ML-Based Service Type Priority Decision Method Using Ambient Information for 5GB

5G communications systems offer several types of service groups include enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC), and massive machine-type communications (mMTC). The ability to meet various mobile communications requirements of different users is ensured by these service groups. In this paper, a novel service type priority decision method is proposed for 5G and beyond (5GB) systems to determine the most needed service group under a specific region. This approach is useful for the resource allocation planning and optimization through a coverage region. The proposed method is based on the machine learning (ML) usage with several ambient information. Instance-based and model-based techniques are compared for ML. Also, the ensemble methods are tested on the generated synthetic dataset.