Virtual Wireless Network QoS Control Using Traffic Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing multi-tenant wireless networks with varying quality-of-service (QoS) parameters is complex, especially when multiple virtual networks operate on a single physical network, requiring efficient reconfiguration to meet specific QoS demands of each tenant.
Innovation Solution
A multi-tenant network management system utilizing a traffic monitoring system and a virtual network management system (VNMS) with machine learning, such as a neural network, to monitor and analyze short-term and long-term traffic statistics for each virtual wireless network (VWN), and autonomously or recommend modifications to meet individual QoS parameters, including adjusting bandwidth, network topology, and resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual network reconfiguration is performed by network architects, then quality-of-service parameters can be adjusted, but the complexity of managing multiple virtual networks with competing interests increases significantly
Solution Approach 1:
The system employs machine learning models that automatically analyze traffic statistics and autonomously determine reconfiguration actions for virtual networks, eliminating the need for manual intervention by network architects. The ML-based network management system self-adjusts network parameters based on observed traffic patterns and QoS requirements.
Solution Approach 2:
The system continuously monitors traffic statistics from multiple virtual networks and uses this feedback to dynamically adjust network configurations. The machine learning model processes ongoing traffic data and automatically modifies network parameters to maintain QoS levels, creating a closed-loop control system.
2Measurement precision
If traffic statistics are collected and analyzed manually, then network performance can be monitored, but the time and resources required for analysis increase
Solution Approach 1:
The system replaces manual traffic analysis with machine learning-based automated analysis. The ML model processes traffic statistics data automatically, substituting human analytical efforts with computational algorithms that can handle large volumes of data rapidly and accurately.
Solution Approach 2:
The machine learning model acts as an intermediary between raw traffic statistics and network reconfiguration decisions. It processes and interprets traffic data, transforming it into actionable insights that guide automatic network adjustments without requiring manual intervention.
3Reliability
If network reconfiguration is performed frequently to meet QoS metrics, then service quality improves, but network stability and configuration complexity increase
Solution Approach 1:
The system implements dynamic network configuration management where reconfiguration parameters are adjusted based on real-time traffic conditions and QoS requirements. The machine learning model continuously adapts network settings rather than applying fixed configurations, allowing the network to respond flexibly to changing demands while maintaining stability through intelligent control.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Arrangements involving a multi-tenant network management system are presented. A first virtual wireless network can be operated as part of a wireless network. The first virtual wireless network can be mapped to a first set of operating level-of-service parameters. A second virtual wireless network can also be operated as part of the wireless network on behalf of a third entity. The second virtual wireless network can be mapped to a second set of level-of-service operating parameters. A traffic monitoring system may be present that monitors and compiles traffic-related statistics for the first virtual wireless network and the second virtual wireless network separately. A virtual network management system can use a machine learning arrangement to determine how to modify properties of the first virtual wireless network to satisfy the first set of level-of-service operating parameters.