Ultra-short-term wind power prediction method considering space-time conditions and quadratic optimization

The invention belongs to the technical field of wind power prediction, and particularly relates to an ultra-short-term wind power prediction method considering space-time conditions and quadratic optimization, which comprises the following steps of: 1, establishing an EEMD (Ensemble Empirical Mode Decomposition) model, adding a plurality of groups of white noise with a certain signal-to-noise ratio into an original sequence, and decomposing according to an EEMD decomposition method to obtain an EEMD (Ensemble Empirical Mode Decomposition) model; and finally, taking a mean value of the eigenmode functions after multiple decomposition as a final IMF. 2, decomposing a wind power output power time sequence, wherein randomness and volatility of wind power output cause instability of an original wind power sequence; an original sequence is decomposed through an EEMD method, and a stationary component can be obtained; 3, reconstructing a wind power output power time sequence; 4, building a wind power output power AR