Work

Research on efficiency simulation model of pumping stations based on data-driven methods

Year: 2024

Type: article

Abstract: The pumping station's efficiency is influenced by many factors, causing a significant gap between theoretical and actual efficiency. To solve the problem, this study conducts research on efficiency simulation models of pumping based on data driven from 3 aspects: ①model algorithm, ②feature input and ③response output. 8 machine learning models were introduced to establish pumping efficiency simulation models and they were compared with 2 traditional polynomial regression models, and selected the models with better performance. Then the experiment proposed using “upstream water level + downstream water level” (UWL + DWL) instead of the traditional “head” (H) as feature input to train the models, and discussed the effects on efficiency simulation accuracy with direct fitting efficiency and fitting power then calculate the efficiency through formula. An example analysis was carried out with the historical data of 8 units at Pizhou Station and Suining 2nd Station on the East Line of the South-to-North Water Diversion Project. The experimental results show that ①among all methods, the models based on Gaussian Process Regression (GPR) has the best performance, R2 indicator is close to 0.92. ②After UWL + DWL was used to train the models, all the indicators of the GPR models were improved, the EMA indicator has decreased from an average of 0.39% to 0.26%. ③Then the study found that fitting efficiency directly is better than calculation efficiency after fitting the power, but the R2 of fitting the power is better than efficiency, this may provide another idea for the optimal goal of economic operation of pumping stations. ④On the whole, trainning the GPR models with UWL + DWL to simulate efficiency has the best performance, for example the EMA and EMI indicators of No.4 unit in Pizhou station can be reduced from 16.49% and 20.40% to 0.18% and 1.55% respectively.

Source: Energy Reports

DOI: 10.1016/j.egyr.2024.08.048

Authors: Xiaohui Lei, Jingren Yang, Chao Wang, HE Zhongzheng, Qiaoyin Liu

Institutions: China Institute of Water Resources and Hydropower Research, Guizhou Water Conservancy and Hydropower Survey and Design Institute, Nanchang University

Language: English

Topic: Water Systems and Optimization

Subfield: Civil and Structural Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure, Clean water and sanitation

Open Access status: gold

Estimated APC paid: $2,700