Automating computational placement in IoT environments: doctoral symposium.

The growth in the number of Internet of Things (IoT) devices and applications, and an increase in the capabilities of sensors creates an opportunity to optimise IoT applications by partitioning the computation across all components in the processing chain: sensors, field gateways and clouds. This can be done to optimise a range of factors including performance, energy and cost. This paper presents an overview of an optimiser designed to achieve this. It takes as input a high-level, declarative description of the computation, along with a set of non-functional requirements. From this it aims to generate the best deployment plan. The main use case, described in the paper is the use of wearable sensors for the real-time monitoring of the activity and glucose levels of type II diabetes patients. This paper describes the architecture of the optimiser, gives an example of an energy-based cost model, and shows how the approach applies to the diabetes use case.