Intelligent Router Data Object Extraction in 5G Core
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern telecommunications systems face inefficiencies in processing and delivering multimedia content due to the limitations of traditional packet-switching methods, which do not effectively utilize advanced processing capabilities at the network edge, leading to suboptimal bandwidth usage and latency.
Innovation Solution
The implementation of intelligent routers within data pipelines that include solid-state memory devices, graphical processing units, and packet monitoring functions, allowing for the identification and extraction of data objects from data packets, and their transmission to client devices, while decommissioning after delivery, using domain-specific programming languages like P4 for enhanced processing and routing operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional packet-switching methods are used, then network infrastructure is simple and easy to maintain, but data processing efficiency is low and bandwidth usage is suboptimal
Solution Approach 1:
The patent segments the network infrastructure by introducing intelligent routers that operate at the network edge, separating data packet handling from data object processing. This allows traditional core network infrastructure to remain simple while edge devices perform advanced processing, resolving the contradiction between processing efficiency and infrastructure complexity
Solution Approach 2:
The patent introduces intelligent routers as intermediary devices between traditional network infrastructure and client devices. These routers include solid-state memory devices, graphical processing units, and packet monitoring functions that enable efficient data object extraction and delivery without requiring changes to the core network infrastructure
2Speed
If traditional packet-switching methods are used, then network infrastructure is simple, but network latency is high
Solution Approach 1:
The patent implements preliminary action by pre-extracting data objects from data packets at the network edge using intelligent routers with solid-state memory devices. This preparation work is done in advance before client requests arrive, enabling faster response times and reduced latency when actual data delivery is needed
Solution Approach 2:
The patent replaces traditional software-based packet processing with hardware-accelerated processing using graphical processing units and solid-state memory devices in intelligent routers. This substitution of mechanical/hardware systems for software processes significantly reduces processing latency
3Loss of energy
If traditional packet-switching methods are used, then bandwidth usage is suboptimal, but device complexity is low
Solution Approach 1:
The patent extracts data objects from data packets at the network edge using intelligent routers with packet monitoring functions. This extraction enables selective caching and optimized delivery of only the necessary data objects to client devices, improving bandwidth utilization by avoiding transmission of unnecessary packet overhead and enabling parallel delivery to multiple clients
Data Source
AI summary
Aspects of the subject disclosure may include, for example, performing steps including monitoring a plurality of data packets in a data pipeline of a network, such as a User Plane Function of a 5G Core, where the monitoring can include analyzing header information associated with the plurality of data packets, identifying a first data object in the plurality of data packets according to the monitoring of the plurality of data packets, where the identifying the first data object in the plurality of data packets can further comprise identifying metadata associated with the first data object, switching a first set of data packets of the plurality of data packets associated with the first data object to an intelligent router for extracting the first data object from the first set of data packets to generate an extracted first data object responsive to the identifying the first data object in the plurality of data packets, and transmitting the extracted first data object to a client device via the data pipeline of the network. Other embodiments are disclosed.