Emergency logistics is essential for rapid and efficient disaster response, ensuring the timely availability and deployment of resources to affected areas. In the process of rescue work, the dynamic changes in rescue point information greatly increase the difficulty of rescue. This paper establishes a combined neural network model considering soft time-window penalty and applies deep reinforcement learning (DRL) to address the dynamic routing problem in emergency logistics. This method utilizes the actor–critic framework, combined with attention mechanisms, pointer networks, and long short-term memory neural networks, to determine effective disaster relief path, and it compares the obtained scheduling scheme with the results obtained from the DRL algorithm based on the single-network model and ant colony optimization (ACO) algorithm. Simulation experiments show that the proposed method reduces the solution accuracy by nearly 10% compared to the ACO algorithm, but it saves nearly 80% in solution time. Additionally, it slightly increases solution times but improves accuracy by nearly 20% over traditional DRL approaches, demonstrating a promising balance between performance efficiency and computational resource utilization in emergency logistics.
Applying the regression mechanism of intelligent algorithm to transmission line fault location is a new research direction in recent years.The location accuracy of such methods largely depends on the feature selection of the training samples of the algorithm model.This paper proposes a feature extraction method that combines regression algorithm, waveform decomposition and optimization algorithm, which can adaptively extract optimal features according to training samples, thereby ensuring the location accuracy of the algorithm model to the greatest extent. Through the test in a MMC-HVDC transmission line simulation model, the optimal feature reconstruction method proposed in this paper can greatly improve the fault location accuracy of transmission line, and has good location performance in case of high resistance grounding fault.