Tsinghua University

Ershun Du

Ning Zhang

Chongqing Kang

Yi Wang

Qing Xia

The disclosure relates to a quantile probabilistic short-term power load ensemble forecasting method. The method includes: dividing historical power load data of a power system into a first data set and a second data set; performing bootstrap sampling on the first data set to generate multiple training data sets; training a neural network quantile regression model, a random forest quantile regression model and a gradient boosting regression tree regression model for the each training data set to obtain quantile forecasting models; establishing an optimization model with an objective function for minimizing the quantile loss for the second data set, and determining a weight for each of the quantile regression models, to calculate a power load ensemble forecasting model for predicting the power load in the power system.

Method for quantile probabilistic short-term power load ensemble forecasting, electronic device and storage medium

The present disclosure provides a fast model generating and solving method for security-constrained power system operation simulation, which includes: obtaining information of all branches and nodes which are involved during operation simulation time period, calculating original-node impedance matrix, load shifting distribution factor original matrix and generator shifting distribution factor original matrix of all involved branches; correcting the load shifting distribution factor original matrix and the generator shifting distribution factor original matrix according to the on-off state of branches; obtaining output of each generator unit at each time period according to no-security-constraint unit commitment model, and determining overload of each branch again; solving iteratively until no branch is overloaded, and obtaining output of each generator unit at each time period under security constraint of operation simulation for the current simulation day, performing operating simulation for the rest simulation days to obtain security-constraint operation simulation result for the whole year.

Growing community of inventors

Beijing, China

Ershun Du