閱讀全文 | |
篇名 |
Cluster-based Task Scheduling Using K-Means Clustering for Load Balancing in Cloud Datacenters
|
---|---|
並列篇名 | Cluster-based Task Scheduling Using K-Means Clustering for Load Balancing in Cloud Datacenters |
作者 | Geetha Muthusamy、Suganthe Ravi Chandran |
英文摘要 | Load balancing is a process of distributing incoming tasks to available resources in cloud datacenters, where a resource exists in terms of a virtual machine (VM). Proper load balancing results in minimizing the computation time and improving the resource utilization rate. Various scheduling algorithms are applied to achieve load balancing in cloud datacenters. Due to the heterogeneous nature of resources in the cloud, greedy approaches are used to schedule the tasks to the VMs. This paper suggests a cluster-based task scheduling framework (CBTS) using K-Means clustering by considering task length and VM capacity. Here, the tasks are clustered based on their length, and the VMs are grouped based on their processing capacity. After clustering, the individual task in each cluster is scheduled to appropriate VM in the VM groups.The proposed system performs dynamic load balancing with an aim in minimizing the makespan and execution time. The experimental results reveal that the proposed method produces better results in terms of execution time, makespan, and deviation in workload than the conventional Min-Min algorithm and the recently developed heuristic algorithms such as Online Potential Finish Time (OPFT), Dynamic Cloud Task Scheduling (DCTS), and Grouped Task Scheduling (GTS). |
起訖頁 | 121-130 |
關鍵詞 | Cloud computing、Scheduling,Lload balancing、Clustering、Virtualization |
刊名 | 網際網路技術學刊 |
期數 | 202101 (22:1期) |
出版單位 | 台灣學術網路管理委員會 |
DOI |
|
QR Code | |
該期刊 上一篇
| Multilevel Fault-Tolerance Aware Scheduling Technique in Cloud Environment |
該期刊 下一篇
| Personalized Fall Detection Monitoring System Based on Learning from the User Movements |