Intelligent Cyber Threat Detection and Energy Forecasting Using Rooster and Sparrow Optimization Algorithms in IoT-Enabled Systems

Abstract

The rapid expansion of the Internet of Things (IoT) has ushered in an era of intelligent automation and data-driven decision-making across diverse domains such as smart cities, energy management, and industrial automation. However, the increasing interconnectedness of IoT networks has also exposed them to a multitude of cyber threats, compromising data integrity, privacy, and service continuity. Additionally, the dynamic nature of energy consumption in IoT ecosystems poses significant forecasting challenges due to fluctuating patterns and contextual dependencies. This research presents an integrated deep learning framework for Intelligent Cyber Threat Detection and Energy Forecasting using two advanced bio-inspired metaheuristic algorithms — Rooster Optimization Algorithm (ROA) and Sparrow Search Algorithm (SSA). The proposed system leverages these algorithms to optimize feature selection and model training in deep neural networks, ensuring high precision and computational efficiency. The model was validated through extensive experimentation on benchmark IoT datasets for both security and energy domains, achieving remarkable performance in detection accuracy, energy prediction reliability, and computational stability. The results demonstrate that the hybrid integration of ROA and SSA enhances convergence speed and mitigates overfitting, making it an ideal framework for real-time IoT analytics and security applications.