Title: Mobility-aware optical random waypoint and transfer learning-based load balancing

Authors: Arunkumar Ramakrishnan; Thanasekhar Balaiah

Addresses: Department of Computer Science and Engineering, Rajalakshmi Institute of Technology, Tamil Nadu, Chennai, India ' Department of Computer Technology, Anna University, Chennai, Tamil Nadu, 600044, India

Abstract: In recent years, a hopeful model of hybrid networks based on light fidelity (LiFi) and wireless fidelity (Wi-Fi) named hybrid LiFi-Wi-Fi networks (HLWNets) has been introduced. To address this issue, an innovative approach sewing training inspired optimisation_transfer learning (STIO_TL) is introduced for AP selection in the handover process. Initially, a system model of HLWNets is developed and the mobility-aware optical RWP is designed for the handover process. In the handover process, location is predicted every time using the deep recurrent neural network (DRNN). Afterwards, the AP selection is done by the proposed STIO_TL and is processed by several parameters. The proposed STIO_TL is the integration of the sewing circle inspired optimisation algorithm (STBO) and training-based optimisation algorithm (CIOA). Additionally, the effectiveness of the proposed STIO_TL is evaluated based on the evaluation metrics, like delay, handover occurrence, energy efficiency, and network throughput of 0.111 mS, 6.086, 0.099 Mbits/joules and 0.913 Mbps respectively.

Keywords: sewing training inspired optimisation; deep recurrent neural network; DRNN; transfer learning; circle inspired optimisation algorithm; multipath transmission control protocol.

DOI: 10.1504/IJAHUC.2025.143978

International Journal of Ad Hoc and Ubiquitous Computing, 2025 Vol.48 No.2, pp.94 - 109

Received: 19 Mar 2024
Accepted: 21 Jun 2024
Published online: 16 Jan 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article