Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Temporal fusion transformer based vertical scaling management for Kubernetes

  • Bora, Kemalcan
  • Kartsakli, Elli
  • Quiñones Moreno, Eduardo
Language Models (LMs) deployed in Kubernetes face resource management challenges due to their variable computational demands. Traditional scaling methods, like the default Vertical Pod Autoscaler (VPA), struggle to adapt, often causing inefficient resource use and performance issues. We propose the Temporal Fusion Transformer Based Dynamic Vertical Pod Autoscaler (TFT-DVPA), which employs advanced time series forecasting to predict and adjust memory allocation. Tested with three Small Language Models (under 100 million parameters) under simulated fluctuating workloads, TFT-DVPA outperforms the default VPA, achieving lower prediction errors and improved resource efficiency., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the EXTRACT Project, grant agreement n° 101093110 and the PROXIMITY project (PID2021- 124122OA-I00/AEI/10.13039/501100011033). This work is co-financed by the ASCENDER project of the UNICO I+D Cloud program that has Ministry for Digital Transformation and of Civil Service and the EU-Next Generation EU as financing entities, within the framework of the PRTR and the MRR. The first author also acknowledges support from the AI4Science Fellowships (AI4S) program. This initiative is part of the talent attraction and retention programs within Investment 4 of Component 19 of the Recovery, Transformation, and Resilience Plan (C005/24-ED CV1)., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Temporal fusion transformer based vertical scaling management for Kubernetes

  • Bora, Kemalcan
  • Kartsakli, Elli
  • Quiñones Moreno, Eduardo
Language Models (LMs) deployed in Kubernetes face resource management challenges due to their variable computational demands. Traditional scaling methods, like the default Vertical Pod Autoscaler (VPA), struggle to adapt, often causing inefficient resource use and performance issues. We propose the Temporal Fusion Transformer Based Dynamic Vertical Pod Autoscaler (TFT-DVPA), which employs advanced time series forecasting to predict and adjust memory allocation. Tested with three Small Language Models (under 100 million parameters) under simulated fluctuating workloads, TFT-DVPA outperforms the default VPA, achieving lower prediction errors and improved resource efficiency., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the EXTRACT Project, grant agreement n° 101093110 and the PROXIMITY project (PID2021- 124122OA-I00/AEI/10.13039/501100011033). This work is co-financed by the ASCENDER project of the UNICO I+D Cloud program that has Ministry for Digital Transformation and of Civil Service and the EU-Next Generation EU as financing entities, within the framework of the PRTR and the MRR. The first author also acknowledges support from the AI4Science Fellowships (AI4S) program. This initiative is part of the talent attraction and retention programs within Investment 4 of Component 19 of the Recovery, Transformation, and Resilience Plan (C005/24-ED CV1)., Peer Reviewed, Postprint (author's final draft)