pone.0342331.t007 - <p> </p>

A 5.5 KB Excel file containing data related to a hybrid forecasting method for energy storage power stations. The dataset likely contains results or inputs from a model integrating chaos theory, signal decomposition, and deep learning, optimized with an adaptive genetic algorithm. It was authored by Lingzhi Xi and last updated on April 24, 2026.

Use Cases

• Benchmark day-ahead power forecasting models based on the described MSE, MAE, and R² metrics.
• Study the application of Ensemble Empirical Mode Decomposition (EEMD) and chaotic phase-space reconstruction for feature extraction from power time series.
• Explore hyperparameter optimization for CNN-LSTM-MLP hybrid architectures using an Adaptive Genetic Algorithm.
• Analyze the integration of a refined physical loss model (for batteries, PCS, transformers) with data-driven forecasting techniques.

Strengths

• The underlying research model achieved specific performance metrics: MSE of 6.41 MW², MAE of 7.68 MW, and R² of 0.898.
• Methodology is described in detail, integrating a physical loss model with advanced signal processing and deep learning techniques.
• Data is derived from actual operational data of a 10 MW/20 MWh electrochemical energy storage power station.

Limitations

• Row count and column definitions are unknown; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), indicating limited scope, likely containing summary results or a small sample rather than extensive raw data.
• Description metadata is limited; actual data content and structure require manual inspection.

Provenance

Source

Lingzhi Xi, via figshare.

Collection Method

Likely derived from experiments using operational data from a 10 MW/20 MWh energy storage power station.

Time Range

null

Freshness

Last updated 2026-04-24 17:32:09; freshness should be verified.

Geography

null