Autonomous Operation Strategy for Integrated Energy System based on Constraint Policy Optimization

In pursuit of the dual carbon objectives, there is a rapid expansion of distributed renewable energy sources. The integrated energy systems(IES) has emphasized the significance of multi-energy complementarity advantage in shaping the future energy landscape which consists of photovoltaics, combined heat and power units(CHP), and energy storage systems. The intricate coupling of diverse energy sources within these systems poses a challenge for accurate modeling using conventional approaches. This paper proposed an autonomous operational strategy for IES based on constrained policy optimization(CPO). By dynamically interacting with the environment, the proposed method seeks to maximize rewards while integrating constraints such as power balance and voltage stability into the training process. The effectiveness of the proposed approach is validated through simulation using a real-world case study. A comparative analysis with traditional solvers is conducted with evaluating economic cost and solution time. The findings affirm that the proposed method achieves both safe and economical operation of IES with a marked enhancement in computational efficiency. This research contributes valuable insights to the research in this field.