Micro-economics based resource allocation in Grid-Federation environment

Abstract

A Grid-Federation environment is composed of a collection of autonomous and selfish distributed cluster resource managers. These selfish managers participate in Grid-Federation to share their resources. Market models could be used to motivate the self-interested participants to share their resources. In this paper, firstly, a market for resource exchange in grid federation environment is established. Then, in order that the market reaches a Walrasian equilibrium, a computationally tractable mechanism is proposed. A Walrasian equilibrium problem consists of finding a set of prices and allocations of resources in such a way that the cluster resource managers could maximize their utilities and the market clears. Market clears when the resource supply equals to the demand. We show that in a Walrasian equilibrium, the Grid Federation market reaches an efficient resource allocation.

A Novel Resource Pricing Mechanism based on Multi-Player Gaming Model in Cloud Environments

“…In the past few years, there have been plenty of studies exploiting market pricing mechanism for distributed resource allocation, and the well-known distributed systems [5,6,7,8,9,10]. Beside this systems, many economic-based policies and scheduling algorithms have also be widely studied, include Resource Auction [11,12], FirstPrice [13], FirstProfit [14], and Proportional-Share [15].…”