A comprehensive survey of machine learning based mobile data traffic prediction models for 5G cellular networks

• Main Authors: Mohan, R. Raj, Vijayalakshmi, K., Augustine, P. John, Venkatesh, R., Nayagam, M. Gomathy, Jegajohi, B.
• Format: Conference Proceeding
• Language: English
• Subjects: 5G mobile communication; Artificial intelligence; Cellular communication; Communications traffic; Machine learning; Prediction models; Quality of service architectures; Traffic models; User experience; Wireless networks
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0177504

The advanced progression of mobile technology leads to a dramatic expansion in cellular data traffic (DT). Especially, the development of precise time series model in a 5G cellular network, becomes indispensable to increase the quality of services (QoS) and forecast cellular DT. The cellular DT predictive models allow the operator in adapting to the traffic demand of the networks with user experience and better resource usage. Furthermore, owing to the characteristics of the higher heterogeneities amongst a number of base stations with traffic load, the cellular DT predictive model becomes challenging. Thus, the study develops a detailed analysis of artificial intelligence (AI) based techniques to predict mobile DT. An extensive analysis of existing ML model has been presented for the cellular DT prediction in 5G network. Additionally, a wide-ranging description of the advancement of mobile networks is provided. Likewise, the present approaches are studied in different ways including underlying methodologies, merits, major objectives, performance measures, and inferences. Also, wide-ranging experimental analyses of the surveyed methods have been taking place for recognizing the exclusive features of all approaches. Lastly, an overview of future directions and challenging issues are extensively discussed.