The telecommunications industry is advancing rapidly with the introduction of 5G technology, which promises enhanced broadband cellular networks. However, alongside the benefits come challenges, particularly in ensuring the security of these networks against cyber attacks. This paper focuses on Network Anomaly Detection (NAD) in 5G, aiming to detect and prevent abnormal behaviors within the network that could signify potential security threats. Various methods, including machine learning algorithms, are explored to achieve effective NAD. Specifically, the KNN and K-prototype algorithms are tested alongside an integrated approach, with the integrated method demonstrating superior performance.