<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>0121-1129</journal-id>
<journal-title><![CDATA[Revista Facultad de Ingeniería]]></journal-title>
<abbrev-journal-title><![CDATA[Rev. Fac. ing.]]></abbrev-journal-title>
<issn>0121-1129</issn>
<publisher>
<publisher-name><![CDATA[Universidad Pedagógica y Tecnológica de Colombia]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0121-11292024000300010</article-id>
<article-id pub-id-type="doi">10.19503/01211129.v33.n69.2024.18057</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[PERFORMANCE ANALYSIS OF ACCESS AND MOBILITY MANAGEMENT FUNCTION ON A 5G CORE BASED ON CPU USAGE PREDICTIONS]]></article-title>
<article-title xml:lang="es"><![CDATA[Análisis de desempeño de la función de gestión de acceso y movilidad en un Core 5G basado en predicciones del uso de CPU]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Campo-Muñoz]]></surname>
<given-names><![CDATA[Wilmar-Yesid]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Amaya-Suárez]]></surname>
<given-names><![CDATA[Jhon-Alexander]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Caviedes-Valencia]]></surname>
<given-names><![CDATA[Juan-Camilo]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad del Quindío  ]]></institution>
<addr-line><![CDATA[Armenia Quindío]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universidad del Quindío  ]]></institution>
<addr-line><![CDATA[Armenia Quindío]]></addr-line>
<country>Colombia</country>
</aff>
<aff id="Af3">
<institution><![CDATA[,Universidad Nacional de Colombia  ]]></institution>
<addr-line><![CDATA[Bogotá-Distrito Capital ]]></addr-line>
<country>Colombia</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>09</month>
<year>2024</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>09</month>
<year>2024</year>
</pub-date>
<volume>33</volume>
<numero>69</numero>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_arttext&amp;pid=S0121-11292024000300010&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_abstract&amp;pid=S0121-11292024000300010&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_pdf&amp;pid=S0121-11292024000300010&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[ABSTRACT The increasing number of mobile devices and the growing demand for services lead to an increase in the access requests per second to the Access and Mobility Management Function (AMF) of the control plane in a Fifth Generation (5G) mobile network. It causes congestion of the function and affects the overall network performance. Therefore, this paper proposes a self-scaling mechanism for the AMF in a 5G core by CPU usage predictions using the Long Short-Term Memory (LSTM) machine learning (ML) technique. The mechanism predicts the percentage of CPU usage in the pod containing the AMF and establishes scaling policies that determine the necessary number of AMF pods. The performance of the AMF is evaluated through success rate, loss rate, and latency of access requests per second in three scenarios: a reactive one with scaling based on current CPU thresholds, a predictive one using CPU predictions, and another using both the scaling policies and the LSTM technique. With the previous scenarios, the AMF is scaled reactively and predictively. Results show that the scaling policies and the ML algorithm significantly improve the performance of the function in terms of success rate and loss rate of access requests per second. An efficient self-scaling of the AMF is achieved, which contributes both to the optimization of computational resources and to improving the availability of the 5G mobile network.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[RESUMEN El aumento en el número de dispositivos móviles y la creciente demanda de servicios generan un incremento en las solicitudes de acceso por segundo que llegan a la función de gestión de acceso y movilidad (AMF, Access and Mobility Management Function) del plano de control en una red móvil de quinta generación (5G, Fifth Generation), lo que provoca congestión en la función y afecta el desempeño general de la red. En este artículo se propone un mecanismo de autoescalado para el AMF en un core 5G utilizando predicciones de uso de la CPU obtenidas mediante la técnica de aprendizaje automático (ML, Machine Learning) de memoria a largo y corto plazo (LSTM, Long Short-Term Memory). El mecanismo predice el porcentaje de uso de la CPU en el pod que contiene la AMF y establece políticas de escalado que determinan la cantidad necesaria de pods AMF. Se evalúa el desempeño del componente AMF a través de la tasa de éxito, tasa de pérdidas y latencia de las solicitudes de acceso por segundo en tres escenarios diferentes: uno reactivo con escalado basado en límites (Thresholds) actuales de CPU, otro predictivo utilizando predicciones de CPU, y otro en el que se involucran tanto las políticas de escalamiento como la técnica LSTM. Con los escenarios anteriores, se escala el AMF de forma reactiva y predictiva. Los resultados muestran que las políticas de escalamiento y el algoritmo de ML mejoran significativamente el desempeño de la función en términos de tasa de éxito y tasa de pérdidas de solicitudes de acceso por segundo. Se logra implementar un autoescalado eficiente del AMF, lo cual contribuye tanto a la optimización de recursos computacionales como a mejorar la disponibilidad de la red móvil 5G.