Service-Chained Probe Data Fabric for Cellular Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Customers of cellular networks, such as enterprise customers, lack access to meaningful and insightful data and metadata generated by network resources, hindering their ability to manage and optimize network usage effectively.
Innovation Solution
An adaptive service-chained probe data generation platform that provides customized service-chained probe data to customers by combining measurements from multiple probes, using intelligent data collectors, and leveraging machine learning models to generate predictive data and performance indicators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If customers access raw probe data from network resources, then data availability improves, but data usability and insight quality deteriorate due to lack of processing and contextualization
Solution Approach 1:
The system performs preliminary actions by pre-processing, aggregating, and contextualizing probe data before it reaches the customer. Data collectors gather raw data from multiple probes, apply filtering and aggregation logic, and prepare processed data in advance, so customers receive ready-to-use insights rather than raw unprocessed data requiring their own processing infrastructure.
Solution Approach 2:
The patent introduces an intermediary data processing layer between the network probes and customers. This intermediary system includes data collectors, processing engines, and service modules that transform raw probe data into meaningful metrics and insights, acting as a mediator that bridges the gap between data generation and data consumption.
2Measurement precision
If multiple probes are deployed to monitor network resources, then measurement coverage improves, but system complexity increases due to data integration requirements
Solution Approach 1:
The system merges data from multiple independent probes into a unified data stream. Data collectors aggregate measurements from multiple probes monitoring different network resources, combine them with contextual information, and present integrated insights, reducing the complexity customers would face if they tried to integrate multiple probe systems themselves.
Solution Approach 2:
The patent creates a universal data collection and processing platform that can handle multiple probe types and network resources through a single interface. The system is designed to be multi-functional, accommodating various probe configurations and data formats while providing consistent processed output, eliminating the need for separate integration systems for each probe.
3Loss of time
If real-time probe data is provided to customers, then response time improves, but data processing overhead increases
Solution Approach 1:
The system applies partial processing by selectively filtering and aggregating only the most relevant probe data in real-time, rather than processing all raw data completely. It provides real-time responses for critical metrics while using less intensive processing for secondary information, balancing response time requirements with processing overhead.
Solution Approach 2:
The system performs preliminary filtering, aggregation, and prioritization of probe data before real-time delivery to customers. By pre-processing data to identify and extract only the most time-critical information, it reduces the processing overhead required for real-time response while maintaining fast response times for important metrics.
Data Source
AI summary
Technologies for providing service-chained probe data in a cellular network are described. One method includes generating a data fabric from data from a plurality of probes of a cellular network. The method further includes determining a first subset of the data fabric that is associated with a target key performance indicator of the cellular network. The method further includes determining a key performance value associated with the target key performance indicator based on the first subset of the data fabric. The method further includes providing the key performance value to a northbound application associated with the cellular network.