QoS Representation, Negotiation and Assurance in Cloud Services

Abstract

Cloud services are Internet-based IT services. Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and Software as a Service (SaaS) are three representative examples. As the cloud market becomes more open and competitive, Quality of Service (QoS) will be more important. However, cloud providers and cloud consumers have different and sometimes opposite preferences. If such a conflict occurs, a Service Level Agreement (SLA) cannot be established without negotiation.

To allow service consumers to express their QoS requirements, and negotiate them with service providers, we argue for cloud service negotiation. It aims to establish and enforce SLAs for cloud services. Specifically, we study how to measure, negotiate, and enforce QoS requirements for cloud services, and so formulate three research problems, i.e., QoS measurement, QoS negotiation, and QoS assurance. In terms of its scope, the topic covers business side automated negotiation and technical side resource allocation techniques. As a result, it has a potential impact on cloud service adoption.

To address QoS measurement, we initiate a quality model named CLOUDQUAL for cloud services. It is a model with quality dimensions and metrics that targets general cloud services. CLOUDQUAL contains six quality dimensions, i.e., usability, availability, reliability, responsiveness, security, and elasticity, of which usability is subjective, whereas the others are objective.

To address QoS negotiation, we present a mixed negotiation approach for cloud services, which is based on the “game of chicken”. In particular, if a party is uncertain about the strategy of its counterpart, it is best to mix concession and tradeoff strategies in negotiation. In fact, the mixed approach, which exhibits a certain degree of intelligence, can achieve a higher utility than a concession approach, while incurring fewer failures than a tradeoff approach.

To address QoS assurance, we propose a QoS-driven resource allocation method for cloud services. It can meet users’ QoS requirements while minimizing resources consumed. Especially, to honor a QoS specified in a SLA, we develop QoS assurance mechanisms, and determine the minimum resources that should be allocated. As a result, the method makes both technical and economic sense for cloud providers.