An End-to-End Deep Learning QoS Prediction Model Based on Temporal Context and Feature Fusion

Existing end-to-end quality of service (QoS) prediction methods based on deep learning often use one-hot encodings as features, which are input into neural networks. It is difficult for the networks to learn the information that is conducive to prediction. Aiming at the above problem, an end-to-end deep learning QoS prediction model based on a temporal context and feature fusion is proposed. In the proposed model, three blocks are designed for QoS prediction. Firstly, a user-service encoding conversion block is designed to convert the one-hot encodings of users and services into the latent features of users and services, which can make full use of the data in sparse matrices. Then a time feature extraction block is designed to extract time features based on the time-varying characteristics of QoS values. Finally, the time features are fused with the latent features of users and services to predict QoS values. The experimental results show that on existing datasets, the proposed model has better prediction accuracy than other advanced methods in response time and throughput.