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

Internet of Things (IoT) sensor networks comprise diminutive sensor units primarily designed for monitoring phenomena within a designated area. However, reaching the complete potential of this kind of network is extremely difficult due to several challenges, including the fact that the data transmitted by the sensor nodes contains a large amount of duplicates. Data aggregation can be employed to address this issue in routing packets from nodes that send data to the base station (BS). In this study, a novel, hybrid data aggregation framework for IoT sensor networks is proposed by integrating Self-Organizing Maps (SOMs) with the Firefly Optimization Algorithm (FOA). The core motivation for this integration is to address persistent challenges in IoT sensor networks, chiefly energy efficiency, network longevity, and the reliability of data transmission. By combining the adaptive, unsupervised clustering capabilities of SOMs with the robust, multi-objective optimization properties of the FOA, the method aims to achieve more intelligent, adaptive, and practical solutions for real-world IoT systems. This work presents an innovative framework that synergistically leverages the strengths of FOA and SOM, offering a new methodology that addresses key challenges in scalable and energy-efficient IoT sensor network clustering. The suggested algorithm's validity has been verified using an experimental analysis performed in MATLAB. Experimental results show the proposed method extends network lifetime by 15% and reduces energy consumption by 10% compared to FOA, SOM, and LEACH benchmarks. A notable classification rate was attained after implementing and testing the proposed method using the Intel Berkeley Research Lab dataset.