Microgrid control for renewable energy sources based on deep reinforcement learning and numerical optimization approaches
Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ, Tome 19 (2023) no. 3, pp. 391-402
Voir la notice de l'article provenant de la source Math-Net.Ru
Optimal scheduling of battery energy storage system plays crucial part in distributed energy system. As a data driven method, deep reinforcement learning does not require system knowledge of dynamic system, present optimal solution for nonlinear optimization problem. In this research, financial cost of energy consumption reduced by scheduling battery energy using deep reinforcement learning method (RL). Reinforcement learning can adapt to equipment parameter changes and noise in the data, while mixed-integer linear programming (MILP) requires high accuracy in forecasting power generation and demand, accurate equipment parameters to achieve good performance, and high computational cost for large-scale industrial applications. Based on this, it can be assumed that deep RL based solution is capable of outperform classic deterministic optimization model MILP. This study compares four state-of-the-art RL algorithms for the battery power plant control problem: PPO, A2C, SAC, TD3. According to the simulation results, TD3 shows the best results, outperforming MILP by 5 % in cost savings, and the time to solve the problem is reduced by about a factor of three.
Keywords:
reinforcement learning, energy management system, distributed energy system, numerical optimization.
@article{VSPUI_2023_19_3_a6,
author = {A. Yu. Zhadan and H. Wu and P. S. Kudin and Y. Zhang and O. L. Petrosian},
title = {Microgrid control for renewable energy sources based on deep reinforcement learning and numerical optimization approaches},
journal = {Vestnik Sankt-Peterburgskogo universiteta. Prikladna\^a matematika, informatika, processy upravleni\^a},
pages = {391--402},
publisher = {mathdoc},
volume = {19},
number = {3},
year = {2023},
language = {en},
url = {http://geodesic.mathdoc.fr/item/VSPUI_2023_19_3_a6/}
}
TY - JOUR AU - A. Yu. Zhadan AU - H. Wu AU - P. S. Kudin AU - Y. Zhang AU - O. L. Petrosian TI - Microgrid control for renewable energy sources based on deep reinforcement learning and numerical optimization approaches JO - Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ PY - 2023 SP - 391 EP - 402 VL - 19 IS - 3 PB - mathdoc UR - http://geodesic.mathdoc.fr/item/VSPUI_2023_19_3_a6/ LA - en ID - VSPUI_2023_19_3_a6 ER -
%0 Journal Article %A A. Yu. Zhadan %A H. Wu %A P. S. Kudin %A Y. Zhang %A O. L. Petrosian %T Microgrid control for renewable energy sources based on deep reinforcement learning and numerical optimization approaches %J Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ %D 2023 %P 391-402 %V 19 %N 3 %I mathdoc %U http://geodesic.mathdoc.fr/item/VSPUI_2023_19_3_a6/ %G en %F VSPUI_2023_19_3_a6
A. Yu. Zhadan; H. Wu; P. S. Kudin; Y. Zhang; O. L. Petrosian. Microgrid control for renewable energy sources based on deep reinforcement learning and numerical optimization approaches. Vestnik Sankt-Peterburgskogo universiteta. Prikladnaâ matematika, informatika, processy upravleniâ, Tome 19 (2023) no. 3, pp. 391-402. http://geodesic.mathdoc.fr/item/VSPUI_2023_19_3_a6/