{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-10170"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-10170","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Next-Generation Self-Organizing Communications Networks: Synergistic Application of Machine Learning and User-Centric Technologies","abstract":"The telecommunications industry is going through a metamorphic journey where the 5G and 6G technologies will be deeply rooted in the society forever altering how people access and use information. In support of this transformation, this dissertation proposes a fundamental paradigm shift in the design, performance assessment, and optimization of wireless communications networks developing the next-generation self-organizing communications networks with the synergistic application of machine learning and user-centric technologies. This dissertation gives an overview of the concept of self-organizing networks (SONs), provides insight into the “hot” technology of machine learning (ML), and offers an intuitive understanding of the user-centric (UC) technology that form the foundation of the research initiatives conceived, implemented, and validated in this dissertation. A three-layered approach based on the synergistic application of SON, ML, and UC technologies is applied for anomaly detection, load balancing and capacity optimization, and radio access network-based notification area (RNA) configuration and management. In the first research initiative, ML is applied to learn and predict a UC key performance indicator that imports the effect of the end-user perception of the quality of service to achieve end-to-end service assurance and proactively detect dysfunctional network nodes enabling automatic detection and remediation of failing network nodes to mitigate network degradation in self-healing SON systems. In the second research initiative a UC and ML based methodology called US-OCSP (i.e. user-specific optimal capacity and shortest path) is developed that can be integrated with an auto or personal navigation system to provide routing that avoids congested network traffic and effects resource optimization enabling load balancing and capacity optimization in self-optimizing SON systems. In the third research initiative, a UC and ML-embedded clustering mechanism is developed for dynamic configuration and management of RAN-based notification areas (i.e. RAN-based paging areas) that can help achieve improved signaling and paging load to attain reduced latency and improved network capacity, while lowering power consumption supporting emerging 5G/6G applications and services that generate an extensive amount of random aperiodic and keep-alive data traffic in self-configuring SON systems. Finally, a high-level framework consisting of several core building blocks is provided to support UC and ML-infused network standardization that the network operators can adopt to shape the network of tomorrow.","abstract_html":"The telecommunications industry is going through a metamorphic journey where the 5G and 6G technologies will be deeply rooted in the society forever altering how people access and use information. In support of this transformation, this dissertation proposes a fundamental paradigm shift in the design, performance assessment, and optimization of wireless communications networks developing the next-generation self-organizing communications networks with the synergistic application of machine learning and user-centric technologies. This dissertation gives an overview of the concept of self-organizing networks (SONs), provides insight into the “hot” technology of machine learning (ML), and offers an intuitive understanding of the user-centric (UC) technology that form the foundation of the research initiatives conceived, implemented, and validated in this dissertation. A three-layered approach based on the synergistic application of SON, ML, and UC technologies is applied for anomaly detection, load balancing and capacity optimization, and radio access network-based notification area (RNA) configuration and management. In the first research initiative, ML is applied to learn and predict a UC key performance indicator that imports the effect of the end-user perception of the quality of service to achieve end-to-end service assurance and proactively detect dysfunctional network nodes enabling automatic detection and remediation of failing network nodes to mitigate network degradation in self-healing SON systems. In the second research initiative a UC and ML based methodology called US-OCSP (i.e. user-specific optimal capacity and shortest path) is developed that can be integrated with an auto or personal navigation system to provide routing that avoids congested network traffic and effects resource optimization enabling load balancing and capacity optimization in self-optimizing SON systems. In the third research initiative, a UC and ML-embedded clustering mechanism is developed for dynamic configuration and management of RAN-based notification areas (i.e. RAN-based paging areas) that can help achieve improved signaling and paging load to attain reduced latency and improved network capacity, while lowering power consumption supporting emerging 5G/6G applications and services that generate an extensive amount of random aperiodic and keep-alive data traffic in self-configuring SON systems. Finally, a high-level framework consisting of several core building blocks is provided to support UC and ML-infused network standardization that the network operators can adopt to shape the network of tomorrow.","abstract_has_math":false,"creators":["Murudkar, Chetana V."],"institution":"University of South Florida","degree_name":"Doctor of Philosophy (Ph.D.)","degree_level":"Dissertation","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Richard D. Gitlin, Sc.D.","Kwang-Cheng Chen, Ph.D.","Nasir Ghani, Ph.D.","Srinivas Katkoori, Ph.D.","Gabriel Arrobo, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-06-28T07:00:00Z","date_published":"2020-06-28T07:00:00Z","updated_at":"2026-11-19T08:46:56Z","subjects":["5G and 6G Networks","Anomaly Detection","Load Balancing and Capacity Optimization","Quality of Experience","RAN-Based Notification Area Configuration","Artificial Intelligence and Robotics","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/8973","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/8973","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-10170","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Richard D. Gitlin, Sc.D.","Kwang-Cheng Chen, Ph.D.","Nasir Ghani, Ph.D.","Srinivas Katkoori, Ph.D.","Gabriel Arrobo, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Murudkar, Chetana V."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-06-28T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation","Ph.D."]