Wireless Access Point Throughput Prediction via ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wireless computing systems fail to accurately predict the throughput capacity of wireless access points, leading to improper system design and inefficient data load distribution, due to inaccuracies in determining the number of access points required to service user devices.
Innovation Solution
A capacity prediction system that logs throughput data from multiple access points, analyzes characteristics such as type, location, and interference, and uses machine learning techniques like generalized linear models or gradient boosting to predict the maximum capacity based on similar access points, allowing for more accurate predictions and optimization of data throughput.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If conventional wireless computing systems select the number of wireless access points based on expected number of user devices, then system deployment is simplified, but throughput capacity prediction accuracy deteriorates
Solution Approach 1:
The system performs preliminary actions by collecting and storing historical throughput data from access points before making capacity predictions. This pre-collection of operational data enables accurate predictions without complicating the actual deployment process, as the data gathering occurs during normal operation rather than as a preliminary deployment step.
Solution Approach 2:
The system uses feedback mechanisms by continuously monitoring actual throughput performance and comparing it against predicted capacity. This feedback loop allows the system to refine its predictions over time while maintaining simple deployment procedures, as the feedback is incorporated through data collection and analysis rather than complex deployment adjustments.
2Device complexity
If conventional systems use simple deployment methods, then device complexity is reduced, but data load distribution efficiency deteriorates
Solution Approach 1:
The system implements self-service by automatically analyzing historical throughput data and generating capacity predictions without requiring manual configuration or complex system setup. The access points and network infrastructure serve themselves by collecting their own operational data and using machine learning models to determine capacity, eliminating the need for complex manual planning while improving data load distribution efficiency.
Solution Approach 2:
The system replaces mechanical/manual system configuration with automated machine learning-based prediction mechanisms. Instead of requiring manual calculation and configuration of access point capacity, the system uses computational models that process historical data automatically, reducing device complexity while enhancing data load distribution efficiency through intelligent automation.
3Device complexity
If inaccurate throughput predictions are used, then system design is simplified, but reliability deteriorates
Solution Approach 1:
The system performs preliminary data collection and analysis actions to establish accurate capacity predictions before system design finalization. By pre-processing historical throughput data and training machine learning models in advance, the system achieves reliable capacity determination without complicating the final system design, as the complexity is absorbed in the preliminary data preparation phase.
Solution Approach 2:
The system uses feedback from actual throughput measurements to validate and refine capacity predictions. This feedback mechanism ensures reliable throughput capacity determination by continuously comparing predicted versus actual performance, while maintaining simple system design as the feedback is integrated through automated data analysis rather than complex design adjustments.
Data Source
AI summary
Predicting data throughput with a user device comprises a wireless system supported by wireless access points receiving signals from the user device. A wireless prediction system receives data from the wireless system, where the data comprises characteristics of the wireless access point, characteristics of communications with user computing devices, and data throughput statistics. The prediction system categorizes the received data based on one or more of a set of characteristics and determines a maximum data throughput capacity for each of the one or more wireless access points for each of the one or more set of characteristics. The system receives a request for a prediction of data throughput capacity for a particular wireless access point and, based on the characteristics of the particular wireless access point, determines an estimated data throughput capacity based on data throughputs of wireless access points having similar characteristics.