In an era of high penetration of renewable energy, accurate photovoltaic (PV) power forecasting is crucial for balancing and scheduling power systems. However, PV power output has uncertainty since it depends on stochastic weather conditions. In this paper, we propose a novel short-term PV forecasting technique using Delaunay triangulation, of which the vertices are three weather stations that enclose a target PV site. By leveraging a Transformer encoder and gated recurrent unit (GRU), the proposed TransGRU model is robust against weather forecast error as it learns feature representation from weather data. We construct a framework based on Delaunay triangulation and TransGRU and verify that the proposed framework shows a 7-15% improvement compared to other state-of-the-art methods in terms of the normalized mean absolute error. Moreover, we investigate the effect of PV aggregation for virtual power plants where errors can be compensated across PV sites. Our framework demonstrates 41-60% improvement when PV sites are aggregated and achieves as low as 3-4% of forecasting error on average.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9824429 | PMC |
http://dx.doi.org/10.3390/s23010144 | DOI Listing |
Sci Rep
January 2025
College of Mechanical Engineering, Taiyuan University of Technology, Taiyuan, 030024, China.
Mining electric shovels are one of the core equipments for open-pit mining, and are currently moving towards intelligent and unmanned transformation, with intelligent mining instead of traditional manual operation. In the excavation operation process, due to the complexity and changeability of the material surfaces, different excavation strategies should be adopted to achieve the optimal excavation trajectory. It is an important research direction to realize the unmanned excavation of electric shovels by studying a trajectory planning method that is not limited to fixed resting angle surface, can comprehensively consider the type of material surfaces and aim at the minimum excavation energy consumption per unit volume.
View Article and Find Full Text PDFPLoS One
November 2024
Facultad de Ingeniería, Universidad Tecnologica de Bolivar, Cartagena, Colombia.
Image segmentation of the corneal endothelium with deep convolutional neural networks (CNN) is challenging due to the scarcity of expert-annotated data. This work proposes a data augmentation technique via warping to enhance the performance of semi-supervised training of CNNs for accurate segmentation. We use a unique augmentation process for images and masks involving keypoint extraction, Delaunay triangulation, local affine transformations, and mask refinement.
View Article and Find Full Text PDFJ Sports Sci
October 2024
Institute of Exercise Training and Sport Informatics, German Sport University Cologne, Cologne, Germany.
The concept of space has been successfully modelled in football using spatiotemporal player data and Voronoi diagrams. Current approaches, however, are narrow in scope by focusing on an inter-team allocation of space to measure space . The present work extends this widespread perspective with an intra-team application of the Voronoi diagram and its dual Delaunay triangulation to measure space .
View Article and Find Full Text PDFSensors (Basel)
September 2024
Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Udupi 576104, Karnataka, India.
J Hazard Mater
December 2024
College of Hydraulic & Environmental Engineering, China Three Gorges University, Yichang 443002, Hubei, China; Engineering Research Center of Eco-environment in Three Gorges Reservoir Region, Ministry of Education, China Three Gorges University, Yichang 443002, Hubei, China. Electronic address:
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!