JoWUA

Abstract

Increasingly challenging digital learning platforms, such as psychology education platforms, require real-time interaction, high reliability, and adaptive connectivity, which future wireless mesh networks (WMNs) are anticipated to facilitate. Nonetheless, conventional WMNs have long-standing issues with fault tolerance, dynamic load management, and self-optimization. This paper proposes an autonomic communication model that incorporates self-configuration, self-healing, and self-optimization functions to improve live network performance in education. The system uses a hybrid approach that integrates adaptive routing, machine-learned load prediction, and distributed fault identification to dynamically reassign traffic loads and isolate failures at the node level, ensuring continuous service delivery. The experiments have been carried out in a simulated digital psychology learning environment that involves 500-2,000 active users, providing heterogeneous data streams: video sessions, cognitive assessment uploads, and interactive course modules. A statistical analysis shows that the proposed model improves the packet delivery ratio by 18.7 percent, end-to-end latency by 22.4 percent, and network throughput by 15.2 percent relative to traditional WMN routing schemes. The average time to fault recovery dropped by 60.4 percent, from 2.9 seconds to 1.9 seconds. Efficiency in load balancing was also achieved, and the variance in load per node was minimized by 34 percent. The findings suggest that autonomic communication systems contribute significantly to the resilience and adaptability of future WMNs, particularly in online education in digital psychology, where connectivity is crucial for engaging learners and accurately assessing them. The paper ends with recommendations for implementing autonomic systems in large-scale educational infrastructure and provides possible directions for integrating AI-based predictive models and cognitive-based network management strategies.