Explainable Learning Based on Hyperparameters Optimization of Lightweight Spatiotemporal Models for Cellular Traffic Prediction

The rapid development of the Internet of Things and multimedia applications has led to an exponential growth in mobile network traffic year by year. In order to meet the demand for large amounts of data transmission and solve the problem of insufficient spectrum resources, millimeter waves are adopted for 5G communication. For B5G/6G, effective use of spectrum resources is one of the key technologies for the development of mobile communications. Therefore, this study uses a lightweight neural network to predict cellular traffic based on regional data, considering the data types of temporal and spatial dependence at the same time. Furthermore, in order to optimize the prediction performance and reduce the number of parameters of the neural network, this study uses a meta-heuristic algorithm to adjust the hyperparameters and combines local and global explanations to interpret the improvement of traffic prediction. The local explanations show the adjustment results of a single hyperparameter, and global explanations show the correlation between different hyperparameters and their influence on the amount and accuracy of model parameters. The simulation results show that compared with adjustment strategies of the manual method and greedy algorithm, the proposed explainable learning method can effectively improve the accuracy of cellular traffic prediction, reduce the number of parameters and provide a reasonable explanation.

Cellular Traffic Prediction Based on an Intelligent Model

The evolution of cellular technology development has led to explosive growth in cellular network traffic. Accurate time-series models to predict cellular mobile traffic have become very important for increasing the quality of service (QoS) with a network. The modelling and forecasting of cellular network loading play an important role in achieving the greatest favourable resource allocation by convenient bandwidth provisioning and simultaneously preserve the highest network utilization. The novelty of the proposed research is to develop a model that can help intelligently predict load traffic in a cellular network. In this paper, a model that combines single-exponential smoothing with long short-term memory (SES-LSTM) is proposed to predict cellular traffic. A min-max normalization model was used to scale the network loading. The single-exponential smoothing method was applied to adjust the volumes of network traffic, due to network traffic being very complex and having different forms. The output from a single-exponential model was processed by using an LSTM model to predict the network load. The intelligent system was evaluated by using real cellular network traffic that had been collected in a kaggle dataset. The results of the experiment revealed that the proposed method had superior accuracy, achieving R-square metric values of 88.21%, 92.20%, and 89.81% for three one-month time intervals, respectively. It was observed that the prediction values were very close to the observations. A comparison of the prediction results between the existing LSTM model and our proposed system is presented. The proposed system achieved superior performance for predicting cellular network traffic.

Attention based multi-component spatiotemporal cross-domain neural network model for wireless cellular network traffic prediction

Wireless cellular traffic prediction is a critical issue for researchers and practitioners in the 5G/B5G field. However, it is very challenging since the wireless cellular traffic usually shows high nonlinearities and complex patterns. Most existing wireless cellular traffic prediction methods lack the abilities of modeling the dynamic spatial–temporal correlations of wireless cellular traffic data, thus cannot yield satisfactory prediction results. In order to improve the accuracy of 5G/B5G cellular network traffic prediction, an attention-based multi-component spatiotemporal cross-domain neural network model (att-MCSTCNet) is proposed, which uses Conv-LSTM or Conv-GRU for neighbor data, daily cycle data, and weekly cycle data modeling, and then assigns different weights to the three kinds of feature data through the attention layer, improves their feature extraction ability, and suppresses the feature information that interferes with the prediction time. Finally, the model is combined with timestamp feature embedding, multiple cross-domain data fusion, and jointly with other models to assist the model in traffic prediction. Experimental results show that compared with the existing models, the prediction performance of the proposed model is better. Among them, the RMSE performance of the att-MCSTCNet (Conv-LSTM) model on Sms, Call, and Internet datasets is improved by 13.70 ~ 54.96%, 10.50 ~ 28.15%, and 35.85 ~ 100.23%, respectively, compared with other existing models. The RMSE performance of the att-MCSTCNet (Conv-GRU) model on Sms, Call, and Internet datasets is about 14.56 ~ 55.82%, 12.24 ~ 29.89%, and 38.79 ~ 103.17% higher than other existing models, respectively.