Constructed regional photovoltaic generation fields improve ultra-short-term distributed solar forecasting

Dayin Chen; Xiaodan Shi; Xin Xu; Zhongyue Su; Shibo Zhu; Dongxiao Zhang; Yuntian Chen; Jinyue Yan

cs.AIOct 12, 2026

Constructed regional photovoltaic generation fields improve ultra-short-term distributed solar forecasting

Authors: Dayin Chen, Xiaodan Shi, Xin Xu, Zhongyue Su, Shibo Zhu, Dongxiao Zhang, Yuntian Chen, Jinyue Yan

Organizations: Zhejiang Key Laboratory of Industrial Intelligence and Digital Twin, Eastern Institute of Technology, Ningbo 315200, China. · Ningbo Key Laboratory of Advanced Manufacturing Simulation, Eastern Institute of Technology, Ningbo 315200, China · Department of Building Environment and Energy Engineering, and the International Centre of Urban Energy Nexus, The Hong Kong Polytechnic University, Hong Kong SAR, China. · Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden.

Abstract

Ultra-short-term forecasting of densely distributed photovoltaic (PV) systems remains challenging because external meteorological and satellite products may not adequately resolve rapid local variations, while heterogeneous PV systems exhibit different generation responses under similar atmospheric conditions. Meanwhile, dense PV fleets provide spatially distributed measurements that reveal regional generation dynamics. Here, we reformulate fleet-level PV forecasting from modeling discrete station time series to predicting explicit, spatially structured regional PV generation fields. We develop SatPV-Field, a regional-to-local forecasting framework that transforms distributed PV measurements into image-like generation fields and models their spatiotemporal evolution. By combining historical PV fields with satellite-derived future shortwave radiation guidance and meteorological forecasts, the framework predicts future regional generation states, which subsequently provide location-specific guidance for individual-station forecasting. Experiments involving 496 distributed PV systems, including 446 source stations and 50 held-out target stations, demonstrate that these regional fields can be effectively forecast and used to improve station-level predictions. The proposed approach reduces station-level MAE by approximately 10.0% relative to the best-performing single-station temporal baseline and by 2.5% relative to a graph-based regional forecasting approach using the same source fleet. These findings establish an explicit spatial-field modeling paradigm that connects regional generation dynamics with individual-site forecasting.

Figures & tables

Fig. 1: Conceptual motivation for representing distributed PV fleets as an explicit regional generation state. (A) Atmospheric observations describe external conditions but cannot fully determine heterogeneous PV generation responses. (B) Distributed PV systems provide spatially distributed measurements that form a regional sensing network capturing generation dynamics. (C) Multi-site PV measurements can be transformed into an explicit and forecastable regional PV generation field, which provides future regional context for downstream station-level forecasting.

Fig. 2: Overview of SatPV-Field. The framework consists of four stages: (1) construction of historical regional PV generation fields from distributed PV measurements; (2) generation of future irradiance guidance from satellite observations; (3) forecasting of future regional PV generation fields by integrating historical field dynamics, future irradiance guidance, and meteorological information; and (4) regional-to-local station forecasting using predicted local field context together with target-site historical PV and future meteorological information.

Fig. 3: Spatial distribution of 446 source stations and 50 held-out target stations in the PV-field domain.

Fig. 4: Representative source-fleet PV observations and their corresponding regional PV generation fields under different generation regimes. Panels (a)–(b), (c)–(d), and (e)–(f) correspond to stable high-generation, spatially heterogeneous generation, and rapidly varying generation, respectively. The left column shows normalized PV measurements at source stations, while the right column shows the constructed source-supported regional PV generation fields.

