With the prevalence of personal computer devices and the Internet, a multimedia server has to perform videotranscoding to serve users under heterogeneous network environments. In this paper, we propose a stability-dr...
详细信息
ISBN:
(纸本)9781467372206
With the prevalence of personal computer devices and the Internet, a multimedia server has to perform videotranscoding to serve users under heterogeneous network environments. In this paper, we propose a stability-driven hierarchical scheduling algorithm for the cloud-basedvideo streaming system to speed up the videotranscoding process for real-time service applications. The Multi-layer Division of the Max-MCT scheduling algorithm (MDMCT) has been developed to reduce the convoy effect. It helps to coordinate the system operations and dynamically adjust the number of slots so that the cloud cluster-s can finish the process more efficiently. Experimental result-s show that the proposed scheduling control method helps to maintain good system load balancing. The resources utilization of the entire cloud clusters can be maintained at about 98%, and the processing time can be reduced by about 13.4%.
With the prevalence of personal computer devices and the Internet, a multimedia server has to perform videotranscoding to serve users under heterogeneous network environments. In this paper, we propose a stability-dr...
详细信息
ISBN:
(纸本)9781467372220
With the prevalence of personal computer devices and the Internet, a multimedia server has to perform videotranscoding to serve users under heterogeneous network environments. In this paper, we propose a stability-driven hierarchical scheduling algorithm for the cloud-basedvideo streaming system to speed up the videotranscoding process for real-time service applications. The Multi-layer Division of the Max-MCT scheduling algorithm (MDMCT) has been developed to reduce the convoy effect. It helps to coordinate the system operations and dynamically adjust the number of slots so that the cloud cluster-s can finish the process more efficiently. Experimental result-s show that the proposed scheduling control method helps to maintain good system load balancing. The resources utilization of the entire cloud clusters can be maintained at about 98%, and the processing time can be reduced by about 13.4%.
暂无评论