A Self-adaptive Agent-based System for Cloud Platforms

Merzoug Soltane (1) , Yudith Cardinale (2) , Rafael Angarita (3) , Philippe Roose (4, 5) , Marta Rukoz (6) , Derdour Makhlouf (5) , Kazar Okba (7)

1 LINFI - Laboratoire d'Informatique Intelligente
2 USB - Universidad Simon Bolivar
3 ISEP - Institut Supérieur d'Electronique de Paris
4 UPPA - Université de Pau et des Pays de l'Adour
5 LIUPPA - Laboratoire Informatique de l'Université de Pau et des Pays de l'Adour
6 LAMSADE - Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision
7 autre

Cloud computing is a model for enabling on-demand network access to a shared pool of computing resources, that can be dynamically allocated and released with minimal effort. However, this task can be complex in highly dynamic environments with various resources to allocate for an increasing number of different users requirements. In this work, we propose a Cloud architecture based on a multi-agent system exhibiting a self-adaptive behavior to address the dynamic resource allocation. This self-adaptive system follows a MAPE-K approach to reason and act, according to QoS, Cloud service information, and propagated run-time information, to detect QoS degradation and make better resource allocation decisions. We validate our proposed Cloud architecture by simulation. Results show that it can properly allocate resources to reduce energy consumption, while satisfying the users demanded QoS.

Domains: Computer Science [cs]; Other [cs.OH]; Computer Science [cs]

Merzoug Soltane, Yudith Cardinale, Rafael Angarita, Philippe Roose, Marta Rukoz, et al.. A Self-adaptive Agent-based System for Cloud Platforms. PAIS, 2018, Tebessa, Algeria. ⟨hal-02455961⟩