Abstract

Handover is the process of transferring a cellular call or data session from one base station (BS) to another. This process aims to establish reliable and uninterrupted connection, thereby providing satisfactory Quality of Service (QoS) and Quality of Experience (QoE) for users. 5G networks will use millimetre wave (mmWave) frequencies in addition to sub-6 GHz bands, which will make handover (HO) more challenging. This paper focuses on the problem of partially blind HOs which is a novel HO type. In this sense, we modify an extant algorithm used for the partially blind HOs [1] which the algorithm is based on machine learning (ML). In our modified algorithm, we use the extant algorithm with a powerful boosting method that is Categorical Boosting (CatBoost). We compare our modified algorithm with a baseline algorithm, the originally proposed algorithm, Support Vector Machine integrated original algorithm. Different settings of simulation time and number of users are considered in comparing the algorithms, and our modified algorithm outperforms the rest of the algorithms in majority of the settings with higher HO prediction rates as per obtained results. The obtained results clearly indicate that the integration of ML with partially blind HOs enables accurate predictions whether HO execution will be successful in collocated cells in a network in the real-world case. A noteworthy takeaway from the obtained results is that ML deployment with partially blind HOs will likely contribute to self-organizing networks (SONs) in 5G communication systems.