akbulut, Gulsum Gudukbay; Amritkar, Amit et al.
Proceedings - 2023 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023. IEEE Computer Society, 2023. (Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - License Forecasting and Scheduling for HPC

AU - Gulhan, Ahmed Burak

AU - Akbulut, Gulsum Gudukbay

AU - Amritkar, Amit

AU - Sampson, Jack

AU - Honovar, Vasant

AU - Focht, Adam

AU - Pavloski, Chuck

AU - Kandemir, Mahmut

PY - 2023

Y1 - 2023

N2 - This work focuses on forecasting future license usage for high-performance computing environments and using such predictions to improve the effectiveness of job scheduling. Specifically, we propose a model that carries out both short-term and long-term license usage forecasting and a method of using forecasts to improve job scheduling. Our long-term forecasting model achieves a Mean Absolute Percentage Error (MAPE) as low as 0.26 for a 12-month forecast of daily peak license usage. Our job scheduling experimental results also indicate that wasted work from jobs with insufficient licenses can be reduced by up to 92% without increasing the average license-using job completion times, during periods of high license usage, with our proposed license-aware scheduler.

AB - This work focuses on forecasting future license usage for high-performance computing environments and using such predictions to improve the effectiveness of job scheduling. Specifically, we propose a model that carries out both short-term and long-term license usage forecasting and a method of using forecasts to improve job scheduling. Our long-term forecasting model achieves a Mean Absolute Percentage Error (MAPE) as low as 0.26 for a 12-month forecast of daily peak license usage. Our job scheduling experimental results also indicate that wasted work from jobs with insufficient licenses can be reduced by up to 92% without increasing the average license-using job completion times, during periods of high license usage, with our proposed license-aware scheduler.

UR - http://www.scopus.com/inward/record.url?scp=85184516775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85184516775&partnerID=8YFLogxK

U2 - 10.1109/MASCOTS59514.2023.10387539

DO - 10.1109/MASCOTS59514.2023.10387539

M3 - Conference contribution

AN - SCOPUS:85184516775

T3 - Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS

BT - Proceedings - 2023 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023

PB - IEEE Computer Society

T2 - 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023

Y2 - 16 October 2023 through 18 October 2023

ER -

Gulhan AB, Akbulut GG, Amritkar A, Sampson J, Honovar V, Focht A et al. License Forecasting and Scheduling for HPC. In Proceedings - 2023 31st International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2023. IEEE Computer Society. 2023. (Proceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS). doi: 10.1109/MASCOTS59514.2023.10387539

License Forecasting and Scheduling for HPC

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Cite this