A fuzzy based chicken swarm optimization algorithm for efficient fault node detection in Wireless Sensor Networks

Area of Science:

• Computer Science
• Electrical Engineering
• Network Engineering

Background:

• Wireless Sensor Networks (WSN) are crucial for environmental monitoring but suffer from sensor node failures due to deployment challenges and limited resources.
• Node failures in WSN can lead to topology changes, communication disruptions, network partitioning, and data transmission errors.
• Effective detection, diagnosis, and recovery of sensor node failures are critical for WSN reliability.

Purpose of the Study:

• To propose an effective sensor node failure detection algorithm for Wireless Sensor Networks (WSN).
• To improve the accuracy of fault detection, reduce false alarms and false positives, and optimize energy consumption.
• To enhance the localization of defective sensor nodes within the WSN.

Main Methods:

• A novel algorithm combining the Poisson Hidden Markov Model (PHMM) for fault detection and Fuzzy-based Chicken Swarm Optimization (F-CSO) for improved localization and parameter optimization.
• Implementation and simulation using the NS2 simulator with realistic parameters to evaluate performance.
• Comparison with existing state-of-the-art systems to demonstrate effectiveness.

Main Results:

• Achieved 89.5% fault detection accuracy, a significant improvement over existing methods.
• Demonstrated a 19.53% increase in throughput and an 8.43% reduction in energy consumption.
• Showcased minimal delay rates and a lower false positive rate compared to other systems.

Conclusions:

• The proposed PHMM and F-CSO based algorithm offers a highly effective solution for detecting sensor node failures in WSN.
• The approach significantly enhances network performance metrics including accuracy, throughput, and energy efficiency.
• This method provides a robust strategy for maintaining WSN integrity and reliability in the face of node failures.