The topology identification of low-voltage distribution networks is an important foundation for the intelligence of low-voltage distribution networks. Its accuracy fundamentally determines the effectiveness of functions such as power system state estimation, operational control, optimization planning, and intelligent electricity consumption. The low-voltage distribution network is composed of transformers, lines, and end users. The key task of topology identification is to distinguish the connection relationship between distribution transformers, low-voltage lines, and phase sequence with end users, which can be divided into transformer user relationship, line user relationship, and phase user relationship. At present, the main methods of low-voltage network topology identification can be divided into signal injection method and data analysis method. The signal injection method requires a large number of additional terminal devices and is difficult to promote. The data analysis method combines the characteristics of switch state, voltage, current, electrical energy, and other data to perform topology analysis. The commonly used methods include correlation analysis and feature learning. Finally, typical problems that urgently need to be solved in topology recognition and representation were proposed, providing a reference for the research and development of low-voltage distribution network topology automatic recognition technology.

When high precision modelling is required, for example, with the estimation of suspended sediment load (SSL), data-driven models are preferred over physically-based numerical models for their real-time, short-horizon prediction ability. The investigation of SSL, as an important index in engineering practices assessment, like design and operation of the hydraulic structures not only shows the hydrological behaviour of the river, but also illustrates the valuable information about the water quality deterioration, surface-groundwater interaction and land-use changes of the watershed. The following data-driven methods were compared in order to predict SSL at the Seyra gauging station on the Karaj River in Iran: Fuzzy logic (FL), two adaptive neuro-fuzzy inference systems (i.e., ANFIS-GP and ANFIS-FCM models), an artificial neural network (ANN), and least squares support vector machine (LSSVM). Monthly average river flow and SSL data for 50 years were obtained from the Tehran Regional Water Authority (TRWA). The data was first divided into training, validation and test sets and the SSL was then predicted using the ANN, FL, ANFIS, and LSSVM models. The reliability of the applied models was evaluated by the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE). The results showed that the ANFIS models outperformed the ANN, FL, and LSSVM models for predicting SSL using the given input and output data. Overall, the performances of the artificial intelligence models used in the present study were satisfac-tory in predicting the non-linear behaviour of the SSL.