Performance analysis of heuristic-optimized machine learning and swarm intelligence for secure and energy-efficient WSNs

Wireless Sensor Networks (WSNs) are widely used in applications such as environmental monitoring, healthcare, and industrial automation, but they face critical challenges of security vulnerabilities and limited energy resources. The study proposes a unified framework that combines machine learning–based intrusion detection with swarm intelligence–driven routing optimization to address these dual concerns. Intrusion detection is enhanced through heuristic optimization, where Particle Swarm Optimization (PSO) fine-tunes classifiers like Multi-Layer Perceptron (MLP), achieving high accuracy with low false alarm rates. On the routing side, clustering protocols such as LEACH, HEED, and TEEN are optimized using the Chaotic Firefly Algorithm (CFA), extending network lifetime, improving throughput, and reducing latency. By integrating these layers, the framework effectively isolates malicious nodes while ensuring balanced energy consumption, delivering a resilient and sustainable solution for next-generation WSN deployments.