• Aucun résultat trouvé

Case-Based Reasoning in the Cloud

N/A
N/A
Protected

Academic year: 2022

Partager "Case-Based Reasoning in the Cloud"

Copied!
2
0
0

Texte intégral

(1)

Case-based Reasoning in the Cloud

Mirjam Minor

Goethe University Frankfurt am Main, Germany minor@cs.uni-frankfurt.de

Abstract. Cloud computing has its roots clearly in industry. A huge variety of successful cloud services have been developed in a rather prag- matic manner. Recently, Cloud computing is increasing its attraction also as a research topic. Many basic questions especially in cloud man- agement still remain open.Cloud managementdeals with management methods for provisioning and use of cloud services [1]. For instance, rapid scalability is often achieved by a massive overprovisioning of resources today, which causes overcharged prices and a waste of energy. A sys- tematic approach including thourough concepts for monitoring, analysis, search, reuse, orchestration and configuration of cloud services might be extremely benefitial for both cloud providers and users.

The keynote will highlight the potential of intelligent cloud management methods, particularly from the field of Case-based Reasoning.Case-based Reasoning(CBR) is a sub-area of Artificial Intelligence that deals with the reuse of experience recorded in cases [5]. Recent work on case-based, automated cloud management [3, 4] will be presented. Future research issues for CBR in the cloud will be investigated, including the semantic description and retrieval of cloud services, the case-based analysis of time series [2] applicable to the monitoring of service level agreements, for instance, and the potential ”cloudification” of CBR methods such as rapidly scalable case retrieval and case adaptation. Potential business application scenarios will be discussed.

The aim of this keynote is to demonstrate that, beyond the buzzword, cloud computing provides novel, intriguing opportunities for research.

References

1. C. Baun, M. Kunze, J. Nimis, and S. Tai. Cloud Computing - Web-Based Dynamic IT Services. Springer, 2011.

2. Odd Erik Gundersen. Toward measuring the similarity of complex event sequences in real-time. In Bel´en D´ıaz Agudo and Ian Watson, editors,Case-Based Reasoning Research and Development, number 7466 in Lecture Notes in Computer Science, pages 107–121. Springer Berlin Heidelberg, January 2012.

Copyright c 2014by the paper’s authors. Copying permitted only for private and academic purposes. In: T. Seidl, M. Hassani, C. Beecks (Eds.): Proceedings of the LWA 2014 Workshops: KDML, IR, FGWM, Aachen, Germany, 8-10 September 2014, published at http://ceur-ws.org

261

(2)

3. Michael Maurer, Ivona Brandic, and Rizos Sakellariou. Adaptive resource configu- ration for cloud infrastructure management. Future Generation Computer Systems, 29(2):472–487, 2013.

4. Mirjam Minor and Eric Schulte-Zurhausen. Towards process-oriented cloud man- agement with case-based reasoning. InProc. ICCBR 2014, LNCS 8766, pages 303 – 312. Springer, 2014. The original publication is available at www.springerlink.com.

5. Michael M. Richter and Rosina Weber. Case-Based Reasoning: A Textbook.

Springer, auflage: 2013 edition, November 2013.

262

Références

Documents relatifs

Using generic agents and adequate case base structure associated with a dedicated recall algorithm, we improve retrieval performance under time pressure compared to classic CBR

The monitor combines information obtained at the level of main memory, disk storage and network traffic of the sandbox VME. VM instances such that VMI access is enabled from a monitor

This paper document offers a description of the same information protection and confidentiality issues related to sharing cloud technology and sets out all the

To determine a methylation signature, the top 1 feature-selected gene, top 2 feature-selected genes and so forth were selected, until reaching the top 15 feature-selected genes.

 the relative simplicity of the redistribution of resources between local data centres (computing power, data storages, transmission channels), geographically remote from

Those columns are cropped and re- placed with Secret customer ID during migration to the cloud using AWS Database Migration Service (initial load). b) INSERT and UPDATE

The two prediction modes are evaluated with only the geometric compensation enabled (“geo”) and both the geometric and photometric compensations enabled (“geo+photo”). The

This paper sketches a new approach for rule-based reasoning, enabling distributed rule evaluation on edge nodes and reducing the latency for IoT applications while avoiding the