Efficient and Green Service Function Chain Deployment and Scheduling for Mobile Edge Computing

Abstract

Service Function Chain (SFC) decomposes a user’s overall service into multiple service components and links them in an orderly manner, providing more flexible, efficient, and responsive services for compute-intensive applications in mobile edge computing. Existing research primarily focuses on optimizing the deployment cost and system efficiency of SFC. However, the dynamic nature of user trajectories, along with the absence of adaptive scheduling and service component sharing in complex and heterogeneous environments, hinders existing approaches from achieving optimal resource efficiency. To achieve adaptive optimization of SFC deployment and efficient component sharing across multiple SFCs, we propose an SFC Deployment and Scheduling strategy based on the Soft Actor-Critic (SAC) algorithm, named SAC-DS. The proposed SAC-DS strategy first employs a Long Short-Term Memory (LSTM) model to predict user trajectories, thereby accurately forecasting future service demands. Based on these predictions, an SAC-based agent is trained to dynamically optimize SFC deployment and scheduling policies in real time. SAC-DS integrates SFC deployment, component sharing, and scheduling into a unified framework, effectively improving system throughput while minimizing overall deployment costs, thereby enhancing user experience. Compared with existing baseline methods, SAC-DS improves network throughput by 3.1%–18.1% and reduces average cost by 1.8%–10.0%.