Energy management system scheduling optimization based on an improved generative adversarial network deep reinforcement learning algorithm

Households, as electricity consumers, play a critical role in achieving the carbon peak and carbon neutrality goals. The development of smart grids provides technical support for the efficient integration and distribution of renewable energy, gradually extending to household users. This has led to h...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Engineering applications of artificial intelligence Ročník 161; s. 112129
Hlavní autoři:	Chao, Weipeng, Shi, Yuanbo, Li, Yushuai, Liu, Meng, Leng, Xiaoling
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.12.2025
Témata:	Deep reinforcement learning algorithm Energy management system Energy system efficiency improvement Energy uncertainty management Generative adversarial network Renewable energy Deep reinforcement learning algorithm Energy system efficiency improvement Renewable energy Energy management system Energy uncertainty management Generative adversarial network
ISSN:	0952-1976
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Households, as electricity consumers, play a critical role in achieving the carbon peak and carbon neutrality goals. The development of smart grids provides technical support for the efficient integration and distribution of renewable energy, gradually extending to household users. This has led to higher demands for the stability of electricity supply to address the growing electricity demand and the uncertainties associated with renewable energy. To address this, this paper proposes an improved generative adversarial network and an enhanced deep reinforcement learning algorithm to improve the scheduling capability of the energy management system. First, we introduce an improved wasserstein generative adversarial network that combines stochastic differential equations and autocorrelation penalty terms with the generator. The experimental results demonstrate that the proposed method can generate high-quality time series data. The generated data were used to train our scheduling model, effectively enhancing its generalization capability. Secondly, We introduced the Minmax mechanism to address Q-value estimation bias by utilizing multiple Q-networks. This mechanism first divides the target Q-values into several groups, selects the maximum value from each group, and then takes the minimum among these maxima as the final target Q-value. We applied this mechanism to improve deep reinforcement learning algorithms based on multi-Q-value evaluation. Comparison experiments show that this improvement significantly enhances the algorithm’s performance, outperforming traditional algorithms in terms of convergence, volatility, and final rewards. The energy management system demonstrates stronger adaptability when handling uncertainties arising from renewable energy variations, ensuring reliable power supply and achieving balanced energy management. •Proposed an enhanced GAN capturing data nonlinearity and randomness.•Mitigated deep RL bias and optimized energy scheduling.•Proposed a new evaluation method to stabilize learning and improve reliability.•Proposed a scheduling optimization to enhance system stability under renewable energy.•Extensive experiments demonstrated the improvement’s superiority.
ISSN:	0952-1976
DOI:	10.1016/j.engappai.2025.112129