<p>The temporal Scale-Free networks dynamic systems where interactions between nodes evolve over time is a critical challenge with applications in epidemiology, social networks, and infrastructure management. Predicting control nodes in temporal scale-free networks is crucial for understanding and influencing the dynamic behavior of complex systems, enabling targeted interventions in applications such as disease control, infrastructure resilience, and information dissemination. In this paper, a novel Temporal Graph Convolutional Neural Network (TGCN) framework is proposed for predicting type of control nodes on the temporal scale-free networks. For this purpose, a temporal GCN network is proposed that is compatible with temporal scale-free networks. The approach leverages the power of deep learning to learn the underlying patterns of controllability from temporal scale-free network data, enabling efficient and accurate identification of critical, redundant, and ordinary control nodes. The results demonstrate the effectiveness of proposed method on synthetic and real-world temporal scale-free networks, showing that it outperforms traditional methods in terms of both accuracy and computational efficiency.</p>