User Topology in the Low-Voltage Area using Firebug Swarm Optimization with Support Vector Machine

In recent years, accurately evaluating the user topology in the low-voltage area is crucial for research applications. However, low-voltage distribution substations faced challenges due to their many clients and complex connection patterns. Hence, to identify low-voltage link relationships between users and substation transformers in substation information, a machine learning approach known as the Firebug Swarm Optimization – Support Vector Machine (FSO-SVM) is proposed in this research. Initially, it utilized topological structure identification to identify the properties that can characterize the relationship of distribution transformers. Next, the utilization of the user profile feature is determined by the factors influencing the topological structure identification. User station visualization, which is predicated on the integrated connection feature matrix, is used to produce detailed profiles. Finally, the proposed hybridized FSO-SVM improves low-voltage grid management accuracy and efficiency by optimizing power flow and decreasing outages. The results showed that the suggested FSO-SVM method attained better performance in accuracy of 99.85% than existing models, such as Low-Voltage Distribution Networks (LVDNs), Active Low-Voltage Distribution Networks (ALVDN), and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) respectively.