Optimized Security and Energy Efficiency for MQTT-based WSN-IoT: A GDMSOA-driven Framework with Adaptive Authentication

The proliferation of Wireless Sensor Network (WSN)-based Internet of Things (IoT) systems has intensified concerns around secure, energy-efficient, and reliable data transmission in constrained environments. Existing cryptographic protocols and traditional security approaches frequently prove impractical in WSN deployments, owing to their elevated computational demands, elevated latency penalties, and disproportionate energy overhead. Lightweight communication protocols such as Message Queuing Telemetry Transport (MQTT), despite their widespread adoption, remain susceptible to a broad range of cyber threats and unauthorized access attempts. To address these persistent challenges, this study proposes a novel GDMSOA-driven framework for secure and energy-efficient data transmission in WSN-enabled IoT networks. The framework unifies the Genetic Dual-Mutation Seagull Optimization Algorithm (GDMSOA) with a machine-learning-based intrusion detection system and an adaptive secure authentication protocol, thereby strengthening communication security without sacrificing network efficiency. Data aggregation and GDMSOA-guided cluster-head selection reduce redundant transmissions and lower energy expenditure, while dynamic hyperparameter tuning and MQTT communication optimization improve both detection accuracy and transmission reliability. Experimental evaluation on benchmark datasets comprising MQTTset, N-BaIoT, BoT-IoT, and UNSW-NB15 shows that the proposed framework attains a detection accuracy of 98.6%, a security rate of 91%, a packet delivery ratio exceeding 96%, and an energy reduction of 18–25% relative to established state-of-the-art methods. These quantitative outcomes confirm the framework’s viability for real-time, secure, and resource-constrained IoT and WSN deployments.