Routing with Cooperative Nodes Using Improved Learning Approaches

Abstract

In IoT, routing among the cooperative nodes plays an incredible role in fulfilling the network requirements and enhancing system performance. The evaluation of optimal routing and related routing parameters over the deployed network environment is challenging. This research concentrates on modelling a memory-based routing model with Stacked Long Short Term Memory (s − LSTM) and Bi-directional Long Short Term Memory (b − LSTM). It is used to hold the routing information and random routing to attain superior performance. The proposed model is trained based on the searching and detection mechanisms to compute the packet delivery ratio (PDR), end-to-end (E2E) delay, throughput, etc. The anticipated s − LSTM and b − LSTM model intends to ensure Quality of Service (QoS) even in changing network topology. The performance of the proposed b − LSTM and s − LSTM is measured by comparing the significance of the model with various prevailing approaches. Sometimes, the performance is measured with Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) for measuring the error rate of the model. The prediction of error rate is made with Learning-based Stochastic Gradient Descent (L − SGD). This gradual gradient descent intends to predict the maximal or minimal error through successive iterations. The simulation is performed in a MATLAB 2020a environment, and the model performance is evaluated with diverse approaches. The anticipated model intends to give superior performance in contrast to prevailing approaches.