Wind Power Prediction Data from Four Geographic Sites

Usman Ali published a dataset on 2026-04-30 for analyzing machine learning algorithms in wind power forecasting. The data, stored in an XLS file of 5.5 KB, originates from four different geographical locations and has been processed to remove outliers. It was used to evaluate XGBoost, Random Forest Regression, and Support Vector Regression models for predicting wind power output.

Use Cases

• Benchmarking regression algorithms like XGBoost and SVR based on the described model evaluation.
• Training wind power prediction models based on data from multiple geographic sites.
• Comparing outlier removal methods (Z-score and IQR) on time-series energy data as described in the study.

Strengths

• Data is licensed under CC-BY-4.0, allowing for open sharing and modification.
• The associated study reports high model performance, with R² values of 0.99 for some algorithms across sites.

Limitations

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

Provenance

Source

Usman Ali via figshare

Collection Method

Data likely collected from wind farms; processed by removing outliers using Z-score and IQR methods.

Freshness

Last updated 2026-04-30 17:54:47; freshness should be verified.

Geography

Data from four different geographical locations (specifics unknown).