2023/09/19 by Atta Rahman, Rahman, Atta Ur, Bibi Saqia +9
Computer Science · Engineering · #FOS: Electrical engineering #IoT and Edge/Fog Computing #Signal Processing (eess.SP) #Software-Defined Networks and 5G #Traffic Prediction and Management Techniques #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2309.10347
openalex publication_date 2023/09/19 · openalex created_date 2023/09/21 · openalex updated_date 2026/07/28
This study suggests a new strategy for improving congestion control by deploying Long Short-Term Memory (LSTM) networks. LSTMs are recurrent neural networks (RNN), that excel at capturing temporal relationships and patterns in data. IoT-specific data such as network traffic patterns, device interactions, and congestion occurrences are gathered and analyzed. The gathered data is used to create and train an LSTM network architecture specific to the IoT environment. Then, the LSTM model's predictive skills are incorporated into the congestion control methods. This work intends to optimize congestion management methods using LSTM networks, which results in increased user satisfaction and dependable IoT connectivity. Utilizing metrics like throughput, latency, packet loss, and user satisfaction, the success of the suggested strategy is evaluated. Evaluation of performance includes rigorous testing and comparison to conventional congestion control methods.