Energy-aware offloading in mobile cloud systems with delay considerations

摘要

In Mobile Cloud Computing where computing power and data storage are moving away from mobile devices to remote computing resources, traffic computational offloading has been proposed as a key enabling technology to provide improved computational performance and maximize the battery lifetime of end devices. However, traffic offloading can only be adopted, if strict latency constraints imposed by the mobile cloud services are satisfied. To achieve this, significant amounts of computational and network resources need to be allocated, leading to increased operational and capital expenditures for the physical infrastructure providers. To address this issue, a multi-objective service provisioning scheme is proposed that tries to optimize the performance of both the network and computation infrastructure and the battery lifetime of the mobile devices under worst case delay conditions using network calculus theory.