Development of Fused Recurrent Neural Network‐Gated Recurrent Unit with Improved Sandpiper Optimization‐based Intelligent Node Localization Framework in WSN

• Published in: International journal of communication systems Vol. 37; no. 13
• Main Authors: Raghuvanshi, Akash, Kumar, Awadhesh, Chandra, Nilesh
• Format: Journal Article
• Language: English
• Published: Chichester Wiley Subscription Services, Inc 10.09.2024
• Subjects: Algorithms; Average LE; Deep learning; Energy requirements; Gated Recurrent Unit; Global positioning systems; GPS; Localization; Machine learning; Modified Exploration‐based Sandpiper Optimization Algorithm; Neural networks; Node Localization; Nodes; Optimization; Packets (communication); Recurrent Neural Network; Recurrent neural networks; Wireless Sensor Networks
• ISSN: 1074-5351; 1099-1131
• DOI: 10.1002/dac.5826

Summary Employing mobile nodes or Sensor Nodes (SN) in the Wireless Sensor Networks (WSNs) is a critical task within the coverage area. However, these techniques produce huge errors in the evaluated distance between source nodes and unknown nodes, which increases the average NL error of the unknown node. The usage of a Global Positioning System (GPS) for all the SNs needs high cost for implementation in large‐scale WSNs. The designing of NL in WSN with less energy requirements and less cost is very significant. Enhanced NL is performed with deep learning techniques together with the heuristic strategy for performance enhancement. The developed localization model is mainly utilized for providing fast, scalable, and easily implementable results over heterogeneous and homogeneous networks. Moreover, it is applicable for sparse and dense deployment of nodes. Here, a hybridized deep structured approach is employed by integrating the Recurrent Neural Network (RNN) with a Gated Recurrent Unit (GRU) for calculating the distance among the source nodes to facilitate determining the optimal location for the unidentified node by analyzing the node information present in the received packets. Here, the optimization of constraints executed in the deep learning techniques with the Modified Exploration‐based Sandpiper Optimization Algorithm (ME‐SOA), and also it is utilized to find the optimal location of unknown nodes based on computed distance from the received packets that minimize the average localization error. The experimental results are validated and show the effectiveness of the proposed algorithm with a reduced error rate than other algorithms. In the WSN network, the total communication area is divided into more regions to reduce the LE, and the location of the unknown node is determined by using the known location of the source node whenever transmitting data packets between the two source node. Several set of SN is deployed in the 2‐dimensional area of the WSN network, where the set of SN are represented as SO=SO1SO2SO3…SOP. Moreover, initialize the source node and the unknown nodes in a particular area, where the set of k source nodes are assumed as AH=AH1AH2AH3…AHk and the set of P−k unknown nodes are considered as X=Xk+1Xk+2Xk+3…XP, where the exact location of t via the statistics by transmitting the information from the anchor node to the unknown node. Here, the sensor node is assumed as SO=AH∪XP. Initially, the source node AHg in the WSN is positioned at a known location that is represented by the dimension of ugvg, where the term g is taken as g=1,2,3,…,k. Main aim of this NL algorithm is to estimate the unknown position of the unknown node. The direction of the unknown node is indicated by the term uqvq, where the term q=k+1,k+2,k+3,…,P. Minimum number of hops between the nodes u and v is indicated by the term HPu,v. The distance computation among the nodes u and v is indicated by the term DTu,v, the estimated distance between the nodes u and v is denoted by the term DTu,vEMT and the actual distance among the nodes u and v is represented by the term DTu,vTR. In the WSN, the SN chooses the one hop away, and then the node u can transmit the data directly to the node v because there is no error in the finally evaluated distance. The error increases when the number of hops in between the SN increases. In this research work, the node positioning in unknown node is obtained by leveraging the known position as well as the distance of the source node.