Deep Reinforcement Learning Based Security-Aware Computational Offloading and Resource Allocation for MEC Systems

The Internet of Things (IoT) is becoming integral to our daily lives, facilitating data collection and analysis for informed decision-making as devices generate vast amounts of data. The transition from Mobile Cloud Computing (MCC) to Mobile Edge Computing (MEC) is increasingly favored for its benefits, including reduced communication latency and efficient bandwidth utilization; however, offloading tasks to the MEC encounters challenges related to data privacy and energy consumption. This study presents an advanced Deep Reinforcement Learning (DRL) based security-aware data offloading and resource allocation model for industrial IoT devices that prioritizes security while effectively managing their computational and radio resources. The model aims to minimize computation latency and energy consumption, which we address using a deep learning optimization strategy. Furthermore, an AES-based security layer is integrated to meet data security needs. Experimental results show that our model significantly reduces offloading overhead compared to both local execution and full offloading, while also demonstrating exceptional scalability for large-scale IoT deployments.