Affiliation:
1. SASTRA University, India
Abstract
Rainfall prediction is a pivotal aspect of climate forecasting, influencing agriculture, water resource management, and disaster preparedness. This comprehensive review explores the integration of advanced algorithms and edge analytics within a fog computing framework to elevate the accuracy of rainfall predictions. The introduction outlines the significance of accurate rainfall predictions, the limitations of traditional methods, and the motivation for embracing fog computing, advanced algorithms, and edge analytics. A detailed examination of fog computing architecture underscores its decentralized nature and proximity to data sources, addressing challenges inherent in centralized models. The integration of edge analytics is discussed in depth, emphasizing its crucial role in preprocessing IMD data at the source. Insights gained from these implementations offer valuable perspectives on the practical implications, successes, and challenges associated with these methodologies.
Reference19 articles.
1. A Review of Fog Computing and Machine Learning: Concepts, Applications, Challenges, and Open Issues
2. A Review on Cloud, Fog, Roof, and Dew Computing
3. Bulla, C., & Birje, M. N. (2022). Anomaly detection in industrial IoT applications using deep learning approach. Artificial Intelligence in Industrial Applications: Approaches to Solve the Intrinsic Industrial Optimization Problems, 127-147.
4. Fernández, C. M., Rodríguez, M. D., & Muñoz, B. R. (2018, May). An edge computing architecture in the Internet of Things. In 2018 IEEE 21st international symposium on real-time distributed computing (ISORC) (pp. 99-102). IEEE.
5. Vehicular Cloud and Fog Computing Architecture, Applications, Services, and Challenges