Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts
Recently, there has been an increasing need for new applications and services such as big data, blockchains, vehicle-to-everything (V2X), the Internet of things, 5G, and beyond. Therefore, to maintain quality of service (QoS), accurate network resource planning and forecasting are essential steps fo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/9/3592 |
| _version_ | 1797502734386069504 |
|---|---|
| author | Mohamed Khalafalla Hassan Sharifah Hafizah Syed Ariffin N. Effiyana Ghazali Mutaz Hamad Mosab Hamdan Monia Hamdi Habib Hamam Suleman Khan |
| author_facet | Mohamed Khalafalla Hassan Sharifah Hafizah Syed Ariffin N. Effiyana Ghazali Mutaz Hamad Mosab Hamdan Monia Hamdi Habib Hamam Suleman Khan |
| author_sort | Mohamed Khalafalla Hassan |
| collection | DOAJ |
| description | Recently, there has been an increasing need for new applications and services such as big data, blockchains, vehicle-to-everything (V2X), the Internet of things, 5G, and beyond. Therefore, to maintain quality of service (QoS), accurate network resource planning and forecasting are essential steps for resource allocation. This study proposes a reliable hybrid dynamic bandwidth slice forecasting framework that combines the long short-term memory (LSTM) neural network and local smoothing methods to improve the network forecasting model. Moreover, the proposed framework can dynamically react to all the changes occurring in the data series. Backbone traffic was used to validate the proposed method. As a result, the forecasting accuracy improved significantly with the proposed framework and with minimal data loss from the smoothing process. The results showed that the hybrid moving average LSTM (MLSTM) achieved the most remarkable improvement in the training and testing forecasts, with 28% and 24% for long-term evolution (LTE) time series and with 35% and 32% for the multiprotocol label switching (MPLS) time series, respectively, while robust locally weighted scatter plot smoothing and LSTM (RLWLSTM) achieved the most significant improvement for upstream traffic with 45%; moreover, the dynamic learning framework achieved improvement percentages that can reach up to 100%. |
| first_indexed | 2024-03-10T03:40:21Z |
| format | Article |
| id | doaj.art-b68b7701720e4ee8ab7915cf747120e8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:40:21Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b68b7701720e4ee8ab7915cf747120e82023-11-23T09:20:44ZengMDPI AGSensors1424-82202022-05-01229359210.3390/s22093592Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic ForecastsMohamed Khalafalla Hassan0Sharifah Hafizah Syed Ariffin1N. Effiyana Ghazali2Mutaz Hamad3Mosab Hamdan4Monia Hamdi5Habib Hamam6Suleman Khan7School of Electrical Engineering, University Technology Malaysia, Skudai, Johor 81310, MalaysiaSchool of Electrical Engineering, University Technology Malaysia, Skudai, Johor 81310, MalaysiaSchool of Electrical Engineering, University Technology Malaysia, Skudai, Johor 81310, MalaysiaSchool of Telecommunication Engineering, Future University, Khartoum 10553, SudanDepartment of Computer Science, University of São Paulo, São Paulo 05508-090, BrazilDepartment of Information Technology, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaFaculty of Engineering, Uni de Moncton, Moncton, NB E1A3E9, CanadaSchool of Psychology and Computer Science, University of Central Lancashire, Preston PR1 2HE, UKRecently, there has been an increasing need for new applications and services such as big data, blockchains, vehicle-to-everything (V2X), the Internet of things, 5G, and beyond. Therefore, to maintain quality of service (QoS), accurate network resource planning and forecasting are essential steps for resource allocation. This study proposes a reliable hybrid dynamic bandwidth slice forecasting framework that combines the long short-term memory (LSTM) neural network and local smoothing methods to improve the network forecasting model. Moreover, the proposed framework can dynamically react to all the changes occurring in the data series. Backbone traffic was used to validate the proposed method. As a result, the forecasting accuracy improved significantly with the proposed framework and with minimal data loss from the smoothing process. The results showed that the hybrid moving average LSTM (MLSTM) achieved the most remarkable improvement in the training and testing forecasts, with 28% and 24% for long-term evolution (LTE) time series and with 35% and 32% for the multiprotocol label switching (MPLS) time series, respectively, while robust locally weighted scatter plot smoothing and LSTM (RLWLSTM) achieved the most significant improvement for upstream traffic with 45%; moreover, the dynamic learning framework achieved improvement percentages that can reach up to 100%.https://www.mdpi.com/1424-8220/22/9/3592traffic forecastslicelocal smoothingLSTMdynamic learning |
| spellingShingle | Mohamed Khalafalla Hassan Sharifah Hafizah Syed Ariffin N. Effiyana Ghazali Mutaz Hamad Mosab Hamdan Monia Hamdi Habib Hamam Suleman Khan Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts Sensors traffic forecast slice local smoothing LSTM dynamic learning |
| title | Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts |
| title_full | Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts |
| title_fullStr | Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts |
| title_full_unstemmed | Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts |
| title_short | Dynamic Learning Framework for Smooth-Aided Machine-Learning-Based Backbone Traffic Forecasts |
| title_sort | dynamic learning framework for smooth aided machine learning based backbone traffic forecasts |
| topic | traffic forecast slice local smoothing LSTM dynamic learning |
| url | https://www.mdpi.com/1424-8220/22/9/3592 |
| work_keys_str_mv | AT mohamedkhalafallahassan dynamiclearningframeworkforsmoothaidedmachinelearningbasedbackbonetrafficforecasts AT sharifahhafizahsyedariffin dynamiclearningframeworkforsmoothaidedmachinelearningbasedbackbonetrafficforecasts AT neffiyanaghazali dynamiclearningframeworkforsmoothaidedmachinelearningbasedbackbonetrafficforecasts AT mutazhamad dynamiclearningframeworkforsmoothaidedmachinelearningbasedbackbonetrafficforecasts AT mosabhamdan dynamiclearningframeworkforsmoothaidedmachinelearningbasedbackbonetrafficforecasts AT moniahamdi dynamiclearningframeworkforsmoothaidedmachinelearningbasedbackbonetrafficforecasts AT habibhamam dynamiclearningframeworkforsmoothaidedmachinelearningbasedbackbonetrafficforecasts AT sulemankhan dynamiclearningframeworkforsmoothaidedmachinelearningbasedbackbonetrafficforecasts |