Load splitting in clusters of video servers

Nowadays, video on demand is one of the services more highly appreciated and demanded by customers. As the number of users increases, the capacity of the system that provides these services must also be increased to guarantee the required quality of service. An approach to that end is to have available several videoservers at various distribution points in order to satisfy the different incoming demands (videoservercluster). When a movie demand arrives to such a cluster, a load balancing device must assign the request to a specific server according to a procedure that must be fast, easy to implement and scalable. In this article we consider the problem of appropriately splitting this load to improve on the system performance. After an analysis of the video packet generation, we point out the similarity between this problem and that of optimally routing packets in data networks. With this similarity in mind, a new mechanism to select the appropriate videoserver is proposed. The purpose of this mechanism is to minimize the average packet transfer time (waiting time plus transmission time) at the videoservercluster. In this way, we are able to obtain a dynamic load balancing policy that performs satisfactorily and that is very easy to implement in practice. The results of several experiments run with real data are shown and commented to substantiate our claims. A description of a practical implementation of the system is also included.Peer Reviewe