Abstract

The application of market mechanisms for the allocation of computing services is a  demanding task,

which requires bridging economic  and associated  technical challenges. Even if the market-based

approach promises an efficient allocation of computing services, the wide heterogeneity of consumer

requirements and the diversity of computational services on provider side  are  challenging the

processes of finding, allocating, and using an appropriate service in an autonomous way. The focus of

the  most papers is mainly  devoted to  the optimization embedded in the allocation process itself.

However, we think that the optimization process starts  much earlier and contains the information

gathering until the final market-based resource allocations.

In this paper we introduce an integrated framework for market-based allocation of computing

services, integrating information retrieval  of market information, prediction models, bidding

strategies and marked mechanisms.  As proof-of-concept, we  implemented  a  first  prototype  of the

framework. Furthermore, we  propose a methodology for  evaluating strategic behavior in market

mechanisms  with bidding strategies  using market information and statistical prediction techniques.

First simulation results show strategic behavior  in selected market mechanisms by applying the

proposed techniques.

Download

Share

COinS