Speculatively Reconfigurable Big Data Processing Infrastructure Capable of Bursty Load Fluctuation

2015 Fiscal Year Final Research Report

• Project/Area Number: 25280022
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Software
• Research Institution: Ochanomizu University
• Principal Investigator: Oguchi Masato お茶の水女子大学, 基幹研究院, 教授 (60328036)
• Co-Investigator(Kenkyū-buntansha): YAMAGUCHI Saneyasu 工学院大学, 工学部, 准教授 (50439262) ; NAKANO Miyuki 産業技術大学院大学, 情報アーキテクチャ専攻, 教授 (30227863) ; GOTOU Atsuhiro 情報セキュリティ大学院大学, 情報セキュリティ研究科, 教授 (90558868) ; SHINTANI Takahiko 電気通信大学, 大学院情報システム学研究科, 准教授 (30604623)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: ビッグデータ / バースト性 / 投機的再構成 / ソーシャル情報 / クラウド / SDN

Outline of Final Research Achievements

In this research work, a method for speculative reconstruction of a Big Data processing system is proposed, which is responded to a bursty load increase. The method is implemented on an experiment system and evaluated. A bursty load change is predicted by monitoring data, and a virtual machine of a Cloud computing system is migrated and relocated based on the prediction, and the network traffic is controlled using the information. A Big Data processing system that is tolerable to a bursty load increase is constructed and evaluated using data in an emergency case.

Free Research Field

ネットワークコンピューティング・ミドルウェア