Approximating the solution of an economic MPC using artificial neural networks

Abstract

Abstract: Economic model predictive control is a recognized advanced control strategy which calculates control actions by solving an optimization problem in real time. The issue of numerical computation is the main barrier to implementing this type of controller. Deep learning has emerged as a promising solution to reduce the computational cost. This paper proposes a deep learning approximation of an Economic MPC, particularly with artificial neural networks, of the control strategy for managing energy resources in a residential microgrid. Operational data were generated from the solution established by the controller to train, validate and test the neural network using Matlab. Simulation results showed that the proposed approach can approximate the control strategy correctly.

Description

Keywords

deep learning, approximate economic model pre-dictive control, artificial neural networks

Citation

Endorsement

Review

Supplemented By

Referenced By

Creative Commons license

Except where otherwised noted, this item's license is described as Attribution-NonCommercial-NoDerivs 2.5 Argentina