Enhancing Higher Vocational English Teaching through Edge Computing: A Framework for Real-Time Language Learning

Abstract

In higher vocational English teaching, delivering teaching materials promptly and enabling instantaneous feedback is crucial for effective language learning. This paper presents a novel algorithm applying Adversarial Autoencoders (AAE) to reduce latency in 5G networks. The proposed algorithm integrates the characteristics of small base station collaboration, multicast, and predictable user behavior, namely the AAE-based collaborative multicast proactive caching scheme (AAE-CMPC). Initially, students are grouped into different preference clusters based on their characteristics. Subsequently, the AAE technique is employed to predict the content that each group might request. To reduce the redundancy of cache content, an ant colony algorithm is used to pre-deploy the predicted content to each small base station to realize the collaboration between small base stations. The proposed AAE-CMPC scheme demonstrates superior performance when compared to three benchmarks. The simulation results indicate that an increase in the storage capacity of the macro base station leads to a reduction in loss rate, and it can be attributed to the enhanced cache hit ratios achieved through proactive caching. The AAE-CMPC algorithm revolutionizes higher vocational English teaching by reducing latency and enabling instantaneous feedback. Students can access teaching materials promptly, receive real-time feedback on their progress, and engage in collaborative activities seamlessly. The framework also leverages edge computing, allowing for increased storage capacity, scalability, and reliability, resulting in an enriched learning experience.