Short-term load probability density prediction method, device and system based on quantile regression

Short-term load probability density prediction method, device and system based on quantile regression

The invention discloses a short-term load probability density prediction method, device and system based on quantile regression, and the method comprises the steps: obtaining a DL-LSTM-A deep network model, wherein the DL-LSTM-A deep network model comprises a plurality of double-layer LSTM network c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LYU PENGPENG, TAO XIAOFENG, ZHOU YANG, YANG XUELIANG, DENG LIANGZHU, LIU NIEXUAN, HUANG CHAO, XIONG XIA, LU YANG, SUN MENG, HUANG FUXING, LI YUANHANG, ZHANG QUNXING
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
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 load probability density prediction method, device and system based on quantile regression, and the method comprises the steps: obtaining a DL-LSTM-A deep network model, wherein the DL-LSTM-A deep network model comprises a plurality of double-layer LSTM network cells and an attention mechanism module, the output end of each double-layer LSTM network cell is connected with the attention mechanism module, the attention mechanism module performs weighted summation on the output of each double-layer LSTM network cell, and each double-layer LSTM network cell comprises two LSTM cells which are connected in sequence; carrying out training by using the training data to obtain to-be-optimized parameters in the DL-LSTM-A network, and obtaining an optimized DL-LSTM-A deep network model; inputting the obtained influence factors of the power load consumption into the optimized DL-LSTM-A deep network model to obtain the quantile; and processing the quantile by adopting a non-parametric