Current approaches to energy consumption forecasting in manufacturing systems often fail to fully capture the complex spatiotemporal relationships inherent in these systems. Manufacturing systems can be effectively modelled as networks that represent these dynamic relationships. Such a network-based representation offers a valuable opportunity to enhance existing energy consumption forecasting methods. This paper proposes a spatiotemporal framework that models manufacturing systems as spatiotemporal networks and introduces a novel spatiotemporal neural network for forecasting energy consumption of these systems. Validation using a publicly available dataset shows that the proposed framework outperforms several state-of-the-art baseline models, demonstrating its superior capability in energy forecasting with improvements of up to 53% in certain metrics.