# Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting

arXiv: https://arxiv.org/abs/2606.07457 · HTML: https://mlsanity.com/paper/2606.07457/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning](https://mlsanity.com/paper/2505.23719/) (2025)
- [Moirai 2.0: When Less Is More for Time Series Forecasting](https://mlsanity.com/paper/2511.11698/) (2025)
- [From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting](https://mlsanity.com/paper/2501.02945/) (2025)
- [TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2410.11802/) (2024)
- [Model-Free Renewable Scenario Generation Using Generative Adversarial Networks](https://mlsanity.com/paper/1707.09676/) (2017)
- [Benchmarking Time Series Foundation Models for Short-Term Household Electricity Load Forecasting](https://mlsanity.com/paper/2410.09487/) (2024)
- [SolNet: Open-source deep learning models for photovoltaic power forecasting across the globe](https://mlsanity.com/paper/2405.14472/) (2024)
- [Time Series Foundation Models for Energy Load Forecasting on Consumer Hardware: A Multi-Dimensional Zero-Shot Benchmark](https://mlsanity.com/paper/2602.10848/) (2026)
- [SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Models](https://mlsanity.com/paper/2502.10307/) (2025)

## Built on by (most cited first, 1 of 1)

- [On the Encoding of Calendar Features in Covariate-Informed Time Series Foundation Models](https://mlsanity.com/paper/2610.13676/) (2026)

## Abstract (arXiv)

At commissioning time, Photovoltaic (PV) operators must forecast production before target-site observations are available, limiting the direct use of standard supervised forecasters. This cold-start setting is addressed with a zero-shot pipeline that generates a synthetic production history from plant metadata and meteorological covariates, enabling time-series foundation models (TSFMs) to forecast through inference-time conditioning. Five TSFMs are benchmarked against classical baselines under strict Cold-Start Baseline, Real Feedback, and Self-Forecast Feedback strategies. The evaluation spans 440 PV sites across four datasets and diverse climate regimes. Covariate-aware foundation models outperform baselines by approximately 1.7-2×: TabPFN-TS achieves the lowest error under Real Feedback (MAE 0.514, RMSE 0.721 kWh kWp-1 d-1), while Chronos-2 is most robust under Self-Forecast Feedback. Performance is largely insensitive to the synthetic-history source, indicating that accuracy is driven more by the availability of plausible temporal context than by the specific generator.