当前位置: X-MOL 学术J. Grid Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Scheduling Algorithms for Heterogeneous Cloud Environment: Main Resource Load Balancing Algorithm and Time Balancing Algorithm
Journal of Grid Computing ( IF 5.5 ) Pub Date : 2019-11-19 , DOI: 10.1007/s10723-019-09499-7
Weiwei Lin , Gaofeng Peng , Xinran Bian , Siyao Xu , Victor Chang , Yin Li

Cloud computing and Internet of Things (IoT) are two of the most important technologies that have significantly changed human’s life. However, with the growing prevalence of Cloud-IoT paradigm, the load imbalance and higher SLA lead to more resource wastage and energy consumption. Although there are many researches that study Cloud-IoT from the perspective of offloading side, few of them have focused on how the offloaded workload are dealt with in Cloud. This paper proposes two IoT-aware multi-resource task scheduling algorithms for heterogeneous cloud environment namely main resource load balancing and time balancing. The algorithms aim to obtain better result of load balance, Service-Level Agreement (SLA) and IoT task response time and meanwhile to reduce the energy consumption as much as possible. They both are devised to assign single task to a properly selected Virtual Machine (VM) each time. The task placed in a pre-processed queue is assigned sequentially each time. And the VM selection rule is carried out based on the newly inventive ideas called relative load or relative time cost. Besides, two customized parameters that influence the result of pre-process tasks are provided for users or administrators to flexibly control the behavior of the algorithms. According to the experiments, the main resource load balancing performs well in terms of SLA and load balance, while time balancing is good at saving time and energy. Besides, both of them perform well in IoT task response time.

中文翻译:

异构云环境的调度算法:主资源负载均衡算法和时间均衡算法

云计算和物联网(IoT)是已显着改变人类生活的两项最重要的技术。但是,随着Cloud-IoT范式的普及,负载不平衡和更高的SLA导致更多的资源浪费和能源消耗。尽管有许多研究是从卸载方面来研究Cloud-IoT的,但很少有研究专注于如何在Cloud中处理卸载的工作负载。本文针对异构云环境提出了两种基于物联网的多资源任务调度算法,即主资源负载均衡和时间均衡。该算法旨在获得更好的负载平衡,服务水平协议(SLA)和IoT任务响应时间的结果,同时尽可能降低能耗。它们都被设计为每次将单个任务分配给正确选择的虚拟机(VM)。每次都按顺序分配放置在预处理队列中的任务。并且,VM选择规则是基于称为相对负载或相对时间成本的新发明思想来执行的。此外,还为用户或管理员提供了两个影响预处理任务结果的自定义参数,以灵活地控制算法的行为。根据实验,主要资源负载均衡在SLA和负载均衡方面表现良好,而时间均衡则可以节省时间和能源。此外,它们在物联网任务响应时间上均表现良好。并且,VM选择规则是基于称为相对负载或相对时间成本的新发明思想来执行的。此外,还为用户或管理员提供了两个影响预处理任务结果的自定义参数,以灵活地控制算法的行为。根据实验,主要资源负载均衡在SLA和负载均衡方面表现良好,而时间均衡则可以节省时间和能源。此外,它们在物联网任务响应时间上均表现良好。并且,VM选择规则是基于称为相对负载或相对时间成本的新发明思想来执行的。此外,还为用户或管理员提供了两个影响预处理任务结果的自定义参数,以灵活地控制算法的行为。根据实验,主要资源负载均衡在SLA和负载均衡方面表现良好,而时间均衡则可以节省时间和能源。此外,它们在物联网任务响应时间上均表现良好。主要资源负载平衡在SLA和负载平衡方面表现良好,而时间平衡则可以节省时间和能源。此外,它们在物联网任务响应时间上均表现良好。主要资源负载平衡在SLA和负载平衡方面表现良好,而时间平衡则可以节省时间和能源。此外,它们在物联网任务响应时间上均表现良好。
更新日期:2019-11-19
down
wechat
bug