Intelligent Forecasting of Energy Depletion in Underwater Wireless Sensor Networks: A Machine Learning Paradigm for Energy Hole Prediction DOI Creative Commons

Anandkumar Pandya,

Tanmay Pawar

International Journal of Electrical and Electronics Engineering, Journal Year: 2024, Volume and Issue: 11(4), P. 198 - 205

Published: April 30, 2024

Underwater Wireless Sensor Networks (UWSNs) play a pivotal role in aquatic environments, facilitating data collection and communication for various applications. However, the limited energy resources of sensor nodes pose critical challenge, leading to emergence holes that can adversely impact network performance longevity. This research proposes novel two-part approach address this challenge by leveraging Neural both hole classification prediction UWSNs. The study begins with an in-depth literature review covering management UWSNs application deep learning techniques, particularly neural networks, predicting network-related issues. Through exploration, unique challenges associated underwater environments are identified, forming foundation proposed network-based solution. 1. Energy Hole Classification: Extensive simulations scenarios conducted classify instances holes. These generate rich dataset featuring crucial columns such as residual energy, hop distance from surface sink, zone, source address, destination etc. is meticulously prepared preprocessed ensure its suitability training model classification. 2. Prediction: phase then utilized train designed capture dependencies among features distance, addresses. trained evaluated on distinct test dataset, using metrics accuracy, precision, recall, F1 score measure success results showcase model's ability learn generalize extensive providing valuable insights into potential occurrences based specified features. paradigm, incorporating offers promising solution enhance UWSNs, ultimately improving longevity performance. concludes discussions implications results, real-world applications, avenues future intersection networks.

Language: Английский

Wireless Sensor Network Optimization and Management With EH and Machine Learning Prognostication Algorithm DOI Open Access

Gayatri Bedre,

Damodar Reddy Edla

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 30 - 38

Published: Jan. 1, 2025

Language: Английский

Citations

0
An Energy Efficient and Scalable WSN with Enhanced Data Aggregation Accuracy DOI Creative Commons
Noor Raad Saadallah, Salah Abdulghani Alabady

Journal of Telecommunications and Information Technology, Journal Year: 2024, Volume and Issue: unknown, P. 48 - 57

Published: May 7, 2024

This paper introduces a method that combines the K-means clustering genetic algorithm (GA) and Lempel-Ziv-Welch (LZW) compression techniques to enhance efficiency of data aggregation in wireless sensor networks (WSNs). The main goal this research is reduce energy consumption, improve network scalability, accuracy. Additionally, GA technique employed optimize cluster formation process by selecting heads, while LZW compresses aggregated transmission overhead. To further traffic, scheduling mechanisms are introduced contribute packets being transmitted from sensors heads. findings study will advancing packet for WSNs order number Simulation results confirm system's effectiveness compared other methods non-compression scenarios relied upon LEACH, M-LEACH, multi-hop sLEACH approaches.

Language: Английский

Citations

1
Intelligent Forecasting of Energy Depletion in Underwater Wireless Sensor Networks: A Machine Learning Paradigm for Energy Hole Prediction DOI Creative Commons

Anandkumar Pandya,

Tanmay Pawar

International Journal of Electrical and Electronics Engineering, Journal Year: 2024, Volume and Issue: 11(4), P. 198 - 205

Published: April 30, 2024

Underwater Wireless Sensor Networks (UWSNs) play a pivotal role in aquatic environments, facilitating data collection and communication for various applications. However, the limited energy resources of sensor nodes pose critical challenge, leading to emergence holes that can adversely impact network performance longevity. This research proposes novel two-part approach address this challenge by leveraging Neural both hole classification prediction UWSNs. The study begins with an in-depth literature review covering management UWSNs application deep learning techniques, particularly neural networks, predicting network-related issues. Through exploration, unique challenges associated underwater environments are identified, forming foundation proposed network-based solution. 1. Energy Hole Classification: Extensive simulations scenarios conducted classify instances holes. These generate rich dataset featuring crucial columns such as residual energy, hop distance from surface sink, zone, source address, destination etc. is meticulously prepared preprocessed ensure its suitability training model classification. 2. Prediction: phase then utilized train designed capture dependencies among features distance, addresses. trained evaluated on distinct test dataset, using metrics accuracy, precision, recall, F1 score measure success results showcase model's ability learn generalize extensive providing valuable insights into potential occurrences based specified features. paradigm, incorporating offers promising solution enhance UWSNs, ultimately improving longevity performance. concludes discussions implications results, real-world applications, avenues future intersection networks.

Language: Английский

Citations

0