Publication record · 18.cifr/2022.briggs.federated-load-forecast

Federated Learning for Short-Term Residential Load Forecasting

v1.0.0

Christopher Briggs (Keele University), Zhong Fan (Keele University), Peter Andras (Keele University)

RAI18.cifr/2022.briggs.federated-load-forecast

IEEE Open Access Journal of Power and Energy· 2022· doi:10.1109/OAJPE.2022.3206220

This paper investigates federated learning for short-term residential load forecasting, addressing privacy concerns in smart grid data. Local LSTM models are trained on individual household data and aggregated using FedAvg, demonstrating competitive accuracy compared to centralised training while preserving data privacy.

federated learningload forecastingLSTMsmart gridprivacyFedAvg

✦ Research context

What this agent contributes to the literature.

Problem solved

Smart grid operators need accurate short-term load forecasts without accessing private household consumption data.
Centralised training requires aggregating raw data, creating privacy and regulatory risks for residential users.
Prior federated approaches had not been validated specifically for per-household LSTM load forecasting.

Novelty

Applies FedAvg aggregation over LSTM local models for 24-hour residential load forecasting.

Related research

Computing related research...

Canvas contract1-in / 1-out · unpacked into clients, config legacy ports

Sample data

Loading sample data...

Total calls

This month

Citations

Last called

4/15/2026

Image digest

sha256:cb7e3c67f38b28ffac71d28a400b84b3c0903375c53217c78064713a9b8162eb

Invoke command

python main.py

Inputs

input:application/json

Outputs

output:application/json

Citation

Loading DOI…

Invoke

CPU compute only

How to get GPU access: Your university, lab, or company can become a CIFR institutional member. Members get GPU-accelerated runs for all their researchers. Contact us

Pre-filled with the paper's canonical scenario. Click Invoke agent to reproduce the original result, or edit the JSON below to run a counterfactual.

inputapplication/jsonoptional

Unified canvas input. The executor unpacks this JSON blob into legacy per-port files: clients, config

Leave empty to run the paper's canonical scenario.

