Optimizing energy consumption in industrial wireless sensor networks using a hybrid FCM and GWO machine learning approach
- 1Department of Electronics and Communication Engineering, Rajalakshmi Engineering College
- 2Department of Electronics Engineering, Anna University – MIT Campus
Abstract
Wireless sensor networks (WSNs) plays a dynamic role in enabling industrial applications such as production, logistics, and predictive maintenance. The present study investigates optimal strategies for sensor node placement and energy consumption optimisation to enhance the functionality of industrial WSNs. Currently an industrial automation application energy consumption of the field devices and data aggregation in promptly in the real time process are very difficult due to the dynamic environment. In this paper machine learning enhanced hybrid Fuzzy C - means and grey wolf optimisation (MLFCGO) algorithm is proposed to accomplish efficient energy management and enhanced performance of a network consider in terms of sensor node deployment and energy consumption method. The FCM algorithm provides flexible cluster formation through its soft clustering mechanism, where each sensor node possesses varying degrees of membership across clusters. This enables better adaptability and precision in node deployment, under different strength conditions using FCM in a 3D environment. The GWO component of the hybrid approach further augments the system’s performance by optimising routing paths and head selection of cluster. In industrial wireless sensor network (IWSN) environments, GWO demonstrates substantial improvements compared with existing hybrid algorithms such as ALO, PSO, DA and SA. Through its nature-inspired, low-overhead optimisation process, GWO ensures balanced energy utilisation, stable communication links, and extended network lifetime. By combining the clustering adaptability of FCM and the optimisation strength of GWO, the proposed MLFCGO technique significantly enhances random and fixed deployment nodes of parameters such as minimum energy consumption (0.40–0.45 J), lowest latency (80–90 ms), highest packet delivery ratio (95–97%), and maximum throughput (135–145 kbps). In addition, it delivers the longest network lifetime (280–300 days) and maintains the highest average residual energy (0.55–0.60 J), indicating strong energy efficiency and prolonged operational sustainability even in large scale deployments.
Related
- Optimized Artifact Removal Algorithm for Microwave Imaging in Industrial Wireless Sensor Networks
- Adaptive intelligent resource optimization in wireless sensor networks using reinforcement learning and compressive sensing
- Stability and Hopf Criteria in a Malware Dissemination Model for Wireless Sensor Networks with Distributed Recovery Delays
- A predictive ant colony optimization routing protocol for correlated link stability in wireless body area networks.
- Machine learning for intelligent beam divergence compensation in orbital angular momentum-based wireless communication systems
BibTeX
@article{ravindrakumar2026optimizing,
title = {{Optimizing energy consumption in industrial wireless sensor networks using a hybrid FCM and GWO machine learning approach}},
author = {B. Ravindrakumar and M. Vasim Babu},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-71905-4},
url = {https://doi.org/10.1038/s41598-026-71905-4},
note = {CC BY},
}
RIS
TY - JOUR
TI - Optimizing energy consumption in industrial wireless sensor networks using a hybrid FCM and GWO machine learning approach
AU - B. Ravindrakumar
AU - M. Vasim Babu
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-71905-4
UR - https://doi.org/10.1038/s41598-026-71905-4
AB - Wireless sensor networks (WSNs) plays a dynamic role in enabling industrial applications such as production, logistics, and predictive maintenance. The present study investigates optimal strategies for sensor node placement and energy consumption optimisation to enhance the functionality of industrial WSNs. Currently an industrial automation application energy consumption of the field devices and data aggregation in promptly in the real time process are very difficult due to the dynamic environment. In this paper machine learning enhanced hybrid Fuzzy C - means and grey wolf optimisation (MLFCGO) algorithm is proposed to accomplish efficient energy management and enhanced performance of a network consider in terms of sensor node deployment and energy consumption method. The FCM algorithm provides flexible cluster formation through its soft clustering mechanism, where each sensor node possesses varying degrees of membership across clusters. This enables better adaptability and precision in node deployment, under different strength conditions using FCM in a 3D environment. The GWO component of the hybrid approach further augments the system’s performance by optimising routing paths and head selection of cluster. In industrial wireless sensor network (IWSN) environments, GWO demonstrates substantial improvements compared with existing hybrid algorithms such as ALO, PSO, DA and SA. Through its nature-inspired, low-overhead optimisation process, GWO ensures balanced energy utilisation, stable communication links, and extended network lifetime. By combining the clustering adaptability of FCM and the optimisation strength of GWO, the proposed MLFCGO technique significantly enhances random and fixed deployment nodes of parameters such as minimum energy consumption (0.40–0.45 J), lowest latency (80–90 ms), highest packet delivery ratio (95–97%), and maximum throughput (135–145 kbps). In addition, it delivers the longest network lifetime (280–300 days) and maintains the highest average residual energy (0.55–0.60 J), indicating strong energy efficiency and prolonged operational sustainability even in large scale deployments.
SN - 2045-2322
ER -