1.School of Electrical and Power Engineering, Hohai University, Nanjing 211100, China;2.Electric Power Research Institute of State Grid Jiangsu Electric Power Co., Ltd., Nanjing 211103, China

With the large-scale integration of distributed resources into the active distribution network, internal uncertainties of the active distribution network increase. To establish an accurate dispatch model, the uncertainty of photovoltaic output and the randomness of load are described as the uncertainty of corresponding prediction errors, and the probability distribution of uncertain variables is obtained through data-driven methods. Considering that the power flow model based on second-order cone relaxation (SOCR) may violate relaxation constraints and introduce errors, the power flow model is re-derived based on the Euler equations, thereby further establishing a stochastic optimal power dispatch model for active distribution networks that is both economical and secure. Aiming at the characteristics of the proposed model, this paper presents a real-time stochastic dispatch method for active distribution networks using fuzzy neural network (FNN) pre-decision. First, the FNN is employed to provide a fuzzy description of the probability distribution of uncertain variables, and its output is used as the initial value for solver optimization. Then, the solver is utilized to accelerate the solution process. Finally, the effectiveness of the proposed model and method is validated through a modified IEEE 33-bus system.