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[AMF]]></kwd>
<kwd lng="en"><![CDATA[CPU]]></kwd>
<kwd lng="en"><![CDATA[LSTM]]></kwd>
<kwd lng="en"><![CDATA[scaling policies]]></kwd>
<kwd lng="en"><![CDATA[self-scaling]]></kwd>
<kwd lng="es"><![CDATA[AMF]]></kwd>
<kwd lng="es"><![CDATA[autoescalamiento]]></kwd>
<kwd lng="es"><![CDATA[CPU]]></kwd>
<kwd lng="es"><![CDATA[LSTM]]></kwd>
<kwd lng="es"><![CDATA[políticas de escalamiento]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<label>[1]</label><nlm-citation citation-type="">
<collab>Ericsson</collab>
<source><![CDATA[Explore the Ericsson Mobility Report]]></source>
<year>2024</year>
</nlm-citation>
</ref>
<ref id="B2">
<label>[2]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Alam]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Survey of Network Virtualization Techniques for Internet of Things Using SDN and NFV]]></article-title>
<source><![CDATA[ACM Computing Surveys]]></source>
<year>2020</year>
<volume>53</volume>
<numero>2</numero>
<issue>2</issue>
</nlm-citation>
</ref>
<ref id="B3">
<label>[3]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chavez-Picon]]></surname>
<given-names><![CDATA[J. L.]]></given-names>
</name>
<name>
<surname><![CDATA[Campo-Muñoz]]></surname>
<given-names><![CDATA[W. Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Chanchí-Golondrino]]></surname>
<given-names><![CDATA[G. E.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Arquitectura para implementación de servicios de video sobre redes móviles mediante redes definidas por software y segmentación de red]]></article-title>
<source><![CDATA[Revista Colombiana de Tecnologías de Avanzada]]></source>
<year></year>
<volume>2</volume>
<numero>42</numero>
<issue>42</issue>
</nlm-citation>
</ref>
<ref id="B4">
<label>[4]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chouman]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Manias]]></surname>
<given-names><![CDATA[D. M.]]></given-names>
</name>
<name>
<surname><![CDATA[Shami]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[A Reliable AMF Scaling and Load Balancing Framework for 5G Core Networks]]></source>
<year>2023</year>
<conf-name><![CDATA[ International Wireless Communications and Mobile Computing]]></conf-name>
<conf-loc>Marrakesh, Morocco </conf-loc>
<page-range>252-7</page-range></nlm-citation>
</ref>
<ref id="B5">
<label>[5]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Atarashi]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Iwamura]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Nagata]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Nakamura]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Toskala]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[5G Targets and Standardization]]></article-title>
<source><![CDATA[5G Technoly 3GPP Evolution to 5G-Advanced]]></source>
<year>2024</year>
<page-range>13-26</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>[6]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Toskala]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Poikselkä]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[5G Architecture]]></article-title>
<source><![CDATA[5G Technoly 3GPP Evolution to 5G-Advanced]]></source>
<year>2024</year>
<page-range>67-86</page-range></nlm-citation>
</ref>
<ref id="B7">
<label>[7]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Christakis]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Makris]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Korakis]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Fdida]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[On the Automated Scaling of User Plane Function for 5G: An Experimental Evaluation]]></source>
<year>2024</year>
<conf-name><![CDATA[ Joint European Conference on Networks and Communications &amp; 6G Summit (EuCNC/6G Summit)]]></conf-name>
<conf-loc>Belgium </conf-loc>
<page-range>979-84</page-range></nlm-citation>
</ref>
<ref id="B8">
