A Multivariate Time-Series Based Approach for Quality Modeling in Wireless Networks

Area of Science:

• Wireless communication networks
• Network performance monitoring
• Data analytics

Background:

• Accurate estimation of Key Quality Indicators (KQIs) is crucial for managing modern wireless networks.
• Existing methods may struggle with the dynamic and non-stationary nature of 5G and 6G environments.
• The need for efficient, real-time KQI estimation techniques is increasing.

Purpose of the Study:

• To develop and evaluate a novel method for estimating KQIs from wireless network node measurements.
• To create a KQI time-series suitable for network management systems.
• To design a framework adaptable to 5G and 6G systems, capable of handling non-stationary conditions.

Main Methods:

• Utilized multivariate adaptive filtering for signal processing.
• Employed a clustering algorithm to group network data.
• Developed a framework for online training and flexible implementation.
• Evaluated feasibility using live heterogeneous network measurements.

Main Results:

• The proposed method successfully generated KQI time-series from network measurements.
• Initial results demonstrated the method's effectiveness compared to linear regression techniques.
• The framework showed adaptability to non-stationary network environments.

Conclusions:

• The presented method offers a viable approach for estimating KQIs in advanced wireless networks.
• The framework's design supports efficient, real-time KQI monitoring for 5G and 6G.
• Further research can refine the algorithms for enhanced performance and broader applicability.