A novel deep reinforcement learning system is introduced, revolutionizing grid-forming inverter control through an attention-based neural architecture with adaptive policy optimization. The system uniquely integrates real-time stability constraints with multi-objective learning, addressing the fundamental challenges of power system control under uncertain conditions. The approach employs a comprehensive state-space representation incorporating grid dynamics and historical information, complemented by an advanced attention mechanism that enables selective feature prioritization across varying operational conditions. The learning architecture combines a hierarchical policy network structure with a prioritized experience replay mechanism, achieving rapid adaptation and stable control performance. The result validation demonstrates improvements over conventional methods, including a 43.75% reduction in harmonic distortion (from 3.2% to 1.8%), a 46.7% faster dynamic response (8 vs 15 ms), and a 50% extension in stable operation range under weak grid conditions (operational down to short circuit ratio, SCR=1.5). The system maintains 96% inference accuracy while executing within 50  μ s, meeting real-time control requirements. Additionally, the system demonstrates superior power decoupling performance, reducing coupling effects by 80% compared to traditional approaches while maintaining stable operation across diverse grid conditions. Learning-based control systems in power electronics demonstrate strong generalization across various operating conditions while ensuring stability. Integrating deep learning with power system constraints opens up new applications for complex real-time control problems that require adaptability and reliability.

1.
D.
Al Kez
,
A. M.
Foley
,
F.
Ahmed
, and
D. J.
Morrow
, “
Overview of frequency control techniques in power systems with high inverter-based resources: Challenges and mitigation measures
,”
IET Smart Grid
6
,
447
469
(
2023
).
2.
M.
Khan
,
W.
Wu
, and
L.
Li
, “
Grid-forming control for inverter-based resources in power systems: A review on its operation, system stability, and prospective
,”
IET Renewable Power Gener.
18
,
887
907
(
2024
).
3.
A.
Criollo
,
L. I.
Minchala-Avila
,
D.
Benavides
,
P.
Arévalo
,
M.
Tostado-Véliz
,
D.
Sánchez-Lozano
, and
F.
Jurado
, “
Enhancing virtual inertia control in microgrids: A novel frequency response model based on storage systems
,”
Batteries
10
,
18
(
2024
).
4.
B.
Long
,
C.
Hu
,
Z.
Chen
,
J.
Hu
, and
J.
Rodríguez
, “
Transient stability analysis and virtual power compensation of a virtual synchronous generator under low-voltage fault
,”
IEEE Trans. Power Electron.
39
,
12803
12814
(
2024
).
5.
X.
Lin
,
J. C.-H.
Peng
,
Q.
Li
,
D.
Cheng
,
J.
Yu
, and
H.
Wen
, “
Power coupling and stability analysis of GFM due to rotational frames and control loops interaction
,”
Int. J. Electr. Power Energy Syst.
157
,
109829
(
2024
).
6.
C. C.
Liu
,
K. T.
Chi
, and
J.
Yang
, “
Nonlinear behavior and transient stability of grid-following converters using direct power control under weak grid
,”
IEEE Trans. Sustainable Energy
15
,
2287
(
2024
).
7.
N. H.
Abas
,
M. Z. A.
Ab Kadir
,
N.
Azis
,
J.
Jasni
,
N. F.
Ab Aziz
, and
Z. M.
Khurshid
, “
Optimizing grid with dynamic line rating of conductors: A comprehensive review
,”
IEEE Access
12
,
9738
9756
(
2024
).
8.
R.
Debnath
,
D.
Kumar
,
G. S.
Gupta
,
S. R.
Samantaray
, and
E. F.
El-Saadany
, “
A unified novel Koopman based model predictive control scheme to achieve seamless stabilization of nonlinear dynamic transitions in inverter based stochastic microgrid clusters
,”
IEEE Trans. Smart Grid
15
,
5441
(
2024
).
9.
X.
Zhang
,
Z.
Wu
,
Q.
Sun
,
W.
Gu
,
S.
Zheng
, and
J.
Zhao
, “
Application and progress of artificial intelligence technology in the field of distribution network voltage control: A review
,”
Renewable Sustainable Energy Rev.
192
,
114282
(
2024
).
