Machine learning application in software-defined networking based agricultural Internet of Things: a systematic literature review

Machine learning application in software-defined networking based agricultural Internet of Things: a systematic literature review

연구 분야: Networking

학회: Cluster Computing

As a cornerstone of human civilization, agriculture has continuously evolved to meet the growing demands for food, fiber, and fuel. In recent years, technological advances have revolutionized traditional farming practices, leading to the emergence of smart farming. Smart farming integrates cutting-edge technologies such as the Internet of Things (IoT), Software-Defined Networking (SDN), and Machine Learning (ML) into agricultural operations. IoT collects real-time data from farm sensors, monitoring factors such as soil conditions, livestock health, and machinery performance while enabling remote control of operations. SDN ensures efficient, scalable communication by dynamically managing network resources and facilitating seamless data transmission. ML analyzes these data to uncover patterns, predict trends, and optimize farming decisions, improving productivity and sustainability. These technologies enable farmers to make data-driven decisions, improve productivity, minimize resource wastage, and ensure sustainable agricultural practices for a rapidly growing global population. This paper is a systematic literature review (SLR) that delves into a comprehensive exploration of the intersection between ML and SDN methodologies within smart farming. In addition, it investigates the pivotal role of ML and SDN in addressing key issues about irrigation systems, monitoring techniques, crop quality improvement, and security measures. Putting emphasis on both the challenges and potential perspectives of smart agricultural systems based on ML and SDN, this study provides a springboard for researchers to dive deeper into this burgeoning field.