Packet Correlation Engine for High-Speed Control and User Plane Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to adequately correlate control and user information at high speeds required by modern telecom networks, leading to poor network conditions in areas such as billing, security, and performance.
Innovation Solution
A lockless multi-core system with dedicated cores for specific tasks, utilizing DPDK for fast packet processing, and a correlation engine to match extracted control and tunnel information, enhancing data correlation efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If conventional methods are used to process control and user packets, then device complexity is reduced, but processing speed and correlation accuracy deteriorate
Solution Approach 1:
The system divides packet processing into separate functional modules: control packet processing module, user packet processing module, and correlation module. Each module handles specific tasks independently, enabling high-speed processing without requiring a completely complex monolithic system. The control plane and user plane are separated into distinct processing paths.
Solution Approach 2:
A correlation database acts as an intermediary structure between control packet processing and user packet processing. Control information is extracted and stored in the correlation database, which then serves as a reference for correlating user packets with their corresponding control information, enabling high-speed correlation without direct complex interactions between processing modules.
2Loss of information
If control information is not extracted and correlated with user information, then processing speed is maintained, but network visibility and correlation accuracy deteriorate
Solution Approach 1:
The system extracts control information (such as QoS parameters, subscriber identifiers, and session information) from control packets and stores it in the correlation database. This extracted information is then available for rapid correlation with user packets without requiring reprocessing of the original control packets, maintaining processing efficiency while achieving complete correlation.
Solution Approach 2:
Control information is extracted and prepared in advance during control packet processing, before user packets arrive. The correlation database is pre-populated with relevant control information indexed by correlation keys (such as subscriber identifiers or session identifiers), enabling immediate correlation when user packets are processed without delay.
3Productivity
If high-speed packet processing is implemented, then productivity is improved, but measurement precision and correlation accuracy may deteriorate
Solution Approach 1:
The system creates simplified copies of control information (such as subscriber identifiers, QoS parameters, and session keys) and stores them in the correlation database. These copies contain only the essential correlation fields needed for matching user packets, enabling high-speed processing while maintaining accurate correlation. The full control packet data is not stored, only the necessary correlation fields.
Data Source
AI summary
In some implementations, the method may include receiving a control packet. In addition, the method may include decoding the control packet once it has been received. The method may include initiating a session tracking of the control packet. Moreover, the method may include extracting subscriber information from the control packet to create extracted control information. Also, the method may include storing the extracted control information into a control hash database. Further, the method may include receiving a user plane packet. In addition, the method may include load-balancing and packet-preprocessing the user plane packet. The method may include extracting tunnel information from the user plane packet to create extracted tunnel information. Moreover, the method may include matching, by a correlation engine, the extracted tunnel information with the extracted control information to create correlated data. Also, the method may include executing, by the correlation engine, a performance action.