A New IoT-Based Platform for Greenhouse Crop Production

This article proposes a cloud solution to build an Internet of Things (IoT) platform applied in a greenhouse crop production context. Real-time and historical data, as well as prediction models, can be accessed by means of representational state transfer (RESTful) Web services developed for such a purpose. Forecasting is also provided following a Greenhouse Models as a Service (GMaaS) approach. Currently, our GMaaS tool provides forecasting based on computational models developed for inside climate, crop production, and irrigation processes. Traditionally, such models are hardcoded in applications or embedded in software tools to be used as decision support systems (DSSs). However, using a GMaaS approach, models are available as RESTful services to be used as needed. In addition, the proposed platform allows users to register new IoT devices and their greenhouse data in the FIWARE platform, providing a cloud-scale solution for the case study. RESTful services of the proposed platform are also used by a Web application, allowing users to interact easily with the system.

I. Introduction

In the last years, the European Union is boosting the digitalization process in different areas, introducing topics, such as the Internet of Things (IoT), big data, or artificial intelligence in many different contexts (e.g., agriculture, smart cities, smart agrifood, and so on). One example is the IoF2020 project, which introduces and enhances digitalization in several sectors, such as agriculture, livestock, and food in Europe with the aim of significantly improving productivity and sustainability of the system. Within this project, the user case 4.2 deals with the digitalization of the protected agriculture based on the integration and the use of the data generated by physical and virtual sensors, control loops, networks, models, and optimization techniques. FIWARE is another example of the firm commitment of the European Union in the digitalization process.