Dataset of the article - Deep Reinforcement Learning-Based Secondary Control for Microgrids in Islanded Mode

Published: 15 July 2022| Version 1 | DOI: 10.17632/w3r29kbgcf.1
Contributors:
, Vinícius Lacerda, Ricardo Fernandes, Denis Coury

Description

This article proposes an intelligent secondary controller for islanded microgrids using the Deep Deterministic Policy Gradient (DDPG). The proposed controller could maintain the microgrid voltage and frequency stability for three different scenarios. Moreover, the proposed control performance was compared to another one based in the droop method.

Files

Steps to reproduce

Reproduce the training: 1 - Run the Principal.m file. Reproduce the test step: 1 - Run the Principal.m file without the command "train" (at the end of the code); 2 - Load the best agent saved (Agent60.mat); 3 - Configure in MRagent_phasor2.slx one of the cases to be tested; and 4 - Use the command "sim" to run the MRagent_phasor2.slx with the saved_agent.

Institutions

Universidade de Sao Paulo Escola de Engenharia de Sao Carlos, Universitat Politecnica de Catalunya, Universidade Federal de Sao Carlos

Categories

Microgrid Control, Deep Reinforcement Learning

Licence