@article {10.3844/jcssp.2025.322.335,
article_type = {journal},
title = {Enhancing Telecommunication Network Management with Autonomous Optimization Agents and Machine Learning},
author = {Sibarani, Danny Adil and Madyatmadja, Evaristus Didik},
volume = {21},
number = {2},
year = {2025},
month = {Mar},
pages = {322-335},
doi = {10.3844/jcssp.2025.322.335},
url = {https://thescipub.com/abstract/jcssp.2025.322.335},
abstract = {This study explores the integration of Machine Learning (ML) and Autonomous Optimization Agents (AOAs) in the management and optimization of Radio Access Networks (RAN). The research addresses the growing challenges posed by the need for skilled network experts capable of managing and analyzing large-scale network data, including Key Performance Indicators (KPIs) and thousands of network configuration parameters. To overcome these challenges, the study proposes ML-based AOAs that autonomously monitor, manage, and optimize network performance, thereby reducing reliance on human expertise. Specifically, the study utilizes Deep Reinforcement Learning (DRL) to analyze network data and optimize key network parameters. Focusing on 4G LTE networks in a region of Indonesia, managed by a well-known operator, the study demonstrates the potential of AOAs in improving network efficiency, managing information overload, and optimizing critical KPIs. The findings highlight the significant impact of ML and AOAs on telecommunication network management, offering a more sustainable, efficient, and effective solution for RAN optimization.},
journal = {Journal of Computer Science},
publisher = {Science Publications}
}