NetSel-RF: A Model for Network Selection Based on Multi-Criteria and Supervised Learning
Network selection plays a pivotal role in ensuring efficient handover management. Some existing approaches for network selection may use one criterion, such as RSSI (Received Signal Strength Indicator) or SINR (Signal to Interference Noise Ratio). However, these approaches are reactive and may lead...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/12/4382 |
| _version_ | 1827714260046708736 |
|---|---|
| author | Daniela Alexandra Embus Andres Julián Castillo Fulvio Yesid Vivas Oscar Mauricio Caicedo Armando Ordóñez |
| author_facet | Daniela Alexandra Embus Andres Julián Castillo Fulvio Yesid Vivas Oscar Mauricio Caicedo Armando Ordóñez |
| author_sort | Daniela Alexandra Embus |
| collection | DOAJ |
| description | Network selection plays a pivotal role in ensuring efficient handover management. Some existing approaches for network selection may use one criterion, such as RSSI (Received Signal Strength Indicator) or SINR (Signal to Interference Noise Ratio). However, these approaches are reactive and may lead to incorrect decisions due to the limited information. Other multi-criteria-based approaches use techniques, such as statistical mathematics, heuristics methods, and neural networks, to optimize the network selection. However, these approaches have shortcomings related to their computational complexity and the unnecessary and frequent handovers. This paper introduces NetSel-RF, a multi-criteria model, based on supervised learning, for network selection in WiFi networks. Here, we describe the created dataset, the data preparation and the evaluation of diverse supervised learning techniques (Random Forest, Support Vector Machine, Adaptive Random Forest, Hoeffding Adaptive Tree, and Hoedding Tree techniques). Our evaluation results show that Random Forest outperforms other algorithms in terms of its accuracy and Matthews correlation coefficient. Additionally, NetSel-RF performs better than the Signal Strong First approach and behaves similarly to the Analytic Hierarchy Process–Technique for Order Preferences by Similarity to the Ideal Solution (AHP-TOPSIS) approach in terms of the number of handovers and throughput drops. Unlike the latter, NetSel-RF is proactive and therefore is more efficient regarding Quality of Services (QoS) and Quality of Experience (QoE) since the end-devices perform the handover before the network link quality degrades. |
| first_indexed | 2024-03-10T18:53:13Z |
| format | Article |
| id | doaj.art-572d4b0ef5a44c51bd7bee0a30cf74ce |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T18:53:13Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-572d4b0ef5a44c51bd7bee0a30cf74ce2023-11-20T04:58:55ZengMDPI AGApplied Sciences2076-34172020-06-011012438210.3390/app10124382NetSel-RF: A Model for Network Selection Based on Multi-Criteria and Supervised LearningDaniela Alexandra Embus0Andres Julián Castillo1Fulvio Yesid Vivas2Oscar Mauricio Caicedo3Armando Ordóñez4Departmento de Telemática, Universidad del Cauca, Popayán, Cauca 190002, ColombiaDepartmento de Telemática, Universidad del Cauca, Popayán, Cauca 190002, ColombiaDepartmento de Telemática, Universidad del Cauca, Popayán, Cauca 190002, ColombiaDepartmento de Telemática, Universidad del Cauca, Popayán, Cauca 190002, ColombiaDepartmento de Telemática, Universidad del Cauca, Popayán, Cauca 190002, ColombiaNetwork selection plays a pivotal role in ensuring efficient handover management. Some existing approaches for network selection may use one criterion, such as RSSI (Received Signal Strength Indicator) or SINR (Signal to Interference Noise Ratio). However, these approaches are reactive and may lead to incorrect decisions due to the limited information. Other multi-criteria-based approaches use techniques, such as statistical mathematics, heuristics methods, and neural networks, to optimize the network selection. However, these approaches have shortcomings related to their computational complexity and the unnecessary and frequent handovers. This paper introduces NetSel-RF, a multi-criteria model, based on supervised learning, for network selection in WiFi networks. Here, we describe the created dataset, the data preparation and the evaluation of diverse supervised learning techniques (Random Forest, Support Vector Machine, Adaptive Random Forest, Hoeffding Adaptive Tree, and Hoedding Tree techniques). Our evaluation results show that Random Forest outperforms other algorithms in terms of its accuracy and Matthews correlation coefficient. Additionally, NetSel-RF performs better than the Signal Strong First approach and behaves similarly to the Analytic Hierarchy Process–Technique for Order Preferences by Similarity to the Ideal Solution (AHP-TOPSIS) approach in terms of the number of handovers and throughput drops. Unlike the latter, NetSel-RF is proactive and therefore is more efficient regarding Quality of Services (QoS) and Quality of Experience (QoE) since the end-devices perform the handover before the network link quality degrades.https://www.mdpi.com/2076-3417/10/12/4382network selectionmulti-criteriarandom forestAHP-TOPSISstrongest signal first |
| spellingShingle | Daniela Alexandra Embus Andres Julián Castillo Fulvio Yesid Vivas Oscar Mauricio Caicedo Armando Ordóñez NetSel-RF: A Model for Network Selection Based on Multi-Criteria and Supervised Learning Applied Sciences network selection multi-criteria random forest AHP-TOPSIS strongest signal first |
| title | NetSel-RF: A Model for Network Selection Based on Multi-Criteria and Supervised Learning |
| title_full | NetSel-RF: A Model for Network Selection Based on Multi-Criteria and Supervised Learning |
| title_fullStr | NetSel-RF: A Model for Network Selection Based on Multi-Criteria and Supervised Learning |
| title_full_unstemmed | NetSel-RF: A Model for Network Selection Based on Multi-Criteria and Supervised Learning |
| title_short | NetSel-RF: A Model for Network Selection Based on Multi-Criteria and Supervised Learning |
| title_sort | netsel rf a model for network selection based on multi criteria and supervised learning |
| topic | network selection multi-criteria random forest AHP-TOPSIS strongest signal first |
| url | https://www.mdpi.com/2076-3417/10/12/4382 |
| work_keys_str_mv | AT danielaalexandraembus netselrfamodelfornetworkselectionbasedonmulticriteriaandsupervisedlearning AT andresjuliancastillo netselrfamodelfornetworkselectionbasedonmulticriteriaandsupervisedlearning AT fulvioyesidvivas netselrfamodelfornetworkselectionbasedonmulticriteriaandsupervisedlearning AT oscarmauriciocaicedo netselrfamodelfornetworkselectionbasedonmulticriteriaandsupervisedlearning AT armandoordonez netselrfamodelfornetworkselectionbasedonmulticriteriaandsupervisedlearning |