Optimized Jordan Neural Network and Bandwidth Aware Routing Protocol for Congestion Prediction and Avoidance in IOT for Effective Communication

Abstract

Development of 5G internet in today’s trend leads to the evaluation of many IOT devices. The information is transmitted by a network in IOT to store the data in the cloud. Due to the wide usage of IOT devices by people, congestion may occurs in IOT networks, which delays the information or sometimes resulting in data loss despite the implementation of congestion control methods. So many machine learning and congestion control protocols are used to predict and avoid congestion in IOT network. But these existing systems consist of drawbacks such as accuracy drop for prediction, packet loss and time delay. Hence, the Bandwidth Aware Routing Strategy (BARS) protocol using Jordan Neural Network (JNN) was developed to predict and avoid congestion in the network. Initially, the IOT nodes are deployed and the data are collected and preprocessed using a sigmoidal function and Extreme Learning machine to improve the quality of the original data. Then extract the features from the pre-processed data using Locality Preserving Projection (LPP). After that, Jordan Neural Network is used for congestion prediction and pine cone optimization is used to tune the hyper parameters such as learning rate and batch size which is utilized to improve the classifier performance. Then, BARS protocol is used to avoid the congestion present in the IOT network. According to the experimental approach, the proposed techniques achieves 95.45% of Accuracy, 95.71% of Precision, 95.39% of F1-Scorce and 95.02 of specificity. Thus, the congestion and avoidance of Information in the IOT network is processed in high efficiency by using this proposed approach.