Research on throughput prediction of 5G network based on LSTM
This paper proposes a wireless network traffic prediction model based on long-term and short-term memory cyclic neural networks. Through simulation experiments, the throughput prediction of 5G wireless networks using different scheduling algorithms for many different types of services is studied. Th...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2022-06-01
|
| Series: | Intelligent and Converged Networks |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.23919/ICN.2022.0006 |
| _version_ | 1798029069809352704 |
|---|---|
| author | Lanlan Li Tao Ye |
| author_facet | Lanlan Li Tao Ye |
| author_sort | Lanlan Li |
| collection | DOAJ |
| description | This paper proposes a wireless network traffic prediction model based on long-term and short-term memory cyclic neural networks. Through simulation experiments, the throughput prediction of 5G wireless networks using different scheduling algorithms for many different types of services is studied. The results verify that the long short-term memory prediction model has acceptable prediction accuracy and algorithm training speed, meets the needs of wireless network traffic prediction, and has a good application prospect. |
| first_indexed | 2024-04-11T19:18:22Z |
| format | Article |
| id | doaj.art-f2e725491c134de2811a5117366e714d |
| institution | Directory Open Access Journal |
| issn | 2708-6240 |
| language | English |
| last_indexed | 2024-04-11T19:18:22Z |
| publishDate | 2022-06-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Intelligent and Converged Networks |
| spelling | doaj.art-f2e725491c134de2811a5117366e714d2022-12-22T04:07:23ZengTsinghua University PressIntelligent and Converged Networks2708-62402022-06-013221722710.23919/ICN.2022.0006Research on throughput prediction of 5G network based on LSTMLanlan Li0Tao Ye1Purple Mountain Labs, Nanjing 210000, ChinaChina Communications Construction Second Harbor Engineering Company Ltd., Wuhan 430040, ChinaThis paper proposes a wireless network traffic prediction model based on long-term and short-term memory cyclic neural networks. Through simulation experiments, the throughput prediction of 5G wireless networks using different scheduling algorithms for many different types of services is studied. The results verify that the long short-term memory prediction model has acceptable prediction accuracy and algorithm training speed, meets the needs of wireless network traffic prediction, and has a good application prospect.https://www.sciopen.com/article/10.23919/ICN.2022.0006wireless networkflow forecastlong short-term memory (lstm)schedulethroughput |
| spellingShingle | Lanlan Li Tao Ye Research on throughput prediction of 5G network based on LSTM Intelligent and Converged Networks wireless network flow forecast long short-term memory (lstm) schedule throughput |
| title | Research on throughput prediction of 5G network based on LSTM |
| title_full | Research on throughput prediction of 5G network based on LSTM |
| title_fullStr | Research on throughput prediction of 5G network based on LSTM |
| title_full_unstemmed | Research on throughput prediction of 5G network based on LSTM |
| title_short | Research on throughput prediction of 5G network based on LSTM |
| title_sort | research on throughput prediction of 5g network based on lstm |
| topic | wireless network flow forecast long short-term memory (lstm) schedule throughput |
| url | https://www.sciopen.com/article/10.23919/ICN.2022.0006 |
| work_keys_str_mv | AT lanlanli researchonthroughputpredictionof5gnetworkbasedonlstm AT taoye researchonthroughputpredictionof5gnetworkbasedonlstm |