Multi-Service Demand Forecasting Using Graph Neural Networks

Theodoros Theodoropoulos, Antonios Makris, Ioannis Kontopoulos, Angelos-Christos Maroudis, Konstantinos Tserpes

Abstract: Accurate service demand forecasting is crucial towards achieving effective resource allocation and service orchestration. However, existing solutions require separate prediction models for each service, which consumes significant computation resources. In this paper, we propose a novel approach that introduces a global prediction model capable of generating accurate multi-step predictions involving multiple services and that can potentially leveraged for facilitating proactive strategies for orchestrating multiple services. The proposed model is based on an Encoder-Decoder architecture that utilizes Graph Neural Networks (GNNs) to capture interdependencies among input variables and their trends. By iteratively updating graph node representations, our model effectively incorporates historical trends and potential dependencies. Furthermore, the incorporation of GNNs into the Encoder-Decoder architecture enables the proposed approach to leverage the correlations among input variables, thus making it suitable for multivariate forecasting. Experimental results demonstrate the superiority of the proposed approach in terms of accurately conducting multi-step multiservice demand predictions, when compared against numerous contemporary deep learning models.