# ProfileSR-GAN: A GAN based Super-Resolution Method for Generating High-Resolution Load Profiles

arXiv: https://arxiv.org/abs/2107.09523 · HTML: https://mlsanity.com/paper/2107.09523/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jul 2021.

## Built on by (most cited first, 8 of 8)

- [SRGS: Super-Resolution 3D Gaussian Splatting](https://mlsanity.com/paper/2404.10318/) (2024)
- [Customized Load Profiles Synthesis for Electricity Customers Based on Conditional Diffusion Models](https://mlsanity.com/paper/2304.12076/) (2023)
- [EnergyDiff: Universal Time-Series Energy Data Generation using Diffusion Models](https://mlsanity.com/paper/2407.13538/) (2024)
- [Generating Synthetic Net Load Data with Physics-informed Diffusion Model](https://mlsanity.com/paper/2406.01913/) (2024)
- [A Flow-Based Model for Conditional and Probabilistic Electricity Consumption Profile Generation and Prediction](https://mlsanity.com/paper/2405.02180/) (2024)
- [BERT-PIN: A BERT-based Framework for Recovering Missing Data Segments in Time-series Load Profiles](https://mlsanity.com/paper/2310.17742/) (2023)
- [Creating Temporally Correlated High-Resolution Profiles of Load Injection Using Constrained Generative Adversarial Networks](https://mlsanity.com/paper/2311.12166/) (2023)
- [SmartMeterFM: Unifying Smart Meter Data Generative Tasks Using Flow Matching Models](https://mlsanity.com/paper/2601.21706/) (2026)

## Abstract (arXiv)

It is a common practice for utilities to down-sample smart meter measurements from high resolution (e.g. 1-min or 1-sec) to low resolution (e.g. 15-, 30- or 60-min) to lower the data transmission and storage cost. However, down-sampling can remove high-frequency components from time-series load profiles, making them unsuitable for in-depth studies such as quasi-static power flow analysis or non-intrusive load monitoring (NILM). Thus, in this paper, we propose ProfileSR-GAN: a Generative Adversarial Network (GAN) based load profile super-resolution (LPSR) framework for restoring high-frequency components lost through the smoothing effect of the down-sampling process. The LPSR problem is formulated as a Maximum-a-Prior problem. When training the ProfileSR-GAN generator network, to make the generated profiles more realistic, we introduce two new shape-related losses in addition to conventionally used content loss: adversarial loss and feature-matching loss. Moreover, a new set of shape-based evaluation metrics are proposed to evaluate the realisticness of the generated profiles. Simulation results show that ProfileSR-GAN outperforms Mean-Square Loss based methods in all shape-based metrics. The successful application in NILM further demonstrates that ProfileSR-GAN is effective in recovering high-resolution realistic waveforms.