A Prediction Model Based Energy Efficient Data Collection for Wireless Sensor Networks

Abstract

Many real-time applications make use of advanced wireless sensor networks (WSNs). Because of the limited memory, power limits, narrow communication bandwidth, and low processing units of wireless sensor nodes (SNs), WSNs suffer severe resource constraints. Data prediction algorithms in WSNs have become crucial for reducing redundant data transmission and extending the network's longevity. Redundancy can be decreased using proper machine learning (ML) techniques while the data aggregation process operates. Researchers persist in searching for effective modelling strategies and algorithms to help generate efficient and acceptable data aggregation methodologies from preexisting WSN models. This work proposes an energy-efficient Adaptive Seagull Optimization Algorithm (ASOA) protocol for selecting the best cluster head (CH). An extreme learning machine (ELM) is employed to select the data corresponding to each node as a way to generate a tree to cluster sensor data. The Dual Graph Convolutional Network (DGCN) is an analytical method that predicts future trends using time series data. Data clustering and aggregation are employed for each cluster head to efficiently perform sample data prediction across WSNs, primarily to minimize the processing overhead caused by the prediction algorithm. Simulation findings suggest that the presented method is practical and efficient regarding reliability, data reduction, and power usage. The results demonstrate that the suggested data collection approach surpasses the existing Least Mean Square (LMS), Periodic Data Prediction Algorithm (P-PDA), and Combined Data Prediction Model (CDPM) methods significantly. The proposed DGCN method has a transmission suppression rate of 92.68%, a difference of 22.33%, 16.69%, and 12.54% compared to the current methods (i.e., LMS, P-PDA, and CDPM).