Traffic Steering Inference via Channel and Load Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques lack a frame structure, data collection method, and method for using learning data for implementing machine learning in traffic steering during roaming in wireless communication systems.
Innovation Solution
A communication apparatus that transmits an inference request to a server with information about wireless channel quality, access point load conditions, traffic characteristics, and time-series data, and uses the server's inference result to determine whether to execute traffic steering and provide information on communication changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning is employed for optimization of traffic steering, then communication efficiency is improved, but data collection framework and implementation methods are missing
Solution Approach 1:
The patent divides the data collection system into separate functional components: a data collection framework that gathers wireless channel quality, AP load, and traffic characteristics; a data storage unit that persists collected data; and an inference server that processes data for machine learning models. This segmentation allows each component to be independently developed and optimized while working together to enable traffic steering optimization.
Solution Approach 2:
The patent introduces an inference server as an intermediary component between the data collection framework and the machine learning models. This intermediary collects raw data from multiple sources, stores it in a data storage unit, and then feeds processed data to inference models, enabling the system to leverage machine learning for traffic steering optimization.
2Reliability
If traffic steering processing is executed to tune connection state and communication path, then communication characteristics are improved, but data for machine learning inference is insufficient
Solution Approach 1:
The patent implements a feedback mechanism where the system collects data about wireless channel quality, AP load conditions, and traffic characteristics, stores this data, and uses it for machine learning inference. The inference results then feed back into traffic steering decisions, creating a closed-loop system that continuously improves communication characteristics while accumulating learning data.
Solution Approach 2:
The patent performs preliminary data collection and storage before machine learning inference is executed. The data collection framework continuously gathers information about wireless channels, AP loads, and traffic patterns, storing this data in advance so that when inference is needed, the required data is already available for processing.
3Productivity
If multiple access points are connected in distributed manner, then network load is balanced, but data collection and processing complexity increases
Solution Approach 1:
The patent designs a universal data collection framework that can operate across multiple access points and collect various types of data (wireless channel quality, AP load, traffic characteristics). This multi-functional framework can be deployed in different network configurations and serves multiple purposes: monitoring, optimization, and machine learning training, thereby managing complexity through a single versatile system.
Data Source
AI summary
A communication apparatus transmits, to a server, an inference request including all or part of information about wireless channel quality, information indicating conditions of loads of a plurality of access points, information about characteristics of traffic, and time-series data on any of the foregoing pieces of information in a unit of time. The inference request requests inference of quality of communication with another communication apparatus in a case where traffic steering processing for tuning at least any one of a connection state and a communication path between the communication apparatus and another communication apparatus is executed. The communication apparatus acquires an inference result for the quality of the communication from the server, determines whether to execute the traffic steering based on the inference result, and provides information about change of the communication to the another communication apparatus in a case where the traffic steering is determined to be executed.