New EKL model enhances temporal QoS prediction with Kalman Filter integration

Researchers have developed a new model called EKL, which combines an Extended Kalman Filter with Latent Feature Analysis to improve temporal Quality of Service (QoS) prediction. This approach aims to capture non-stationary temporal patterns more effectively than purely data-driven methods, which can degrade in accuracy with fluctuating data. The EKL model incorporates a model-driven feature producer for temporal latent features and a data-driven producer for time-invariant features, alongside a parallel strategy for workload balancing. Theoretical analysis confirms the model's convergence, and experimental results show it outperforms existing state-of-the-art models in both computational efficiency and prediction accuracy for missing temporal QoS data. AI

IMPACT This research could lead to more efficient and accurate network service optimization and resource allocation in cloud computing environments.

RANK_REASON Academic paper detailing a novel model for QoS estimation. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• Connected Papers
• DagsHub
• EKL
• Extended Kalman Filter
• Gotit.pub
• Hugging Face
• Influence Flower
• Latent Feature Analysis
• Litmaps
• ScienceCast
• scite Smart Citations
• Wang Song

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →