Adaptive Feedforward and Feedback Control for Cloud Services

Sophie Cerf 1 Mihaly Berekmeri 2, 1 Bogdan Robu 1 Nicolas Marchand 1 Sara Bouchenak 3 Ioan Doré Landau 4
GIPSA-DA - Département Automatique
3 DRIM - Distribution, Recherche d'Information et Mobilité
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
GIPSA-DA - Département Automatique
Abstract : The use of cloud services is becoming increasingly common. As the cost of these services is continuously decreasing, service performance is becoming a key differentiator between providers. Solutions that aim to guarantee Service Level Objectives (SLO) in term of performance by controlling cluster size are already used by cloud providers. However most of these control solutions are based on static if-then rules, they are therefore inefficient in handling the highly varying service dynamics of cloud environments. Client concurrency, network bottlenecks or non homogeneity of resources are just a few of the many causes that make the behavior of cloud services highly non linear and time varying. In this paper a novel control theoretical approach is presented that is robust to these phenomena. It consists of PI and feedforward controller adapted online. A stability analysis of the adaptive control configuration is provided. Simulations using a cloud service model taken from the literature illustrate the performance of the system under various conditions. The use of adaptation significantly improves control efficiency and robustness with respect to variations in the dynamic of the plant.
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download
Contributor : Sophie Cerf <>
Submitted on : Monday, January 8, 2018 - 3:42:35 PM
Last modification on : Saturday, December 15, 2018 - 1:50:07 AM



Sophie Cerf, Mihaly Berekmeri, Bogdan Robu, Nicolas Marchand, Sara Bouchenak, et al.. Adaptive Feedforward and Feedback Control for Cloud Services. 20th IFAC World Congress (IFAC WC 2017), Jul 2017, Toulouse, France. pp.5504 - 5509, ⟨10.1016/j.ifacol.2017.08.1090⟩. ⟨hal-01397666v2⟩



Record views


Files downloads