Intelligent forecasting and techno-economic optimization of a grid-connected hybrid solar-wind system: A case study of Longgang, China

Huning Dai, Ziqian Wang, Mingjie Xia, Yuyam Cheung, Zhiming Guo and Cheng Gong

Renewable Energy, 2026, vol. 256, issue PI

Abstract: Solar and wind energy are among the most abundant renewable resources and are increasingly central to sustainable microgrid development. However, their inherent intermittency creates significant challenges for power quality, stability, and economic feasibility. While many forecasting methods exist, most approaches either address solar and wind independently or lack integration with system-level techno-economic optimization, leaving a gap in reliable decision-support frameworks for hybrid renewable energy systems (HRES). To address this gap, a hybrid forecasting–optimization framework is proposed, combining the African Vulture Optimization Algorithm (AVOA) with the Simple Recurrent Unit (SRU). The AVOA-SRU model predicts Direct Normal Irradiance (DNI) and Wind Speed (WS) with high precision, achieving R2 values of 0.995 and 0.984, respectively, and outperforming advanced baselines. Forecast-informed optimization was then applied to a grid-connected HRES in Longgang, Shenzhen, incorporating Photovoltaic (PV), wind turbines, batteries, electrolyzers, hydrogen storage, Proton exchange membrane fuel cells, and grid interaction. The optimized configuration yielded a Net Present Cost of 49,882,460 $ and a Levelized Cost of Electricity of 0.22 $/kWh. Comparative experiments demonstrated that AVOA surpassed three widely used optimizers by converging faster and producing more cost-effective solutions. Sensitivity analysis revealed that NPC and LCOE are most influenced by PV and battery costs, underscoring the importance of technological cost reductions. Environmental assessment showed an annual reduction of approximately 5484 tons of CO2 compared to a grid-only baseline, translating into avoided carbon costs of nearly 383,900 $ per year. These findings demonstrate that the proposed AVOA-SRU framework not only can enhance forecasting accuracy but also strengthen the economic and environmental performance of HRES, offering a scalable pathway for sustainable energy system design.

Keywords: Renewable energy forecasting; Machine learning; Microgrid; Net present cost; Levelized cost of electricity (search for similar items in EconPapers)
Date: 2026
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148125023006
Full text for ScienceDirect subscribers only

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:eee:renene:v:256:y:2026:i:pi:s0960148125023006

DOI: 10.1016/j.renene.2025.124636

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().