WLAN Traffic Prediction Using Multi-Factor AP Control Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional traffic prediction methods in wireless local area networks (WLAN) lack consideration of comprehensive network factors, leading to inaccurate predictions and poor user experience due to improper network adjustments and high computation complexity.
Innovation Solution
A control apparatus and method that utilizes communication condition data, including RSSI, negotiation rate, network topology, and traffic usage behavior, to train a prediction model for accurate traffic probability patterns, enabling actions such as connection switching, power/bandwidth adjustments, and security checks based on predicted traffic patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional traffic prediction methods are used in WLAN, then the network can perform basic traffic forecasting, but the prediction accuracy is low due to lack of comprehensive network factors consideration
Solution Approach 1:
The patent combines multiple diverse network factors including communication conditions (RSSI, negotiation rate), network topology, application types, and traffic usage behaviors into a unified traffic prediction model. This merging of heterogeneous data sources enables comprehensive analysis and significantly improves traffic prediction accuracy compared to conventional methods that consider only limited factors.
Solution Approach 2:
The prediction model is designed to handle multiple types of network factors and traffic patterns universally. It can process various communication conditions, topology structures, and traffic characteristics through a single integrated framework, making the system adaptable to different WLAN scenarios while maintaining high prediction accuracy.
2Measurement precision
If conventional traffic prediction methods are used in WLAN, then the system structure can be kept simple, but the prediction accuracy deteriorates due to poor network adjustments
Solution Approach 1:
The patent segments the traffic prediction system into distinct functional modules: communication condition acquisition module, traffic prediction module, and network adjustment module. Each module handles specific tasks independently, which organizes the complexity into manageable segments while achieving high prediction accuracy through their coordinated operation.
Solution Approach 2:
The patent introduces a prediction model as an intermediary component that processes communication condition data and generates traffic predictions. This intermediary layer separates the data acquisition from the prediction logic and adjustment actions, allowing each component to be optimized independently while maintaining overall system accuracy.
3Measurement precision
If comprehensive traffic prediction is implemented, then accurate traffic forecasting can be achieved, but the computation complexity increases
Solution Approach 1:
The patent performs preliminary processing of communication condition data before feeding it into the prediction model. Communication conditions are collected and pre-processed in advance, allowing the prediction model to receive organized input data and reduce computation complexity during the actual prediction phase while maintaining accurate forecasting capabilities.
4Reliability
If traffic prediction is used for network adjustments, then user experience can be improved, but improper adjustments may occur due to inaccurate predictions
Solution Approach 1:
The patent implements a feedback mechanism where traffic predictions are used to guide network adjustments (such as bandwidth allocation and parameter optimization), and the actual traffic outcomes are fed back to validate and refine the prediction model. This closed-loop feedback ensures that network adjustments are based on accurate predictions and continuously improves prediction accuracy over time, enhancing overall network stability.
Data Source
Figure 1
Figure 2~3A
Figure 3B
AI summary
This disclosure provides a control apparatus, a model training apparatus, and a control method and a model training method for an access point (AP) connected with a client device. The control method includes: obtaining communication condition data of the client device at a given time; and predicting a traffic probability pattern of the client device at the given time by using the communication condition data, time information related to the given time and a prediction model.