When large-scale wind power is connected to the power grid, the fluctuation and uncertainty in the wind power reduce the stability and accuracy of the grid's reactive voltage division results based on the electrical distance matrix and affect the grid's reactive power regulation. This paper proposes a grid reactive voltage partitioning method that considers the wind power stability and accuracy in a comprehensive manner. The wind power uncertainty and zoning results are characterized by the distribution of wind power forecast error intervals and changes in the zoning result nodes at different moments when the wind power is connected. Regarding volatility, according to the discretization of the probability distribution of the active power output at a certain time based on the wind power prediction, a calculation interval of the wind power output under a single cross-section is formed, and multiple sequential power flow sections within a long time scale are clustered and partitioned by an agglomeration hierarchical clustering method. Finally, an optimal zoning model of reactive voltage is established over a long time scale with the minimum comprehensive stability serving as the objective function. A simulation analysis of the improved IEEE39 node system shows that the partition combination can effectively increase the stability and accuracy of the reactive partitioning.

Accurate reactive load prediction can improve the accuracy and process of reactive power optimization for power grids and improve the control effect. The changes in the bus reactive load and active load are not synchronous, the base of the reactive load is small, nonlinear changes are abundant, and it is difficult to mine the inherent data trends. In view of the above problems, this paper proposes a method for predicting bus reactive loads based on deep learning. A bus reactive load prediction model is constructed based on a dual-input long short-term memory neural network to mine the detailed characteristics of active and reactive load data. Active and reactive loads are used as input and output data for the dynamic modeling of load time series data to form integrated forecasts of bus active and reactive loads. The experimental results show that this method can accurately predict the reactive power load of buses, and the prediction accuracy is better than that of time series and general long short-term memory neural network prediction models. INDEX TERMS Reactive power optimization, reactive load prediction, long short-term memory neural network.

No abstract

No abstract

No abstract