Title: Virtual MIMO-based cross-layer: optimisation strategy for routing in WSN
Authors: Monali R. Prajapati; Jay M. Joshi; Maulin M. Joshi; Upena Devang Dalal
Addresses: Department of Electronics & Communication, Government Polytechnic Gandhinagar, Ahmedabad, Gujarat, India ' Department of Electronics & Communication, Government Engineering Collage Bharuch, Bharuch, Gujarat, India ' Department of Electronics & Communication, Sarvajanik College of Engineering and Technology (SCET), Surat, Gujarat, India ' Department of Electronics Engineering, Sardar Vallabhbhai National Institute of Technology, Dumas Road (Gaurav path), Surat, India
Abstract: Wireless Sensor Networks (WSNs) consist of numerous sensor nodes connected through wireless medium. Virtual Multiple-Input Multiple-Output (V-MIMO) provides reliable communication over long distances. Since, V-MIMO ensures reliable communication across intermediate nodes becomes challenging and causes interference during transmission. To address this issue, a new Cluster-Based Multi-hop V-MIMO protocol is suggested, which significantly enhances communication performance. In this study, the Convolutional Neural Network (CNN) model is utilised for energy prediction, while considering type and location of nodes. Subsequently, K-Means algorithm is used for clustering the nodes within the network. Then, Cluster Heads (CHs) are chosen using a hybrid Coati Assisted Osprey Optimisation (CAOsO) algorithm while considering constraints like node energy, QoS, modified trust evaluation and risk. Then, the CAOsO is employed for optimal routing and also to optimise BER in the data transmission phase. In comparison with traditional algorithms, the CAOsO shows faster convergence with a minimal cost rate of 0.824.
Keywords: V-MIMO; CAOsO algorithm; K-means clustering algorithm; bit error rate performance; CNN model.
DOI: 10.1504/IJWMC.2025.149195
International Journal of Wireless and Mobile Computing, 2025 Vol.29 No.4, pp.365 - 384
Received: 14 Jun 2024
Accepted: 13 Dec 2024
Published online: 17 Oct 2025 *