Neural Network-Based Approximation of Continuous Control Set MPC for the Primary Control of DERs in AC Microgrids
- 12 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Smart Grid
- Vol. 17 (3) , 2033-2046
Abstract
This article presents the design and functional validation of deep neural network-based approximators for the control policy of constrained model predictive control applied to a distributed energy resource unit operating in grid-supporting mode within an AC microgrid. The control scheme follows a conventional cascaded architecture, consisting of a zero-level control loop that regulates the DER output voltage, and a primary control loop responsible for balancing power supply and demand. Simulations show that the control policy approximated using neural networks achieves functional performance equivalent to a conventional implicit formulation of MPC. Moreover, the execution time of neural networks is expected to scale better to high-dimensional optimization problems compared to conventional iterative solvers. Experimental validation was carried out on a lab-scale plant prototype with controllers executed on dSPACE MicroLabBox platform. To meet execution-time requirements for a target control interval of $200\mu $ s, the conventional implicit formulation requires simplifying the constraints, which restrict the maximum actuation voltage, and adopting a short prediction horizon. In contrast, the neural-network-based controller enables the use of more complex constraint sets and a longer prediction horizon, thereby maximizing the utilization of the variable inverter voltage.Keywords
Funding Information
- Agencia Nacional de Investigación y Desarrollo (1211630)
- Agencia Nacional de Investigación y Desarrollo (1211676)
- Agencia Nacional de Investigación y Desarrollo (AFB180002)
- Agencia Nacional de Investigación y Desarrollo (FB0008)
This publication has 36 references indexed in Scilit:
- Reach-SDP: Reachability Analysis of Closed-Loop Systems with Neural Network Controllers via Semidefinite Programming2020
- A Neural-Network-Based Model Predictive Control of Three-Phase Inverter With an Output $LC$ FilterIEEE Access, 2019
- Predictive Control for Linear and Hybrid Systems2017
- Simple and systematic LCL filter design for three-phase grid-connected power convertersMathematics and Computers in Simulation, 2016
- Constrained long-horizon direct model predictive control for power electronics2016
- Regions of active damping control for LCL filters2012
- Linear offset-free Model Predictive ControlAutomatica, 2009
- A Survey on Explicit Model Predictive Control2009
- The explicit linear quadratic regulator for constrained systemsAutomatica, 2002
- Constraint handing and stability properties of model‐predictive controlAIChE Journal, 1994