Case 2 Simulation Results for Graph-Based Power Load Forecasting

Case 2 simulation results by Mengze Gu, last updated April 23, 2026. The dataset contains results from a study proposing an Edge Graph Attention Network (EGAT) for power load forecasting, comparing it against GRU, MLP, and LSTM models. The data is stored in a 5.5 KB XLS file.

Use Cases

• Benchmarking graph-based forecasting models against traditional methods like GRU and LSTM based on the described comparison.
• Analyzing the performance trade-offs between forecasting accuracy and computational cost based on the described limitation.
• Studying the impact of graph construction parameters on time-series forecasting performance based on the described connectivity patterns.

Strengths

• Dataset is openly licensed under CC-BY-4.0, permitting reuse with attribution.
• File size is 5.5 KB, indicating a compact and likely focused set of simulation results.

Limitations

• Row count and column-level documentation are unknown, which limits suitability assessment.
• The description suggests the proposed method has increased computational cost and memory usage, which may be reflected in the data.
• Dataset scale is tiny (5.5 KB), indicating very limited scope, likely containing summary results rather than raw training data.

Provenance

Source

Mengze Gu via figshare

Collection Method

Simulation results from a proposed Edge Graph Attention Network (EGAT) model.

Time Range

null

Freshness

Last updated 2026-04-23 17:25:28; freshness should be verified.

Geography

null