ANNs Going Beyond Time Series Forecasting: An Urban Network Perspective

Abstract

5G is expected to bring forth disruptive indus-trial-societal transformation by enabling a broad catalog of (radically new, highly heterogeneous) applications and services. This scenario has called for zero-touch network and service management (ZSM). With the recent advancements in artificial intelligence, key ZSM capabilities such as the runtime prediction of user demands can be facilitated by data-driven and machine learning methods. In this respect, the article proposes a runtime prediction approach that transforms time series forecasting into a simpler multivariate regression problem with artificial neural networks (ANNs), structurally optimized with a genetic algorithm (GA) metaheuristic. Leveraging on a novel set of input features that capture seasonality and calendar effects, the proposed approach removes the prediction accuracy's dependence on the temporal succession of input data and the forecast horizon. Evaluation results based on real telecommunications data show that the GA-optimized ANN regressor has better prediction performance. It achieved average improvements of ~59 percent and ~86 percent compared to 1-day and 1-hour ahead forecasts obtained with state-of-the-art multi-seasonal time series and long short-term memory forecasting models, respectively. Furthermore, despite its longer training times compared to the baseline models, the proposed ANN regressor relaxes the monitoring requirements in 5G dynamic management systems by allowing less frequent retraining offline.