Network load prediction and anomaly detection using ensemble learning in 5G cellular networks
School of Engineering
Deanship of Scientific Research, King Khalid University
Network data analytics significantly improved the 5G cellular networks. Data analytics allows network administrators and operators to use the machine and deep learning to analyse the network data efficiently. The standard protocols defined by the 3rd Generation Partnership Project (3GPP) for the network data analytics function are discussed to incorporate into the dataset. The dataset is based on cells in the network considering anomalies and fields of 3GPP, i.e., data rates and information related to the network area. Moreover, machine and deep learning techniques can be used to classify the anomalies. In this regard, we employed Decision trees (DT), Random Forest (RF), Support Vector Machines (SVM) and ensemble learning (EL) to enhance the network prediction performance. For this purpose, we used machine and deep learning techniques, i.e., one-dimensional Convolutional Neural Networks (1D CNN), Multi-Layer Perceptron (MLP), and k-Nearest Neighbours (kNN), respectively. We also used bagging-based three regressors, i.e., 1D CNN, MLP, and kNN, to predict the network load. In addition, we addressed both anomaly detection and load prediction because the presence of anomalies results in high load. The accurate detection of anomalies will result in less network load. Thus, anomalies like a sudden increase in network traffic from a certain cell are also added based on the network traffic pattern to make the dataset more realistic. The simulation results showed that the bagging-based EL outperformed the existing techniques in predicting network load. Moreover, the voting technique outperforms in the case of anomaly detection.
Haider, U., Waqas, M., Hanif, M., Alasmary, H., & Qaisar, S. M. (2023). Network load prediction and anomaly detection using ensemble learning in 5G cellular networks. Computer Communications, 197, 141-150. https://doi.org/10.1016/j.comcom.2022.10.017