Comparative study of neuroevolution and deep reinforcement learning for voltage regulation in power systems

The regulation of voltage in transmission networks is becoming increasingly complex due to the dynamic behavior of modern power systems and the growing penetration of renewable generation. This study presents a comparative analysis of three artificial intelligence approaches—Deep Q-Learning (DQL), G...

Descripción completa

Detalles Bibliográficos
Autores: Alarcón Becerra, Adrián|||0009-0000-2842-7944, Albernaz Lacerda Freitas, Vinícius|||0000-0001-8648-9027, Rocca, Roberto|||0000-0001-5996-2755, Talayero Navales, Ana Patricia|||0000-0001-9823-4777, Llombart Estopiñán, Andrés|||0000-0001-6350-4474
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/450731
Acceso en línea:https://hdl.handle.net/2117/450731
https://dx.doi.org/10.3390/inventions10060110
Access Level:acceso abierto
Palabra clave:Voltage regulation
Deep reinforcement learning
Neuroevolution
Particle swarm optimization
Smart grids
GridCal
Reactive power management
On-load tap changer (OLTC)
Àrees temàtiques de la UPC::Enginyeria elèctrica
Descripción
Sumario:The regulation of voltage in transmission networks is becoming increasingly complex due to the dynamic behavior of modern power systems and the growing penetration of renewable generation. This study presents a comparative analysis of three artificial intelligence approaches—Deep Q-Learning (DQL), Genetic Algorithms (GAs), and Particle Swarm Optimization (PSO)—for training agents capable of performing autonomous voltage control. A unified neural architecture was implemented and tested on the IEEE 30-bus system, where the agent was tasked with adjusting reactive power set points and transformer tap positions to maintain voltages within secure operating limits under a range of load conditions and contingencies. The experiments were carried out using the GridCal simulation environment, and performance was assessed through multiple indicators, including convergence rate, action efficiency, and cumulative reward. Quantitative results demonstrate that PSO achieved 3% higher cumulative rewards compared to GA and 5% higher than DQL, while requiring 8% fewer actions to stabilize the system. GA showed intermediate performance with 6% faster initial convergence than DQL but 4% more variable results than PSO. DQL demonstrated consistent learning progression throughout training, though it required approximately 12% more episodes to achieve similar performance levels. The quasi-dynamic validation confirmed PSO’s advantages over conventional AVR-based strategies, achieving voltage stabilization approximately 15% faster. These findings underscore the potential of neuroevolutionary algorithms as competitive alternatives for advanced voltage regulation in smart grids and point to promising research avenues such as topology optimization, hybrid metaheuristics, and federated learning for scalable deployment in distributed power systems.