ABSTRACT
Video service providers (VSPs) can now take advantage of cloud computing to manage their video application infrastructure efficiently and cheaply. Virtual machines (VM) are rented from different clouds that are close geographically to the requester to use this method. Cost-effectiveness for VSPs depends on optimising the set of possible VMs decided to rent from public cloud in various locations over a given period due to the unpredictability of user requests and the time- and location-dependent pricing of VMs. The rented VMs must also be designed to ensure a high quality of experience (QoE) for the end user. In order to solve this issue, we can use a method called Interactive Request Redirection and Resource Provisioning (D3RP). To address this issue, we propose framing it as a conceptual optimization model and developing an optimization algorithm template that can be executed in an online environment. The theoretical investigation shows that the online algorithm provides a solution that is superior to the optimal solution obtained by using offline computing.
