Peer-driven task scheduling and resource allocation for enhanced performance in industrial IoT systems

Peer-to-Peer (P2P) systems in the smart industry, enhanced by the Industrial Internet of Things (IIoT), provide a robust framework for efficiently managing and processing distributed tasks. However, resource sharing and allocation in these systems, often conducted one-to-one, can lead to task stagnancy when multiple resources are required in sequence. This paper proposes a novel Peer-dependent Scheduling and Allocation Scheme (PSAS) that leverages predictive learning to optimize task scheduling and resource allocation to address this limitation. The scheme evaluates resource availability, task length, and deadlines to minimize stagnancy and maximize system throughput. Predictive learning in PSAS enhances decision-making by analyzing historical resource utilization and providing real-time recommendations for resource allocation. This approach ensures scalability, reduces delays in task completion, and enhances overall system reliability, marking a significant advancement in P2P-based IIoT systems. Key performance metrics, including task processing ratio, processing time, stagnancy factor, and wait time, demonstrate that PSAS outperforms existing methods by improving processing ratio by up to 10.62% and reducing stagnancy by 5.06%.