A Novel Approach to Temporal QoS Estimation via Extended Kalman Filter-Incorporated Latent Feature Analysis
2026-06-22 • Machine Learning
Machine Learning
AI summaryⓘ
The authors address the challenge of predicting changing Quality of Service (QoS) data over time, which is important for improving cloud and network services. They note that existing methods struggle with fluctuating patterns because they rely only on data-driven approaches. To fix this, the authors combine a model-driven technique called Extended Kalman Filter with data-driven methods to better capture both changing and constant features. Their new EKL model also uses a smart sorting strategy to speed up calculations. Tests on real datasets show their method predicts QoS more accurately and efficiently than current top models.
Quality of Service (QoS)Temporal data predictionExtended Kalman FilterLatent Feature AnalysisData-driven learningModel-driven learningAlternating least squaresNon-stationary time seriesCloud computingService invocation density
Authors
Ye Yuan, Song Wang, Hongxun Zhou, Ling Wang, Xin Luo
Abstract
Predicting temporal Quality of Service (QoS) data is critical for optimizing network services and rationalizing resource allocation in cloud computing and service-oriented systems. Existing mainstream methods have achieved promising predictive performance. However, their purely data-driven manner limits their ability to capture non-stationary temporal patterns, thereby leading to accuracy degradation when temporal QoS data exhibits fluctuations. To tackle this limitation, we propose a novel Extended Kalman Filter-Enhanced Latent Feature Analysis (EKL) model to perform efficient and accurate temporal QoS prediction from the perspective of bidirectional model-data-driven learning. Its main idea is three-fold: a) designing a model-driven feature producer to obtain the temporal latent features to capture the intricate temporal pattern following the principle of an Extended Kalman Filter; b) building a data-driven feature producer based on the alternating least squares algorithm to identify time-invariant latent features describing intrinsic user-service characteristics; c) exploiting a density-oriented parallel strategy that achieves workload balancing by sorting users in accordance with their service invocation density, which effectively elevates computational efficiency. In addition, we provide a rigorous theoretical analysis to formally prove the convergence of the proposed EKL. Experimental evaluations conducted on real-world temporal QoS datasets reveal that our proposed EKL surpasses existing state-of-the-art models with respect to both computational efficiency and prediction accuracy for missing temporal QoS data.