Complexity of cloud-based transcoding platform for scalable and effective video streaming services

Nowadays, a fast network improves the quality of our daily life and we can enjoy a variety of services over the Internet. Different types of media streaming services have been proposed and utilized as the network speed is now sufficiently fast to deliver high-quality live streaming. Usually, different media streaming services deliver streaming data by using different protocols such as the real-time message protocol (RTMP), real-time streaming protocol (RTSP), and Windows media HTTP streaming protocol (WMSP). In this paper, we propose and implement a cloud-based scalable and cost-effective video streaming transcoding service platform to provide the service of changing real-time streaming protocols (RTMP/RTSP) and codecs (H.263/H.264). A transcoder dispatching problem (TDP) over the cloud platform is also defined, which attempts to serve all the transcoding requests by minimizing the cost of virtual machines. Further, a transcoder dispatching algorithm and an online transcoder dispatching algorithm are proposed for the TDP. These algorithms are implemented on the Amazon EC2 platform. Experimental results demonstrate that by renting different levels of virtual machines dynamically and intelligently, we can provide a scalable and cost-effective transcoding service for bridging heterogeneous streaming media.     

A novel resource allocation mechanism for live cloud-based video streaming service

With the recent emergence of cloud computing, growing numbers of clients are using online cloud services through the Internet such as video streaming service. The rent costs of cloud service providers increase when the resource utilizations of the cloud-servers are not well. Therefore, resource allocation is a crucial problem for cloud data centers. The resource allocation problem is an NP-hard problem. This paper proposes a novel cloud resource allocation mechanism based on a winning strategy for a Nim game. This mechanism offers all clients an effective number of running cloud servers, and allocates cloud resources rapidly and effectively by using a pre-pairing approach. The proposed mechanism does not require searching for remaining resources of the running cloud server; hence, it can reduce the time taken to arrange resources. The experimental results show that the proposed mechanism can improve utilization of cloud servers and reduce the rent costs of the cloud service providers. The proposed mechanism can reach the utilization of cloud servers by as much as 99.96 %. The proposed mechanism is approximately 9 % more efficient than the market-based grid resource allocation algorithm, and 19 % more efficient than the modified best fit decreasing algorithm.