{
  "clients": {
    "clients": [
      {
        "client_id": "house_01",
        "load": [
          0.3,
          0.28,
          0.25,
          0.22,
          0.21,
          0.23,
          0.35,
          0.52,
          0.61,
          0.58,
          0.54,
          0.5,
          0.48,
          0.45,
          0.47,
          0.55,
          0.63,
          0.7,
          0.68,
          0.6,
          0.55,
          0.45,
          0.38,
          0.32,
          0.3,
          0.27,
          0.24,
          0.22,
          0.2,
          0.22,
          0.34,
          0.5,
          0.6,
          0.57,
          0.53,
          0.49,
          0.47,
          0.44,
          0.46,
          0.54,
          0.62,
          0.69,
          0.67,
          0.59,
          0.54,
          0.44,
          0.37,
          0.31,
          0.29,
          0.26,
          0.23,
          0.21,
          0.19,
          0.21,
          0.33,
          0.49,
          0.59,
          0.56,
          0.52,
          0.48,
          0.46,
          0.43,
          0.45,
          0.53,
          0.61,
          0.68,
          0.66,
          0.58,
          0.53,
          0.43,
          0.36,
          0.3
        ]
      },
      {
        "client_id": "house_02",
        "load": [
          0.45,
          0.42,
          0.39,
          0.37,
          0.36,
          0.38,
          0.5,
          0.68,
          0.79,
          0.75,
          0.71,
          0.67,
          0.64,
          0.61,
          0.63,
          0.72,
          0.81,
          0.89,
          0.86,
          0.77,
          0.71,
          0.59,
          0.51,
          0.46,
          0.44,
          0.41,
          0.38,
          0.36,
          0.35,
          0.37,
          0.49,
          0.67,
          0.78,
          0.74,
          0.7,
          0.66,
          0.63,
          0.6,
          0.62,
          0.71,
          0.8,
          0.88,
          0.85,
          0.76,
          0.7,
          0.58,
          0.5,
          0.45,
          0.43,
          0.4,
          0.37,
          0.35,
          0.34,
          0.36,
          0.48,
          0.66,
          0.77,
          0.73,
          0.69,
          0.65,
          0.62,
          0.59,
          0.61,
          0.7,
          0.79,
          0.87,
          0.84,
          0.75,
          0.69,
          0.57,
          0.49,
          0.44
        ]
      },
      {
        "client_id": "house_03",
        "load": [
          0.2,
          0.18,
          0.16,
          0.15,
          0.14,
          0.16,
          0.24,
          0.38,
          0.45,
          0.43,
          0.4,
          0.37,
          0.35,
          0.33,
          0.34,
          0.4,
          0.47,
          0.53,
          0.51,
          0.45,
          0.41,
          0.34,
          0.27,
          0.22,
          0.21,
          0.19,
          0.17,
          0.16,
          0.15,
          0.17,
          0.25,
          0.39,
          0.46,
          0.44,
          0.41,
          0.38,
          0.36,
          0.34,
          0.35,
          0.41,
          0.48,
          0.54,
          0.52,
          0.46,
          0.42,
          0.35,
          0.28,
          0.23,
          0.22,
          0.2,
          0.18,
          0.17,
          0.16,
          0.18,
          0.26,
          0.4,
          0.47,
          0.45,
          0.42,
          0.39,
          0.37,
          0.35,
          0.36,
          0.42,
          0.49,
          0.55,
          0.53,
          0.47,
          0.43,
          0.36,
          0.29,
          0.24
        ]
      },
      {
        "client_id": "house_04",
        "load": [
          0.55,
          0.52,
          0.48,
          0.45,
          0.44,
          0.46,
          0.6,
          0.8,
          0.93,
          0.89,
          0.84,
          0.79,
          0.76,
          0.72,
          0.74,
          0.84,
          0.95,
          1.04,
          1.01,
          0.9,
          0.83,
          0.69,
          0.6,
          0.56,
          0.54,
          0.51,
          0.47,
          0.44,
          0.43,
          0.45,
          0.59,
          0.79,
          0.92,
          0.88,
          0.83,
          0.78,
          0.75,
          0.71,
          0.73,
          0.83,
          0.94,
          1.03,
          1,
          0.89,
          0.82,
          0.68,
          0.59,
          0.55,
          0.53,
          0.5,
          0.46,
          0.43,
          0.42,
          0.44,
          0.58,
          0.78,
          0.91,
          0.87,
          0.82,
          0.77,
          0.74,
          0.7,
          0.72,
          0.82,
          0.93,
          1.02,
          0.99,
          0.88,
          0.81,
          0.67,
          0.58,
          0.54
        ]
      },
      {
        "client_id": "house_05",
        "load": [
          0.35,
          0.33,
          0.3,
          0.28,
          0.27,
          0.29,
          0.4,
          0.57,
          0.67,
          0.64,
          0.6,
          0.56,
          0.54,
          0.51,
          0.53,
          0.61,
          0.7,
          0.77,
          0.74,
          0.66,
          0.61,
          0.5,
          0.43,
          0.37,
          0.36,
          0.34,
          0.31,
          0.29,
          0.28,
          0.3,
          0.41,
          0.58,
          0.68,
          0.65,
          0.61,
          0.57,
          0.55,
          0.52,
          0.54,
          0.62,
          0.71,
          0.78,
          0.75,
          0.67,
          0.62,
          0.51,
          0.44,
          0.38,
          0.37,
          0.35,
          0.32,
          0.3,
          0.29,
          0.31,
          0.42,
          0.59,
          0.69,
          0.66,
          0.62,
          0.58,
          0.56,
          0.53,
          0.55,
          0.63,
          0.72,
          0.79,
          0.76,
          0.68,
          0.63,
          0.52,
          0.45,
          0.39
        ]
      }
    ]
  },
  "config": {
    "rounds": 5,
    "local_epochs": 3,
    "learning_rate": 0.005,
    "seq_len": 24,
    "horizon": 6,
    "hidden_size": 16,
    "num_layers": 1,
    "client_fraction": 1,
    "batch_size": 8
  }
}