Learning-Based Model Predictive Control of DC-DC Buck Converters in DC Microgrids: A Multi-Agent Deep Reinforcement Learning Approach
Abstract
:1. Introduction
- A learning-based FCS-MPC is proposed to regulate the output voltage of DG units in a DC-MG. A multi-agent DRL-based approach is used to provide an online and adaptive tuning of weighting coefficients of the FCS-MPC.
- Unlike the FCS-MPC with constant coefficients, which are typically designed for a specified operating condition, the proposed approach avoids the dependency of the converter control system on the operating conditions.
- Usually, the control design of the converters follows this presumption that the CPLs are ideal, while in practice, the CPLs are of unknown and/or time-varying character. Hence, the performance of the proposed controller is investigated against the power changes in the non-ideal CPLs.
- One of the critical issues in MGs is DGs’ plug-and-play (PnP) operation due to the inherently discontinuous nature of renewable energy sources. To address this issue, the dynamic performance of the proposed controller is examined under the PnP operation of DG units.
2. Model of Microgrid
3. Proposed Controller Design
4. Multi-Agent DRL-Based Regulation Scheme
Algorithm 1 The pseudo-code for the standard DDPG |
|
5. Simulation Results
- Unknown load dynamics
- Variation of input voltage
- PnP operation
- Variation of reference voltage
5.1. Study 1: Unknown Load Dynamics
5.2. Study 2: Input Voltage Variations
5.3. Study 3: PnP Operation
5.4. Study 4: Variation of Reference Voltage
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
FCS-MPC | Finit Control Set-Model Predictive Control |
DC-MG | DC Microgrid |
MG | Microgrid |
DG | Distributed Generation |
CPL | Constant Power Load |
SMC | Sliding Mode Control |
PI | Proportional-integer |
MPC | Model Predictive Control |
UPS | Uninterrupted Power Supply |
RL | Reinforcement Learning |
DRL | Deep Reinforcemnt Learning |
DQN | Deep Q Network |
DDPG | Deep Deterministic Policy Gradient |
PnP | Pluy and Play |
OF | Objective Function |
ZOH | Zero-Order Hold |
MDP | Decision-making process |
AVF | Active-Value Function |
Variables and Parameters | |
Load current | |
Converter current | |
Converter’s output voltage | |
Capacitor voltage | |
, | Filter parameter |
State variable | |
Control input | |
Exogenous input | |
Reference voltage | |
Angular frequency | |
Predicted voltage | |
Predicted current | |
Voltage weighting coefficient | |
Switching weighting coefficient | |
Current weighting coefficient | |
Current limiting term | |
Switching penalization | |
e | Error between the average of voltages broadcasted |
from each DG and the reference voltage | |
N | Number of DGs |
s | State |
A | Action |
P | State transition probility |
R | Reward |
F | Replay buffer |
m | Total number of transitions in the replay buffer F |
Discount factor | |
Learning rate | |
Anticipated return | |
J | Discount return |
Environment | |
Discounted distribution | |
Specific policy to the current policy |
References
- Oshnoei, S.; Aghamohammadi, M.; Oshnoei, S.; Oshnoei, A.; Mohammadi-Ivatloo, B. Provision of Frequency Stability of an Islanded Microgrid Using a Novel Virtual Inertia Control and a Fractional Order Cascade Controller. Energies 2021, 14, 4152. [Google Scholar] [CrossRef]
- Oshnoei, S.; Aghamohammadi, M.; Oshnoei, S. A novel fractional order controller based on fuzzy logic for regulating the frequency of an Islanded Microgrid. In Proceedings of the International Power System Conference (PSC), Tehran, Iran, 9–11 December 2019; pp. 320–326. [Google Scholar]
- Aguirre, M.; Kouro, S.; Rojas, C.A.; Vazquez, S. Enhanced Switching Frequency Control in FCS-MPC for Power Converters. IEEE Trans. Ind. Electron. 2021, 68, 2470–2479. [Google Scholar] [CrossRef]
- De Bosio, F.; De Souza Ribeiro, L.A.; Freijedo, F.D.; Pastorelli, M.; Guerrero, J.M. Effect of State Feedback Coupling and System Delays on the Transient Performance of Stand-Alone VSI with LC Output Filter. IEEE Trans. Ind. Electron. 2016, 63, 4909–4918. [Google Scholar] [CrossRef] [Green Version]
