Research on CNN-LSTM DC power system fault diagnosis and differential protection strategy based on reinforcement learning

Introduction: With the development of artificial intelligence technology, more and more fields are applying deep learning and reinforcement learning techniques to solve practical problems. In the power system, both the direct current (DC) power system and the power grid substation are important components, and their reliability and stability are crucial for production efficiency and safety. The power grid substation is used to convert power from high-voltage transmission lines to low-voltage transmission lines, or from alternating current to direct current (or vice versa), in order to efficiently transmit and distribute power in the power system. However, diagnosing faults and designing cascaded protection strategies has always been a challenge due to the complexityand uncertainty of the DC power system. Methods: To improve the reliability and stability of the DC power system and power grid substation, this paper aims to develop an intelligent fault diagnosis system and cascaded protection strategy to reduce faults and downtime, lower maintenance costs, and increase production efficiency. We propose a method based on reinforcement learning and a convolutional neural network-long short-term memory (CNN-LSTM) model for fault diagnosis and cascaded protection strategy design in the DC power system. CNN is used to extract features from raw data, while LSTM models time-series data. In addition, we use reinforcement learning to design cascaded protection strategies to protect the power system from the impact of faults. Results: We tested our method using real 220V DC power system data in experiments. The results show that our method can effectively diagnose faults in the DC power system and formulate effective cascaded protection strategies. Discussion: Compared with traditional methods, this intelligent method can diagnose faults faster and more accurately, and formulate better cascaded protection strategies. This method helps reduce maintenance costs, increase production efficiency, and can be applied to other fields.