In new generation networks, 5G and 6G networks, intelligent mechanisms based on artificial intelligence algorithms are playing a relevant role in the performance improvement at different network levels. In 5G networks, different techniques are used, such as MIMO systems, and its network infrastructure is utilized by diverse services, for instance, vehicular communications. Thus, the description and the tracing of a communication scenario needs a large volume of data. Because of the difficulty to implement actual 5G networks, there is a lack of datasets containing complete 5G scenarios, the data is not enough or contain imbalanced classes to properly train machine learning (ML) algorithms. In this context, we propose a method to increase the amount of data to improve the machine learning performance of some classification models, specifically Random Forest, Multilayer Perceptron, and k-Nearest Neighbors. In the experimental results of the test phase, considering the inclusion of synthetic data, Random Forest, Multilayer Perceptron and k-Nearest Neighbors reached macro F1 scores of 0.9341, 0.9241 and 0.9456, respectively, which are superior to the results obtained when training with the original data only.