A K-nearest Neighbours Inspired Direct MPC for SOC Balancing in Smart Batteries
Uložené v:
| Názov: | A K-nearest Neighbours Inspired Direct MPC for SOC Balancing in Smart Batteries |
|---|---|
| Autori: | Simonetti, Francesco, Fonso, Roberta, Di, Teodorescu, Remus |
| Prispievatelia: | Aalborg University Aalborg (AAU), GDR SEEDS France & EPE Association |
| Zdroj: | The 26th European Conference on Power Electronics and Applications ; https://utc.hal.science/hal-05100715 ; The 26th European Conference on Power Electronics and Applications, GDR SEEDS France & EPE Association, Mar 2025, Paris, France. ⟨10.34746/epe2025-0209⟩ ; https://epe2025.com/ |
| Informácie o vydavateľovi: | CCSD |
| Rok vydania: | 2025 |
| Zbierka: | Université de Technologie de Compiègne: HAL |
| Predmety: | Machine Leaning, Optimization, MPC (Model-based Predictive Control), Battery Management Systems (BMS), Battery energy storage systems, [SPI.NRJ]Engineering Sciences [physics]/Electric power, [SPI.AUTO]Engineering Sciences [physics]/Automatic |
| Geografické téma: | Paris, France |
| Popis: | International audience ; Lithium-ion batteries dominate energy storage systems. Working circumstances and parameter variations in single cells can result in state of charge imbalances that reduce the battery's lifetime. Modular batteries have been proven to be capable of actively reducing the imbalance among the cells by connecting or bypassing the individual batteries, sharing the work load in real-time. This paper presents a machine learning-inspired direct model predictive control for reconfigurable batteries to balance the cells that solves the underlying optimization problem in polynomial time. |
| Druh dokumentu: | conference object |
| Jazyk: | English |
| DOI: | 10.34746/epe2025-0209 |
| Dostupnosť: | https://utc.hal.science/hal-05100715 https://utc.hal.science/hal-05100715v1/document https://utc.hal.science/hal-05100715v1/file/0209-epe2025-full-16264197.pdf https://doi.org/10.34746/epe2025-0209 |
| Rights: | http://creativecommons.org/licenses/by/ ; info:eu-repo/semantics/OpenAccess |
| Prístupové číslo: | edsbas.7ED1CD6B |
| Databáza: | BASE |
Nájsť tento článok vo Web of Science | Abstrakt: | International audience ; Lithium-ion batteries dominate energy storage systems. Working circumstances and parameter variations in single cells can result in state of charge imbalances that reduce the battery's lifetime. Modular batteries have been proven to be capable of actively reducing the imbalance among the cells by connecting or bypassing the individual batteries, sharing the work load in real-time. This paper presents a machine learning-inspired direct model predictive control for reconfigurable batteries to balance the cells that solves the underlying optimization problem in polynomial time. |
|---|---|
| DOI: | 10.34746/epe2025-0209 |