Mobile Network Configuration Recommendation Using Deep Generative Graph Neural Network
There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to su...
Gespeichert in:
| Veröffentlicht in: | IEEE networking letters 2024-09, Vol.6 (3), p.179-182 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 182 |
|---|---|
| container_issue | 3 |
| container_start_page | 179 |
| container_title | IEEE networking letters |
| container_volume | 6 |
| creator | Piroti, Shirwan Chawla, Ashima Zanouda, Tahar |
| description | There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to sub-optimal results. To improve this, a framework using a Deep Generative Graph Neural Network (GNN) is proposed. It encodes the network into a graph, extracts subgraphs for each RAN node, and employs a Siamese GNN (S-GNN) to learn embeddings. The framework recommends configuration parameters for a multitude of parameters and detects misconfigurations, handling both network expansion and existing cell reconfiguration. Tested on real-world data, the model surpasses baselines, demonstrating accuracy, generalizability, and robustness against concept drift. |
| doi_str_mv | 10.1109/LNET.2024.3422482 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_LNET_2024_3422482</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10584078</ieee_id><sourcerecordid>3120655792</sourcerecordid><originalsourceid>FETCH-LOGICAL-c912-d9cbf041517dad516c845df83cd3dd978dbb5035c9837936947e6a5ae97f6bb3</originalsourceid><addsrcrecordid>eNpNkF1LwzAUhoMoOOZ-gOBFwevOfDbJpcw5hTlBp7chTU5n59bUdFP897Z0wq7OOfC874EHoUuCx4RgfTNfTJdjiikfM04pV_QEDaiQWcqIyE6P9nM0apo1xphirqRiA_T-FPJyA8kCdj8hfiaTUBXlah_trgxV8gIubLdQ-f58a8pqldwB1MkMKuigb0hm0dYfbUEb2vz3XKCzwm4aGB3mEL3eT5eTh3T-PHuc3M5TpwlNvXZ5gTkRRHrrBcmc4sIXijnPvNdS-TwXmAmnFZOaZZpLyKywoGWR5Tkbouu-tY7haw_NzqzDPlbtQ8MIxZkQUtOWIj3lYmiaCIWpY7m18dcQbDp_pvNnOn_m4K_NXPWZEgCOeKE4br39AfEJbEw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3120655792</pqid></control><display><type>article</type><title>Mobile Network Configuration Recommendation Using Deep Generative Graph Neural Network</title><source>IEEE Electronic Library (IEL)</source><creator>Piroti, Shirwan ; Chawla, Ashima ; Zanouda, Tahar</creator><creatorcontrib>Piroti, Shirwan ; Chawla, Ashima ; Zanouda, Tahar</creatorcontrib><description>There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to sub-optimal results. To improve this, a framework using a Deep Generative Graph Neural Network (GNN) is proposed. It encodes the network into a graph, extracts subgraphs for each RAN node, and employs a Siamese GNN (S-GNN) to learn embeddings. The framework recommends configuration parameters for a multitude of parameters and detects misconfigurations, handling both network expansion and existing cell reconfiguration. Tested on real-world data, the model surpasses baselines, demonstrating accuracy, generalizability, and robustness against concept drift.</description><identifier>ISSN: 2576-3156</identifier><identifier>EISSN: 2576-3156</identifier><identifier>DOI: 10.1109/LNET.2024.3422482</identifier><identifier>CODEN: INLEBB</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Accuracy ; Computer architecture ; Configurations ; Decoding ; graph neural network ; Graph neural networks ; Graph theory ; Long Term Evolution ; Parameters ; Reconfiguration ; siamese neural network ; Telecom network configuration management ; Training ; Vectors</subject><ispartof>IEEE networking letters, 2024-09, Vol.6 (3), p.179-182</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c912-d9cbf041517dad516c845df83cd3dd978dbb5035c9837936947e6a5ae97f6bb3</cites><orcidid>0009-0007-8954-2293 ; 0000-0001-5933-3107 ; 0009-0005-3646-600X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10584078$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27923,27924,54757</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10584078$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Piroti, Shirwan</creatorcontrib><creatorcontrib>Chawla, Ashima</creatorcontrib><creatorcontrib>Zanouda, Tahar</creatorcontrib><title>Mobile Network Configuration Recommendation Using Deep Generative Graph Neural Network</title><title>IEEE networking letters</title><addtitle>LNET</addtitle><description>There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to sub-optimal results. To improve this, a framework using a Deep Generative Graph Neural Network (GNN) is proposed. It encodes the network into a graph, extracts subgraphs for each RAN node, and employs a Siamese GNN (S-GNN) to learn embeddings. The framework recommends configuration parameters for a multitude of parameters and detects misconfigurations, handling both network expansion and existing cell reconfiguration. Tested on real-world data, the model surpasses baselines, demonstrating accuracy, generalizability, and robustness against concept drift.