SolarBoost: Distributed Photovoltaic Power Forecasting Amid Time-varying Grid Capacity

2025-10-23

AI Summary

Distributed photovoltaic (DPV) power forecasting faces critical challenges—including grid-level data scarcity, time-varying installed capacity, and spatial–technological heterogeneity—rendering conventional centralized approaches ineffective. To address these, we propose SolarBoost: the first method to decouple total DPV output into “unit-output function × dynamic installed capacity,” enabling independent modeling of generation patterns and capacity evolution. SolarBoost integrates fine-grained spatial aggregation with an upper-bound approximation optimization algorithm, balancing forecasting accuracy and computational scalability. It unifies time-series modeling, capacity normalization, and distributed aggregation analysis to support efficient training and inference at scale. Empirical evaluation across multiple Chinese cities demonstrates substantial reductions in dispatch errors and associated economic losses. The open-sourced implementation exhibits strong generalizability and practical engineering applicability for real-world DPV forecasting systems.

Technology Category

• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

This paper presents SolarBoost, a novel approach for forecasting power output in distributed photovoltaic (DPV) systems. While existing centralized photovoltaic (CPV) methods are able to precisely model output dependencies due to uniformity, it is difficult to apply such techniques to DPV systems, as DPVs face challenges such as missing grid-level data, temporal shifts in installed capacity, geographic variability, and panel diversity. SolarBoost overcomes these challenges by modeling aggregated power output as a composite of output from small grids, where each grid output is modeled using a unit output function multiplied by its capacity. This approach decouples the homogeneous unit output function from dynamic capacity for accurate prediction. Efficient algorithms over an upper-bound approximation are proposed to overcome computational bottlenecks in loss functions. We demonstrate the superiority of grid-level modeling via theoretical analysis and experiments. SolarBoost has been validated through deployment across various cities in China, significantly reducing potential losses and provides valuable insights for the operation of power grids. The code for this work is available at https://github.com/DAMO-DI-ML/SolarBoost.

Problem

• Forecasting distributed photovoltaic power output accurately
• Overcoming missing data and capacity variation challenges
• Modeling grid-level power via unit output and capacity

Innovation

• Models aggregated output from small grids
• Decouples unit output from dynamic capacity
• Uses upper-bound approximation for efficiency