Assistant decision-making method for new energy microgrid optimal dispatching based on deep learning

Xingchang Wang and Yali Sun

International Journal of Low-Carbon Technologies, 2025, vol. 20, 901-909

Abstract: With the continuous maturation of distributed generation technology, the continuous decrease in the cost of new energy generation, and the rapid development of energy storage devices, microgrid (MG) optimizes the dispatching of distributed units through energy management system, realizes energy complementarity and economic operation in the network, and improves energy utilization. However, the optimal scheduling of electrothermal energy MG involves multi-objective, non-linear and non-convex problems. Traditional methods have difficulties in real-time computation and convergence in the optimal scheduling solution. To solve the above problems, this article proposes a new energy MG optimal scheduling assistant decision-making method based on deep learning. First, an AC–DC HM model including wind power generation, photovoltaic power generation, micro gas turbine, fuel cell, and energy storage device was constructed, and then the optimal scheduling of AC/DC hybrid MG power supply was studied based on an improved particle swarm optimization algorithm. Finally, the optimal scheduling of distributed power supply in MG was simulated and analyzed in island mode and grid-connected mode. Through the comparative analysis of practical examples, it can be seen that the Improved Particle Swarm Optimization (IPSO) proposed in this article effectively improves the stability and accuracy of the scheduling strategy compared with the traditional linear programming algorithm and the classical particle swarm optimization algorithm, and its economic benefits have better advantages in the application of hybrid MG power optimization scheduling.

Keywords: distribution network; distributed photovoltaic; high permeability; quasi-Monte Carlo; risk assessment (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1093/ijlct/ctae193 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oup:ijlctc:v:20:y:2025:i::p:901-909.

Access Statistics for this article

International Journal of Low-Carbon Technologies is currently edited by Saffa B. Riffat

More articles in International Journal of Low-Carbon Technologies from Oxford University Press
Bibliographic data for series maintained by Oxford University Press ().