AI-based modeling and data-driven evaluation for smart farming-oriented big data architecture using IoT with energy harvesting capabilities

Abstract

The use of Internet of Things (IoT) networks offers great advantages over wired networks, especially due to their simple installation, low maintenance costs, and automatic configuration. IoT facilitates the integration of sensing and communication for various industries, including smart farming and precision agriculture. For several years, many researchers have strived to find new sources of energy that are always “cleaner” and more environmentally friendly. Energy harvesting technology is one of the most promising environment-friendly solutions that extend the lifetime of these IoT devices. In this paper, the state-of-art of IoT energy harvesting capabilities and communication technologies in smart agriculture is presented. In addition, this work proposes a comprehensive architecture that includes big data technologies, IoT components, and knowledge-based systems for innovative farm architecture. The solution answers some of the biggest challenges the agriculture industry faces, especially when handling small files in a big data environment without impacting the computation performance. The solution is built on top of a pre-defined big data architecture that includes an abstraction layer of the data lake that handles data quality following a data migration strategy to ensure the data's insights. Furthermore, in this paper, we compared several machine learning algorithms to find the most suitable smart farming analytics tools in terms of forecasting and predictions.