Short-term photovoltaic power prediction method based on optimized DBN and Bi-LSTM

The invention discloses a short-term photovoltaic power prediction method based on optimized DBN and Bi-LSTM, and the method comprises the steps: building an SSA optimized DBN and PSO optimized Bi-LSTM combined prediction model through employing the characteristic that the DBN can capture nonlinear...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	SONG LI, LIU GANG, WANG SHUNJIANG, LI DIANYANG, WANG DUO, LING ZHAOWEI, ZHOU GUIPING
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	CALCULATING CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING CONVERSION OR DISTRIBUTION OF ELECTRIC POWER COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES ELECTRIC DIGITAL DATA PROCESSING ELECTRICITY GENERATION PHYSICS SYSTEMS FOR STORING ELECTRIC ENERGY SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The invention discloses a short-term photovoltaic power prediction method based on optimized DBN and Bi-LSTM, and the method comprises the steps: building an SSA optimized DBN and PSO optimized Bi-LSTM combined prediction model through employing the characteristic that the DBN can capture nonlinear features and the capability of the Bi-LSTM for processing time sequence features, completing the deep feature extraction of a training data sequence, carrying out the parameter optimization of the DBN through employing the SSA, and carrying out the prediction of the short-term photovoltaic power of the DBN. The DBN convergence speed and the feature extraction capability are improved, and the generalization performance is improved; according to the method, the hidden layer unit number alpha, the learning rate epsilon and the discarding probability rho in the Bi-LSTM are adjusted through PSO, the network robustness and the global search capability are improved, and the convergence speed is increased. 本发明公开了一种基于优化DBN和