Efficient cost-optimization frameworks for hybrid cloudlet placement over fiber-wireless networks

Over the past few decades, researchers studying mobile cloud computing have focused mainly on the energy savings of mobile devices by offloading computation and communication intensive jobs to remote clouds. However, the access delay between mobile users and the clouds usually is large and inappropriate for the low-latency applications. “Cloudlets” or “edge clouds” is a new technology that is capable of bridging this gap and has shown potential to enhance the performance of mobile devices significantly while meeting the stringent response time requirements of mobile users. In this paper, we propose a method to find the lower bound of integer programming based cost-optimization frameworks for hybrid cloudlet placement against different deployment scenarios. We apply commonly used techniques to solve convex optimization problems that resolve the scalability issues arising from integer-programming-based frameworks, thus providing a first-hand estimation of the cloudlet deployment cost against any deployment scenario. We verify that the results produced by this method can be considered as tight lower bounds to that produced by integer-programming-based frameworks for most practical scenarios. We further perform a parametric analysis to understand the dependence of cloudlet deployment cost on various network parameters.