The electric grid is a key enabling infrastructure for the ambitious transition towards carbon neutrality as we grapple with climate change. With deepening penetration of renewable energy resources and electrified transportation, the reliable and secure operation of the electric grid becomes increasingly challenging. In this paper, we present PSML, a first-of-its-kind open-access multi-scale time-series dataset, to aid in the development of data-driven machine learning (ML) based approaches towards reliable operation of future electric grids. The dataset is generated through a novel transmission + distribution (T+D) co-simulation designed to capture the increasingly important interactions and uncertainties of the grid dynamics, containing electric load, renewable generation, weather, voltage and current measurements at multiple spatio-temporal scales. Using PSML, we provide state-of-the-art ML baselines on three challenging use cases of critical importance to achieve: (i) early detection, accurate classification and localization of dynamic disturbance events; (ii) robust hierarchical forecasting of load and renewable energy with the presence of uncertainties and extreme events; and (iii) realistic synthetic generation of physical-law-constrained measurement time series. We envision that this dataset will enable advances for ML in dynamic systems, while simultaneously allowing ML researchers to contribute towards carbon-neutral electricity and mobility.

We put Full dataset in Zenodo. Please download, unzip and put somewhere for later benchmark results reproduction and data loading and performance evaluation for proposed methods.

wget https://zenodo.org/record/5130612/files/PSML.zip?download=1
7z x 'PSML.zip?download=1' -o./

• File Name
  • ISO_zone_#.csv: CAISO_zone_1.csv contains minute-level load, renewable and weather data from 2018 to 2020 in the zone 1 of CAISO.
• Field Description
  • Field time: Time of minute resolution.
  • Field load_power: Normalized load power.
  • Field wind_power: Normalized wind turbine power.
  • Field solar_power: Normalized solar PV power.
  • Field DHI: Direct normal irradiance.
  • Field DNI: Diffuse horizontal irradiance.
  • Field GHI: Global horizontal irradiance.
  • Field Dew Point: Dew point in degree Celsius.
  • Field Solar Zeinth Angle: The angle between the sun's rays and the vertical direction in degree.
  • Field Wind Speed: Wind speed (m/s).
  • Field Relative Humidity: Relative humidity (%).
  • Field Temperature: Temperature in degree Celsius.

• File Name
  • case #: The case 0 folder contains all data of scenario setting #0.
    • pf_input_#.txt: Selected load, renewable and solar generation for the simulation.
    • pf_result_#.csv: Voltage at nodes and power on branches in the transmission system via T+D simualtion.
• Filed Description
  • Field time: Time of minute resolution.
  • Field Vm_###: Voltage magnitude (p.u.) at the bus ### in the simulated model.
  • Field Va_###: Voltage angle (rad) at the bus ### in the simulated model.
  • Field P_#_#_#: P_3_4_1 means the active power transferring in the #1 branch from the bus 3 to 4.
  • Field Q_#_#_#: Q_5_20_1 means the reactive power transferring in the #1 branch from the bus 5 to 20.

• File Name
  • Forced Oscillation: The folder contains all forced oscillation cases.
    • row_#: The folder contains all data of the disturbance scenario #.
      • dist.csv: Three-phased voltage at nodes in the distribution system via T+D simualtion.
      • info.csv: This file contains the start time, end time, location and type of the disturbance.
      • trans.csv: Voltage at nodes and power on branches in the transmission system via T+D simualtion.
  • Natural Oscillation: The folder contains all natural oscillation cases.
    • row_#: The folder contains all data of the disturbance scenario #.
      • dist.csv: Three-phased voltage at nodes in the distribution system via T+D simualtion.
      • info.csv: This file contains the start time, end time, location and type of the disturbance.
      • trans.csv: Voltage at nodes and power on branches in the transmission system via T+D simualtion.
• Filed Description

  trans.csv

  • Field Time(s): Time of millisecond resolution.
  • Field VOLT ###: Voltage magnitude (p.u.) at the bus ### in the transmission model.
  • Field POWR ### TO ### CKT #: POWR 151 TO 152 CKT '1 ' means the active power transferring in the #1 branch from the bus 151 to 152.
  • Field VARS ### TO ### CKT #: VARS 151 TO 152 CKT '1 ' means the reactive power transferring in the #1 branch from the bus 151 to 152.

  dist.csv

  • Field Time(s): Time of millisecond resolution.
  • Field ####.###.#: 3005.633.1 means per-unit voltage magnitude of the phase A at the bus 633 of the distribution grid, the one connecting to the bus 3005 in the transmission system.

• Install PSML from source.

git clone https://github.com/tamu-engineering-research/Open-source-power-dataset.git

• Create and activate anaconda virtual environment

conda create -n PSML python=3.7.10
conda activate PSML

• Install required packages

pip install -r ./Code/requirements.txt

We've prepared the standard interfaces of data loaders and evaluators for all of the three time series tasks:

We prepare the following Pytorch data loaders, with both data processing and splitting included. You can easily load data with a few lines for different tasks by simply modifying the task parameter.

from Code.dataloader import TimeSeriesLoader

loader = TimeSeriesLoader(task='forecasting', root='./PSML') # suppose the raw dataset is downloaded and unzipped under Open-source-power-dataset
train_loader, test_loader = loader.load(batch_size=32, shuffle=True)

We also provide evaluators to support fair comparison among different approaches. The evaluator receives the dictionary input_dict (we specify key and value format of different tasks in evaluator.expected_input_format), and returns another dictionary storing the performance measured by task-specific metrics (explanation of key and value can be found in evaluator.expected_output_format).

from Code.evaluator import TimeSeriesEvaluator
evaluator = TimeSeriesEvaluator(task='classification', root='./PSML') # suppose the raw dataset is downloaded and unzipped under Open-source-power-dataset
# learn the appropriate format of input_dict
print(evaluator.expected_input_format) # expected input_dict format
print(evaluator.expected_output_format) # expected output dict format
# prepare input_dict
input_dict = {
    'classification': classfication,
    'localization': localization,
    'detection': detection,
}
result_dict = evaluator.eval(input_dict)
# sample output: {'#samples': 110, 'classification': 0.6248447204968943, 'localization': 0.08633372048006195, 'detection': 42.59349593495935}

Please see detailed explanation and comments in each subfolder.

• BenchmarkModel
  • EventClassification: baseline models for event detection, classification and localization
  • LoadForecasting: baseline models for hierarchical load and renewable point forecast and prediction interval
  • Synthetic Data Generation: baseline models for synthetic data generation of physical-laws-constrained PMU measurement time series
• Joint Simulation: python codes for joint steady-state and transient simulation between transmission and distribution systems
• Data Processing: python codes for collecting the real-world load and weather data

The PSML dataset is published under CC BY 4.0 license, meaning everyone can use it for non-commercial research purpose.

• Please cite the following paper when you use this data hub:

@article{zheng2021psml,
  title={PSML: A Multi-scale Time-series Dataset for Machine Learning in Decarbonized Energy Grids},
  author={Zheng, Xiangtian and Xu, Nan and Trinh, Loc and Wu, Dongqi and Huang, Tong and Sivaranjani, S and Liu, Yan and Xie, Le},
  journal={arXiv preprint arXiv:2110.06324},
  year={2021}
}

Please contact us if you need further technical support or search for cooperation. Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Email contact:   Le Xie,   Yan Liu,   Xiangtian Zheng,   Nan Xu,   Dongqi Wu,   Loc Trinh,   Tong Huang,   S. Sivaranjani.