Self-learning cloud controllers: Fuzzy Q-learning for knowledge evolution
MetadataShow full item record
Auto-scaling features enable cloud applications to maintain enough resources to satisfy demand spikes, reduce costs and keep performance in check. Most auto-scaling strategies rely on a predefined set of rules to scale up/down the required resources depending on the application usage. Those rules are however difficult to devise and generalize, and users are often left alone tuning auto-scale parameters of essentially blackbox applications. In this paper, we propose a novel fuzzy reinforcement learning controller, FQL4KE, which automatically scales up or down resources to meet performance requirements. The Q-Learning technique, a model-free reinforcement learning strategy, frees users of most tuning parameters. FQL4KE has been successfully applied and we therefore think that a fuzzy controller with Q-Learning is indeed a promising combination for auto-scaling resources.
Showing items related by title, author, creator and subject.
Dodero, G; Chowdhury, A; Geraci, L; Del Fatto, V (Knowledge Systems Institute, 2013)In this paper we explore how topics from two different fields of computer science, such as Geographic Information Systems and E-learning Systems, can contribute to the Mobile Learning field. In particular, starting from a ...
Dodero, G; Forcheri, P; Di Cerbo, F (Scuola IaD : F&D, 2010)The DULP vision is providing an innovative perspective for rethinking learning processes, to become, among the others, ubiquitous and focused on persons in their daily activities, according to the new dynamic reality that ...