7.7.11. Grid Stability

Predict power grid stability from node parameters.

7.7.11.1. Overview

This example predicts the stability of a power grid based on node-level parameters. It helps operators anticipate instability conditions and take preventive actions before grid failures occur.

Application: Smart grid, power system operation, renewable energy integration

Task Type: Time Series Classification

Data Type: Multivariate (node parameters)

Four-Node Star Network:

Four-Node Star Grid

Four-node star network used for grid stability analysis

7.7.11.2. Configuration

common:
  target_module: 'timeseries'
  task_type: 'generic_timeseries_classification'
  target_device: 'F28P55'

dataset:
  dataset_name: 'grid_stability'

training:
  model_name: 'CLS_4k_NPU'
  training_epochs: 50
  batch_size: 32

testing: {}
compilation: {}

7.7.11.3. Running the Example

cd tinyml-modelzoo
./run_tinyml_modelzoo.sh examples/grid_stability/config.yaml

7.7.11.4. Dataset Details

Input Variables:

  • Reaction time of participants

  • Power consumed/produced

  • Price elasticity coefficients

  • Other node parameters

Classes:

  • Stable

  • Unstable

7.7.11.5. See Also