Datasets
Standard Dataset
IEEE 30-bus,118-bus,300-bus dataset for learning for unit commitment
- Citation Author(s):
- Submitted by:
- Zhibo Xu
- Last updated:
- Sat, 10/19/2024 - 07:23
- DOI:
- 10.21227/ggba-yy81
- License:
129 Views- Categories:
- Keywords:
Abstract
The dataset contains IEEE 30-bus, 118-bus, 300-bus dataset we generated for learning for unit commitment. The dataset consists of data from both normal and extended time scales, with a total time span of one year. A data point is defined as the load demand for each period and the on/off status of the units at that moment. This dataset can be used to train a neural network to learn the mapping from load demand information to the on/off status of the units.
The data is stored in three folders: IEEE 30-bus, 118-bus, and 300-bus. In each folder, data_mtco_learning.csv represents the large-scale data with a 4-hour interval, and data_nnfl_learning.csv represents the normal-scale data with a 15-minute interval. The time span of the data is one year. Each row in the .csv file represents the load demand for each period and the on/off status of the units at that moment. In the CSV header, feature_i represents the load demand of the i-th bus during a given period, and label_j represents the on/off status of the j-th unit during that period. In the data_mtco_learning.csv, we introduce the softlabel, which can be interpreted as the probability of the corresponding unit being on status at that period.
