<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In order to accurately detect the photovoltaic energy storage unit charge state, this paper selects the parameter charge state as the detection quantity in the equivalent model, establishes the PSO-ELM method to detect the charge state of photovoltaic energy storage unit, optimizes the limit learning machine network using the particle swarm optimization algorithm, and improves the problems such as redundancy of neurons in the implicit layer of the limit learning machine and the poor ability to identify the unknown input parameter, so as to increase the detection accuracy of the PSO-ELM method to improve the detection accuracy of photovoltaic energy storage unit charge state. The relative error between the method established in this paper and the results of the PV storage unit charge state detected by the definition method in the charging state is kept within ±1.9%, and the detection accuracy of the improved method in the dynamic working condition can reach about 97%. The PSO-ELM method established in this paper can accurately detect the charge state of PV energy storage units under various conditions, as demonstrated experimentally.</p>
</abstract>

In order to accurately detect the photovoltaic energy storage unit charge state, this paper selects the parameter charge state as the detection quantity in the equivalent model, establishes the PSO-ELM method to detect the charge state of photovoltaic energy storage unit, optimizes the limit learning machine network using the particle swarm optimization algorithm, and improves the problems such as redundancy of neurons in the implicit layer of the limit learning machine and the poor ability to identify the unknown input parameter, so as to increase the detection accuracy of the PSO-ELM method to improve the detection accuracy of photovoltaic energy storage unit charge state. The relative error between the method established in this paper and the results of the PV storage unit charge state detected by the definition method in the charging state is kept within ±1.9%, and the detection accuracy of the improved method in the dynamic working condition can reach about 97%. The PSO-ELM method established in this paper can accurately detect the charge state of PV energy storage units under various conditions, as demonstrated experimentally.

Research on photovoltaic energy storage unit charge state detection method based on improved limit learning machine

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

In order to accurately detect the photovoltaic energy storage unit charge state, this paper selects the parameter charge state as the detection quantity in the...

Research on photovoltaic energy storage unit charge state detection method based on improved limit learning machine

Pubblicato online: 31 gen 2024

Pagine: -

Ricevuto: 18 dic 2023

Accettato: 25 dic 2023

DOI: https://doi.org/10.2478/amns-2024-0176

Parole chiave
Extreme learning machine, Photovoltaic energy storage unit, Charge state detection, Particle swarm optimization algorithm, Parametric charge state

© 2024 Xue Ma et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on photovoltaic energy storage unit charge state detection method based on improved limit learning machine

Pubblicato online: 31 gen 2024

Pagine: -

Ricevuto: 18 dic 2023

Accettato: 25 dic 2023

DOI: https://doi.org/10.2478/amns-2024-0176

Parole chiaveExtreme learning machine, Photovoltaic energy storage unit, Charge state detection, Particle swarm optimization algorithm, Parametric charge state

© 2024 Xue Ma et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Extreme learning machine, Photovoltaic energy storage unit, Charge state detection, Particle swarm optimization algorithm, Parametric charge state