Enhanced mobile sink path optimization using RPP-RNN algorithm for energy efficient data acquisition in WSNs

• Published in: Wireless networks Vol. 31; no. 2; pp. 1705 - 1717
• Main Authors: K, Vignesh Saravanan, S, Kavipriya, K, Vijayalakshmi
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.02.2025; Springer Nature B.V
• Subjects: Algorithms; Communications Engineering; Communications traffic; Computer Communication Networks; Data acquisition; Data collection; Deep learning; Electrical Engineering; Energy consumption; Engineering; Environmental monitoring; IT in Business; Networks; Neural networks; Nodes; Optimization; Original Paper; Path planning; Recurrent neural networks; Sensors; Simulation; Travel; Wireless networks; Wireless sensor networks; Mobile sink path optimization; Network lifetime; Recurrent neural networks; Energy efficiency; Data acquisition
• ISSN: 1022-0038; 1572-8196
• DOI: 10.1007/s11276-024-03850-x

Energy use and data collection are the main issues in real time wireless sensor network scenarios. Mobile sinks help balance energy usage, reduce multi-hop transmission, and extend network lifetime through moving around the network to collect data at predetermined locations. The proposed novel Rank-Based Path Planning algorithm with Recurrent Neural Networks identifies hotspot nodes based on energy dissemination, network traffic, and multi-hop transmission. Mobile sink only visits the hotspot nodes to collect data, while other nodes forward data to the nearest hotspot. Experimental results shows 35% decrease in energy consumption and 13% increase in network life compared to existing state-of-art algorithms and moderate increases in simulation time, ensuring efficient data collection.