PRACTICAL ANALYSIS OF CLOUD OFFLOADING STRATEGIES FOR HEAVY AI PROCESSING MOBILE GAMES

Modern mobile devices, such as smartphones and tablets, are offering a wide range of entertainment applications that require an increasing amount of computational and storage resources. To address such needs, developers transfer the load from the mobiles to remote resources, usually in a Cloud infrastructure. The focus of our work is to find policies for balancing the load between devices and remote resources using offloading techniques. We apply these techniques on a popular artificial intelligence intensive mobile game, OpenTTD and seek to reduce the server-side load by leveraging the devices computing capabilities.