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (Ph.D.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["5G and 6G Networks","Anomaly Detection","Load Balancing and Capacity Optimization","Quality of Experience","RAN-Based Notification Area Configuration","Artificial Intelligence and Robotics","Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/8973"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The telecommunications industry is going through a metamorphic journey where the 5G and 6G technologies will be deeply rooted in the society forever altering how people access and use information. In support of this transformation, this dissertation proposes a fundamental paradigm shift in the design, performance assessment, and optimization of wireless communications networks developing the next-generation self-organizing communications networks with the synergistic application of machine learning and user-centric technologies. This dissertation gives an overview of the concept of self-organizing networks (SONs), provides insight into the “hot” technology of machine learning (ML), and offers an intuitive understanding of the user-centric (UC) technology that form the foundation of the research initiatives conceived, implemented, and validated in this dissertation. A three-layered approach based on the synergistic application of SON, ML, and UC technologies is applied for anomaly detection, load balancing and capacity optimization, and radio access network-based notification area (RNA) configuration and management. In the first research initiative, ML is applied to learn and predict a UC key performance indicator that imports the effect of the end-user perception of the quality of service to achieve end-to-end service assurance and proactively detect dysfunctional network nodes enabling automatic detection and remediation of failing network nodes to mitigate network degradation in self-healing SON systems. In the second research initiative a UC and ML based methodology called US-OCSP (i.e. user-specific optimal capacity and shortest path) is developed that can be integrated with an auto or personal navigation system to provide routing that avoids congested network traffic and effects resource optimization enabling load balancing and capacity optimization in self-optimizing SON systems. In the third research initiative, a UC and ML-embedded clustering mechanism is developed for dynamic configuration and management of RAN-based notification areas (i.e. RAN-based paging areas) that can help achieve improved signaling and paging load to attain reduced latency and improved network capacity, while lowering power consumption supporting emerging 5G/6G applications and services that generate an extensive amount of random aperiodic and keep-alive data traffic in self-configuring SON systems. Finally, a high-level framework consisting of several core building blocks is provided to support UC and ML-infused network standardization that the network operators can adopt to shape the network of tomorrow."]},{"key":"dc:title","label":"Title","values":["Next-Generation Self-Organizing Communications Networks: Synergistic Application of Machine Learning and User-Centric Technologies"]}]}],"canonical_facts":{"dc:contributor":["Richard D. Gitlin, Sc.D.","Kwang-Cheng Chen, Ph.D.","Nasir Ghani, Ph.D.","Srinivas Katkoori, Ph.D.","Gabriel Arrobo, Ph.D."],"dc:creator":["Murudkar, Chetana V."],"dc:date":["2020-06-28T07:00:00Z"],"dc:description":["The telecommunications industry is going through a metamorphic journey where the 5G and 6G technologies will be deeply rooted in the society forever altering how people access and use information. In support of this transformation, this dissertation proposes a fundamental paradigm shift in the design, performance assessment, and optimization of wireless communications networks developing the next-generation self-organizing communications networks with the synergistic application of machine learning and user-centric technologies. This dissertation gives an overview of the concept of self-organizing networks (SONs), provides insight into the “hot” technology of machine learning (ML), and offers an intuitive understanding of the user-centric (UC) technology that form the foundation of the research initiatives conceived, implemented, and validated in this dissertation. A three-layered approach based on the synergistic application of SON, ML, and UC technologies is applied for anomaly detection, load balancing and capacity optimization, and radio access network-based notification area (RNA) configuration and management. In the first research initiative, ML is applied to learn and predict a UC key performance indicator that imports the effect of the end-user perception of the quality of service to achieve end-to-end service assurance and proactively detect dysfunctional network nodes enabling automatic detection and remediation of failing network nodes to mitigate network degradation in self-healing SON systems. In the second research initiative a UC and ML based methodology called US-OCSP (i.e. user-specific optimal capacity and shortest path) is developed that can be integrated with an auto or personal navigation system to provide routing that avoids congested network traffic and effects resource optimization enabling load balancing and capacity optimization in self-optimizing SON systems. In the third research initiative, a UC and ML-embedded clustering mechanism is developed for dynamic configuration and management of RAN-based notification areas (i.e. RAN-based paging areas) that can help achieve improved signaling and paging load to attain reduced latency and improved network capacity, while lowering power consumption supporting emerging 5G/6G applications and services that generate an extensive amount of random aperiodic and keep-alive data traffic in self-configuring SON systems. Finally, a high-level framework consisting of several core building blocks is provided to support UC and ML-infused network standardization that the network operators can adopt to shape the network of tomorrow."],"dc:identifier":["https://digitalcommons.usf.edu/etd/8973"],"dc:subject":["5G and 6G Networks","Anomaly Detection","Load Balancing and Capacity Optimization","Quality of Experience","RAN-Based Notification Area Configuration","Artificial Intelligence and Robotics","Electrical and Computer Engineering"],"dc:title":["Next-Generation Self-Organizing Communications Networks: Synergistic Application of Machine Learning and User-Centric Technologies"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Dissertation","Ph.D."],"thesis:degree_name":["Doctor of Philosophy (Ph.D.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:46:56Z"}