Approximate Model Predictive Control for Microgrid Energy Management via Imitation Learning
This addresses efficient and reliable microgrid operation for energy systems with increasing renewable integration, representing an incremental improvement through a hybrid method.
The paper tackles microgrid energy management by proposing an imitation learning framework that approximates mixed-integer Economic Model Predictive Control (EMPC) to enable fast, real-time decision-making without online optimization. The learned policy achieves economic performance comparable to EMPC while reducing computation time to 10% of the optimization-based approach.
Efficient energy management is essential for reliable and sustainable microgrid operation amid increasing renewable integration. This paper proposes an imitation learning-based framework to approximate mixed-integer Economic Model Predictive Control (EMPC) for microgrid energy management. The proposed method trains a neural network to imitate expert EMPC control actions from offline trajectories, enabling fast, real-time decision making without solving optimization problems online. To enhance robustness and generalization, the learning process includes noise injection during training to mitigate distribution shift and explicitly incorporates forecast uncertainty in renewable generation and demand. Simulation results demonstrate that the learned policy achieves economic performance comparable to EMPC while only requiring $10\%$ of the computation time of optimization-based EMPC in practice.