Power flow analysis and volt/var control strategy of the active distribution network based on data-driven method

The traditional Power Flow Calculation (PLF) method of the distribution network is affected by the accuracy of model parameters, the convergence of the solution method, and other factors. At the same time, the accuracy of the PLF of the distribution network will directly affect the optimization effect of the distribution network. In this paper, a data-driven power flow analysis and the volt/var optimization control strategy for the distribution network are proposed. Firstly, the CatBoost machine learning model for the distribution network power flow analysis is proposed, and the nonlinear mapping relationship between the distribution network state and power flow results is described from the data-driven perspective. Secondly, the influence of PhotoVoltaic (PV) power supply on the distribution network is analyzed, and the volt/var optimization model based on PV power supply is proposed. Then, the volt/var optimization strategy of the distribution network based on data-driven power flow analysis is proposed to ensure the safe and stable operation of the distribution network voltage and reduce the operating network loss of the distribution network without the need for network parameters and other information. Finally, the IEEE 33 node system is used to verify the effectiveness of the proposed strategy, the results of the example show that the data-driven PLF method can accurately perceive the voltage and loss of the distribution network. The proposed optimization strategy can stabilize the voltage of the distribution network in the range of 0.95–1.05, and the loss of the distribution network is reduced from 6.879 MWh to 3.369 MWh.