Weighted Combined Water Level Prediction Based on Nonlinear Programming Genetic Algorithm

A single prediction method has its own advantages and disadvantages in different aspects. In order to improve the accuracy of water level prediction, a water level prediction method combining The Autoregressive Integrated Moving Average (ARIMA) Model, Exponential Smoothing (ES) model and Long Short-...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2022 7th International Conference on Computational Intelligence and Applications (ICCIA) S. 140 - 145
Hauptverfasser: Wang, Congyou, Cuan, Wanbing, Jia, Lu
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 24.06.2022
Schlagworte:
Aerospace electronics
combined water level prediction
Computational modeling
Lakes
nonlinear programming genetic algorithm
Predictive models
Programming
Resource management
Smoothing methods
weighted combination
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A single prediction method has its own advantages and disadvantages in different aspects. In order to improve the accuracy of water level prediction, a water level prediction method combining The Autoregressive Integrated Moving Average (ARIMA) Model, Exponential Smoothing (ES) model and Long Short-term Memory (LSTM) model through nonlinear programming genetic algorithm is proposed in this paper. By combining the advantages of local search of nonlinear programming and global search of genetic algorithm, this method uses nonlinear programming genetic algorithm to allocate the weights of ARIMA model, ES model and LSTM model, and obtains the final water level prediction result by weighting. The empirical results show that this method not only has higher prediction accuracy than single model, but also has higher prediction accuracy than using nonlinear programming or genetic algorithm to allocate weight.
DOI:10.1109/ICCIA55271.2022.9828456