{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/self-learning-cloud-controllers-fuzzy-q","title":"Self-Learning Cloud Controllers: Fuzzy Q-Learning for Knowledge Evolution","arxiv_id":"1507.00567","date":"2015-07-02","proceeding":null,"authors":["Pooyan Jamshidi","Amir Sharifloo","Claus Pahl","Andreas Metzger","Giovani Estrada"],"abstract":"Cloud controllers aim at responding to application demands by automatically\nscaling the compute resources at runtime to meet performance guarantees and\nminimize resource costs. Existing cloud controllers often resort to scaling\nstrategies that are codified as a set of adaptation rules. However, for a cloud\nprovider, applications running on top of the cloud infrastructure are more or\nless black-boxes, making it difficult at design time to define optimal or\npre-emptive adaptation rules. Thus, the burden of taking adaptation decisions\noften is delegated to the cloud application. Yet, in most cases, application\ndevelopers in turn have limited knowledge of the cloud infrastructure. In this\npaper, we propose learning adaptation rules during runtime. To this end, we\nintroduce FQL4KE, a self-learning fuzzy cloud controller. In particular, FQL4KE\nlearns and modifies fuzzy rules at runtime. The benefit is that for designing\ncloud controllers, we do not have to rely solely on precise design-time\nknowledge, which may be difficult to acquire. FQL4KE empowers users to specify\ncloud controllers by simply adjusting weights representing priorities in system\ngoals instead of specifying complex adaptation rules. The applicability of\nFQL4KE has been experimentally assessed as part of the cloud application\nframework ElasticBench. The experimental results indicate that FQL4KE\noutperforms our previously developed fuzzy controller without learning\nmechanisms and the native Azure auto-scaling.","url_abs":"http://arxiv.org/abs/1507.00567v1","url_pdf":"http://arxiv.org/pdf/1507.00567v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"self-learning-cloud-controllers-fuzzy-q","repo_url":"https://github.com/pooyanjamshidi/ElasticBench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"self-learning","task_name":"Self-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}