VivaKitSolar PV Power Output & Irradiance Forecasting System
Utility-scale day-ahead solar power generation and irradiance forecasting engine trained and evaluated on 2 full years (17,520 hours) of real hourly satellite data from NASA POWER for Bhadla Solar Park (Rajasthan, India), the world's largest solar installation. Combines gradient boosted ensemble regressors with Sandia/Evans-Florschuetz photovoltaic cell thermal physics (NOCT modeling, convective wind cooling, temperature derating, inverter clipping). Achieves a 79.7% error reduction over the classical 24-hour persistence baseline on an unseen held-out annual test year.
Secure checkout by Dodo Payments (UPI, cards). Your personalised download link is e-mailed within 24 hours. One purchase covers one project team of up to 4 students. See terms and refunds.
Our honest results
| AC Power Model R² (vs simulated plant) | 0.9987 (8,760 held-out hours; target simulated from real NASA weather with the standard NOCT/inverter physics model) |
| Normalized RMSE (nRMSE) | 0.99% (Relative to 950 kWac nameplate inverter capacity) |
| AC Power MAE | 4.65 kW (vs. 22.91 kW Persistence Baseline — 79.7% Error Reduction) |
| Pipeline | Real NASA POWER weather (Bhadla, Rajasthan) → physics plant model → ML surrogate; pair with a weather forecast for day-ahead power forecasts |
Evaluated strictly on 8,760 held-out hours from calendar year 2023 without temporal data leakage. Includes 1 MW reference plant model, pre-packaged seasonal scenario profiles, Gradio 6 console with interactive diurnal generator and thermal loss simulator, automated pytest suite, and 15 viva voce questions on solar geometry, NOCT derating, and grid dispatch scheduling.
What's included
- Readable source codeSmall, commented modules you can explain line by line in your viva.
- Demo appA local web app to show your examiners - runs offline on your laptop.
- Trained model + reference resultsSo you can compare your own runs fairly.
- Learning guide with viva Q&ABackground, design choices explained, limitations and extension ideas.
- One-click setup & testsWindows setup script and tests that prove it works on your PC.
- Dataset download scriptFetches the public data from its original source, with the citation.
Dataset credit
NASA Langley Research Center POWER Project hourly meteorological & solar irradiance data for Bhadla Solar Park (NASA Open Data).
Academic integrity
We sell code and teaching, not finished projects. You must understand, extend and write up the work yourself, acknowledge the kit and cite the dataset. No ready-made reports.