Distributed Routing Table for Local Data Termination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The current Evolved Packet Core (EPC) network architecture is not suitable for efficiently processing locally terminated data, which can improve security and reduce delay in communication, especially for delay-sensitive applications like real-time gaming, due to its centralized deployment of Packet Data Network Gateways (PGWs).
Innovation Solution
A distributed hash table (DHT) is used to maintain a distributed routing table (DRT) across multiple packet processing units (PPUs) in a communications network, where each PPU stores a portion of the routing table entries based on a key-value pair system, allowing efficient lookup and routing of data packets without relying on a hierarchical structure of Serving Gateways and Packet Data Network Gateways.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a centralized PGW architecture is used, then network management and control is simplified, but locally terminated data processing efficiency deteriorates and delay increases
Solution Approach 1:
The patent segments the centralized PGW architecture into multiple distributed PPUs (Packet Processing Units). Each PPU can independently process data packets for locally terminated data, eliminating the single point of congestion. The routing table is also segmented and distributed across multiple PPUs using a distributed hash table (DHT), allowing parallel lookup operations and reducing centralized bottlenecks.
Solution Approach 2:
The patent introduces a new dimensional approach by implementing a flat, distributed network topology instead of the traditional hierarchical structure. Data packets can be routed directly between PPUs in parallel, adding a spatial dimension to data flow that bypasses the sequential processing constraints of centralized architecture, thereby reducing delay.
2Ease of operation
If a centralized PGW architecture is used, then network control is simplified, but security for locally terminated data deteriorates
Solution Approach 1:
The patent segments the network control function across multiple distributed PPUs rather than concentrating it in a single centralized PGW. This segmentation creates multiple independent security domains, where a security breach in one PPU does not necessarily compromise the entire network. Each PPU maintains its own routing decisions and data processing, isolating potential security threats.
3Stability of the object's composition
If a hierarchical SGW/PGW structure is used, then network architecture is well-defined, but adaptability to locally terminated data deteriorates
Solution Approach 1:
The patent inverts the traditional hierarchical approach by implementing a flat, peer-to-peer distributed architecture. Instead of data packets flowing upward through multiple hierarchical levels (SGW to PGW), the inverted architecture allows direct horizontal routing between PPUs. This inversion enables local data to be terminated at the appropriate PPU without traversing upward and downward through the hierarchy, significantly improving adaptability.
Solution Approach 2:
The patent implements dynamic routing capabilities where PPUs can adaptively determine the optimal destination for data packets based on real-time network conditions and destination IP addresses. The distributed routing table allows dynamic updates and flexible reconfiguration, enabling the network to adapt to varying local termination requirements without rigid hierarchical constraints.
4Productivity
If multiple PPUs are used for distributed processing, then local data processing efficiency is improved, but routing table management complexity increases
Solution Approach 1:
The patent introduces a distributed hash table (DHT) as an intermediary mechanism that automatically manages routing table entries across multiple PPUs. The DHT algorithm acts as a mediator that determines which PPU should store and manage each routing entry based on hash functions of destination IP addresses. This intermediary automates the complex task of distributed routing table management, reducing the burden on individual PPUs while maintaining high processing throughput.
Data Source
AI summary
A non-transitory computer readable medium has instructions stored therein to be executed by a packet processing unit (PPU) in a communications network to allow a plurality of PPUs in the communication network to route data packets. The plurality of PPUs collectively maintain a distributed hash table (DHT). The DHT stores a distributed routing table (DRT), where the DRT includes a DRT entry that maps a key to a value. The key is based on a destination Internet Protocol (IP) address and an access point name (APN) associated with an IP session of a user entity (UE). The value represents both an IP address of one of the plurality of PPUs currently serving the IP session of the UE and an IP session identifier that identifies, to that PPU currently serving the IP session of the UE, the IP session of the UE.