Authors: Benedikt Pittl; Irfan Ul-Haq; Werner Mach; Erich Schikuta
Addresses: Faculty of Computer Science, University of Vienna, Vienna, Austria ' Department of CIS, Pakistan Institute of Engineering and Applied Sciences, Islamabad, Pakistan ' Faculty of Computer Science, University of Vienna, Vienna, Austria ' Faculty of Computer Science, University of Vienna, Vienna, Austria
Abstract: Today, cloud services, such as virtual machines, are traded directly at fixed prices between consumers and providers on platforms, e.g. Amazon EC2. The recent development of Amazon's EC2 spot market shows that dynamic cloud markets are gaining popularity. Hence, autonomous multi-round bilateral negotiations, also known as bazaar negotiations, are a promising approach for trading cloud services on future cloud markets. They play a vital role for composing service chains. Based on a formal description we describe such service chains and derive different negotiation types. We implement them in a simulation environment and evaluate our approach by executing different market scenarios. Therefore, we developed three negotiation strategies for cloud resellers. Our simulation results show that cloud resellers as well as their negotiation strategies have a significant impact on the resource allocation of cloud markets. Very high as well as very low mark-ups reduce the profit of a reseller.
Keywords: cloud computing; cloud marketplace; IaaS; infrastructure as a service; bazaar-negotiation; SLA negotiation; simulation; cloud service chain; cloud reseller; multi-round negotiation; cloud economics.
International Journal of Grid and Utility Computing, 2019 Vol.10 No.6, pp.593 - 606
Received: 08 Nov 2017
Accepted: 19 Feb 2018
Published online: 09 Aug 2019 *