DocumentCode
167021
Title
QoS management by competitive agent-based negotiation in distributed cloud services
Author
Ravindran, Kaliappa
Author_Institution
City Coll. & Grad. Center, City Univ. of New York CUNY, New York, NY, USA
fYear
2014
fDate
8-10 Oct. 2014
Firstpage
191
Lastpage
196
Abstract
Agent-level negotiations between an application and a cloud service provider (SP) face two complexities: i) inaccuracy of computational models in capturing the behavior of a cloud-based system made up of diverse components and resources; and ii) disparity in the goals and priorities of an application and the SP in exercising a cloud-based system. The paper suggests trial actions by an agent to learn about the system behavior and the opponent agent goals, as part of effective negotiation strategy. The paper identifies transaction-style primitives for agents to invoke trial actions on the system QoS space: searching, alternations, and improvements. A larger goal of optimal QoS control can be achieved with our primitives. A case study of CDN realized on a cloud is also described.
Keywords
cloud computing; learning (artificial intelligence); quality of service; software agents; QoS management; SP; agent-based negotiation; automated learning; cloud service provider; quality of service; transaction-style primitives; Bandwidth; Conferences; Delays; Quality of service; Resource management; Servers;
fLanguage
English
Publisher
ieee
Conference_Titel
Cloud Networking (CloudNet), 2014 IEEE 3rd International Conference on
Conference_Location
Luxembourg
Type
conf
DOI
10.1109/CloudNet.2014.6968991
Filename
6968991
Link To Document