Network Traffic Suppression Prediction With Adaptive Policy Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication networks lack predictive means to anticipate traffic suppression, leading to suboptimal network adjustments and user experience degradation when maximum traffic volume is reached.
Innovation Solution
A method involving a network traffic model to predict traffic suppression by determining a suppression point based on a mapping relationship between network parameters and traffic values, using machine learning models to forecast parameter changes and adjust network policies proactively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional reactive network diagnosis and policy adjustment methods are used, then network issues can be addressed after detection, but user experience deteriorates due to delayed response and traffic suppression
Solution Approach 1:
The patent applies preliminary action by using machine learning models to predict traffic suppression events before they occur. The system analyzes historical network data, identifies patterns leading to suppression, and triggers early warnings, enabling network operators to take preventive measures before traffic suppression actually happens, thus eliminating the delayed response characteristic of conventional reactive methods
Solution Approach 2:
The patent implements feedback mechanisms by continuously monitoring network parameters, comparing actual values against predicted suppression thresholds, and adjusting network policies based on prediction results. This closed-loop feedback system enables real-time adaptive optimization, transforming the static reactive approach into a dynamic predictive system that continuously learns from and responds to network conditions
2Productivity
If maximum traffic volume is reached, then network capacity utilization is optimized, but traffic suppression occurs leading to decreased total traffic volume
Solution Approach 1:
The patent applies preliminary anti-action by predicting traffic suppression events before they occur and implementing countermeasures in advance. The system identifies when network parameters are approaching suppression thresholds and triggers preventive policy adjustments, such as load balancing or resource allocation changes, to counteract the suppression effect before it reduces total traffic volume
Solution Approach 2:
The patent implements dynamics by making network policies adaptive and changeable based on real-time predictions. Instead of static policies, the system dynamically adjusts network parameters, resource allocation, and traffic routing based on predicted suppression risks, allowing the network to flexibly respond to changing conditions and maintain optimal performance across varying traffic loads
3Ease of operation
If network parameters are monitored and adjusted reactively, then some network issues can be addressed, but predictive optimization is impossible affecting overall network efficiency
Solution Approach 1:
The patent applies self-service by implementing automated machine learning models that independently analyze network data, predict suppression events, and generate optimization recommendations without requiring manual intervention. The system autonomously performs pattern recognition, threshold determination, and policy adjustment suggestions, reducing operational complexity while enhancing network efficiency through continuous automated optimization
Data Source
AI summary
A method for predicting traffic suppression, an electronic device and a storage medium are disclosed. The method may include: determining a traffic value of suppression point according to a preset network traffic model which represents a mapping relationship between a numerical value of a network parameter of a transmission network and a traffic value, wherein the traffic value of suppression point is a traffic threshold of the transmission network under a current running policy; determining a suppression reference value of a target network parameter corresponding to the traffic value of suppression point; and acquiring a parameter prediction value corresponding to the target network parameter, and determining a traffic suppression prediction result according to the parameter prediction value and the suppression reference value.