Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter Systems
The battery-based multilevel inverter has grown in popularity due to its ability to boost a system’s safety while increasing the effective battery life. Nevertheless, the system’s high degree of freedom, induced by a large number of switches, provides difficulties. In the past, central computation s...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Electricity |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4826/4/3/14 |
| _version_ | 1797580484482433024 |
|---|---|
| author | Ali Mashayekh Sebastian Pohlmann Julian Estaller Manuel Kuder Anton Lesnicar Richard Eckerle Thomas Weyh |
| author_facet | Ali Mashayekh Sebastian Pohlmann Julian Estaller Manuel Kuder Anton Lesnicar Richard Eckerle Thomas Weyh |
| author_sort | Ali Mashayekh |
| collection | DOAJ |
| description | The battery-based multilevel inverter has grown in popularity due to its ability to boost a system’s safety while increasing the effective battery life. Nevertheless, the system’s high degree of freedom, induced by a large number of switches, provides difficulties. In the past, central computation systems that needed extensive communication between the master and the slave module on each cell were presented as a solution for running such a system. However, because of the enormous number of slaves, the bus system created a bottleneck during operation. As an alternative to conventional multilevel inverter systems, which rely on a master–slave architecture for communication, decentralized controllers represent a feasible solution for communication capacity constraints. These controllers operate autonomously, depending on local measurements and decision-making. With this approach, it is possible to reduce the load on the bus system by approximately 90 percent and to enable a balanced state of charge throughout the system with an absolute maximum standard deviation of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.1</mn><mspace width="3.33333pt"></mspace><mo>×</mo><mspace width="3.33333pt"></mspace><msup><mn>10</mn><mrow><mo>−</mo><mn>5</mn></mrow></msup></mrow></semantics></math></inline-formula>. This strategy results in a more reliable and versatile multilevel inverter system, while the load on the bus system is reduced and more precise switching instructions are enabled. |
| first_indexed | 2024-03-10T22:51:39Z |
| format | Article |
| id | doaj.art-e65774f7be5c47a29267a167b31af7b3 |
| institution | Directory Open Access Journal |
| issn | 2673-4826 |
| language | English |
| last_indexed | 2024-03-10T22:51:39Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electricity |
| spelling | doaj.art-e65774f7be5c47a29267a167b31af7b32023-11-19T10:20:30ZengMDPI AGElectricity2673-48262023-07-014323525210.3390/electricity4030014Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter SystemsAli Mashayekh0Sebastian Pohlmann1Julian Estaller2Manuel Kuder3Anton Lesnicar4Richard Eckerle5Thomas Weyh6Department of Electric Power Supply, Universität der Bundeswehr München, 85577 Neubiberg, GermanyDepartment of Electric Power Supply, Universität der Bundeswehr München, 85577 Neubiberg, GermanyDepartment of Electric Power Supply, Universität der Bundeswehr München, 85577 Neubiberg, GermanyBavertis GmbH, 81929 Munich, GermanyDepartment of Electric Power Supply, Universität der Bundeswehr München, 85577 Neubiberg, GermanyDepartment of Electric Power Supply, Universität der Bundeswehr München, 85577 Neubiberg, GermanyDepartment of Electric Power Supply, Universität der Bundeswehr München, 85577 Neubiberg, GermanyThe battery-based multilevel inverter has grown in popularity due to its ability to boost a system’s safety while increasing the effective battery life. Nevertheless, the system’s high degree of freedom, induced by a large number of switches, provides difficulties. In the past, central computation systems that needed extensive communication between the master and the slave module on each cell were presented as a solution for running such a system. However, because of the enormous number of slaves, the bus system created a bottleneck during operation. As an alternative to conventional multilevel inverter systems, which rely on a master–slave architecture for communication, decentralized controllers represent a feasible solution for communication capacity constraints. These controllers operate autonomously, depending on local measurements and decision-making. With this approach, it is possible to reduce the load on the bus system by approximately 90 percent and to enable a balanced state of charge throughout the system with an absolute maximum standard deviation of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.1</mn><mspace width="3.33333pt"></mspace><mo>×</mo><mspace width="3.33333pt"></mspace><msup><mn>10</mn><mrow><mo>−</mo><mn>5</mn></mrow></msup></mrow></semantics></math></inline-formula>. This strategy results in a more reliable and versatile multilevel inverter system, while the load on the bus system is reduced and more precise switching instructions are enabled.https://www.mdpi.com/2673-4826/4/3/14batterybattery management systemdecentralized controllingmultilevel inverterSoC balancingmulti-agent reinforcement learning |
| spellingShingle | Ali Mashayekh Sebastian Pohlmann Julian Estaller Manuel Kuder Anton Lesnicar Richard Eckerle Thomas Weyh Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter Systems Electricity battery battery management system decentralized controlling multilevel inverter SoC balancing multi-agent reinforcement learning |
| title | Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter Systems |
| title_full | Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter Systems |
| title_fullStr | Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter Systems |
| title_full_unstemmed | Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter Systems |
| title_short | Multi-Agent Reinforcement Learning-Based Decentralized Controller for Battery Modular Multilevel Inverter Systems |
| title_sort | multi agent reinforcement learning based decentralized controller for battery modular multilevel inverter systems |
| topic | battery battery management system decentralized controlling multilevel inverter SoC balancing multi-agent reinforcement learning |
| url | https://www.mdpi.com/2673-4826/4/3/14 |
| work_keys_str_mv | AT alimashayekh multiagentreinforcementlearningbaseddecentralizedcontrollerforbatterymodularmultilevelinvertersystems AT sebastianpohlmann multiagentreinforcementlearningbaseddecentralizedcontrollerforbatterymodularmultilevelinvertersystems AT julianestaller multiagentreinforcementlearningbaseddecentralizedcontrollerforbatterymodularmultilevelinvertersystems AT manuelkuder multiagentreinforcementlearningbaseddecentralizedcontrollerforbatterymodularmultilevelinvertersystems AT antonlesnicar multiagentreinforcementlearningbaseddecentralizedcontrollerforbatterymodularmultilevelinvertersystems AT richardeckerle multiagentreinforcementlearningbaseddecentralizedcontrollerforbatterymodularmultilevelinvertersystems AT thomasweyh multiagentreinforcementlearningbaseddecentralizedcontrollerforbatterymodularmultilevelinvertersystems |