No abstract

Abstract-Cloud computing is a solution for addressing challenges such as licensing, distribution, configuration, and operation of enterprise applications associated with the traditional IT infrastructure, software sales and deployment models. Migrating from a traditional model to the Cloud model reduces the maintenance complexity and cost for enterprise customers, and provides on-going revenue for Software as a Service (SaaS) providers. Clients and SaaS providers need to establish a Service Level Agreement (SLA) to define the Quality of Service (QoS). The main objectives of SaaS providers are to minimize cost and to improve Customer Satisfaction Level (CSL). In this paper, we propose customer driven SLA-based resource provisioning algorithms to minimize cost by minimizing resource and penalty cost and improve CSL by minimizing SLA violations. The proposed provisioning algorithms consider customer profiles and providers' quality parameters (e.g., response time) to handle dynamic customer requests and infrastructure level heterogeneity for enterprise systems. We also take into account customer-side parameters (such as the proportion of upgrade requests), and infrastructure-level parameters (such as the service initiation time) to compare algorithms. Simulation results show that our algorithms reduce the total cost up to 54 percent and the number of SLA violations up to 45 percent, compared with the previously proposed best algorithm.

No abstract

Service monitoring is required for meeting regulatory requirements and verifying compliance to Service Level Agreements (SLAs). As such, monitoring is an essential part of web service-based systems. However, service monitoring comes with a cost, including an impact on the quality of monitored services and systems. To deliver the best value to a service provider, it is important to balance meeting monitoring requirements and reducing monitoring impacts. We introduce a novel approach to configuring the web service monitors deployed in a system so that they provide an adequate level of monitoring but with minimized quality impacts, delivering the best value proposition in terms of monitoring benefits and costs. We use a prototype system to demonstrate that by optimizing a web service monitoring system, we can reduce the impact of a set of deployed web service monitors by up to two thirds.

Abstract-Service monitoring is an essential part of serviceoriented software systems and is required for meeting regulatory requirements, verifying compliance to service-level agreements, optimising system performance, and minimising the cost of hosting Web services. However, service monitoring comes with a cost, including a performance impact on the monitored services and systems. Therefore, it is important to deploy the right level of monitoring at the appropriate time and location in order to achieve the objectives of monitoring whilst minimising its impact on services and systems. Although there have been many efforts to create Web services monitoring techniques and frameworks, there has been limited work in quantifying the impact of Web service monitoring. In this paper, we report on experiments assessing the performance impact of service monitoring under typical system monitoring settings. The performance impact of monitoring method, monitor location, monitor processing capability, and monitoring mode are taken into consideration. Based on the experimental results, we advise on the most appropriate ways to deploy service monitoring.