Joint probability density prediction method of short-term output power of plurality of wind power plants

Abstract

The invention discloses a joint probability density prediction method of short-term output power of a plurality of wind power plants. The method comprises the following steps: carrying out single point value prediction on output power of each wind power plant by using a support vector machine regression prediction model; building a sparse bayesian learning model as to a prediction error to carry out probability density prediction of the error, so as to obtain an expected value and a variance of marginal probability density function prediction of the output power of a single wind power plant; carrying out statistic analysis on the prediction error characteristics of the output power of the plurality of wind power plants, building a dynamic conditional correlation-multivariate generalized autoregressive condition heteroscedasticity model, and integrating a marginal probability density prediction result of the output power of the single wind power plant and a correlation coefficient matrix to obtain a joint probability density function of the output power of the plurality of wind power plants; forming a multidimensional scene including space-time correlation characteristics by using a sampling technique. By adopting the joint probability density prediction method, a mean prediction value and prediction uncertainty information of the output power of the single wind power plant can be provided; the dynamic space-time correlation characteristics between output power prediction of the plurality of wind power plants also can be quantitatively described.

Description

technical field [0001] The invention relates to a method for predicting joint probability density of short-term output power of multiple wind farms. Background technique [0002] The large-scale grid-connection of wind power has relieved my country's energy pressure and brought huge economic and environmental benefits. It is currently the most mature technology and most suitable for large-scale development of renewable energy. However, wind power is an intermittent and uncontrollable power source, and its large-scale integration into the grid will inevitably increase the difficulty of system operation and control, and increase the burden of system backup. Therefore, it is very important to predict the output power of wind farms and wind farm groups [Lei Yazhou. Research topics related to wind power grid integration [J]. Electric Power System Automation, 2003,27(8):84-89.] . [0003] Short-term wind power prediction is generally to predict the active power of wind turbines ...

AI Technical Summary

Problems solved by technology

Literature [Wang Songyan, Yu Jilai. Combined conditional probability prediction method of wind speed and wind power[J]. Chinese Journal of Electrical Engineering, 2011, 31(7): 7-14.] Based on the measured value of the current period and the forecast of the next period The value is a joint condition, and the wind speed and wind power of a single wind farm are predicted probabilistically; literature [TASTU J, PINSON P, KOTWA E, et al.Spatio-temporal analysis and modeling of wind power forecast errors (space-time analysis and wind power Forecasting error modeling)[J].Wind Energy,2011,14(1):43-46.] analyzed the spatio-temporal propagation characteristics of wind farm power prediction errors that are adjacent to each other due to the inertia of the weather forecasting system, and Realized 1h advance wind power prediction; literature [GNEITING T, LARSON K, WESTRICK K, et al.Calibrated probabilistic forecasting at the stateline wind energy center: The regime-switching space–time method : State transition space-time method)[J].Journal of the American Statistical Association,2006,101(475):968-979.]Considering the time-space correlation information between wind fields, the wind speed is predicted 2h ahead; literature [PINSON P ,PAPAEFTHYMIOU G, KLOCKL B, et al.Generation of statistical scenarios of short-term wind power production [C] / / .Power Tech,2007IEEE Lausanne.IEEE,2007:491-496. ] Taking the probabilistic forecast results as input, the short-term wind power statistical scene formed contains the correlation characteristics between the forecast periods, but only a single wind farm is studied

None of these research works took into account the correlation between forecast periods and the spatio-temporal correlation characteristics between the output power forecasts of multiple wind farms.

Images