Brokering of risk‐aware service level agreements in grids

Abstract

Service level agreements (SLAs) are facilitators for widening the commercial uptake of Grid technology. They provide explicit statements of expectation and obligation between service consumers and providers. However, without the ability to assess the probability that an SLA might fail, commercial uptake will be restricted, since neither party will be willing to agree. Therefore, risk assessment mechanisms are critical to increase confidence in Grid technology usage within the commercial sector. This paper presents an SLA brokering mechanism with risk assessment support, which evaluates the probability of SLA failure. WS-Agreement and risk metrics are used to facilitate SLA creation between service consumers and providers within a typical Grid resource usage scenario. An evaluation is conducted to examine risk models, the performance of the broker's implementation as well as a comparison of its capabilities against similar SLA-based solutions from the literature. BROKERING OF RISK-AWARE SLAS IN GRIDS 1559with such a provider. It is necessary to incorporate provider reliability into this risk assessment process, in order to verify the expected integrity of a provider's guarantees when they make any SLA offer. Consequently, the broker role can determine the reputation and trustworthiness of a provider.Clearly, these concepts on their own will not remove the caution displayed by providers and end-users when agreeing to SLAs for Grid-based computing services. From the perspective of the provider, such SLAs represent commitments to meet the objectives specified therein and to pay penalties if their services fail to deliver that agreed upon. Without a means of formally evaluating the probability and expected impact of such negative events, a provider faces serious difficulties and potential risk in deciding upon which SLA requests to accept. Such provider risk assessment techniques have already been the focus of previous research to enable a provider to identify infrastructure bottlenecks and mitigate potential risk, in some cases by identifying fault tolerance (FT) mechanisms to prevent SLA violations [4][5][6].Allied to a provider's desire to assess risk is an end-user's wish to know the probability of an SLA violation in order to accurately compare providers' SLA quotes. Without such knowledge end-users cannot make appropriate decisions in relation to acceptable costs and penalty fees, since these may also have a consequential impact.Therefore, the main contributions of this work are the following. First, a broker architecture which focuses on the management of risk-aware SLAs in Grids is proposed. Second, a framework to evaluate the risk involved in mapping an SLA for single tasks and workflows based on the provider's own risk assessment, therefore evaluating its reliability, is developed. The implementation of a software component-a confidence service, designed to perform independent risk assessments and provider evaluations is detailed. The impartiality of these assessments and evaluations provides the end-user wi...

A Risk Assessment Framework for Cloud Computing

“…Therefore, the SP, before sending an SLA request, assesses the risk of dealing with all known IPs (see Figure 1, stage 1). Such provider assessment builds on the research in [6] which addresses the problem of dealing with missing provider information to produce a ranking of the providers based on specified criteria. The assessment of an IP by an SP is based on seven criteria, which are based on information collected from Cloud providers willing to share this information with the general public, or proposed guidelines by the National Institute for Standards and Technology (NIST) [9] and the European Network and Information Security Agency (ENISA) [10].…”

“…Finally, a preference value for provider A relative to provider B is computed, and if P (A > B) > 0.5 then provider A is preferred. Details on the risk assessment model are found in [1], [12], [6].…”

“…3) General Security Practice: Facility Security Level. Details on the risk assessment model are found in [1], [12], [6].…”

“…Risk assessment has been introduced into utility computing such as Grids and clouds either as a general methodology [2], [3], [4] or focusing on a specific type of risk, such as security and SLA fulfilment [5], [6]. However, the aim of this paper is to propose a risk assessment framework for cloud service provision, in terms of assessing and improving the reliability and productivity of fulfilling an SLA in a cloud environment.…”

Cloudy with a Chance of Load Spikes: Admission Control with Fuzzy Risk Assessments

“…Nevertheless, they assume that users provide information regarding the degree of overbooking that their applications may tolerate as well as their time periods, which may be known by the users in a cluster environments but is not available for cloud infrastructures. There are also examples of risk evaluation and SLA management applied to Grids, such as the one presented by Djemame et al in [23]. A more recent study focusing on clouds analyze the risks of overbooking resources and proposes a threshold-based overbooking scheme [24].…”