Maximizing revenue in Grid markets using an economically enhanced resource manager

Abstract

Traditional resource management has had as its main objective the optimization of throughput, based on parameters such as CPU, memory, and network bandwidth. With the appearance of Grid markets, new variables that determine economic expenditure, benefit and opportunity must be taken into account.\ud The Self-organizing ICT Resource Management (SORMA) project aims at allowing resource owners and consumers to exploit market mechanisms to sell and buy resources across the Grid. SORMA’s motivation is to achieve efficient resource utilization by maximizing revenue for resource providers and minimizing\ud the cost of resource consumption within a market environment. An overriding factor in Grid markets is the need to ensure that the desired quality of service levels meet the expectations of market participants.\ud This paper explains the proposed use of an economically enhanced resource manager (EERM) for resource provisioning based on economic models. In particular, this paper describes techniques used by the EERM\ud to support revenue maximization across multiple service level agreements and provides an application scenario to demonstrate its usefulness and effectiveness.Peer ReviewedPostprint (published version

The ISQoS Grid Broker for Temporal and Budget Guarantees

“…In more recent years work such upon the SORMA project has created the Economically Enhanced Resource Manager (EERM) [24,26]. This includes various features such as: demand forecasting, dynamic pricing, SLA formation and the ability to selectively violate less interesting SLAs [24].…”

Rule-based SLA management for revenue maximisation in Cloud Computing Markets

“…When the provider is not able to fulfil all the SLAs that has agreed, the EERM can perform a selective violation of some SLAs for minimising the economic impact of the penalties [2]. The set of SLAs to violate is chosen according to the next process: the future profit of the provider is estimated for each possible SLA violation in the system, by adding all the revenues and penalties of all the SLAs.…”

“…This paper defends the idea that revenue can be maximized by establishing a bidirectional data flow between market and resource layers: market brokers can perform negotiations that are more profitable if they use resource-level data, and the resource manager can help maximising the revenue if it manages the SLAs by considering this BLO. This bidirectional data flow is performed by an intermediate entity, called Economically Enhanced Resource Manager (EERM) [2].…”

SLA‐Based Resource Management and Allocation

“…Macias et al [28] performed some experiments that demonstrated the economic benefit of taking into account penalties and rewards in system overloading scenarios: if not all the SLAs can be agreed to, it is possible to combine selective SLA violations and task reallocations to minimize the economic loss. Figure 12.4 shows that using selective SLA fulfillment will allow providers have up to 60% of higher economic revenue when the resource pool is heavily overloaded: in a farm of 75 resources, if part of the resource pool crashes, a portion of the previously accepted SLAs will be violated.…”