Economic models for resource management and scheduling in Grid computing

Abstract

SUMMARYThe accelerated development in peer-to-peer and Grid computing has positioned them as promising nextgeneration computing platforms. They enable the creation of virtual enterprises for sharing resources distributed across the world. However, resource management, application development and usage models in these environments is a complex undertaking. This is due to the geographic distribution of resources that are owned by different organizations or peers. The resource owners of each of these resources have different usage or access policies and cost models, and varying loads and availability. In order to address complex resource management issues, we have proposed a computational economy framework for resource allocation and for regulating supply and demand in Grid computing environments. This framework provides mechanisms for optimizing resource provider and consumer objective functions through trading and brokering services. In a real world market, there exist various economic models for setting the price of services based on supply-and-demand and their value to the user. They include commodity market, posted price, tender and auction models. In this paper, we discuss the use of these models for interaction between Grid components to decide resource service value, and the necessary infrastructure to realize each model. In addition to usual services offered by Grid computing systems, we need an infrastructure to support interaction protocols, allocation mechanisms, currency, secure banking and enforcement services. We briefly discuss existing technologies that provide some of these services and show their usage in developing the Nimrod-G grid resource broker. Furthermore, we demonstrate the effectiveness of some of the economic models in resource trading and scheduling using the Nimrod/G resource broker, with deadline and cost constrained scheduling for two different optimization strategies, on the World-Wide Grid testbed that has resources distributed across five continents.

Dynamic Pricing Scheme for Resource Allocation in Multi-Cloud Environment

“…There are still various issues and challenges that need to be addressed especially in the area of pricing model [3][4][5][6][7]. The fixed pricing schemes that currently used by the service providers are not able to adapt to the rapid changes between supply and demand in the market.…”

Agent-Based Grid Scheduling with Calana

“…Furthermore, stakeholders are not able to express complex preferences and adjust their strategies quickly, which is a strong prerequisite in order to establish a computational economy [10]. In real economies, these problems are solved by the established market structures [11].…”

“…During the transaction phase, the auctioneer uses the scoring rule to evaluate all bids and select the best. This makes the implementation of a software system for auctions easy [11]. There are many different auction types.…”

Scheduling Independent Tasks with QoS Requirements in Grid Computing with Time-Varying Resource Prices

“…As noted in [3], Globus [1], Legion [4], and few other RMS systems developed adopt the conventional style of RMS where a scheduling component allocates computing resources to tasks with the goal of optimizing a certain objective function, e.g., minimizing the makespan of tasks. Such an objective function is typically defined in a way that optimizing the function results in better system throughput and utilization.…”

“…In contrast to the conventional style is the computational economy style of RMS where users adopt the strategy of executing their tasks at low cost and resource providers pursue the strategy of maximizing their profits and resource utilization. In a Grid environment, a computational economy style of RMS has several advantages over a conventional one [3]. For example, in computational economy, users may be allowed to specify their resource requirements and preference parameters by a utility model.…”