- Li, D.; Ho, C.N.M. A Module-Based Plug-n-Play DC Microgrid with Fully Decentralized Control for IEEE Empower a Billion Lives Competition. IEEE Trans. Power Electron. 2021, 36, 1764–1776. [Google Scholar] [CrossRef]
- Zhu, X.; Meng, F.; Xie, Z.; Yue, Y. An Inertia and Damping Control Method of DC-DC Converter in DC Microgrids. IEEE Trans. Energy Convers. 2020, 35, 799–807. [Google Scholar] [CrossRef]
- Sorouri, H.; Sedighizadeh, M.; Oshnoei, A.; Khezri, R. An intelligent adaptive control of DC–DC power buck converters. Int. J. Electr. Power Energy Syst. 2022, 141, 108099. [Google Scholar] [CrossRef]
- Kwasinski, A.; Onwuchekwa, C.N.; Member, S. Dynamic Behavior and Stabilization of DC Microgrids With Instantaneous Constant-Power Loads. IEEE Trans. Power Electron. 2011, 26, 822–834. [Google Scholar] [CrossRef]
- Hossain, E.; Perez, R.; Nasiri, A.; Padmanaban, S. A Comprehensive Review on Constant Power Loads Compensation Techniques. IEEE Access 2018, 6, 33285–33305. [Google Scholar] [CrossRef]
- Cespedes, M.; Xing, L.; Sun, J. Constant-power load system stabilization by passive damping. IEEE Trans. Power Electron. 2011, 26, 1832–1836. [Google Scholar] [CrossRef]
- Dragicevic, T.; Vazquez, S.; Wheeler, P. Advanced control methods for power converters in DG systems and microgrids. IEEE Trans. Ind. Electron. 2020, 68, 5847–5862. [Google Scholar] [CrossRef]
- Garcia, C.; Mohammadinodoushan, M.; Yaramasu, V.; Norambuena, M.; Davari, S.A.; Zhang, Z.; Khaburi, D.A.; Rodriguez, J. FCS-MPC based pre-filtering stage for computational efficiency in a flying capacitor converter. IEEE Access 2021, 9, 111039–111049. [Google Scholar] [CrossRef]
- Karamanakos, P.; Geyer, T.; Kennel, R. Computationally efficient optimization algorithms for model predictive control of linear systems with integer inputs. In Proceedings of the 54rd IEEE Conference on Decision and Control, Osaka, Japan, 15–18 December 2015; pp. 3663–3668. [Google Scholar] [CrossRef]
- Grainger, B.M.; Zhang, Q.; Reed, G.F.; Mao, Z.H. Modern controller approaches for stabilizing constant power loads within a DC microgrid while considering system delays. In Proceedings of the 2016 IEEE 7th International Symposium on Power Electronics for Distributed Generation Systems (PEDG 2016), Vancouver, BC, Canada, 27–30 June 2016; pp. 3–8. [Google Scholar] [CrossRef]
- Tiwari, R.; Ramesh Babu, N.; Arunkrishna, R.; Sanjeevikumar, P. Comparison between PI controller and fuzzy logic-based control strategies for harmonic reduction in grid-integrated wind energy conversion system. Lect. Notes Electr. Eng. 2018, 435, 297–306. [Google Scholar] [CrossRef]
- Yoo, H.J.; Nguyen, T.T.; Kim, H.M. MPC with constant switching frequency for inverter-based distributed generations in microgrid using gradient descent. Energies 2019, 12, 1156. [Google Scholar] [CrossRef] [Green Version]
- Ding, D.; Yeganeh, M.S.; Mijatovic, N.; Wang, G.; Dragicevic, T. Model predictive control on three-phase converter for PMSM drives with a small DC-link capacitor. In Proceedings of the 2021 IEEE International Conference on Predictive Control of Electrical Drives and Power Electronics (PRECEDE), Jinan, China, 18–20 September 2021; pp. 224–228. [Google Scholar]
- Sorouri, H.; Sedighizadeh, M. Robust control of DC-DC converter supplying constant power load with Finite-Set Model Predictive Control. In Proceedings of the 12th Power Electronics, Drive Systems, and Technologies Conference (PEDSTC), Tabriz, Iran,, 2–4 February 2021; pp. 1–3. [Google Scholar]
- Khorsandi, A.; Ashourloo, M.; Mokhtari, H.; Iravani, R. Automatic droop control for a low voltage DC microgrid. IET Gener. Transm. Distrib. 2016, 10, 41–47. [Google Scholar] [CrossRef]
- Dragičević, T.; Novak, M. Weighting Factor Design in Model Predictive Control of Power Electronic Converters: An Artificial Neural Network Approach. IEEE Trans. Ind. Electron. 2019, 66, 8870–8880. [Google Scholar] [CrossRef] [Green Version]
- Khezri, R.; Oshnoei, A.; Oshnoei, S.; Bevrani, H.; Muyeen, S.M. An intelligent coordinator design for GCSC and AGC in a two-area hybrid power system. Appl. Soft Comput. J. 2019, 76, 491–504. [Google Scholar] [CrossRef]
