A Machine Learning-Based Model Predictive Control Method for Pumped Storage Systems
Integrated systems required for renewable energy use are under development. These systems impose more stringent control requirements. It is quite challenging to control a pumped storage system (PSS), which is a key component of such power systems. Because of the S-characteristic area of the PSS pump...
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | article |
| Langue: | EN |
| Publié: |
Frontiers Media S.A.
2021
|
| Sujets: | |
| Accès en ligne: | https://doaj.org/article/95836f2206e745e6848d31d7e8b3f0dd |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| id |
oai:doaj.org-article:95836f2206e745e6848d31d7e8b3f0dd |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:95836f2206e745e6848d31d7e8b3f0dd2021-11-08T06:19:48ZA Machine Learning-Based Model Predictive Control Method for Pumped Storage Systems2296-598X10.3389/fenrg.2021.757507https://doaj.org/article/95836f2206e745e6848d31d7e8b3f0dd2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fenrg.2021.757507/fullhttps://doaj.org/toc/2296-598XIntegrated systems required for renewable energy use are under development. These systems impose more stringent control requirements. It is quite challenging to control a pumped storage system (PSS), which is a key component of such power systems. Because of the S-characteristic area of the PSS pump turbine, traditional proportional-integral-derivative (PID) control induces considerable speed oscillation under medium and low water heads. PSSs are difficult to model because of their nonlinear characteristics. Therefore, we propose a machine learning (ML)-based model predictive control (MPC) method. The ML algorithm is based on Koopman theory and experimental data that includes PSS state variables, and is used to establish linear relationships between the variables in high-dimensional space. Subsequently, a simple, accurate mathematical PSS model is obtained. This mathematical model is used via the MPC method to obtain the predicted control quantity value quickly and accurately. The feasibility and effectiveness of this method are simulated and tested under various operating conditions. The results demonstrate that the proposed MPC method is feasible. The MPC method can reduce the speed oscillation amplitude and improve the system response speed more effectively than PID control.Qingsen CaiXingqi LuoXingqi LuoChunyang GaoPengcheng GuoShuaihui SunSina YanPeiyu ZhaoFrontiers Media S.A.articlemodel predictive controlmachine Learningpumped storage systemsustainable hydropowerintelligent controlGeneral WorksAENFrontiers in Energy Research, Vol 9 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
model predictive control machine Learning pumped storage system sustainable hydropower intelligent control General Works A |
| spellingShingle |
model predictive control machine Learning pumped storage system sustainable hydropower intelligent control General Works A Qingsen Cai Xingqi Luo Xingqi Luo Chunyang Gao Pengcheng Guo Shuaihui Sun Sina Yan Peiyu Zhao A Machine Learning-Based Model Predictive Control Method for Pumped Storage Systems |
| description |
Integrated systems required for renewable energy use are under development. These systems impose more stringent control requirements. It is quite challenging to control a pumped storage system (PSS), which is a key component of such power systems. Because of the S-characteristic area of the PSS pump turbine, traditional proportional-integral-derivative (PID) control induces considerable speed oscillation under medium and low water heads. PSSs are difficult to model because of their nonlinear characteristics. Therefore, we propose a machine learning (ML)-based model predictive control (MPC) method. The ML algorithm is based on Koopman theory and experimental data that includes PSS state variables, and is used to establish linear relationships between the variables in high-dimensional space. Subsequently, a simple, accurate mathematical PSS model is obtained. This mathematical model is used via the MPC method to obtain the predicted control quantity value quickly and accurately. The feasibility and effectiveness of this method are simulated and tested under various operating conditions. The results demonstrate that the proposed MPC method is feasible. The MPC method can reduce the speed oscillation amplitude and improve the system response speed more effectively than PID control. |
| format |
article |
| author |
Qingsen Cai Xingqi Luo Xingqi Luo Chunyang Gao Pengcheng Guo Shuaihui Sun Sina Yan Peiyu Zhao |
| author_facet |
Qingsen Cai Xingqi Luo Xingqi Luo Chunyang Gao Pengcheng Guo Shuaihui Sun Sina Yan Peiyu Zhao |
| author_sort |
Qingsen Cai |
| title |
A Machine Learning-Based Model Predictive Control Method for Pumped Storage Systems |
| title_short |
A Machine Learning-Based Model Predictive Control Method for Pumped Storage Systems |
| title_full |
A Machine Learning-Based Model Predictive Control Method for Pumped Storage Systems |
| title_fullStr |
A Machine Learning-Based Model Predictive Control Method for Pumped Storage Systems |
| title_full_unstemmed |
A Machine Learning-Based Model Predictive Control Method for Pumped Storage Systems |
| title_sort |
machine learning-based model predictive control method for pumped storage systems |
| publisher |
Frontiers Media S.A. |
| publishDate |
2021 |
| url |
https://doaj.org/article/95836f2206e745e6848d31d7e8b3f0dd |
| work_keys_str_mv |
AT qingsencai amachinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT xingqiluo amachinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT xingqiluo amachinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT chunyanggao amachinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT pengchengguo amachinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT shuaihuisun amachinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT sinayan amachinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT peiyuzhao amachinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT qingsencai machinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT xingqiluo machinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT xingqiluo machinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT chunyanggao machinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT pengchengguo machinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT shuaihuisun machinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT sinayan machinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems AT peiyuzhao machinelearningbasedmodelpredictivecontrolmethodforpumpedstoragesystems |
| _version_ |
1718442929184309248 |