Predictive Session Admission in Communications Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current communication networks face challenges in efficiently managing session admissions based on Quality of Service (QoS) requirements, as they often rely on static routing and bandwidth allocation, which can lead to suboptimal resource utilization and potential service degradation due to lack of predictive analytics for traffic management.
Innovation Solution
Implementing a method that uses predictive models to evaluate the performance of network tunnels based on historical data and real-time metrics, allowing for dynamic allocation of resources and adaptive QoS management by determining if a tunnel can support a session at a higher class of service, and if not, dividing the session into portions to ensure adequate QoS across multiple tunnels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If static routing and bandwidth allocation are used for session admission, then network configuration and management are simplified, but resource utilization efficiency deteriorates and service degradation occurs due to lack of predictive analytics
Solution Approach 1:
The patent implements dynamic routing and bandwidth allocation by using predictive analytics to determine optimal paths and resource allocation in real-time. The system continuously monitors network conditions and adjusts session admission decisions based on predicted future states, transforming static configuration into adaptive, dynamic resource management that improves utilization without requiring complex manual configuration.
Solution Approach 2:
The patent applies preliminary action by using predictive analytics to forecast future network conditions and session demands before they occur. The system pre-calculates optimal routing paths and bandwidth allocation strategies based on historical data and current trends, enabling proactive session admission decisions that prevent service degradation and optimize resource utilization in advance.
2Productivity
If predictive analytics and dynamic resource allocation are implemented, then resource utilization efficiency and QoS management improve, but system complexity increases
Solution Approach 1:
The patent introduces an intermediary predictive analytics layer that sits between network monitoring and session admission control. This intermediary component analyzes historical data, current network state, and future predictions to generate optimized routing and bandwidth allocation decisions, simplifying the overall system architecture by centralizing complex analytical functions in a dedicated mediation layer rather than distributing complexity across multiple network elements.
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors actual network performance and session outcomes, compares them with predictive analytics forecasts, and uses this feedback to refine future predictions and decisions. This closed-loop feedback system enables the network to learn from experience and improve resource allocation accuracy over time, reducing the complexity burden by making the system progressively more efficient.
3Loss of time
If sessions are admitted based on current bandwidth availability without predictive analysis, then admission decisions are made quickly, but service degradation occurs due to inadequate QoS management under changing network conditions
Solution Approach 1:
The patent applies preliminary action by performing predictive analytics on historical network data and current conditions to forecast future bandwidth availability and QoS outcomes before making admission decisions. This allows the system to evaluate not just current resources but also predicted future states, enabling faster yet more reliable decisions that account for upcoming network changes and prevent service degradation.
Solution Approach 2:
The patent enables the network system to self-service by automatically collecting historical performance data, generating predictive analytics models, and using these predictions to make autonomous session admission decisions. The system serves itself by continuously learning from past performance and adapting its admission criteria without external intervention, thereby maintaining quick decision-making while improving QoS reliability through data-driven insights.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A session admission process is provided which identifies the weakest link in a route between a first node and a second node and determines if the route is able to cope if the session is admitted. The suitability of a link is determined on the basis of: historical link performance; the predicted future performance of the link; and the predicted future demands on the link from other sessions supported by that link.