- Oshnoei, A.; Sadeghian, O.; Mohammadi-Ivatloo, B.; Freijedo, F.D.; Anvari-Moghaddam, A. Data-driven coordinated control of AVR and PSS in power systems: A deep reinforcement learning method. In Proceedings of the 2021 IEEE International Conference on Environment and Electrical Engineering and 2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), Bari, Italy, 7–10 September 2021. [Google Scholar] [CrossRef]
- Yan, Z.; Xu, Y. Data-driven load frequency control for stochastic power systems: A deep reinforcement learning method with continuous action search. IEEE Trans. Power Syst. 2019, 34, 1653–1656. [Google Scholar] [CrossRef]
- Zhu, J.; Zhu, J.; Wang, Z.; Guo, S.; Xu, C. Hierarchical Decision and Control for Continuous Multitarget Problem: Policy Evaluation with Action Delay. IEEE Trans. Neural Netw. Learn. Syst. 2019, 30, 464–473. [Google Scholar] [CrossRef]
- Wang, Y.; Sun, J.; He, H.; Sun, C. Deterministic Policy Gradient with Integral Compensator for Robust Quadrotor Control. IEEE Trans. Syst. Man Cybern. Syst. 2020, 50, 3713–3725. [Google Scholar] [CrossRef]
- Gheisarnejad, M.; Farsizadeh, H.; Khooban, M.H. A Novel Nonlinear Deep Reinforcement Learning Controller for DC-DC Power Buck Converters. IEEE Trans. Ind. Electron. 2021, 68, 6849–6858. [Google Scholar] [CrossRef]
- Wan, Y.; Dragičević, T.; Mijatovic, N.; Li, C.; Rodriguez, J. Reinforcement learning based weighting factor design of model predictive control for power electronic converters. In Proceedings of the IEEE International Conference on Predictive Control of Electrical Drives and Power Electronics (PRECEDE), Jinan, China, 18–20 September 2021. [Google Scholar]
- Riar, B.S.; Scoltock, J.; Madawala, U.K. Model Predictive Direct Slope Control for Power Converters. IEEE Trans. Power Electron. 2017, 32, 2278–2289. [Google Scholar] [CrossRef]
- Sampedro, C.; Bavle, H.; Rodriguez-Ramos, A.; de la Puente, P.; Campoy, P. Laser-based reactive navigation for multirotor aerial robots using deep reinforcement learning. In Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, 1–5 October 2018; pp. 1024–1031. [Google Scholar]
- Dragičević, T. Dynamic Stabilization of DC Microgrids with Predictive Control of Point-of-Load Converters. IEEE Trans. Power Electron. 2018, 33, 10872–10884. [Google Scholar] [CrossRef] [Green Version]
Refs. | Controller | PnP Capability | Robust | Adaptive | Multi DG Units | CPL |
---|---|---|---|---|---|---|
[7] | ANN-Backstepping | – | ✓ | ✓ | – | ✓ |
[12] | FCS-MPC | – | – | – | – | – |
[16] | FCS-MPC | – | – | – | – | – |
[18] | FCS-MPC | – | ✓ | – | – | ✓ |
[20] | ANN-MPC | – | ✓ | ✓ | – | – |
[26] | DDPGiPI | – | ✓ | ✓ | – | ✓ |
[27] | RL-MPC | – | ✓ | ✓ | – | – |
This paper | DDPG-MPC | ✓ | ✓ | ✓ | ✓ | ✓ |
Parameters | Values |
---|---|
DG1 parameters | mH, F |
DG2 parameters | mHF |
DG3 parameters | mHF |
LC filter on the DG1 | HF |
LC filter on the DG2 | HF |
LC filter on the DG1 | HF |
Input voltage | V |
Sampling time | s |
Switching frequency | kHz |
CPL | W |
Reference voltage | V |
Parameters | Values |
---|---|
Discount factor, | 0.9995 |
Learning rate, | 0.0001 |
Mini-batch size | 128 |
Reply buffer size | 1,000,000 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sorouri, H.; Oshnoei, A.; Novak, M.; Blaabjerg, F.; Anvari-Moghaddam, A. Learning-Based Model Predictive Control of DC-DC Buck Converters in DC Microgrids: A Multi-Agent Deep Reinforcement Learning Approach. Energies 2022, 15, 5399. https://0-doi-org.brum.beds.ac.uk/10.3390/en15155399
Sorouri H, Oshnoei A, Novak M, Blaabjerg F, Anvari-Moghaddam A. Learning-Based Model Predictive Control of DC-DC Buck Converters in DC Microgrids: A Multi-Agent Deep Reinforcement Learning Approach. Energies. 2022; 15(15):5399. https://0-doi-org.brum.beds.ac.uk/10.3390/en15155399
Chicago/Turabian StyleSorouri, Hoda, Arman Oshnoei, Mateja Novak, Frede Blaabjerg, and Amjad Anvari-Moghaddam. 2022. "Learning-Based Model Predictive Control of DC-DC Buck Converters in DC Microgrids: A Multi-Agent Deep Reinforcement Learning Approach" Energies 15, no. 15: 5399. https://0-doi-org.brum.beds.ac.uk/10.3390/en15155399