Learning Deployment Trade-offs for Self-Optimization of Internet of Things Applications

The Internet of Things (IoT) is the next big wave in computing characterized by large scale open ended heterogeneous network of things, with varying sensing, actuating, computing and communication capabilities. Compared to the traditional field of autonomic computing, the IoT is characterized by an open ended and highly dynamic ecosystem with variable workload and resource availability. These characteristics make it difficult to implement self-awareness capabilities for IoT to manage and optimize itself. In this work, we introduce a methodology to explore and learn the trade-offs of different deployment configurations to autonomously optimize the QoS and other quality attributes of IoT applications. Our experiments demonstrate that our proposed methodology can automate the efficient deployment of IoT applications in the presence of multiple optimization objectives and variable operational circumstances.