Multi Server Based Cloud-Assisted Real-time Transrating for Http Live Streaming

Background/Objective: The main objective of this work is to reduce the load balancing problems and problems like frozen play in the HTTP live streaming. Methods/Statistical Analysis: Cloud based http live streaming system used in the previous researches provides improved client satisfaction level but the main issue is the load balancing where the multiple clients' requests need to be processed in the single HLS server. The burden of HLS server would be increased in case of presence of multiple user requests. To overcome this problem multi server based HTTP live streaming approach is proposed. Findings: The multiple clients' requests would be handled by providing the appropriate services to them based on PSO approach which is used to calculate the weight function. An efficient particle swarm optimization is used for access the multimedia content from appropriate severs when client send the request to multiple servers. The multi-server concept can eliminate the high load variation problem by changing the load request based on user requirements dynamically. Applications/Improvements: Experimental results prove that the proposed methodology provides better result than the existing approach in terms bandwidth utilization and Peak signal-to-noise ratio.