English teaching evaluation based on reinforcement learning in content centric data center network

Abstract

With the increasing enrollment of higher education in China, teaching quality evaluation is an urgent problem to be studied. Colleges and universities should also have their own set of teaching quality evaluation system with the evaluation activities, and thus pre-evaluate their teaching and ensure the teaching quality between the two teaching evaluations. At present, big data is more and more widely used, and distributing these big data to corresponding scores through content centric data center networks (CCDCNs) provides Quality of Experience (QoE) for English teaching quality assessment. Therefore, one of the challenges faced by the current network is to enhance QoE under content distribution. In this work, in order to solve this problem, we schedule the cached teaching feature vector to the corresponding score level. Three cache scheduling algorithms are constructed in CCDCNs. Firstly, an approximate dynamic algorithm is proposed, which has high complexity. Then, based on the characteristics of node centralization, we propose an improved approximate dynamic scheduling algorithm. Although the algorithm includes the scheduling of cached content and the scheduling of content transmission rate, it has low complexity in processing scheduling. In addition, we propose a cache scheduling algorithm based on deep reinforcement learning (DRL). Although the algorithm has high complexity, the scheduling accuracy is also high. Experiments show that the method proposed in this work can obtain higher QoE, and excellent performance in English teaching evaluation, about 7.8% improvement degree.