Remaining Available Energy Prediction for Energy Storage Batteries Based on Interpretable Generalized Additive Neural Network
Precise estimation of the remaining available energy in batteries is not only key to improving energy management efficiency, but also serves as a critical safeguard for ensuring the safe operation of battery systems. To address the challenges associated with energy state estimation under dynamic ope...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Batteries |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-0105/11/7/276 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849246354024431616 |
|---|---|
| author | Ji Qi Pengrui Li Yifan Dong Zhicheng Fu Zhanguo Wang Yong Yi Jie Tian |
| author_facet | Ji Qi Pengrui Li Yifan Dong Zhicheng Fu Zhanguo Wang Yong Yi Jie Tian |
| author_sort | Ji Qi |
| collection | DOAJ |
| description | Precise estimation of the remaining available energy in batteries is not only key to improving energy management efficiency, but also serves as a critical safeguard for ensuring the safe operation of battery systems. To address the challenges associated with energy state estimation under dynamic operating conditions, this study proposes a method for predicting the remaining available energy of energy storage batteries based on an interpretable generalized additive neural network (IGANN). First, considering the variability in battery operating conditions, the study designs a battery working voltage threshold that accounts for safety margins and proposes an available energy state assessment metric, which enhances prediction consistency under different discharge conditions. Subsequently, 12 features are selected from both direct observation and statistical characteristics to capture the operating condition information of the battery, and a dataset is constructed using actual operational data from an energy storage station. Finally, the model is trained and validated on the feature dataset. The validation results show that the model achieves an average absolute error of 2.39%, indicating that it effectively captures the energy variation characteristics within the 0.2 C to 0.6 C dynamic current range. Furthermore, the contribution of each feature is analyzed based on the model’s interpretability, and the model is optimized by utilizing high-contribution features. This optimization improves both the accuracy and runtime efficiency of the model. Finally, a dynamic prediction is conducted for a discharge cycle, comparing the predictions of the IGANN model with those of three other machine learning methods. The IGANN model demonstrates the best performance, with the average absolute error consistently controlled within 3%, proving the model’s accuracy and robustness under complex conditions. |
| format | Article |
| id | doaj-art-c847a0ebc28a455ca4e8ba3368acd280 |
| institution | Kabale University |
| issn | 2313-0105 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Batteries |
| spelling | doaj-art-c847a0ebc28a455ca4e8ba3368acd2802025-08-20T03:58:31ZengMDPI AGBatteries2313-01052025-07-0111727610.3390/batteries11070276Remaining Available Energy Prediction for Energy Storage Batteries Based on Interpretable Generalized Additive Neural NetworkJi Qi0Pengrui Li1Yifan Dong2Zhicheng Fu3Zhanguo Wang4Yong Yi5Jie Tian6Shenzhen Power Supply Co., Ltd., Guangdong Provincial Key Laboratory of Source-Grid-Load-Storage Interactive Collaborative Technology (No. 2024B1212020004), Shenzhen 518000, ChinaSchool of Electrical Engineering, Beijing Jiaotong University, Beijing 100091, ChinaSchool of Electrical Engineering, Beijing Jiaotong University, Beijing 100091, ChinaSchool of Electrical Engineering, Beijing Jiaotong University, Beijing 100091, ChinaSchool of Electrical Engineering, Beijing Jiaotong University, Beijing 100091, ChinaShenzhen Power Supply Co., Ltd., Guangdong Provincial Key Laboratory of Source-Grid-Load-Storage Interactive Collaborative Technology (No. 2024B1212020004), Shenzhen 518000, ChinaShenzhen Power Supply Co., Ltd., Guangdong Provincial Key Laboratory of Source-Grid-Load-Storage Interactive Collaborative Technology (No. 2024B1212020004), Shenzhen 518000, ChinaPrecise estimation of the remaining available energy in batteries is not only key to improving energy management efficiency, but also serves as a critical safeguard for ensuring the safe operation of battery systems. To address the challenges associated with energy state estimation under dynamic operating conditions, this study proposes a method for predicting the remaining available energy of energy storage batteries based on an interpretable generalized additive neural network (IGANN). First, considering the variability in battery operating conditions, the study designs a battery working voltage threshold that accounts for safety margins and proposes an available energy state assessment metric, which enhances prediction consistency under different discharge conditions. Subsequently, 12 features are selected from both direct observation and statistical characteristics to capture the operating condition information of the battery, and a dataset is constructed using actual operational data from an energy storage station. Finally, the model is trained and validated on the feature dataset. The validation results show that the model achieves an average absolute error of 2.39%, indicating that it effectively captures the energy variation characteristics within the 0.2 C to 0.6 C dynamic current range. Furthermore, the contribution of each feature is analyzed based on the model’s interpretability, and the model is optimized by utilizing high-contribution features. This optimization improves both the accuracy and runtime efficiency of the model. Finally, a dynamic prediction is conducted for a discharge cycle, comparing the predictions of the IGANN model with those of three other machine learning methods. The IGANN model demonstrates the best performance, with the average absolute error consistently controlled within 3%, proving the model’s accuracy and robustness under complex conditions.https://www.mdpi.com/2313-0105/11/7/276lithium-ion batteriesremaining available energyinterpretable generalized additive neural networkfeature extraction |
| spellingShingle | Ji Qi Pengrui Li Yifan Dong Zhicheng Fu Zhanguo Wang Yong Yi Jie Tian Remaining Available Energy Prediction for Energy Storage Batteries Based on Interpretable Generalized Additive Neural Network Batteries lithium-ion batteries remaining available energy interpretable generalized additive neural network feature extraction |
| title | Remaining Available Energy Prediction for Energy Storage Batteries Based on Interpretable Generalized Additive Neural Network |
| title_full | Remaining Available Energy Prediction for Energy Storage Batteries Based on Interpretable Generalized Additive Neural Network |
| title_fullStr | Remaining Available Energy Prediction for Energy Storage Batteries Based on Interpretable Generalized Additive Neural Network |
| title_full_unstemmed | Remaining Available Energy Prediction for Energy Storage Batteries Based on Interpretable Generalized Additive Neural Network |
| title_short | Remaining Available Energy Prediction for Energy Storage Batteries Based on Interpretable Generalized Additive Neural Network |
| title_sort | remaining available energy prediction for energy storage batteries based on interpretable generalized additive neural network |
| topic | lithium-ion batteries remaining available energy interpretable generalized additive neural network feature extraction |
| url | https://www.mdpi.com/2313-0105/11/7/276 |
| work_keys_str_mv | AT jiqi remainingavailableenergypredictionforenergystoragebatteriesbasedoninterpretablegeneralizedadditiveneuralnetwork AT pengruili remainingavailableenergypredictionforenergystoragebatteriesbasedoninterpretablegeneralizedadditiveneuralnetwork AT yifandong remainingavailableenergypredictionforenergystoragebatteriesbasedoninterpretablegeneralizedadditiveneuralnetwork AT zhichengfu remainingavailableenergypredictionforenergystoragebatteriesbasedoninterpretablegeneralizedadditiveneuralnetwork AT zhanguowang remainingavailableenergypredictionforenergystoragebatteriesbasedoninterpretablegeneralizedadditiveneuralnetwork AT yongyi remainingavailableenergypredictionforenergystoragebatteriesbasedoninterpretablegeneralizedadditiveneuralnetwork AT jietian remainingavailableenergypredictionforenergystoragebatteriesbasedoninterpretablegeneralizedadditiveneuralnetwork |