Research on Wireless Network Optimization based on Attention Mechanism

LI Mingchun; LI Ming; WANG Suyi

doi:10.13756/j.gtxyj.2024.230146

您当前的位置：

首页 >

文章列表页 >

Research on Wireless Network Optimization based on Attention Mechanism

更新时间：2024-08-05

- Research on Wireless Network Optimization based on Attention Mechanism
- Study on Optical Communications Issue 4, Pages: 23014601-23014604(2024)
- 作者机构：
  
  烽火通信科技股份有限公司，武汉　430074
- 作者简介：
- 基金信息：
- DOI：10.13756/j.gtxyj.2024.230146
  CLC： TN929
- Published：10 August 2024，
  
  Received：15 September 2023，
  
  Revised：19 October 2023，
- 稿件说明：
扫描看全文
李明春，李明，王素椅，等. 基于注意力机制的无线网络优化研究[J]. 光通信研究，2024(4)：230146.

Li M C, Li M, Wang S Y, et al. Research on Wireless Network Optimization based on Attention Mechanism [J]. Study on Optical Communications, 2024(4)：230146.
李明春，李明，王素椅，等. 基于注意力机制的无线网络优化研究[J]. 光通信研究，2024(4)：230146. DOI： 10.13756/j.gtxyj.2024.230146.

Li M C, Li M, Wang S Y, et al. Research on Wireless Network Optimization based on Attention Mechanism [J]. Study on Optical Communications, 2024(4)：230146. DOI： 10.13756/j.gtxyj.2024.230146.

摘要

【目的】

无线网络设备故障诊断的意义在于帮助解决网络连接问题，提高用户体验，确保网络的稳定性和可靠性，然而现有方法的准确率有待进一步提高。

【方法】

针对该问题，文章在卷积神经网络（CNN）－门控循环单元（GRU）网络结构中引入了注意力机制，提出了一种基于CNN-GRU-Attention网络结构的无线网络设备故障诊断方法。

【结果】

相较于其他方法，文章所提方法在仿真实验中模型的准确率从91%提升到了98%，提升效果明显。

【结论】

文章所提方法提高了无线网络设备运营的质量和效率，提升了网络容量、功能以及可靠性，满足了人们日益增长的无线网络通信需求。

Abstract

【Objective】

The significance of wireless network equipment troubleshooting can be used to solve the network connection problems

improving user experience

and maintaining network stability and reliability. However

the accuracy of existing methods needs to be further improved.

【Methods】

To address this problem

this paper quotes the attention mechanism in the Convolutional Neural Networks(CNN)- Gated Recurrent Unit (GRU) network structure and proposes a wireless network equipment fault diagnosis method based on the CNN-GRU-Attention network structure.

【Results】

Compared with other methods in the simulation experiment

the method in this paper improved the accuracy of the model from 91% to 98%.

【Conclusion】

Through the research of this article

the quality and efficiency of wireless network equipment operation have been improved. The network capacity

functionality and reliability have also been improved

and people's growing communication needs for wireless networks have been met.

关键词

无线故障诊断准确率注意力机制

Keywords

wirelesstroubleshootingaccuracyattention mechanism

references

李明, 李明春, 刘世超. 基于异常识别与有损压缩的无线AP数仓构建方法[J]. 光通信研究, 2022(5):74-78.

Li M, Li M C, Liu S C. Wireless AP Data Warehouse Construction Method based on Anomaly Identification and Lossy Compression[J]. Study on Optical Communications, 2022(5):74-78.

许江波. 基于超限学习机的WSNs链路质量评估方法[D]. 南昌: 南昌航空大学, 2018.

Xu J B. A Link Quality Estimation Method for WSNs based on Extreme Learning Machine[D]. Nanchang, China: Nanchang Hangkong University, 2018.

Zhou Z H, Feng J. Deep Forest [J]. National Science Review, 2019, 6(1):74-86.

何慕. 基于深度森林的链路质量评估方法[D]. 南昌: 南昌航空大学, 2021.

He M. Link Quality Assessment Method based on Deep Forest[D]. Nanchang, China: Nanchang Hangkong University, 2021.

Wang L N, Mao M X, Xie J L, et al. Accurate Solar PV Power Prediction Interval Method based on Frequency-domain Decomposition and LSTM Model[J]. Energy, 2023, 262:125592.

陈红花, 岑健, 刘溪, 等. 深度学习在化学流程工业故障诊断的研究进展[J]. 计算机工程与应用, 2022, 58(13):48-62.

Chen H H, Cen J, Liu X, et al. Research Progress of Deep Learning in Fault Diagnosis of Chemical Process Industry[J]. Computer Engineering and Applications, 2022, 58(13):48-62.

Stratigakos A, Bachoumis A, Vita V, et al. Short-term Net Load Forecasting with Singular Spectrum Analysis and LSTM Neural Networks[J]. Energies, 2021, 14:4107.

任东方, 马家庆, 何志琴, 等. 基于AVMD-CNN-GRU-Attention的超短期风功率预测研究[J/OL]. 太阳能学报. (2023-07-12)[2023-09-15]. http://doi:10.19912/j.0254-0096.tynxb.2023-0146http://doi:10.19912/j.0254-0096.tynxb.2023-0146.

Ren D F, Ma J Q, He Z Q, et al. Research on Ultra-short-term Wind Power Prediction based on AVMD-CNN-GRU-Attention[J/OL]. Journal of Solar Energy. (2023-07-12)[2023-09-15]. http://doi:10.19912/j.0254-0096.tynxb.2023-0146http://doi:10.19912/j.0254-0096.tynxb.2023-0146.

何其臻. 基于多AP并发场景下WLAN密集部署干扰协调机制研究[D]. 宁波: 宁波大学, 2021.

He Q Z. Research on Interference Coordination Mechanism for Dense WLAN Deployment in Multi-AP Concurrent Scenarios[D]. Ningbo, China: Ningbo University, 2021.

Amina S, Jeroen F, Poorter E D, et al. Survey on Wireless Technology Trade-offs for the Industrial Internet of Things[J]. Sensors, 2020, 20(2):s20020488.

Hassani H, Gringoli F, Leith D J. Quick & Plenty: Achieving Low Delay & High Rate in 802.11ac Edge Networks[J]. Computer Networks, 2021, 187:107820.

魏培瑶, 赵夙, 陈瑾, 等. 面向配电场域网的高可靠路由优化算法研究[J]. 光通信研究, 2023(3):38-45.

Wei P Y, Zhao S, Chen J, et al. Research on High-reliability Routing Optimization Algorithm for Distribution Field Network [J]. Study on Optical Communications, 2023(3):38-45.

Views

下载量

CSCD

CNKI被引量

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

Postal code：430205
Technical support is provided by Beijing Founder electronics co., LTD 鄂ICP备2022010197 鄂公网安备 42011202002092号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：93117 Visits Today：204

⁰