A Method for Fine-Grained Throughput Estimation of Access Points in Enterprise Wireless Networks
A wireless network access and wireless network technology, applied in the field of fine-grained estimation of wireless network access point throughput, can solve the problems of small time granularity prediction error, difficult to guarantee prediction accuracy, large throughput fluctuation, etc. The effect of small time granularity, high training efficiency, and accurate prediction effect
Active Publication Date: 2022-06-17
SOUTHEAST UNIV
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Traditional forecasting methods are often applied to forecasting scenarios with large time granularity, but the throughput fluctuates greatly at small time granularity, and it is difficult to guarantee the accuracy of forecasting
Currently popular nonlinear regression models such as GPR (Gaussian Process Regression Prediction) models have large errors for small time granularity predictions
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0035] The technical solutions of the present invention will be further described below with reference to the accompanying drawings and embodiments.
[0036] like figure 1 As shown, the invention is based on the overall architecture diagram of the wireless network access point throughput prediction based on the ARIMA model. The network access point AP throughput prediction method solves the problem that the traditional wireless network access point AP throughput prediction method is inaccurate for small time granularity prediction. specific:
[0037] Data collection and processing module: Use data collection tools to obtain AP throughput data, and perform data preprocessing operations such as removing abnormal data and feature extraction from the throughput time series, and perform data preprocessing operations on the collected throughput data according to the time window of W. The granularity is subjected to moving average, and finally the dataset X is produced.
[0038] P...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for fine-grained estimation of the throughput of an enterprise wireless network access point. Suitable for enterprise and campus use. First, collect the throughput samples of the wireless network access terminal AP, and perform data processing operations such as outlier processing, windowing and feature extraction on the samples; according to the obtained wireless network characteristic data set, analyze the stability of the wireless network throughput data set If the data set is not stable, the differential operation is performed on the sequence; through the constructed ARIMA model, the throughput of the access point is predicted based on fine-grained time, and the training set is continuously expanded for rolling prediction, and the model is Interval training to optimize training efficiency. This method can achieve a more accurate prediction effect on the premise of a limited training data set, and at the same time optimize the training efficiency, and this method predicts at a smaller time granularity, and can predict a smaller time granularity and a finer throughput Quantitative sequence results.
Description
technical field [0001] The present invention relates to a method for fine-grained estimation of throughput of wireless network access points, which is especially suitable for a method for fine-grained estimation of throughput of wireless network access points used in enterprise parks, and in particular to a method for throughput prediction based on ARIMA model. method. Background technique [0002] Wireless networks play a pivotal role in all walks of life, such as unmanned vehicles, drones, and smart medical care. With the development of information technology, both enterprises and individuals are increasingly dependent on wireless networks. The growing demand and the emergence of various special demand scenarios have made some problems in wireless network technology increasingly prominent. Especially under the conditions of large scale, high density and large traffic, the problems of scarcity of spectrum resources, overlapping network coverage, many transmission errors an...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04L43/0888H04L41/147H04W24/06
CPCH04L43/0888H04L41/147H04W24/06
Inventor 徐琴珍毛喻杨镇安侯坤林张天怡杨绿溪
Owner SOUTHEAST UNIV