Smart farming IoT platform based on edge and cloud computing

Abstract

Precision Agriculture (PA), as the integration of information, communication and control technologies in agriculture, is growing day by day. The Internet of Things (IoT) and cloud computing paradigms offer advances to enhance PA connectivity. Nevertheless, their usage in this field is usually limited to specific scenarios of high cost, and they are not adapted to semi-arid conditions, or do not cover all PA management in an efficient way. For this reason, we propose a flexible platform able to cope with soilless culture needs in full recirculation greenhouses using moderately saline water. It is based on exchangeable low-cost hardware and supported by a three-tier open source software platform at local, edge and cloud planes. At the local plane, Cyber-Physical Systems (CPS) interact with crop devices to gather data and perform real-time atomic control actions. The edge plane of the platform is in charge of monitoring and managing main PA tasks near the access network to increase system reliability against network access failures. Finally, the cloud platform collects current and past records and hosts data analytics modules in a FIWARE deployment. IoT protocols like Message Queue Telemetry Transport (MQTT) or Constrained Application Protocol (CoAP) are used to communicate with CPS, while Next Generation Service Interface (NGSI) is employed for southbound and northbound access to the cloud. The system has been completely instantiated in a real prototype in frames of the EU DrainUse project, allowing the control of a real hydroponic closed system through managing software for final farmers connected to the platform.