MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202641047819 A) filed by Prathyusha Engineering College on April 15, 2026, for Hybrid Woa-Gwo Based Energy Efficient And Secure Wireless Rechargeable Sensor Network Using Machine Learning Intrusion Detection.
Inventors include S. Arthi; and Reshma V.
The application for the patent was published on June 12, 2026, under issue no. 24/2026.
Abstract: ABSTRACT OF THE INNOVATION The present invention relates to an advanced energy~efficient and secure Wireless Rechargeable . Sensor Network (WRSN) framework that integrates hybrid optimization-based cluster head seleCtion, · periodic wireless energy replenishment, and machine learning-based intrusion detection mechanisms. Wireless sensor networks typically suffer from limited energy resources, uneven energy consumption, and vulnerability to various security threats. To address these challenges, the proposed system · introduces an intelligent and adaptive framework that enhances both network performance and security. The invention employs a hybrid optimization technique that combines the Whale Optimization Algorithm (WOA) and Grey Wolf Optimizer (GWO) to select optimal cluster heads among sensor nodes. This hybrid approach effectively balances exploration and exploitation phases, · enabling efficient identification of the most suitable nodes for cluster head roles. The selection process .. is based on multiple parameters including residual energy, communication distance between nodes, and node distribution, thereby ensuring uniform energy utilization, reduced communication overhead, and improved network stability. To further enhance network lifetime, the system incorporates a periodic wireless recharging mechanism that enables· energy replenishment of cluster head nodes at. predefined intervals using wireless energy transfer. This mechanism ensures that energy-intensive nodes do not deplete quickly, thereby preventing network partitioning and extending overall system longevity. Additionally, a recharge control strategy is implemented to initiate charging only when node energy levels fall below a predefined threshold and to prevent overcharging by limiting maximum energy capacity, thus maintaining energy balance and operational efficiency. The invention also addresses critical security concerns by integrating a machine learning-based intrusion detection system (IDS). The IDS is designed to detect and classify various types of network attacks such as jamming attacks, blackhole attacks, wormhole attacks, and sybil attacks. It utilizes network behavioral features including packet delivery ratio (PDR), node energy levels, cluster head count, and charging frequencyto distinguish between normal and malicious activities. Machine learning algorithms such as Decision Tree, K-Nearest Neighbors (KNN), and Naive Bayes are employed for accurate classification and prediction of network events, ensuring timely detection and mitigation of potential . threats. Furthermore, the system continuously monitors key network performance metrics such as network lifetime, throughput, residual energy distribution, and packet delivery ratio to evaluate and optimize overall performance. The integration of hybrid optimization, intelligent energy management, and data-driven security mechanisms results in a robust and scalable framework. Overall, the proposed invention significantly improves network lifetime, energy efficiency, throughput, and security reliability. The system is highly suitable for large-scale and real-time applications such as environmental monitoring, smart agriculture, industrial automation, healthcare monitoring, and smart city infrastructure, where reliable and secure data transmission is critical.
Disclaimer: Curated by HT Syndication.
