5G Network Traffic Prediction using Text and Image

5G Network Traffic Prediction using Text and Image

Syed Fuzail, Syed Azam Hussain , Asima Siddiqua , Zubiya Sadaf .

Department of Computer Science and Technology , Presidency University, Bengaluru

Under the Guidance of Mr. LAKSHMISHA SK

Department of Computer Science and Engineering, Presidency University, Bengaluru

Email: fuzailsyed29@gmail.com, zubiyasadaf1717@gmail.com, sidiquaasima15@gmail.com,

Syedazamhussain2003@gmail.com.

Abstract

The need for effective network traffic prediction has never been higher due to the explosive growth of digital communication and the introduction of 5G networks. Proactive decision-making, optimal resource allocation, latency reduction, and network congestion prevention are all made possible by network traffic prediction. The dynamic nature of contemporary networks is too much for traditional techniques like rule-based systems and statistical forecasting models, which frequently result in inefficient bandwidth usage and increased packet loss. Artificial Intelligence (AI) and Machine Learning (ML) have emerged as powerful tools for solving complex network management challenges. Of these, Long Short-Term Memory (LSTM) neural networks have shown exceptional efficacy in predicting future network conditions and analysing sequential data. Furthermore, anomaly detection tools like Isolation Forest offer crucial information for spotting odd trends that might