PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Naug, Avisek, Guillen, Antonio, Gutiérrez, Ricardo Luna, Gundecha, Vineet, Markovikj, Dejan, Kashyap, Lekhapriya Dheeraj, Krause, Lorenz, Ghorbanpour, Sahand, Mousavi, Sajad, Babu, Ashwin Ramesh, Sarkar, Soumyendu
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913285616435200
author Naug, Avisek
Guillen, Antonio
Gutiérrez, Ricardo Luna
Gundecha, Vineet
Markovikj, Dejan
Kashyap, Lekhapriya Dheeraj
Krause, Lorenz
Ghorbanpour, Sahand
Mousavi, Sajad
Babu, Ashwin Ramesh
Sarkar, Soumyendu
author_facet Naug, Avisek
Guillen, Antonio
Gutiérrez, Ricardo Luna
Gundecha, Vineet
Markovikj, Dejan
Kashyap, Lekhapriya Dheeraj
Krause, Lorenz
Ghorbanpour, Sahand
Mousavi, Sajad
Babu, Ashwin Ramesh
Sarkar, Soumyendu
contents The increasing global emphasis on sustainability and reducing carbon emissions is pushing governments and corporations to rethink their approach to data center design and operation. Given their high energy consumption and exponentially large computational workloads, data centers are prime candidates for optimizing power consumption, especially in areas such as cooling and IT energy usage. A significant challenge in this pursuit is the lack of a configurable and scalable thermal data center model that offers an end-to-end pipeline. Data centers consist of multiple IT components whose geometric configuration and heat dissipation make thermal modeling difficult. This paper presents PyDCM, a customizable Data Center Model implemented in Python, that allows users to create unique configurations of IT equipment with custom server specifications and geometric arrangements of IT cabinets. The use of vectorized thermal calculations makes PyDCM orders of magnitude faster (30 times) than current Energy Plus modeling implementations and scales sublinearly with the number of CPUs. Also, PyDCM enables the use of Deep Reinforcement Learning via the Gymnasium wrapper to optimize data center cooling and offers a user-friendly platform for testing various data center design prototypes.
format Preprint
id arxiv_https___arxiv_org_abs_2310_03906
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability
Naug, Avisek
Guillen, Antonio
Gutiérrez, Ricardo Luna
Gundecha, Vineet
Markovikj, Dejan
Kashyap, Lekhapriya Dheeraj
Krause, Lorenz
Ghorbanpour, Sahand
Mousavi, Sajad
Babu, Ashwin Ramesh
Sarkar, Soumyendu
Machine Learning
The increasing global emphasis on sustainability and reducing carbon emissions is pushing governments and corporations to rethink their approach to data center design and operation. Given their high energy consumption and exponentially large computational workloads, data centers are prime candidates for optimizing power consumption, especially in areas such as cooling and IT energy usage. A significant challenge in this pursuit is the lack of a configurable and scalable thermal data center model that offers an end-to-end pipeline. Data centers consist of multiple IT components whose geometric configuration and heat dissipation make thermal modeling difficult. This paper presents PyDCM, a customizable Data Center Model implemented in Python, that allows users to create unique configurations of IT equipment with custom server specifications and geometric arrangements of IT cabinets. The use of vectorized thermal calculations makes PyDCM orders of magnitude faster (30 times) than current Energy Plus modeling implementations and scales sublinearly with the number of CPUs. Also, PyDCM enables the use of Deep Reinforcement Learning via the Gymnasium wrapper to optimize data center cooling and offers a user-friendly platform for testing various data center design prototypes.
title PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability
topic Machine Learning
url https://arxiv.org/abs/2310.03906