<label>[8]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rotter]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Van Do]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Queueing Model for Threshold-Based Scaling of UPF Instances in 5G Core]]></article-title>
<source><![CDATA[IEEE Access]]></source>
<year>2021</year>
<volume>9</volume>
<page-range>81443-53</page-range></nlm-citation>
</ref>
<ref id="B9">
<label>[9]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lorido-Botran]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Miguel-Alonso]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Lozano]]></surname>
<given-names><![CDATA[J. A.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Review of Auto-scaling Techniques for Elastic Applications in Cloud Environments]]></article-title>
<source><![CDATA[Journal of Grid Computing]]></source>
<year>2014</year>
<volume>12</volume>
<numero>4</numero>
<issue>4</issue>
<page-range>559-92</page-range></nlm-citation>
</ref>
<ref id="B10">
<label>[10]</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Valencia]]></surname>
<given-names><![CDATA[J. C.]]></given-names>
</name>
</person-group>
<source><![CDATA[Modelo predictivo para la asignación elástica de recursos sobre entornos NFV/SDN basados en OpenStack]]></source>
<year>2021</year>
<publisher-loc><![CDATA[Bogotá, Colombia ]]></publisher-loc>
<publisher-name><![CDATA[Universidad Nacional de Colombia]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B11">
<label>[11]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Alawe]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Ksentini]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Hadjadj-Aoul]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Bertin]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Improving Traffic Forecasting for 5G Core Network Scalability: A Machine Learning Approach]]></article-title>
<source><![CDATA[IEEE Network]]></source>
<year>2018</year>
<volume>32</volume>
<numero>6</numero>
<issue>6</issue>
<page-range>42-9</page-range></nlm-citation>
</ref>
<ref id="B12">
<label>[12]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Alawe]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Ksentini]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Hadjadj-Aoul]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Bertin]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Kerbellec]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<source><![CDATA[On evaluating different trends for virtualized and SDN-ready mobile network]]></source>
<year>2017</year>
<conf-name><![CDATA[ 6thInternational Conference in Cloud Networking]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B13">
<label>[13]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Alam]]></surname>
<given-names><![CDATA[M. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Khatibi]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[CPU resource usage analysis for downlink PDCP processing in CRAN]]></source>
<year>2020</year>
<conf-name><![CDATA[ International Symposium on Personal, Indoor and Mobile Radio Communications]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B14">
<label>[14]</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Trinh]]></surname>
<given-names><![CDATA[H. D.]]></given-names>
</name>
<name>
<surname><![CDATA[Giupponi]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Dini]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
</person-group>
<source><![CDATA[Mobile Traffic Prediction from Raw Data Using LSTM Networks]]></source>
<year>2018</year>
<conf-name><![CDATA[ International Symposium on Personal, Indoor and Mobile Radio Communications]]></conf-name>
<conf-loc> </conf-loc>
<page-range>1827-32</page-range></nlm-citation>
</ref>
<ref id="B15">
<label>[15]</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Nashold]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Krishnan]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
</person-group>
<source><![CDATA[Using LSTM and SARIMA Models to Forecast Cluster CPU Usage]]></source>
<year>2020</year>
</nlm-citation>
</ref>
<ref id="B16">
<label>[16]</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ge]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Huo]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Xie]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Wei]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[VNF Instance Dynamic Scaling Strategy Based on LSTM]]></article-title>
<source><![CDATA[Advances in Intelligent Systems and Computing]]></source>
<year>2021</year>
<volume>1274</volume>
<page-range>335-43</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
