Energy Storage Power Station Day-Ahead Forecast Performance Metrics

5.5 KB of experimental results from a hybrid forecasting model applied to a 10 MW/20 MWh electrochemical energy storage power station. The dataset, authored by Lingzhi Xi and uploaded to figshare in April 2026, contains performance metrics including Mean Squared Error (MSE), Mean Absolute Error (MAE), and Coefficient of Determination (R²) for day-ahead 24-hour power generation forecasts.

Use Cases

• Benchmarking new forecasting algorithms against the reported MSE, MAE, and R² metrics.
• Studying the integration of physical loss models with data-driven deep learning approaches for energy systems.
• Analyzing the performance of hybrid CNN-LSTM-MLP architectures on real-world operational time-series data.

Strengths

• Performance metrics (MSE: 6.41 MW², MAE: 7.68 MW, R²: 0.898) are explicitly reported, allowing for direct comparison.
• Data is derived from actual operational data of a specific 10 MW/20 MWh energy storage power station.
• Published under a permissive CC-BY-4.0 license for reuse.

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 (5.5 KB), indicating limited scope, likely containing summary results rather than raw time-series.

Provenance

Source

figshare, author Lingzhi Xi.

Collection Method

Experiments using actual operational data from an energy storage power station, as described in the associated paper.

Time Range

null

Freshness

Last updated 2026-04-24 17:32:07; freshness should be verified.

Geography

null