Runoff scene reduction method and system based on improved Kernel Herding algorithm

The invention belongs to the field of runoff scene reduction, and particularly discloses a runoff scene reduction method and system based on an improved Kernel Herding algorithm, and the method comprises the steps: employing the maximum mean value difference to measure the distribution difference be...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LIU WAN, XIAO WENJING, CHEN QIN, MO LI, LOU SIJING, TAO YITAO, ZHANG MI, WANG KAISHU, LIU ZIXUAN
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention belongs to the field of runoff scene reduction, and particularly discloses a runoff scene reduction method and system based on an improved Kernel Herding algorithm, and the method comprises the steps: employing the maximum mean value difference to measure the distribution difference between a reserved runoff scene set and an initial runoff scene set; carrying out minimum iteration solution on the distribution difference between the reserved runoff scene set and the initial runoff scene set by adopting a Kernel Herding algorithm, and taking the step length of the pth iteration as 2/(p + 1) in the iteration process; and solving to obtain a corresponding reserved runoff scene set when the distribution difference between the reserved runoff scene set and the initial runoff scene set is minimum, and completing scene reduction of the initial runoff scene set. According to the method, accurate, reliable and universal runoff scene reduction can be realized, and the efficiency and precision of runoff sce