The Internet of Things (IoT) is becoming a tangible reality, with a variety of sensors, devices and data centres interconnected to support scenarios such as Smart City with information about traffic, city administration, health-care services and entertainment. Decomposing these systems into smaller components, results in a variety of requirements for processing and communication resources for each subsystem. Wireless Vision Sensor Network (WVSN) is one of the subsystems, relying on visual sensors that produce several megabytes of data every second, unlike temperature or pressure sensors producing several bytes of data every hour. In addition, to facilitate the deployment of the nodes for different environments, we consider themas battery-operated devices. The high data rates from the imaging sensor have extensive computational and communication requirements, which in the meantime should meet the constraints regarding the energy efficiency of the device, to ensure a satisfactory battery lifetime.

In this thesis we analyse the energy efficiency of the smart camera, including the smart camera architecture, the distribution of the image processing tasks between several processing elements, and the inter-effects of processing and communication. Sensor selection and algorithmic implementation of the image processing tasks affects the processing energy consumption of the node, alongside to the hardware and software implementation of the tasks.

Furthermore, considerations of different intelligence partitioning configurations are included in the analysis of communication related elements, such as communication delays and channel utilisation. The inter-effects resulting from the variety of configurations in image processing allocation and communication technologies with different characteristics provide an insight into the overall variations of the smart camera node energy consumption. The aim of thesis is to facilitate the design of energy efficient smart cameras, while providing an understanding of energy consumption variations related to processing and communication configurations.

The technological shift towards the Internet of Everything has resulted in an ever-increasing interest in smart sensor nodes. The required deployment of these nodes in a variety of environments, powered by constrained energy sources such as energy harvester or conventional batteries, is reflected in the significant constraints in terms of energy consumption for the smart sensor node. Furthermore, the range of applications is expanding and the processing complexity is subsequently growing, resulting in high data volume and energy constrained IoT nodes. The aim of this thesis is to address the energy efficiency of these smart sensor nodes and enhance their design process, which would inherently shorten their time-to-market.

One of the key contributions of this work is the integration of the processing and communication perspectives in a design space exploration method for data intensive smart sensor nodes. This method relies on inputs that are high level estimates of the number of operations and intermediate data volume, and utilises the conflicting nature of the processing and communication as defining components of the energy consumption optimisation. One aspect covered by this method is processing exploration, where we identify areas of the design in which optimisation efforts would have a major impact on the overall node energy consumption. Another aspect is energy budgeting, where based on a set of predefined constraints, we can interpolate the processing energy available for the implementation of the additional processing tasks.

This work considers the sensor node as part of the IoT environment relying not only on in-node processing, but also on fog and cloud computing. The trade-off in processing and communication energy consumption facilitates evidencing the optimal partition point for a given application and the subsequent node offloading. Considerations of node energy consumption, communication latency, and channel utilisation define the distribution of the computational load between the processing entities. To sum up, the methods presented in this thesis dissociates from IoT node optimisation related to a specific scenario, providing a generic design space exploration method that can be applied to any given data intensive IoT node. The aim of this work is to be the starting point for the design of robust tools for design space exploration in smart sensor nodes for IoT applications.