About The Project

In the last few years, we have seen a tremendous leap in utilizing IoT-enabled devices as a key provider for smart-cities and farms. According to the recent statistics, there will be 41.6 billion connected IoT devices that will be generating 79.4 zettabytes of data in 2025 [1]. Amongst this figure, data-driven IoT Agritech-enabled (IoTAg) monitoring will replace the conventional farming techniques and will have a CAGR of 72.4%. This will congest the communication networks and will require more cloud-server capabilities to run the power-consuming machine-learning (ML) algorithms. In addition, IoT devices or Sensor Nodes (SNs) will require an additional cost for onboard sensors which can be eliminated by using ML techniques.

The aim of this project is to spotlight the capabilities of the low-performance edge SN controllers by using light-ML algorithms in order to reduce the expected congestion and capital expenditure of the IoT infrastructure, especially in the Agritech applications. In the context of smart-farming and water-management in Jordan, this will ensure that IoTAg is inclusive to reach not only the high-tech farming industry but also the small/medium-size poor farmers. To ensure the feasibility and efficiency of the proposed solutions, we will try to build a minimum viable product solution by doing a comparative in-lab study of the available microcontrollers in the market. This will build on the currently running projecs on smart farming to ensure that the deployed edge IoT solutions will utilize the very best low-performance microcontrollers that will add a minimal footprint on the communication networks latency and sensor's age of information.