Processed dataset used in Research study
Description
The study utilizes hourly grid-level solar generation data for the period January 2024 to June 2025, extracted from the publicly available dataset published on Mendeley Data (DOI: 10.17632/5kj8nps8.2)
Files
Steps to reproduce
The data were taken from the public Mendeley Data record by Mukherjee et al. (2025, DOI: 10.17632/y58jknpgs8.2), which compiles hourly grid‑level electricity data for India. I extracted the January 2024–June 2025 solar generation series, aligned it to a strict hourly time index, interpolated only short missing gaps, and removed obvious outliers. From this cleaned solar series, I built purely time‑series features (lags, 24‑hour rolling mean and standard deviation, and calendar variables such as hour of day and day of year) using standard Python tools for time‑series processing.
Institutions
- Guru Nanak InstitutionsTelangana, Hyderabad