Performance Management of Cloud Populations via Cloud Probing

• Item type: Journal(1)
• 公開日: 2015-12-15
• タイトル: Performance Management of Cloud Populations via Cloud Probing
• タイトル / 言語: en
• タイトル: Performance Management of Cloud Populations via Cloud Probing
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [一般論文] cloud probing, cloud populations, cloud performance management, active probing, live migration, topology optimization, migration cost, federated clouds
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Department of Artificial Intelligence, Computer Science and Systems Engineering, Kyushu Institute of Technology
• 著者所属(英): en
• 著者所属(英): Department of Artificial Intelligence, Computer Science and Systems Engineering, Kyushu Institute of Technology
• 著者名: Marat, Zhanikeev
• 著者名(英): Marat, Zhanikeev
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Cloud population is a term that describes a cloud application distributed over many virtual machines or container-based boxes. Cloud platforms today offer simple tools for performance management (common example is load balancing) which are not sufficient for managing the performance of cloud populations. This paper proposes a new concept called cloud probing which is where applications themselves probe their host cloud platforms and optimize their own populations at runtime based on measurement data. This paper shows that even a simple optimization algorithm can lead to improved performance for the entire population. Since the only prerequisite function is the ability to migrate, the proposed method is also feasible in federated clouds where apps are fully in charge of managing their own populations spread across multiple cloud providers. This paper showcases the design of the TopoAPI that implements cloud probing, runs independently from physical platforms, and can therefore be used in federated environments.; \n------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.24(2016) No.1 (online); ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Cloud population is a term that describes a cloud application distributed over many virtual machines or container-based boxes. Cloud platforms today offer simple tools for performance management (common example is load balancing) which are not sufficient for managing the performance of cloud populations. This paper proposes a new concept called cloud probing which is where applications themselves probe their host cloud platforms and optimize their own populations at runtime based on measurement data. This paper shows that even a simple optimization algorithm can lead to improved performance for the entire population. Since the only prerequisite function is the ability to migrate, the proposed method is also feasible in federated clouds where apps are fully in charge of managing their own populations spread across multiple cloud providers. This paper showcases the design of the TopoAPI that implements cloud probing, runs independently from physical platforms, and can therefore be used in federated environments.; \n------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.24(2016) No.1 (online); ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00116647
• 書誌情報: 情報処理学会論文誌; 巻 56, 号 12, 発行日 2015-12-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764