[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124519-en":3,"doc-seo-124519-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},124519,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Performance Evaluation of Machine Learning and Deep Learning Models for 5G Resource Allocation","5G network deployment raises demanding requirements for resource allocation while preserving Quality of Service (QoS) amid rapidly varying traffic. This study develops and benchmarks machine learning and deep learning models to predict high resource demand using real-world KPIs including signal strength, latency, and bandwidth. After rigorous data preprocessing, models such as Logistic Regression, Random Forest, XGBoost, and GRU with Attention are compared. The hybrid XGBoost-GRU-Attention model reaches 99.50% accuracy, showing strong capability to learn temporal dynamics and feature interactions for intelligent real-time 5G optimization.","JCSI 37 (2025) 371–378 Received: 12 May 2025  \nAccepted: 11 September 2025  \n\n| Performance Evaluation of Machine Learning and Deep Learning Models for 5G Resource Allocation\u003Cbr>Abdullah Havolli*, Majlinda Fetaji\u003Cbr>South East European University, Tetovo, North Macedonia |\n| --- |\n| Abstract\u003Cbr>The deployment of 5G networks introduces challenges in resource allocation and maintaining Quality of Service (QoS) . This study aims to develop and benchmark machine learning (ML) and deep learning (DL) models for predicting highresource demands using real-world KPIs such as signal strength, latency, and bandwidth. By applying rigorous data preprocessing, we compare models including Logistic Regression, Random Forest, XGBoost, and GRU with Attention. A hybrid XGBoost-GRU-Attention model achieves 99.50% accuracy, demonstrating a superior ability to model temporal and feature interactions. These findings underscore the potential of AI-driven techniques for intelligent and real-time 5G optimization.\u003Cbr>Keywords: Quality of Service (QoS); Resource Allocation; Machine Learning; Artificial Intelligence (AI)\u003Cbr>*Corresponding author\u003Cbr>Email address: [ah30465@seeu.edu.mk](ah30465@seeu.edu.mk) (A. Havolli)\u003Cbr>Published under Creative Common License (CC BY 4.0 Int.) |\n\n1. Introduction  \nThe rapid evolution and widespread deployment of 5G networks have significantly reshaped modern telecommunications by enabling ultra-high-speed data transmission, substantially lower latency, and vastly improved connectivity. These technological advancements have become pivotal in supporting innovative and demanding applications such as autonomous vehicles, smart city infrastructures, remote healthcare services, and advanced industrial automation systems [1, 2]. Nonetheless, as network demands grow exponentially, ensuring efficient resource allocation emerges as a critical challenge, particularly in maintaining a high Quality of Service (QoS) while maximizing the utilization of available bandwidth and infrastructure [3] .  \nTraditional methods for network resource management predominantly rely on static allocation strategies, which are inherently limited in their capacity to adapt to rapidly fluctuating network conditions and dynamic user demands [4, 5] . These conventional techniques often result in either over-allocation, leading to resource wastage, or under-allocation, causing degradation in service quality and user experience [6] . Additionally, static allocation strategies are typically inefficient at handling the heterogeneous and diversified requirements of modern applications, further highlighting the need for dynamic, adaptive solutions.  \nTo overcome these limitations, machine learning (ML) algorithms have been increasingly explored for their ability to predict and optimize resource allocation in realtime, leveraging historical network performance data [7, 8]. ML models can effectively discern patterns associated with varying resource utilization levels, facilitating proactive and intelligent decision-making processes. Logistic regression, a particularly lightweight and computationally efficient ML technique, has emerged as a suitable approach for binary classification tasks within  \ntelecommunication environments, specifically for predicting whether network connections require high or low resource allocation [9, 10, 11] . However, the simplicity and interpretability of logistic regression also imply that it may struggle with complex, nonlinear relationships present in real-world network data.  \nIn recent years, there has been a significant shift toward integrating advanced ML techniques such as Random Forest, Gradient Boosting, and particularly deep learning models like Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) networks with Attention mechanisms to address the nonlinear and sequential nature of network data. These advanced models have shown remarkable success in capturing complex temporal dependencies and interactions between netw","cbCaijh4tTGTuoI2","https://ap.wps.com/l/cbCaijh4tTGTuoI2","pdf",354610,1,"English","en",105,"# Introduction\n## Background and Motivation\n## Limitations of Static Resource Management\n## ML and DL Approaches for Adaptive Allocation\n# Methodology\n## Data and KPI Selection\n## Data Preprocessing\n## Model Selection and Benchmarking\n# Model Comparison and Results\n## Logistic Regression Baseline\n## Advanced ML/DL Models and Hybrid Approach","[{\"question\":\"What problem does the study address in 5G networks?\",\"answer\":\"The study targets efficient 5G resource allocation while maintaining high Quality of Service (QoS) as network demand grows and conditions fluctuate.\"},{\"question\":\"Which KPIs are used to predict high resource demand?\",\"answer\":\"It uses real-world KPIs such as signal strength, latency, and bandwidth-related measurements.\"},{\"question\":\"Which model achieved the highest performance and what does it indicate?\",\"answer\":\"The hybrid XGBoost-GRU-Attention model achieves 99.50% accuracy, indicating superior ability to model temporal dynamics and interactions among features.\"}]","Performance Evaluation of Machine Learning and Deep Learning Models for 5G Resource Allocation | PDF",1785822865,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"performance-evaluation-of-machine-learning-and-deep-learning-models-for-5g-resource-allocation","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/performance-evaluation-of-machine-learning-and-deep-learning-models-for-5g-resource-allocation/124519/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the study address in 5G networks?","Question",{"text":74,"@type":75},"The study targets efficient 5G resource allocation while maintaining high Quality of Service (QoS) as network demand grows and conditions fluctuate.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which KPIs are used to predict high resource demand?",{"text":79,"@type":75},"It uses real-world KPIs such as signal strength, latency, and bandwidth-related measurements.",{"name":81,"@type":72,"acceptedAnswer":82},"Which model achieved the highest performance and what does it indicate?",{"text":83,"@type":75},"The hybrid XGBoost-GRU-Attention model achieves 99.50% accuracy, indicating superior ability to model temporal dynamics and interactions among features.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]