A Novel GRA-NARX Model for Water Level Prediction of Pumping Stations

Liu, Xiaowei; Ha, Ming-Hu; Lei, Xiaohui; Zhang, Zhao

doi:10.3390/w14192954

Cited by 6 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other research uses the Artificial Neural Network algorithm (Kartini et al, 2021;Mohammed et al, 2022;Jayathilake et al, 2023). Apart from that, there are also those that use the GRA-NARX Neural Network algorithm (Liu et al, 2022), Multilayer Perceptron Neural Network, Elman Neural Network (Deng et al, 2022) and Transformer Neural Network (Xu et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Long Short-Term Memory Optimization Using Hybrid Sparrow Search Algorithm and Particle Swarm Optimization in Prediction of Water Level at Sluice Gates

Farisi,

Hardjianto

2024

Astonjadro

View full text Add to dashboard Cite

During the period from 2014 to 2020, approximately 24 out of 44 districts in Jakarta experienced flooding disasters. Notably, at the beginning of January 2020, the Manggarai floodgate recorded a water height of 962 cm, categorized under Alert Level 1, indicating a critical and hazardous situation that required the evacuation of residents to safe places. This circumstance prompted the local government to enhance the monitoring and prediction system for water levels across all floodgates in the DKI Jakarta region. By utilizing improved water height predictions, the government can prepare more effective mitigation measures, such as reinforcing embankments, improving water channels, and implementing preventive actions prior to the occurrence of flooding disasters. The forecasting technique employing Long Short-Term Memory (LSTM) has been widely employed in previous research to predict water heights. Unfortunately, the accuracy of LSTM heavily depends on the manual selection of hyperparameters. The optimization of hyperparameters in LSTM is essential to find the optimal combination of values that influence the performance of the LSTM network. The objective is to maximize the model's performance, such as accuracy or lower error rates on previously unseen data. This optimization process plays a crucial role in achieving good results from the LSTM model, as the right choice of hyperparameters can yield a model that better understands complex patterns in the data. This research aims to determine the optimal hyperparameters using a hybrid optimization method. The hyperparameter optimization involves a combined approach of Sparrow Search Algorithm (SSA) and Particle Swarm Optimization (PSO) known as Hybrid SSA-PSO. This hybrid method is employed to reduce the error rate in predictions. The research outcomes, utilizing the Hybrid SSA-PSO optimization, revealed the smallest Root Mean Square Error (RMSE) evaluation at the Pulo Gadung water gate, measuring 9,553.

show abstract

Section: Introductionmentioning

confidence: 99%

Long Short-Term Memory Optimization Using Hybrid Sparrow Search Algorithm and Particle Swarm Optimization in Prediction of Water Level at Sluice Gates

Farisi,

Hardjianto

2024

Astonjadro

View full text Add to dashboard Cite

show abstract

“…On the basis of predecessors' research results and objective problems, this paper taken the foundation pit of a pumping station project in Wenzhou as the object, and comprehensively used the methods of correlation analysis, GRA [5] and scaling method to fuse and mine the monitoring data, and put forward a foundation pit risk assessment system based on the monitoring data, and used this system to comprehensively judge the foundation pit construction safety, with a view to improving the comprehensive judgment level of water conservancy foundation pit safety and providing reference for similar projects.…”

Section: Introductionmentioning

confidence: 99%

Construction of risk assessment system of a typical foundation pit based on monitoring data

Sha,

Zhang,

Tang

2024

Atlantis Highlights in Engineering

View full text Add to dashboard Cite

Taking the foundation pit of a pumping station project in Wenzhou as the object, a risk assessment system was constructed by making full use of routine monitoring items and monitoring data, and the foundation pit construction safety was comprehensively judged by using this system. The research results showed that: (1) the introduction of correlation calculation and GRA to prioritize the monitoring items can reduce the subjectivity of the evaluation system and improve the reliability of the system; (2) Using the risk assessment system, the dynamic changes of the overall safety of the foundation pit could be effectively presented, which was of great significance for guiding the safe construction of the project.

show abstract

Research on an optimal operation model for cascade pumping stations based on simulations

Zheng,

Gao,

Yang

et al. 2024

Irrigation and Drainage

View full text Add to dashboard Cite

Cascade pumping stations (CPS) consume a large amount of energy every year in lifting districts. To obtain a reasonable and feasible operation scheme for CPS, this paper proposes an optimal operation model for CPS based on simulations. A one‐dimensional unsteady flow model of open canals was coupled with the optimal operation model of CPS, and an energy‐dominated optimization was proposed with the water level of the inlet pool as the coordinated variable. The optimization model was solved by using the catch‐up method and the nondominated sorted genetic algorithm II (NSGA‐II). The optimal operation method was validated and implemented in the first‐stage and second‐stage pumping stations of the Zuncun Irrigation Project by lifting water from the Yellow River in Shanxi province. The results showed that the proposed optimization model can reduce the energy consumption of the CPS by 4% compared with the actual operation. In addition, the optimal operation model of the CPS coupled with simulation can realize the dynamic balance of flow by stabilizing the inlet pool level to operate within a safe range. The energy consumption of the CPS can be reduced by keeping the water level of the intake pool as high a level as possible.

show abstract

A Novel GRA-NARX Model for Water Level Prediction of Pumping Stations

Cited by 6 publications

References 38 publications

Long Short-Term Memory Optimization Using Hybrid Sparrow Search Algorithm and Particle Swarm Optimization in Prediction of Water Level at Sluice Gates

Long Short-Term Memory Optimization Using Hybrid Sparrow Search Algorithm and Particle Swarm Optimization in Prediction of Water Level at Sluice Gates

Construction of risk assessment system of a typical foundation pit based on monitoring data

Research on an optimal operation model for cascade pumping stations based on simulations

Contact Info

Product

Resources

About