Cognitive Network QoS Control via Plane Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Connectionless networks, such as IP networks, face challenges in guaranteeing Quality of Service (QoS) for real-time data services, are inefficient in resource management, and lack secure and predictable performance, leading to high costs and vulnerabilities.
Innovation Solution
A cognitive network system with an end-to-end control mechanism that uses a management plane to determine network state and route data through asynchronous networks, ensuring deterministic performance and enhanced security by mapping specific data protocols to routes and ports, and utilizing out-of-plane dedicated circuits for control, allowing for real-time monitoring and differentiated billing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If connectionless networks are used for data transmission, then network flexibility and simplicity are improved, but Quality of Service guarantee and predictability deteriorate
Solution Approach 1:
The patent segments the network control into three independent planes: bearer plane for data transmission, management plane for policy control, and cognitive plane for intelligence and decision-making. This segmentation allows each plane to optimize its function independently, providing both the flexibility of connectionless networks and the reliability of connection-oriented QoS guarantees through coordinated control across planes.
Solution Approach 2:
The patent introduces a cognitive controller as an intermediary between the management plane and bearer plane elements. This cognitive controller receives policies from the management plane, determines optimal routes using cognitive algorithms, and controls bearer plane elements to enforce QoS. The intermediary enables intelligent mediation between flexibility requirements and reliability guarantees.
2Ease of operation
If distributed autonomous control logic is used at each router, then local decision-making capability is improved, but end-to-end network coordination and optimal efficiency deteriorate
Solution Approach 1:
The patent implements feedback mechanisms where bearer plane elements report their state and performance metrics to the cognitive controller, which in turn adjusts routing decisions and policies. This closed-loop feedback enables continuous optimization of network efficiency while maintaining local autonomy in data forwarding decisions.
Solution Approach 2:
The patent adds a cognitive plane dimension to the traditional two-plane (management and bearer) architecture. This third dimension introduces intelligence and global optimization capabilities without burdening individual routers, enabling end-to-end coordination while preserving local decision-making simplicity.
3Device complexity
If in-band signaling and control are used, then network simplicity is improved, but security and control accessibility deteriorate
Solution Approach 1:
The patent extracts control signaling from the data-bearing plane by implementing a separate management plane for policy control and a cognitive plane for intelligence. This separation removes control information from the data path, preventing users from accessing control commands while maintaining network simplicity through automated control mechanisms.
4Ease of operation
If current IP transport technologies like MPLS are used, then some routing control capability is improved, but transaction record generation and usage-based billing capability deteriorate
Solution Approach 1:
The patent performs preliminary actions by establishing detailed routing paths and service parameters before data transmission begins. The cognitive controller pre-determines optimal routes and allocates resources, creating a structured framework that enables comprehensive transaction record generation and usage-based billing for routing control services.
Data Source
AI summary
A reservation request is received for a data transport session. The reservation request contains a requested class of communication service through the asynchronous network. The state of the network along the route is then preferably determined and at least one end-to-end route through the network is obtained. The route is based on the requested class of communication service and the state of the network. The data transport session is then controlled, such that data is forced to travel along at least one route through the asynchronous network. This is preferably done by controlling multiple data controllers dispersed along the at least one route by mapping specific data protocols to specific routes, or mapping specific data protocols to specific ports in each data controller. If a state of the asynchronous network indicates that the route cannot transport data in conformity to the class of communication service, then the route is changed to a backup route through the network.