Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Digital Twin for Tuning of Server Fan Controllers
RISE Research Institutes of Sweden, Digitala system, Datavetenskap.ORCID-id: 0000-0003-4293-6408
RISE Research Institutes of Sweden.
RISE Research Institutes of Sweden.
RISE Research Institutes of Sweden, Digitala system, Datavetenskap.ORCID-id: 0000-0002-9759-5594
Visa övriga samt affilieringar
2019 (Engelska)Ingår i: 2019 IEEE 17th International Conference on Industrial Informatics (INDIN), 2019, s. 1425-1428Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Cooling of IT equipment consumes a large proportion of a modern data centre’s energy budget and is therefore an important target for optimal control. This study analyses a scaled down system of six servers with cooling fans by implementing a minimal data driven time-series model in TensorFlow/Keras, a modern software package popular for deep learning. The model is inspired by the physical laws of heat exchange, but with all parameters obtained by optimisation. It is encoded as a customised Recurrent Neural Network and exposed to the time-series data via n-step Prediction Error Minimisation (PEM). The thus obtained Digital Twin of the physical system is then used directly to construct a Model Predictive Control (MPC) type regulator that executes in real time. The MPC is then compared in simulation with a self-tuning PID controller that adjust its parameters on-line by gradient descent.

Ort, förlag, år, upplaga, sidor
2019. s. 1425-1428
Serie
IEEE International Conference on Industrial Informatics (INDIN)
Nyckelord [en]
RNN, PEM, TensorFlow, MPC, Digital Twin
Nationell ämneskategori
Reglerteknik
Identifikatorer
URN: urn:nbn:se:ri:diva-64221DOI: 10.1109/INDIN41052.2019.8972291OAI: oai:DiVA.org:ri-64221DiVA, id: diva2:1742678
Konferens
2019 IEEE 17th International Conference on Industrial Informatics (INDIN)
Anmärkning

ISBN för värdpublikation: 978-1-7281-2927-3, 978-1-7281-2928-0

Tillgänglig från: 2023-03-10 Skapad: 2023-03-10 Senast uppdaterad: 2023-06-07Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Person

Brännvall, RickardGustafsson, JonasSummers, Jon

Sök vidare i DiVA

Av författaren/redaktören
Brännvall, RickardGustafsson, JonasSummers, Jon
Av organisationen
DatavetenskapRISE Research Institutes of Sweden
Reglerteknik

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 29 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf