Wind Power and Meteorological Data from Four Geographic Sites

Four datasets from different geographical locations contain meteorological and power data for wind energy forecasting. The data was used in a study by Usman Ali, last updated in April 2026, to evaluate machine learning algorithms like XGBoost and Support Vector Regression. The file is 5.5 KB in size and is available in XLS format.

Use Cases

• Benchmarking regression algorithms like XGBoost and SVR based on the described performance evaluation.
• Developing wind power forecasting models based on the described meteorological and power features.
• Studying the impact of geographic location on model performance based on the analysis of four distinct sites.

Strengths

• Data has been processed for outliers using Z-score and IQR methods, as described.
• The associated study reports high model performance, with R² values of 0.99 for top algorithms on most sites.
• Released under a permissive CC-BY-4.0 license, allowing for broad reuse.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 5.5 KB, indicating a limited scope.

Provenance

Source

figshare, author Usman Ali.

Collection Method

Likely collected from wind farm operations, but the specific collection method is not detailed.

Freshness

Last updated 2026-04-30 17:54:45; freshness should be verified.

Geography

Data is from four distinct geographical locations, but specific sites are not named.