Energy-TSPulse

Energy-TSPulse is a domain-specific Time Series Foundation Model (TSFM) for energy meter data analytics, pretrained on large-scale real-world smart meter data from the EnergyBench corpus. Built upon IBM Research's TSPulse architecture, it learns rich temporal representations from diverse residential and commercial electricity consumption patterns.

The pretrained model is designed for zero-shot and transfer learning across heterogeneous buildings, regions, and operational contexts, while remaining lightweight and computationally efficient. It can be adapted to a variety of downstream energy analytics tasks, including anomaly detection, appliance classification, and missing value imputation.

Pretraining Dataset

EnergyFM is pretrained on EnergyBench, a large-scale real-world smart meter dataset available on Hugging Face:

👉 https://huggingface.co/datasets/ai-iot/EnergyBench

The dataset consists of:

• 76,217 residential and commercial buildings
• 1.26 billion hourly electricity consumption readings
• Multiple countries and climate zones
• Diverse building types and operational patterns

The scale and diversity of EnergyBench enable EnergyFM to learn daily, weekly, and seasonal consumption patterns and to generalize robustly to unseen buildings and regions.

Available Variants

Variant	Description
main	Pretrained on the full EnergyBench dataset containing real-world residential and commercial buildings. Recommended checkpoint for most use cases.
512-comm	Pretrained exclusively on commercial building energy consumption data.
512-res	Pretrained exclusively on residential building energy consumption data.

---

Supported Tasks

Anomaly Detection

Energy-TSPulse detects point and contextual anomalies in smart meter data using joint time–frequency representations.

Classification

Energy-TSPulse supports appliance usage classification using transfer learning on low-frequency smart meter data, achieving competitive or superior performance compared to strong feature-based classifiers.

---

🔵 Energy-TSPulse (Anomaly Detection / Reconstruction)

import torch
from tsfm_public.models.tspulse import TSPulseForReconstruction

device = "cuda" if torch.cuda.is_available() else "cpu"

model = TSPulseForReconstruction.from_pretrained(
    "EnergyFM/energy-tspulse",
    revision="main",       # Loads Energy-TSPulse weights
    num_input_channels=1
).to(device)

🟣 Energy-TSPulse (Classification)

import torch
from tsfm_public.models.tspulse import TSPulseForClassification

device = "cuda" if torch.cuda.is_available() else "cpu"

model = TSPulseForClassification.from_pretrained(
    "EnergyFM/energy-tspulse",
    revision="main"        # Change to 512-res or 512-comm to access commercial or residential specific variant
).to(device)

---

📚 Tutorial Notebooks

Notebook	Open in Colab
⚡ Zero-Shot Energy Anomaly Detection with Energy-TSPulse
⚡ Fine-Tuning Energy Anomaly Detection with Energy-TSPulse
⚡ Appliance Classification with Energy-TSPulse

Resources

• GitHub Repository 👉 https://github.com/energyfms/

• Pretraining Dataset (EnergyBench) 👉 https://huggingface.co/datasets/ai-iot/EnergyBench

Energy Benchmark Leaderboard

To compare EnergyFM against other state-of-the-art Time Series Foundation Models for energy analytics tasks, please visit our public benchmark leaderboard:

👉 Energy Benchmark Leaderboard
https://huggingface.co/spaces/EnergyFM/Leaderboard

The leaderboard provides standardized evaluations across forecasting, anomaly detection, and classification tasks, enabling direct comparison under consistent experimental settings.

---

Limitations and Intended Use

EnergyFM is intended for energy meter analytics and has been pretrained on electricity consumption data. Performance may degrade when applied to unrelated domains or data with significantly different temporal characteristics.

---

Citation

If you use EnergyFM in your work, please cite:

@inproceedings{energyfm2026,
author = {Arjunan, Pandarasamy and Srivastava, Naman and Kumar, Kajeeth and Jati, Arindam and Ekambaram, Vijay and Dayama, Pankaj},
title = {EnergyFM: Pretrained Models for Energy Meter Data Analytics},
year = {2026},
url = {https://doi.org/10.1145/3744255.3798119},
doi = {10.1145/3744255.3798119},
booktitle = {Proceedings of the 17th ACM International Conference on Future and Sustainable Energy Systems},
pages = {556–568},
series = {E-Energy '26}
}