虚拟实验室资源网格多任务调度

Multi-task scheduling for virtual laboratory resource grid

针对虚拟实验室的资源调度问题,提出了一种基于服务质量的网格算法.建立了虚拟实验室资源的网格模型,讨论了其特点;分析了虚拟实验室网格的服务质量体系,从可靠性、响应性、成本等6个方面对实验室服务质量进行量化评估,将用户的多任务调度问题描述为服务质量约束下的多任务协同寻优模型,以满足用户服务质量最大化为目标进行求解,并给出了基于遗传算子的求解算法;通过案例分析对本方案的可行性进行了验证和讨论,结果表明本方案有助于提高虚拟实验室资源利用率和服务水平.

For the resource scheduling problem of virtual laboratory resource grid, a grid algorithm based on quality of service （QoS） was proposed. First a grid model of virtual laboratory resources was established, and its characteristics were discussed. Then the quality of service system of virtual laboratory grid was analyzed, whose QoS was quantitatively evaluated from six aspects including reliability, responsiveness, cost and so on. Therefore its resource scheduling problem was described as a multi-task coordinative optimizing model constrained by QoS, whose objective was to maximize the QoS requirements of user and was solved by a genetic-based algorithm. Finally, a case study was given to validate and discuss the feasibility of the model. The results show that the proposed model is helpful to improve the resource utilization and service level of virtual laboratory.