Energy-Aware and Secure Data Aggregation Framework for Wireless Sensor Networks Using Hybrid Deep Learning and Swarm Intelligence

Abstract

Wireless Sensor Networks (WSNs) play a vital role in distributed sensing applications; however, energy constraints and security vulnerabilities significantly affect their performance and reliability. This paper proposes an Energy-Aware and Secure Data Aggregation Framework (EASDAF) that integrates hybrid deep learning techniques with swarm intelligence optimization to enhance network efficiency and data security. The proposed framework employs a deep learning model to perform intelligent data aggregation by reducing redundancy and extracting meaningful information from sensor nodes. To further optimize energy consumption, a swarm intelligence-based algorithm is incorporated for optimal cluster head selection and routing path optimization, ensuring balanced energy utilization across the network. Additionally, a lightweight security mechanism is embedded within the aggregation process to protect data integrity and prevent malicious attacks. Experimental results demonstrate that the EASDAF framework significantly improves key performance metrics such as network lifetime, energy efficiency, throughput, and packet delivery ratio while maintaining robust security. Comparative analysis with existing approaches shows superior performance in minimizing energy consumption and enhancing secure data transmission. The proposed framework is suitable for real-time WSN applications including healthcare monitoring, environmental sensing, and industrial automation.