Optimization On Stream Transmission Subsystem Of HTTP Streaming Based Course Live Broadcast System

HTTP Streaming is the technology which cuts the media streaminginto fragments and puts them on web server, while clients download suchfragments through HTTP and play them sequentially. HTTP Streaming haslots of advantages, for example, based on the widely used HTTP, it isstable and reliable; it easily avoids NAT and firewall traversal issues; itenables the ability to utilize standard HTTP servers and HTTP caches.Such technology has been quite popular in the field of media streaming.This paper mainly focuses on fixing the shortages those appear whenHTTP Streaming is applied in the large-scale course live broadcast system.HTTP Cache Server plays a key role in increasing the scalability ofHTTP Streaming systems. However mainstream cache servers, such asNginx, Squid and Varnish, behave improperly when the cache file is beingupdated. When used in live HTTP Streaming systems, this behavior willcause the cache server to deliver many unnecessary requests to the originserver periodically so that the scalability of the system is constrained. Thispaper puts forward an optimized behavior of the cache server under cacheupdating period, which is that the cache server just deliver one request toorigin server and refuse all the other requests when the cache is beingupdated. The optimization strategy is implemented on Nginx. Theevaluation results show that the scalability of the system is significantlyenhanced with the optimization. In addition, this paper also has a basic teston some CDN service. The end-to-end delay of typical HTTP Streaming live broadcastsystem is between10s and15s and it is too large for the live coursebroadcast application which needs much interactivity. To optimize everypart that causes end-to-end delay, this paper comes up with a model of lowend-to-end delay HTTP Streaing course live broadcast system and finallythe end-to-end delay could be below5s.