EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Prediction-Guided and Local-Execution Collaborative MPPT Method for Dynamic Environments: Mechanism Insights and Performance Validation

Xia Wei, Tadiwa Elisha Nyamasvisva, Liu Pan

International Journal of Information and Communication Technology Trends · 28.06.2026 · 6 (1) · 269-282

DOI: 10.66525/ijictt92 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Information and Communication Technology Trends, online erschienen am 28.06.2026. Verfasst von Xia Wei und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamic irradiance variations, temperature disturbances, and partial shading conditions continuously shift the maximum power point (MPP) of photovoltaic (PV) systems, increasing the difficulty of maximum power point tracking (MPPT). Conventional MPPT methods mainly rely on real-time feedback and lack the ability to perceive MPP migration trends under dynamic environments, while existing intelligent MPPT studies primarily focus on prediction accuracy rather than the effective integration of predictive information into control processes. To address this issue, a collaborative MPPT method combining gated recurrent unit (GRU)-based prediction guidance and incremental conductance (INC)-based local execution is proposed. The GRU model provides operating-point trend information, while the INC algorithm ensures feedback-based regulation and stable convergence. The proposed method is evaluated under dynamic irradiance variations, temperature disturbances, partial shading conditions, and composite dynamic conditions. Results show that the GRU–INC framework achieves higher tracking efficiency, lower tracking error, and more stable operating trajectories than the conventional INC-based approach, particularly under partial shading and composite dynamic conditions. Ablation studies further demonstrate that the performance improvement mainly originates from the collaboration between prediction guidance and real-time feedback rather than from the prediction module alone. The results confirm the effectiveness of the proposed collaborative mechanism for MPPT under dynamic environments and highlight the benefit of integrating prediction guidance with feedback regulation

Zitieren

APA

Wei, X., Nyamasvisva, T. E., & Pan, L. (2026). A Prediction-Guided and Local-Execution Collaborative MPPT Method for Dynamic Environments: Mechanism Insights and Performance Validation. International Journal of Information and Communication Technology Trends, 6(1), 269-282. https://doi.org/10.66525/ijictt92

Vancouver

Wei X, Nyamasvisva TE, Pan L. A Prediction-Guided and Local-Execution Collaborative MPPT Method for Dynamic Environments: Mechanism Insights and Performance Validation. International Journal of Information and Communication Technology Trends. 2026;6(1):269-282. doi:10.66525/ijictt92

BibTeX
@article{Wei2026,
  author = {Wei, Xia and Nyamasvisva, Tadiwa Elisha and Pan, Liu},
  title = {A Prediction-Guided and Local-Execution Collaborative MPPT Method for Dynamic Environments: Mechanism Insights and Performance Validation},
  journal = {International Journal of Information and Communication Technology Trends},
  year = {2026},
  volume = {6},
  number = {1},
  pages = {269--282},
  doi = {10.66525/ijictt92}
}
Kostenlos starten →