Simultaneous Localization and Mapping (SLAM) remains challenging in dynamic environments. Recent approaches combining deep learning with algorithms for dynamic scenes comprise two types: faster, less accurate object detection-based methods and highly accurate, computationally costly instance segmentation-based methods. In addition, maps lacking semantic information hinder robots from understanding their environment and performing complex tasks. This paper presents a lightweight visual-inertial SLAM system. The system is based on the classic ORB-SLAM3 framework, which starts a new thread for object detection and tightly couples the semantic information of object detection with geometric information to remove feature points from dynamic objects. In addition, Inertial Measurement Unit (IMU) data are employed to assist in feature point extraction, thereby compensating for visual pose tracking loss. Finally, a dense octree-based semantic map is constructed by fusing semantic information and visualized using ROS. LVID-SLAM demonstrates excellent pose accuracy and robustness in highly dynamic scenes on the public TUM dataset, with an average ATE reduction of more than 80% compared to ORB-SLAM3. The experimental results demonstrate that LVID-SLAM outperforms other methods in dynamic conditions, offering both real-time capability and robustness.

The traditional power grid planning lacks consideration of the uncertainty and correlation between wind and solar joint output in the same region, which poses challenges to the stable operation of the power system. Therefore, it is greatly important to consider the environmental and economic dispatch in light of the uncertainties and correlations associated with wind and solar energy. To tackle these issues, this paper introduces a dynamic environmental economic dispatch model that accounts for the uncertainties and correlations between wind and photovoltaic power based on their output characteristics. Initially, a probability model for photovoltaic–wind joint power is established using the Copula function. Subsequently, the Latin hypercube sampling method is employed alongside an improved K-means clustering technique to derive typical output scenarios. An adaptive multi-objective fireworks algorithm, featuring a differential selection strategy, is then utilized to enhance the environmental economic dispatch model. Finally, the IEEE 39 node system is used as an example to demonstrate the solution of the dynamic environmental and economic scheduling model. Simulation results reveal that the method for generating typical output scenarios presented in this paper effectively captures the uncertainties and correlations of photovoltaic–wind joint power. Furthermore, when compared to other optimization algorithms, the improved adaptive multi-objective fireworks algorithm proves to be more efficient in addressing the dynamic environmental economic dispatch challenges within the power system.

With the widespread use of distributed generation and electric vehicles, the uncertainty of distribution network operation is increased, challenging risk assessment. This paper proposes a generalized load modeling and risk assessment method based on GNG–Informer–WOA. GNG adaptively clusters load curves to identify typical patterns and noise; WOA optimizes Informer’s hyperparameters for high-precision prediction. An index system covering voltage out-of-limit, regulation capacity, and new energy consumption risks is established, with weights determined by fusing AHP and PCA via game theory. Case studies on the improved IEEE 33-bus system show the method effectively characterizes generalized load characteristics and accurately evaluates risks under different scenarios, supporting safe operation.

For the connection of DGs in distribution network, the fault power flow is different from that in normal operation. Further, the size of the fault current is limited by the electronic components and greatly reduces. Therefore, fault detection, the protections and their coordination become very complex. Fault detection technology helps to achieve fault isolation and recovery, and plays an important role in distribution network control and operation. This paper proposes a data-driven fault feature selection method for distribution network. This method collects various electrical quantities during normal and short-circuit faults of the distribution network as a feature library, and uses the support vector machine-recursive feature elimination method for feature selection to remove redundant features. The optimized fault features can be used to fault detection for distribution network with DGs.

When a line short-circuit fault occurs in a DC distribution network, the fault current rises quickly and affects a wide range, jeopardizing the safe operation of the system. In order to locate the fault quickly and accurately, this study proposes a fault localization method based on the Variational Mode Decomposition (VMD) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. First, the nonlinear relationship between the intrinsic principal frequency and fault distance is analyzed; then, the intrinsic principal frequency of the faulty traveling wave is extracted by using VMD, and the nonlinear relationship between the spectral energy of the principal frequency of the intrinsic frequency and the fault distance is fitted by training the Bi-LSTM network incorporating the attention mechanism. Finally, in response to the issue that a small amount of fault data in practical engineering is difficult to support the amount of data required for deep learning, a transfer learning method is used to locate the fault in the target domain. A small sample test of the target domain is carried out using the migration learning method. The experimental results show that the proposed method has high localization accuracy and good resistance to over-resistance and noise; compared with the traditional network training, the localization error based on migration learning is smaller, and the network convergence effect is better.