This manuscript investigates the network traffic prediction problem, which is to predict network traffic on a network function virtualization (NFV) enabled and digital twin (DT) assisted physical network for network service providers and network resource provider. It faces several key challenges like Data Privacy, different variation patterns of network traffic for multiple service function chain (SFC) requests, and few existing works have comprehensively considered or solved these challenges. In view of this, we address the network traffic prediction problem by jointly considering the above key challenges in this manuscript. Specifically, we formulate the virtual network function (VNF) migration problem as integer linear programming (ILP) that aim to maximize acceptance ratios, minimize network resource costs, and minimize migration cost. Then, we define the Markov Decision Process (MDP) for the network traffic prediction problem, and propose the novel model and algorithm, Transfer Learning and Deep Deterministic Policy Gradient (TL_DDPG), to solve the problem. Simulation results demonstrate that our scheme achieves better performance.