gridfm-datakit 0.0.9a0

Data Generation Kit

gridfm-datakit

This library is brought to you by the GridFM team to generate power flow data to train machine learning and foundation models.

---

Installation

1. ⭐ Star the repository on GitHub to support the project!

2. Make sure you have Python 3.10, 3.11, or 3.12 installed. ⚠️ Windows users: Python 3.12 is not supported. Use Python 3.10.11 or 3.11.9.

3. Install gridfm-datakit

   python -m pip install --upgrade pip  # Upgrade pip
   pip install gridfm-datakit
   

4. Install Julia with Powermodels and Ipopt

   gridfm_datakit setup_pm
   

For Developers

To install the latest development version from GitHub, follow these steps instead of step 3.

git clone https://github.com/gridfm/gridfm-datakit.git
cd "gridfm-datakit"
python3 -m venv venv
source venv/bin/activate
python -m pip install --upgrade pip  # Upgrade pip to ensure compatibility with pyproject.toml
pip3 install -e '.[test,dev]'

Getting Started

Option 1: Run data gen using interactive interface

To use the interactive interface, either open scripts/interactive_interface.ipynb or copy the following into a Jupyter notebook and follow the instructions:

from gridfm_datakit.interactive import interactive_interface
interactive_interface()

Option 2: Using the command line interface

Generate Data

Run the data generation routine from the command line:

gridfm-datakit generate path/to/config.yaml

Validate Data

Validate generated power flow data for integrity and physical consistency:

gridfm-datakit validate /path/to/data/ [--n-scenarios N] [--sn-mva 100]

Compute Statistics

Generate statistics plots from generated data:

gridfm-datakit stats /path/to/data/ [--sn-mva 100]

Plot Feature Distributions

Create violin plots for bus feature distributions:

gridfm-datakit plots /path/to/data/ [--output-dir DIR] [--sn-mva 100]

Configuration Overview

Refer to the sections Network, Load Scenarios, and Topology perturbations of the documentation for a description of the configuration parameters.

Sample configuration files are provided in scripts/config, e.g. default.yaml:

network:
  name: "case24_ieee_rts" # Name of the power grid network (without extension)
  source: "pglib" # Data source for the grid; options: pglib, file
  # WARNING: the following parameter is only used if source is "file"
  network_dir: "scripts/grids" # if using source "file", this is the directory containing the network file (relative to the project root)

load:
  generator: "agg_load_profile" # Name of the load generator; options: agg_load_profile, powergraph
  agg_profile: "default" # Name of the aggregated load profile
  scenarios: 10000 # Number of different load scenarios to generate
  # WARNING: the following parameters are only used if generator is "agg_load_profile"
  # if using generator "powergraph", these parameters are ignored
  sigma: 0.2 # max local noise
  change_reactive_power: true # If true, changes reactive power of loads. If False, keeps the ones from the case file
  global_range: 0.4 # Range of the global scaling factor. used to set the lower bound of the scaling factor
  max_scaling_factor: 4.0 # Max upper bound of the global scaling factor
  step_size: 0.1 # Step size when finding the upper bound of the global scaling factor
  start_scaling_factor: 1.0 # Initial value of the global scaling factor

topology_perturbation:
  type: "random" # Type of topology generator; options: n_minus_k, random, none
  # WARNING: the following parameters are only used if type is not "none"
  k: 1 # Maximum number of components to drop in each perturbation
  n_topology_variants: 20 # Number of unique perturbed topologies per scenario
  elements: [branch, gen] # elements to perturb. options: branch, gen

generation_perturbation:
  type: "cost_permutation" # Type of generation perturbation; options: cost_permutation, cost_perturbation, none
  # WARNING: the following parameter is only used if type is "cost_permutation"
  sigma: 1.0 # Size of range use for sampling scaling factor

admittance_perturbation:
  type: "random_perturbation" # Type of admittance perturbation; options: random_perturbation, none
  # WARNING: the following parameter is only used if type is "random_perturbation"
  sigma: 0.2 # Size of range used for sampling scaling factor

settings:
  num_processes: 16 # Number of parallel processes to use
  data_dir: "./data_out" # Directory to save generated data relative to the project root
  large_chunk_size: 1000 # Number of load scenarios processed before saving
  overwrite: true # If true, overwrites existing files, if false, appends to files
  mode: "pf" # Mode of the script; options: pf, opf. pf: power flow data where one or more operating limits – the inequality constraints defined in OPF, e.g., voltage magnitude or branch limits – may be violated. opf:  datapoints for training OPF solvers, with cost-optimal dispatches that satisfy all operating limits (OPF-feasible)
  include_dc_res: true # If true, also stores the results of dc power flow (in addition to the results AC power flow). does not work with mode "opf"
  enable_solver_logs: true # If true, write OPF/PF logs to {data_dir}/solver_log; PF fast and DCPF fast do not log.
  pf_fast: true # Whether to use fast PF solver by default (compute_ac_pf from powermodels.jl); if false, uses Ipopt-based PF. Some networks e.g. case10000_goc do not work with pf_fast: true. pf_fast is faster and more accurate than the Ipopt-based PF.
  dcpf_fast: true # Whether to use fast DCPF solver by default (compute_dc_pf from PowerModels.jl)
  max_iter: 200 # Max iterations for Ipopt-based solvers

Output Files

The data generation process writes the following artifacts under: {settings.data_dir}/{network.name}/raw

• tqdm.log: Progress bar log.
• error.log: Error messages captured during generation.
• args.log: YAML dump of the configuration used for this run.
• scenarios_{generator}.parquet: Load scenarios (per-element time series) produced by the selected load generator.
• scenarios_{generator}.html: Plot of the generated load scenarios.
• scenarios_{generator}.log: Generator-specific notes (e.g., bounds for the global scaling factor when using agg_load_profile).
• bus_data.parquet: Bus-level features for each processed scenario (columns BUS_COLUMNS and, if settings.include_dc_res=True, also DC_BUS_COLUMNS).
• gen_data.parquet: Generator features per scenario (columns GEN_COLUMNS).
• branch_data.parquet: Branch features per scenario (columns BRANCH_COLUMNS).
• y_bus_data.parquet: Nonzero Y-bus entries per scenario with columns [scenario, index1, index2, G, B].
• runtime_data.parquet: Runtime data for each scenario (AC and DC solver execution times).