M-SOS: Mobility-Aware Secured Offloading and Scheduling in Dew-Enabled Vehicular Fog of Things

The gradual advancement of Internet-connected vehicles has transformed roads and highways into an intelligent ecosystem. This advancement has led to a widespread adoption of vehicular networks, driven by the enhanced capabilities of automobiles. However, managing mobility-aware computations, ensuring network security amidst instability, and overcoming resource constraints pose significant challenges in heterogeneous vehicular network applications within Fog computing. Moreover, the latency overhead remains a critical issue for tasks sensitive to latency and deadlines. The objective of this research is to develop a Mobility-aware Secured offloading and Scheduling (M-SOS) technique for a Dew-enabled vehicular Fog-Cloud computing system. This technique aims to address the issues outlined above by moving the computations closer to the edge of the network. Initially, a Dew-facilitated vehicular Fog network is proposed, leveraging heterogeneous computing nodes to handle diverse vehicular requests efficiently and ensuring uninterrupted services within the vehicular network. Further, task management is optimized using a Fuzzy logic that categorizes tasks based on their specific requirements and identifies the target layers for offloading. Besides, a cryptographic algorithm known as SHA-256 RSA enhances security. Moreover, a novel Linear Weight-based JAYA scheduling algorithm is introduced to assign tasks to appropriate computing nodes. The proposed algorithm surpasses the comparable algorithms by 23% in terms of AWT, 18% in terms of latency rate, 14% and 23% in terms of meeting the hard-deadline (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$H\_d$ </tex-math></inline-formula>) and soft-deadline (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$S\_d$ </tex-math></inline-formula>), and 35% in terms of average system cost, respectively.