Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting

Nan Qiao; Shuning Wang; Sijing Duan; Wenpeng Cui; Yuzhe Chen; Qingchen Yang; Xingyuan Hua; Ju Ren

cs.LGMar 21, 2026

Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting

Authors: Nan Qiao, Shuning Wang, Sijing Duan, Wenpeng Cui, Yuzhe Chen, Qingchen Yang, Xingyuan Hua, Ju Ren

Organizations: School of Computer Science and Engineering, Central South University, Changsha, Hunan 410083, China · Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing 100084, China · Beijing Smartchip Microelectronics Technology Co., Ltd, Beijing 102200, China

Abstract

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.

Figures & tables

Fig. 1: System model of the proposed cloud-edge PV forecasting.

Symbol	Description
$\mathcal{N}$ , $N$	Set of PV sites and the total number of sites
$t$ , $i$	Time slot index and edge node index
$\mathbf{s}_{i,t}$	Raw local state of node $i$ at time $t$
$\mathbf{x}_{i,t}^{\mathrm{hist}}$	Local historical observation window
$\mathbf{m}_{i,t}$ , $\mathbf{v}_{i,t}$	Meteorological variables
$\mathbf{X}_{i,t}^{\mathrm{loc}}$	Unified local model input

TABLE I: Summary of key notations.

Dataset	Metric	ExO	EdO	CO	ACA	STR	Moirai	AIRG	STKD-PV	CAPE (Ours)
Hunan	nMAE (%FS, $\downarrow$ )	8.54	6.21	3.15	4.10	4.02	3.32	5.54	4.56	3.08
	nRMSE (%FS, $\downarrow$ )	11.23	8.45	4.52	5.91	5.86	4.81	7.23	6.05	4.46
	AUROC ( $\uparrow$ )	–	–	–	0.762	0.755	–	0.685	0.710	0.924
	AUPRC ( $\uparrow$ )	–	–	–	0.654	0.648	–	0.590	0.625	0.885
	REE (%FS, $\downarrow$ )	25.41	18.52	8.56	11.24	11.05	9.04	14.52	12.15	8.45
	DG ( $\downarrow$ )	3.50	2.10	1.15	1.48	1.45	1.18	1.70	1.35	1.12

TABLE II: Performance comparison of different forecasting methods and system baselines on the Hunan and Shanxi datasets. Lower is better for nMAE, nRMSE, REE, and DG, while higher is better for AUROC and AUPRC. All error metrics are reported as full-scale normalized errors (%FS). AUROC/AUPRC are only reported for adaptive-routing methods, while fixed-strategy baselines are marked as “–” since these metrics are not applicable to methods without routing decisions. The best results are shown in bold , and the second-best results are underlined .

Fig. 3: Router action traces at three routing-score levels, where higher scores lead to more frequent escalation to larger models.

Fig. 4: Effect of the Lyapunov trade-off parameter

V

on AUROC under different edge counts

N

Fig. 5: Effect of the Lyapunov trade-off parameter

V

DG

under different edge counts

N

Fig. 6: Sensitivity of

DG

K

under different edge counts

N

Fig. 7: Sensitivity of

DG

\rho_{\max}

under different edge counts

N

Fig. 8: Sensitivity of nMAE to

\tau_{\max}

under different edge counts

N

Explore similar work

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
Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting
Apr 5, 2026Hang Fan, Haoran Pei, Runze Liang +3Solar Power Forecasting Spatiotemporal Forecasting
School of Economic and Management, North China Electric Power University, 102206, Beijing, China · School of Control and Computer Engineering, North China Electric Power University, 102206, Beijing, China · Department of Electrical Engineering, Tsinghua University, 100084, Beijing, China +1
M3S-Net: Multimodal Feature Fusion Network Based on Multi-scale Data for Ultra-short-term PV Power Forecasting
Feb 23, 2026Penghui Niu, Taotao Cai, Suqi Zhang +4Solar Power Forecasting Multimodal Fusion
School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China · University of Southern Queensland, Toowoomba 487-535, Australia · School of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China +3

Jul 9, 2026J/K move · Enter open · S save

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

Hang Fan, Weican Liu, Ying Lu, Dunnan Liu+2

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

Time Series Forecasting Non-Stationary Time Series Forecasting Solar Power Forecasting Physics-Informed ML Retrieval-Augmented Time Series Forecasting

Open paper AskPDF arXiv

Accurate photovoltaic (PV) power forecasting is essential for reliable grid dispatch and renewable energy integration, yet it remains challenging because PV generation is jointly shaped by weather variability, day-night transitions, regime-dependent dynamics, and strict physical constraints. We propose PARA-PV, a Physics-Aware Retrieval-Augmented framework that embeds physical knowledge throughout the forecasting process. The framework first encodes multivariate PV observations into patch-level representations and, through a physics-aware retrieval-augmented learner, retrieves historical patches and analog trajectories that are consistent with the current window in temporal shape, power level, PV operating state, and intra-day period; this yields a physically grounded base forecast. To supplement local memory with broader temporal knowledge, the base forecast is then calibrated against a frozen Chronos time-series foundation-model prior through a lightweight residual adapter, so that general temporal regularities are adapted to PV-specific dynamics without overriding the physically grounded prediction. Because residual conditional distribution shifts persist when weather and diurnal regimes change, a physics-aware distribution shift correction module subsequently adjusts the preliminary forecast using power, weather, timestamp, and day/night conditions, applying gated mean-shift and scale corrections selectively. Finally, a physics-constrained loss function partitions the samples into peak, ramping, night-time, and regular regimes and adaptively reweights their error contributions, preventing the dominant regular regime from suppressing learning of operationally critical states. Our code is available at https://github.com/weican1103/PARA-PV.

Abstract

Explore similar work

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

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

M3S-Net: Multimodal Feature Fusion Network Based on Multi-scale Data for Ultra-short-term PV Power Forecasting