Improving Data Aggregation in IoT Sensor Networks Using Self-Organizing Maps and Firefly Optimization Algorithm.

Area of Science:

• Computer Science
• Electrical Engineering
• Artificial Intelligence

Background:

• Internet of Things (IoT) sensor networks face challenges with redundant data transmission, impacting efficiency.
• Energy efficiency, network longevity, and data reliability are critical for realizing the full potential of IoT sensor networks.
• Existing data aggregation methods struggle to effectively manage duplicate data and optimize network performance.

Purpose of the Study:

• To propose a novel hybrid data aggregation framework for IoT sensor networks.
• To address key challenges in IoT sensor networks, including energy efficiency, network longevity, and data transmission reliability.
• To develop an intelligent and adaptive solution for scalable and energy-efficient IoT sensor network clustering.

Main Methods:

• Integration of Self-Organizing Maps (SOMs) for adaptive, unsupervised clustering.
• Application of the Firefly Optimization Algorithm (FOA) for robust, multi-objective optimization.
• Experimental validation using MATLAB and the Intel Berkeley Research Lab dataset.

Main Results:

• The proposed hybrid framework extends network lifetime by 15% compared to benchmarks.
• Energy consumption is reduced by 10% with the novel approach.
• A notable classification rate was achieved, demonstrating the method's effectiveness.

Conclusions:

• The synergistic integration of SOMs and FOA offers a new methodology for IoT sensor network clustering.
• The framework provides a more intelligent, adaptive, and practical solution for real-world IoT systems.
• The proposed method significantly improves network lifetime and energy efficiency in IoT sensor networks.