Computer Science > Computer Vision and Pattern Recognition
Title:Edge-Adaptive Hiera-Seg Model for Building-Integrated Photovoltaic Power Forecasting
Abstract:Building integrated photovoltaic power forecasting is challenging because facade orientation, rooftop geometry, nearby buildings, vegetation, cloud movement, module temperature, inverter status and edge device reliability jointly affect power generation. This paper proposes an edge-adaptive HieraSeg model for short term BIPV power forecasting with multi-orientation visual-irradiance fusion. RGB facade images, optional thermal cues, irradiance measurements, module temperature, facade orientation, rooftop masks, shading labels, sky condition, historical power and edge device state are aligned into synchronous forecasting windows. HieraSeg extracts hierarchical regions from facade, rooftop, sky, shadow and background images, while the edge-adaptive module changes feature weights under missing frames, latency shifts and local shading changes. The segmentation branch identifies occluded module areas and separates facade, rooftop, sky and background evidence before the forecasting head estimates future BIPV output. Experiments are designed on a simulated multibuilding BIPV dataset with unseen building and unseen orientation tests. The model reports predicted power, confidence interval, dominant evidence, occlusion contribution, orientation contribution and energy-management review priority. This output is intended to show whether the forecast is driven by irradiance change, visible shading, orientation response, stale edge information or recent power history. The framework supports local forecasting at edge controllers with limited communication delay and computing resources, linking visual occlusion, irradiance dynamics and power history to traceable forecasting results for building energy management, microgrid scheduling and BIPV operation planning.
| Comments: | 13 pages, 7 figures, 1 table |
|---|---|
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.21680 [cs.CV] |
| (or arXiv:2611.21680v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21680 arXiv-issued DOI via DataCite (pending registration) |
Submission history
Access Paper:
Additional Features
- Audio Summary
Current browse context:
References & Citations
- Google Scholar
- Semantic Scholar
BibTeX formatted citation
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.