cs.CVNov 15, 2026

Edge-Adaptive Hiera-Seg Model for Building-Integrated Photovoltaic Power Forecasting

Authors: Na Yu

Organizations: First Highway Engineering Co., Ltd. Chengdu 610000, Sichuan , China

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.

Explore similar work

Mar 21, 2026

Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting

Photovoltaic (PV) power forecasting in edge-enabled grids requires balancing forecasting accuracy, robustness under weather-driven distribution shifts, and strict latency constraints. Existing models work well under normal conditions but often struggle with rare ramp events and unexpected weather changes. Relying solely on cloud-based large models often leads to significant communication delays, which can hinder timely and efficient forecasting in practical grid environments. To address these issues, we propose a condition-adaptive cloud-edge collaborative framework CAPE for PV forecasting. CAPE consists of three main modules: a site-specific expert model for routine predictions, a lightweight edge-side model for enhanced local inference, and a cloud-based large retrieval model that provides relevant historical cases when needed. These modules are coordinated by a screening module that evaluates uncertainty, out-of-distribution risk, weather mutations, and model disagreement. Furthermore, we employ a Lyapunov-guided routing strategy to dynamically determine when to escalate inference to more powerful models under long-term system constraints. The final forecast is produced through adaptive fusion of the selected model outputs. Experiments on two real-world PV datasets demonstrate that CAPE achieves superior performance in terms of forecasting accuracy, robustness, routing quality, and system efficiency.
Sep 14, 2026

Horizon-specific Expert Fusion for Photovoltaic Power Forecasting

Short-term photovoltaic power forecasting requires models to represent regular solar cycles and weather-driven fluctuations whose importance changes with the forecast horizon. This study develops a hierarchical ensemble that combines temporal neural models, historical analogs, state climatology, and gradient-boosted trees. Solar geometry and numerical weather forecasts describe the expected generation conditions, while horizon-specific convex weights combine complementary predictions. A separate calibration step uses available historical forecast errors to account for recent bias. The framework is evaluated on public PVDAQ data at 15--240-minute horizons and on three GEFCom2014 solar zones at hourly horizons up to four hours. On PVDAQ, the ensemble achieves a daylight capacity-normalized mean absolute error of 4.315%, reducing error by 4.11% relative to full-feature LightGBM and by 6.03% relative to fine-tuned Chronos-2 under identical calibration. Expert-removal experiments identify redundancy within the ensemble. Across three training seeds on GEFCom2014, learned fusion improves upon equal weighting but performs comparably to LightGBM. The results support horizon-specific combination as a useful forecasting strategy while showing that its advantage over strong individual models depends on the dataset and evaluation period.
Apr 5, 2026

Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting

Photovoltaic (PV) power forecasting plays a critical role in power system dispatch and market participation. Because PV generation is highly sensitive to weather conditions and cloud motion, accurate forecasting requires effective modeling of complex spatiotemporal dependencies across multiple information sources. Although recent studies have advanced AI-based forecasting methods, most fail to fuse temporal observations, satellite imagery, and textual weather information in a unified framework. This paper proposes Solar-VLM, a large-language-model-driven framework for multimodal PV power forecasting. First, modality-specific encoders are developed to extract complementary features from heterogeneous inputs. The time-series encoder adopts a patch-based design to capture temporal patterns from multivariate observations at each site. The visual encoder, built upon a Qwen-based vision backbone, extracts cloud-cover information from satellite images. The text encoder distills historical weather characteristics from textual descriptions. Second, to capture spatial dependencies across geographically distributed PV stations, a cross-site feature fusion mechanism is introduced. Specifically, a Graph Learner models inter-station correlations through a graph attention network constructed over a K-nearest-neighbor (KNN) graph, while a cross-site attention module further facilitates adaptive information exchange among sites. Finally, experiments conducted on data from eight PV stations in a northern province of China demonstrate the effectiveness of the proposed framework. Our proposed model is publicly available at https://github.com/rhp413/Solar-VLM.