DefinePK

Abstract

The necessity of effective anomaly detection is brought to light by the fact that 5G networks are built to handle important application scenarios, as well as the complexity of the architecture and the vast amount of data flow inside them. When it comes to identifying irregularities, commonly known as network breakdowns or increases in congestion, standard methods typically fail to meet expectations. Quality of Service (QoS) and Quality of Experience (QoE) are both susceptible to being negatively impacted by the occurrence of these events. In order to enhance detection skills, there has been a trend toward more advanced approaches, such as deep learning (DL) combined with a variety of classification algorithms. This shift has occurred as a result of the challenge that has been presented. It has been demonstrated that systems that are based on deep learning can significantly improve accuracy. According to studies, some of these systems have achieved an accuracy rate of up to 98.8% and a false positive rate of only 0.44%. The use of deep neural networks (DNNs) is proven to be an effective solution for overcoming the limitations that are associated with traditional methods. The real call detail data (also known as CDRs) is utilized by these networks. A large increase in the intensity of anomaly detection is made possible by the integration of Mobile Edge Computing (MEC), which, in turn, provides real-time monitoring and rapid response. This is accomplished through the decentralization of processing activities. It is absolutely necessary to use this agile strategy in order to successfully handle the dynamic and ever-changing nature of 5G networks. Despite the emergence of new cyber threats and intricate network behaviors, this strategy will guarantee that service will continue to be provided without interruption. For the purpose of addressing the one-of-a-kind challenges that are presented by the next-generation of telecommunications infrastructures, future efforts should continue to improve these systems, with a particular emphasis on scalability, real-time responsiveness, and adaptive intelligence solutions. This will allow for the purpose of addressing them