</description><subject>Accuracy</subject><subject>Computer architecture</subject><subject>Configurations</subject><subject>Decoding</subject><subject>graph neural network</subject><subject>Graph neural networks</subject><subject>Graph theory</subject><subject>Long Term Evolution</subject><subject>Parameters</subject><subject>Reconfiguration</subject><subject>siamese neural network</subject><subject>Telecom network configuration management</subject><subject>Training</subject><subject>Vectors</subject><issn>2576-3156</issn><issn>2576-3156</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkF1LwzAUhoMoOOZ-gOBFwevOfDbJpcw5hTlBp7chTU5n59bUdFP897Z0wq7OOfC874EHoUuCx4RgfTNfTJdjiikfM04pV_QEDaiQWcqIyE6P9nM0apo1xphirqRiA_T-FPJyA8kCdj8hfiaTUBXlah_trgxV8gIubLdQ-f58a8pqldwB1MkMKuigb0hm0dYfbUEb2vz3XKCzwm4aGB3mEL3eT5eTh3T-PHuc3M5TpwlNvXZ5gTkRRHrrBcmc4sIXijnPvNdS-TwXmAmnFZOaZZpLyKywoGWR5Tkbouu-tY7haw_NzqzDPlbtQ8MIxZkQUtOWIj3lYmiaCIWpY7m18dcQbDp_pvNnOn_m4K_NXPWZEgCOeKE4br39AfEJbEw</recordid><startdate>202409</startdate><enddate>202409</enddate><creator>Piroti, Shirwan</creator><creator>Chawla, Ashima</creator><creator>Zanouda, Tahar</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0009-0007-8954-2293</orcidid><orcidid>https://orcid.org/0000-0001-5933-3107</orcidid><orcidid>https://orcid.org/0009-0005-3646-600X</orcidid></search><sort><creationdate>202409</creationdate><title>Mobile Network Configuration Recommendation Using Deep Generative Graph Neural Network</title><author>Piroti, Shirwan ; Chawla, Ashima ; Zanouda, Tahar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c912-d9cbf041517dad516c845df83cd3dd978dbb5035c9837936947e6a5ae97f6bb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Computer architecture</topic><topic>Configurations</topic><topic>Decoding</topic><topic>graph neural network</topic><topic>Graph neural networks</topic><topic>Graph theory</topic><topic>Long Term Evolution</topic><topic>Parameters</topic><topic>Reconfiguration</topic><topic>siamese neural network</topic><topic>Telecom network configuration management</topic><topic>Training</topic><topic>Vectors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Piroti, Shirwan</creatorcontrib><creatorcontrib>Chawla, Ashima</creatorcontrib><creatorcontrib>Zanouda, Tahar</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE networking letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Piroti, Shirwan</au><au>Chawla, Ashima</au><au>Zanouda, Tahar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Mobile Network Configuration Recommendation Using Deep Generative Graph Neural Network</atitle><jtitle>IEEE networking letters</jtitle><stitle>LNET</stitle><date>2024-09</date><risdate>2024</risdate><volume>6</volume><issue>3</issue><spage>179</spage><epage>182</epage><pages>179-182</pages><issn>2576-3156</issn><eissn>2576-3156</eissn><coden>INLEBB</coden><abstract>There are vast number of configurable parameters in a Radio Access Telecom Network. A significant amount of these parameters is configured by Radio Node or cell based on their deployment setting. Traditional methods rely on domain knowledge for individual parameter configuration, often leading to sub-optimal results. To improve this, a framework using a Deep Generative Graph Neural Network (GNN) is proposed. It encodes the network into a graph, extracts subgraphs for each RAN node, and employs a Siamese GNN (S-GNN) to learn embeddings. The framework recommends configuration parameters for a multitude of parameters and detects misconfigurations, handling both network expansion and existing cell reconfiguration. Tested on real-world data, the model surpasses baselines, demonstrating accuracy, generalizability, and robustness against concept drift.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LNET.2024.3422482</doi><tpages>4</tpages><orcidid>https://orcid.org/0009-0007-8954-2293</orcidid><orcidid>https://orcid.org/0000-0001-5933-3107</orcidid><orcidid>https://orcid.org/0009-0005-3646-600X</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2576-3156 |
| ispartof | IEEE networking letters, 2024-09, Vol.6 (3), p.179-182 |
| issn | 2576-3156 2576-3156 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_LNET_2024_3422482 |
| source | IEEE Electronic Library (IEL) |
| subjects | Accuracy Computer architecture Configurations Decoding graph neural network Graph neural networks Graph theory Long Term Evolution Parameters Reconfiguration siamese neural network Telecom network configuration management Training Vectors |
| title | Mobile Network Configuration Recommendation Using Deep Generative Graph Neural Network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T21%3A15%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Mobile%20Network%20Configuration%20Recommendation%20Using%20Deep%20Generative%20Graph%20Neural%20Network&rft.jtitle=IEEE%20networking%20letters&rft.au=Piroti,%20Shirwan&rft.date=2024-09&rft.volume=6&rft.issue=3&rft.spage=179&rft.epage=182&rft.pages=179-182&rft.issn=2576-3156&rft.eissn=2576-3156&rft.coden=INLEBB&rft_id=info:doi/10.1109/LNET.2024.3422482&rft_dat=%3Cproquest_RIE%3E3120655792%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3120655792&rft_id=info:pmid/&rft_ieee_id=10584078&rfr_iscdi=true |