Service-Aware Wi-Fi Traffic Classifier for Power-Save Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in accurately detecting traffic types and identifying quality of service requirements, particularly with the increasing use of security protocols like HTTPS and high-volume traffic, leading to high complexity and hardware costs in real-time inspection and classification.
Innovation Solution
A traffic classifier system utilizing a two-stage random forest model and time domain autoencoder is trained with both offline and online data to detect real-time and streaming traffic, enabling configuration of service level agreements based on detection results and distributing traffic detection across multiple mesh agents, while also selecting power save parameters to balance latency and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deep packet inspection is used for traffic classification, then traffic type detection accuracy is improved, but device complexity and hardware cost increase
Solution Approach 1:
The patent extracts only the essential traffic characteristics needed for classification (packet size, interval, rate) rather than performing full deep packet inspection of packet contents. This extraction approach maintains detection accuracy for common traffic types while significantly reducing computational complexity and hardware requirements.
Solution Approach 2:
The patent employs lightweight machine learning models (random forest, autoencoders) that can be trained offline and deployed with minimal computational resources. These models act as disposable, pre-trained classifiers that require no complex real-time inspection infrastructure, reducing hardware costs while maintaining classification effectiveness.
2Reliability
If real-time traffic inspection is performed, then service level agreement configuration is improved, but processing time and system complexity increase
Solution Approach 1:
The patent performs preliminary training of machine learning models offline using historical traffic data. This preliminary action creates pre-configured classifiers that can be rapidly deployed in real-time without requiring complex online training, thus improving service level agreement configuration while minimizing real-time processing time.
Solution Approach 2:
The system dynamically adapts traffic classification parameters based on observed traffic patterns and service level requirements. By making the classification system dynamic rather than static, it can quickly respond to changing traffic conditions without requiring exhaustive real-time inspection, balancing reliability with processing speed.
Data Source
AI summary
This disclosure provides methods, components, devices and systems for traffic classifier for service aware Wi-Fi operation. The techniques described herein support the creation of a common traffic detection model on an access point (AP) or client. In some examples, the model may reclassify traffic over time to avoid detection failure during an atypical traffic pattern period of an interested flow. The traffic classifier may provide traffic detection results and traffic activity such that a power saving operation may be enabled. Some aspects more specifically relate to mechanisms according to which the AP or client may select power save parameters associated with a classified traffic flow to the AP or client.