10.
V. S. B.
Kurukuru
,
A.
Haque
,
M. A.
Khan
,
S.
Sahoo
,
A.
Malik
, and
F.
Blaabjerg
, “
A review on artificial intelligence applications for grid-connected solar photovoltaic systems
,”
Energies
14
,
4690
(
2021
).
11.
H.
Issa
,
V.
Debusschere
,
L.
Garbuio
,
P.
Lalanda
, and
N.
Hadjsaid
, “
Artificial intelligence-based controller for grid-forming inverter-based generators
,” in
IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe)
(
IEEE
,
2022
), pp.
1
6
.
12.
S.
Saadatmand
,
M. S. S.
Nia
,
P.
Shamsi
,
M.
Ferdowsi
, and
D. C.
Wunsch
, “
Neural network predictive controller for grid-connected virtual synchronous generator
,” in
North American Power Symposium (NAPS)
(
IEEE
,
2019
), pp.
1
6
.
13.
M. K.
Rajak
and
R.
Pudur
, “
Multiobjective adaptive predictive virtual synchronous generator control strategy for grid stability and renewable integration
,”
Sci. Rep.
15
,
9241
(
2025
).
14.
H.
Du
,
L.
Cai
,
Z.
Ma
,
Z.
Rao
,
X.
Shu
,
S.
Jiang
,
Z.
Li
, and
X.
Li
, “
A method for identifying external short-circuit faults in power transformers based on support vector machines
,”
Electronics
13
,
1716
(
2024
).
15.
H.
Kandezy
and
Z.
Jiang
, “
A mixed algorithm combining SINDy and HAVOK for analyzing power systems with inverter-based resources
,” arXiv:2401.67890 (
2024
).
16.
S. S.
Das
,
P. K.
Ray
,
A. K.
Sahoo
,
K. K.
Singh
,
G.
Dhiman
, and
A.
Singh
, “Artificial intelligence based grid connected inverters for power quality improvement in smart grid applications,”
Comput. Elec. Eng.
93
,
107208
(
2021
).
17.
G.
Porawagamage
,
K.
Dharmapala
,
J. S.
Chaves
,
D.
Villegas
, and
A.
Rajapakse
, “
A review of machine learning applications in power system protection and emergency control: Opportunities, challenges, and future directions
,”
Front. Smart Grids
3
,
1371153
(
2024
).
18.
T.
Thangam
,
N.
Rathika
,
M.
Sivasubramanian
,
R. T.
Kumar
,
V. J.
Manohar
et al, “
Artificial intelligence based reduced switch multilevel inverter for grid connected PV applications
,” in
International Conference on Circuit Power and Computing Technologies (ICCPCT)
(
IEEE
,
2023
), pp.
1781
1787
.
19.
M. K.
Rajak
and
R.
Pudur
, “
Mathematical modelling and dynamic optimization of phase-locked loop systems using hybrid PSO-gradient descent approach
,”
Syst. Sci. Control Eng.
13
,
2448636
(
2025
).
20.
B.
Liu
,
Z.
Song
,
B.
Yu
,
G.
Yang
, and
J.
Liu
, “A feedforward control-based power decoupling strategy for grid-forming grid-connected inverters,”
Energies
17
(
2
),
424
(
2024
).
21.
D. B.
Rathnayake
and
B.
Bahrani
, “
Multivariable control design for grid-forming inverters with decoupled active and reactive power loops
,”
IEEE Trans. Power Elec.
38
(
2
),
1635
1649
(
2023
).
22.
R.
El Helou
,
D.
Kalathil
, and
L.
Xie
, “
Fully decentralized reinforcement learning-based control of photovoltaics in distribution grids for joint provision of real and reactive power
,”
IEEE Open Access J. Power Energy
8
,
175
185
(
2021
).
23.
M.
Parhamfar
,
A.
Zabihi
,
M.
Taheri
, and
B. C.
Oyinna
, “
Enhancing cyber attack detection in microgrids for resilient energy networks
,”
J. Mod. Technol.
1
(
2
),
75
86
2024
), see https://review.journal-of-modern-technology.com/index.php/jmt/article/view/10.
You do not currently have access to this content.