Datasets
Standard Dataset
Data-Driven Optimal Power Flow (OPF)
- Citation Author(s):
- Submitted by:
- Altan Unlu
- Last updated:
- Wed, 02/07/2024 - 21:26
- DOI:
- https://doi.org/10.3390/en17040796
- Data Format:
- Links:
- License:
635 Views- Categories:
- Keywords:
Abstract
The dataset contains integrating renewable energy sources into power grids, emphasizing the need for advanced data-driven optimization models for optimal power flow problems. The dataset, which includes comprehensive details on both load and generator buses, covering active and reactive power measurements and voltage magnitudes and angles for the modified IEEE 39 bus system with wind power integration, is ideally suited for data-driven power system analysis studies. The dataset was generated for a part of the experiments. The load data generated from the Monte Carlo simulation and each bus voltage, angle and generator dispatch outputs produced from a power system simulator. Using the data we conducted on research, it evaluates the forecast performance of various data-driven models.
The dataset contains integrating renewable energy sources into power grids, emphasizing the need for advanced data-driven optimization models for optimal power flow problems. The dataset, which includes comprehensive details on both load and generator buses, covering active and reactive power measurements and voltage magnitudes and angles for the modified IEEE 39 bus system with wind power integration, is ideally suited for data-driven power system analysis studies. The dataset was generated for a simulator part of the experiments.The load data generated from the Monte Carlo simulation and each bus voltage, angle and generator dispatch outputs produced from a power system simulator. Using the data we conducted on research, it evaluates the forecast performance of various data-driven models.
If you find this dataset useful for your research, please kindly cite the following paper:
Unlu, A.; Peña, M. Combined MIMO Deep Learning Method for ACOPF with High Wind Power Integration. Energies 2024, 17, 796. https://doi.org/10.3390/en17040796
