出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Cloud computing environments often have to deal with random-arrival computational workloads that vary
in resource requirements and demand high Quality of Service (QoS) obligations. It is typical that a ServiceLevel-Agreement
(SLA) is employed to govern the QoS obligations of the cloud computing service provider
to the client. A typical challenge service-providers face every day is maintaining a balance between the
limited resources available for computing and the high QoS requirements of varying random demands.
Any imbalance in managing these conflicting objectives may result in either dissatisfied clients and potentially
significant commercial penalties, or an over-resourced cloud computing environment that can be
significantly costly to acquire and operate. Thus, scheduling the clients’ workloads as they arrive at the
environment to ensure their timely execution has been a central issue in cloud computing. Various approaches
have been reported in the literature to address this problem: Shortest-Queue, Join-Idle-Queue,
Round Robin, MinMin, MaxMin, and Least Connection, to name a few. However, optimization strategies
of such approaches fail to capture QoS obligations and their associated commercial penalties. This paper
presents an approach for service-level driven load scheduling and balancing in multi-tier environments.
Joint scheduling and balancing operations are employed to distribute and schedule jobs among the resources,
such that the total waiting time of client jobs is minimized, and thus the potential of a penalty to
be incurred by the service provider is mitigated. A penalty model is used to quantify the penalty the service
provider incurs as a function of the jobs’ total waiting time. A Virtual-Queue abstraction is proposed to
facilitate optimal job scheduling at the tier level. This problem is NP-complete, thus, a genetic algorithm is
proposed as a tool for computing job schedules that minimize potential QoS penalties and hence minimize
the likelihood of dissatisfied clients.