Method	MAE $\downarrow$	RMSE $\downarrow$	$R^{2}$ $\uparrow$	SSIM $\uparrow$	DeltaCorr $\uparrow$	SignAcc $\uparrow$	Large- $\Delta$ MAE $\downarrow$
Persistence	0.1483	0.2077	0.6098	0.5516	–	0.0000	0.2520
PV-only U-Net	0.0957	0.1398	0.8233	0.6106	0.5760	0.7677	0.1295
PV+NWP U-Net	0.0942	0.1374	0.8293	0.6043	0.5895	0.7736	0.1255
PV+Past SWR U-Net	0.0983	0.1428	0.8157	0.5998	0.5576	0.7571	0.1334
PV+Past SWR+NWP U-Net	0.0950	0.1392	0.8247	0.6004	0.5737	0.7706	0.1281
Proposed field forecaster	0.0880	0.1306	0.8456	0.6297	0.6132	0.7773	0.1207

TABLE I: Regional PV-field forecasting performance. Large-

\Delta

MAE is evaluated over supported pixels with substantial observed changes (

|\Delta P|\geq 0.10

Fig. 5: Qualitative comparison of regional PV-field forecasts at three forecast lead times. Columns show the ground truth, the PV+NWP U-Net prediction and absolute error, and the proposed field prediction and absolute error. All field maps share the same value scale, while both error maps share the same error scale.

Fig. 6: Example of satellite-derived future irradiance guidance. The red dashed box marks the Ningbo PV region within each large-context forecast. The extracted target-region forecasts are shown with the corresponding ground-truth SWR fields and absolute errors at the three future guidance anchors.

Setting	MAE $\downarrow$	RMSE $\downarrow$	$R^{2}$ $\uparrow$	SSIM $\uparrow$
w/o future irradiance guidance	0.0898	0.1336	0.8385	0.6032
w/o temporal alignment	0.0911	0.1350	0.8352	0.6231
Direct-only head	0.0935	0.1336	0.8386	0.6107
Warp-only head	0.1029	0.1445	0.8111	0.5614
w/o adaptive gate	0.0992	0.1389	0.8255	0.5822
Full model	0.0880	0.1306	0.8456	0.6297

TABLE II: Ablation study of future irradiance guidance and regional field-evolution modeling.

Regional information	MAE $\downarrow$	RMSE $\downarrow$	$R^{2}$ $\uparrow$
None (BiLSTM+NWP)	0.0746	0.1084	0.7956
3-NN PV guidance	0.0737	0.1074	0.7995
Future irradiance guidance	0.0713	0.1033	0.8144
Historical PV-field guidance	0.0725	0.1060	0.8048
Predicted future PV-field guidance	0.0672	0.0999	0.8266
Historical graph guidance	0.0719	0.1058	0.8054

TABLE III: Comparison of regional information sources under a common station-level forecasting backbone. All methods are evaluated on the same test records.

Type	Method	MAE $\downarrow$	RMSE $\downarrow$	$R^{2}$ $\uparrow$
Temporal	LSTM+NWP	0.0754	0.1092	0.7927
Temporal	BiLSTM+NWP	0.0746	0.1084	0.7956
Temporal	TCN+NWP	0.0753	0.1086	0.7949
Temporal	Transformer+NWP	0.0783	0.1125	0.7799
Temporal	PatchTST+NWP	0.0778	0.1130	0.7780
Spatio-temporal	STGCN+NWP	0.0758	0.1082	0.7965

TABLE IV: Station-level forecasting performance compared with existing temporal and spatio-temporal methods.

Panel of Figure 11 — Fig. 7: Forecasting performance across forecast lead times. (a) Station-level MAE for BiLSTM+NWP, AGCRN+NWP, and predicted future PV-field guidance. (b) Regional PV-field MAE for Persistence, PV+NWP U-Net, and the proposed field forecaster.

Ratio	Sources	Patch coverage	Median dist. (km)	Field MAE	Station MAE	Wins/50
25%	112	0.6312	2.60	0.1251	0.0699	43
50%	223	0.8002	1.67	0.1063	0.0680	48
75%	335	0.9119	1.22	0.0914	0.0684	47
100%	446	0.9218	1.12	0.0880	0.0670	49

TABLE V: Sensitivity to source-fleet density. Coverage denotes the supported-pixel ratio within local field patches, and wins denote target stations with lower MAE than BiLSTM+NWP. Station-level results are obtained from independently trained density experiments.

