Towards intelligent and scalable routing in cloud-based smart agriculture: a hybrid deep learning approach in big data era
Year: 2026
Type: article
Abstract: Smart agriculture increasingly relies on cloud computing, IoT, and big data analytics to support real-time decision-making and efficient resource management. As data volume and computational demands grow, intelligent routing and resource allocation become critical challenges in cloud-based agricultural systems. This study proposes a hybrid routing framework for cloud-based smart agriculture that combines AlexNet deep learning with Ant Colony Optimization (ACO) for intelligent routing and resource allocation. AlexNet is used to analyze traffic patterns and predict resource demands, while ACO identifies efficient routing paths based on these predictions. The proposed model was evaluated using the Danmini Doorbell dataset, which contains 90,000 network traffic records and 115 features. Experimental results demonstrate that the proposed approach achieves lower delay, reduced energy consumption, and faster convergence than ACO, GA, and PSO under varying task loads and network sizes. Furthermore, a Friedman statistical test confirmed that the performance differences among the compared algorithms were statistically significant ( p = 0.003). The results indicate that integrating deep learning with nature-inspired optimization provides an effective, scalable, and statistically validated solution for routing and resource management in cloud-based smart agriculture environments.
Source: Journal Of Big Data
Authors: Lina Song, Habibeh Nazif
Institutions: Heze University, Payame Noor University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,290
OpenAlex ID: W7214078686