Classical approaches to performance prediction rely on two, typically antithetic, techniques: Machine Learning (ML) and Analytical Modeling (AM). ML takes a black box ap- proach, whose accuracy strongly depends on the represen- tativeness of the dataset used during the initial training phase. Specifically, it can achieve very good accuracy in areas of the features' space that have been sufficiently ex- plored during the training process. Conversely, AM tech- niques require no or minimal training, hence exhibiting the potential for supporting prompt instantiation of the perfor- mance model of the target system. However, in order to ensure their tractability, they typically rely on a set of sim- plifying assumptions. Consequently, AM's accuracy can be seriously challenged in scenarios (e.g., workload conditions) in which such assumptions are not matched. In this paper we explore several hybrid/gray box techniques that exploit AM and ML in synergy in order to get the best of the two worlds. We evaluate the proposed techniques in case stud- ies targeting two complex and widely adopted middleware systems: a NoSQL distributed key-value store and a Total Order Broadcast (TOB) service. Copyright © 2015 ACM.

Enhancing performance prediction robustness by combining analytical modeling and machine learning / Didona, Diego; Quaglia, Francesco; Romano, Paolo; Torre, Ennio. - STAMPA. - (2015), pp. 145-156. (Intervento presentato al convegno 6th ACM/SPEC International Conference on Performance Engineering, ICPE 2015 tenutosi a Austin; United States; 31 January 2015 through 4 February 2015; Code 110555 nel 31 January - 04 February 2015) [10.1145/2668930.2688047].

Enhancing performance prediction robustness by combining analytical modeling and machine learning

QUAGLIA, Francesco
;
2015

Abstract

Classical approaches to performance prediction rely on two, typically antithetic, techniques: Machine Learning (ML) and Analytical Modeling (AM). ML takes a black box ap- proach, whose accuracy strongly depends on the represen- tativeness of the dataset used during the initial training phase. Specifically, it can achieve very good accuracy in areas of the features' space that have been sufficiently ex- plored during the training process. Conversely, AM tech- niques require no or minimal training, hence exhibiting the potential for supporting prompt instantiation of the perfor- mance model of the target system. However, in order to ensure their tractability, they typically rely on a set of sim- plifying assumptions. Consequently, AM's accuracy can be seriously challenged in scenarios (e.g., workload conditions) in which such assumptions are not matched. In this paper we explore several hybrid/gray box techniques that exploit AM and ML in synergy in order to get the best of the two worlds. We evaluate the proposed techniques in case stud- ies targeting two complex and widely adopted middleware systems: a NoSQL distributed key-value store and a Total Order Broadcast (TOB) service. Copyright © 2015 ACM.
2015
6th ACM/SPEC International Conference on Performance Engineering, ICPE 2015
Software; Analytical models; Artificial intelligence; Middleware
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Enhancing performance prediction robustness by combining analytical modeling and machine learning / Didona, Diego; Quaglia, Francesco; Romano, Paolo; Torre, Ennio. - STAMPA. - (2015), pp. 145-156. (Intervento presentato al convegno 6th ACM/SPEC International Conference on Performance Engineering, ICPE 2015 tenutosi a Austin; United States; 31 January 2015 through 4 February 2015; Code 110555 nel 31 January - 04 February 2015) [10.1145/2668930.2688047].
File allegati a questo prodotto
File Dimensione Formato  
Didona_Enhancing-performance_2015.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.26 MB
Formato Adobe PDF
2.26 MB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/951496
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 59
  • ???jsp.display-item.citation.isi??? ND
social impact