Temporal Quality of Service Prediction

Temporal Quality of Service (QoS) prediction aims to accurately forecast the performance of services over time, crucial for maintaining service reliability and user satisfaction in dynamic systems. Recent research focuses on leveraging graph neural networks and transformers to capture complex user-service interactions and long-term temporal dependencies, often incorporating collaborative filtering techniques to improve prediction accuracy. These advancements address limitations of previous methods, particularly recurrent neural networks, which struggle with long-range dependencies and data sparsity, leading to more robust and accurate QoS predictions. Improved QoS prediction has significant implications for service optimization, resource allocation, and personalized service recommendations in various applications.