Physical and Data-Driven Models for Edge Data Center Cooling System

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2020-10-29

Major/Subject

Mcode

Degree programme

Language

en

Pages

7

Series

2020 Swedish Workshop on Data Science, SweDS 2020

Abstract

Edge data centers are expected to become prevalent providing low latency computing power for 5G mobile and IoT applications. This article develops two models for the complete cooling system of an edge data center: One model based on the laws of thermodynamics and one data-driven model based on LSTM neural networks. The models are validated against an actual edge data center experimental set-up showing root mean squared errors (RMSE) for most individual components below 1 °C over a simulation period of approximately 10 hours; which compares favourably to state-of-the-art models.

Description

Keywords

Cooling System, Data center, Edge, LSTM, Thermal Energy Storage

Other note

Citation

Siltala, M, Brannvall, R, Gustafsson, J & Zhou, Q 2020, Physical and Data-Driven Models for Edge Data Center Cooling System . in 2020 Swedish Workshop on Data Science, SweDS 2020 ., 9275588, IEEE, Swedish Workshop on Data Science, Lulea, Sweden, 29/10/2020 . https://doi.org/10.1109/SweDS51247.2020.9275588