Fault-tolerant application placement in heterogeneous cloud environments

The Internet of Things (IoT) has inspired a myriad of real-time applications, such as robotics and human-machine interaction. Many IoT applications have significant computational requirements, while at the same time they demand very low latencies. The cloud can provide the needed resources on-demand, however often fails to meet these timing requirements. Low response time can only be realized by having computational infrastructure in close vicinity. Therefore we investigate to what extent the cloud can be extended in the direct wireless surroundings of the IoT devices. This environment is highly heterogeneous as it comprises a wide variety of devices, connected using a plethora of technologies (both wired and wireless). A direct implication is that, compared to traditional cloud infrastructure, many of those nodes and links are likely to fail. We propose an application placement that can overcome failure-related challenges. We demonstrate that availability-awareness can increase the number of applications that can be hosted simultaneously by 132%. Furthermore we find that an additional increase of 54% can be realized through redundant provisioning of resources.