Weather conditions (MAE)
Condition	BiLSTM+NWP	PV-field guidance	Reduction
Clear	0.0472	0.0449	4.9%
Partly cloudy	0.1004	0.0921	8.3%
Overcast	0.0801	0.0755	5.7%
Short-term variation conditions (RMSE)
Low variation	0.0621	0.0533	14.2%

TABLE VI: Station-level forecasting performance under different weather and short-term variation conditions. Reduction is calculated relative to BiLSTM+NWP.

Solar Power Forecasting

Solar power forecasting predicts photovoltaic generation and irradiance from weather, imagery, plant data, and recent output to support reliable grid and energy decisions.

See all 45 papers

Foundation-Style Pretraining for Scalable and Transferable Distributed PV Forecasting
Oct 20, 2026Dayin Chen, Xiaodan Shi, Xin Xu +6Solar Power Forecasting Time-Series Foundation Models
Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China · International Centre of Urban Energy Nexus, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China · Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, 315200, China +2
Two-Stage Photovoltaic Forecasting: Separating Weather Prediction from Plant-Characteristics
Mar 4, 2026Philipp Danner, Hermann de MeerSolar Power Forecasting Solar Irradiance Forecasting
University of Passau, Innstraße 41, Passau, Germany
PARA-PV: Physics-Aware Retrieval-Augmented PV Prediction Based on Frozen Foundation Model and Distribution Shift Correction
Jul 9, 2026Hang Fan, Weican Liu, Ying Lu +3Time Series Forecasting Non-Stationary Time Series Forecasting
School of Economics and Management, North China Electric Power University, 102206, Beijing, China · School of Electrical and Electronic Engineering, Nanyang Technological University, 639798, 50 Nanyang Avenue, Singapore · Department of Electrical Engineering, Tsinghua University, 100084, Beijing, China

Oct 20, 2026J/K move · Enter open · S save

Foundation-Style Pretraining for Scalable and Transferable Distributed PV Forecasting

Dayin Chen, Xiaodan Shi, Xin Xu, Zhongyue Su+5

Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China · International Centre of Urban Energy Nexus, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China · Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, 315200, China+2

Solar Power Forecasting Time-Series Foundation Models Self-Supervised Pre-Training Zero-Shot Time Series Forecasting

Open paper AskPDF arXiv

The rapid growth of distributed photovoltaic (PV) generation is increasing the demand for accurate forecasting across large numbers of geographically dispersed stations. Existing approaches are commonly developed for individual sites or specific forecasting horizons, requiring repeated training and maintenance as new stations are integrated and limiting direct reuse at previously unseen sites. To address this scalability gap, this paper presents a domain-specific foundation-style pretraining framework that learns a shared forecasting model from heterogeneous multi-site and multi-horizon PV data. NWP-assisted forecasting is formulated as a sequence-completion problem that unifies historical PV power, meteorological observations, future numerical weather prediction (NWP) forecasts, and time encodings. Three pretraining objectives are designed and systematically evaluated, including forecast-aligned reconstruction, generic reconstruction, and mixed reconstruction. The mixed objective combines the operational structure of PV forecasting with random sequence reconstruction and provides the most balanced performance across forecasting accuracy, degraded NWP conditions, and downstream adaptation. Experiments on 479 distributed PV stations use 340 stations for model development and 139 spatially held-out stations for zero-shot evaluation. Across horizons from 6 hours to 7 days, the multi-site pretrained MR model outperforms representative station-specific and shared baselines, as well as generalist time-series models, including a recent large-scale pretrained foundation model. The pretrained model can also be directly deployed at new PV stations and subsequently adapted to region-specific operational objectives when local data become available, providing a scalable forecasting paradigm for large distributed PV fleets.

Abstract

Solar Power Forecasting

Explore similar work

Foundation-Style Pretraining for Scalable and Transferable Distributed PV Forecasting

Two-Stage Photovoltaic Forecasting: Separating Weather Prediction from Plant-Characteristics

PARA-PV: Physics-Aware Retrieval-Augmented PV Prediction Based on Frozen Foundation Model and Distribution Shift Correction