# Privacy-Preserving Load Forecasting via Personalized Model Obfuscation

arXiv: https://arxiv.org/abs/2312.00036 · HTML: https://mlsanity.com/paper/2312.00036/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 21 Nov 2023.

## Builds on (most cited first, 10 of 10)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Mitigating Bias in Federated Learning](https://mlsanity.com/paper/2012.02447/) (2020)
- [Electrical Load Forecasting Using Edge Computing and Federated Learning](https://mlsanity.com/paper/2201.11248/) (2022)
- [APPFL: Open-Source Software Framework for Privacy-Preserving Federated Learning](https://mlsanity.com/paper/2202.03672/) (2022)
- [Attention-based Neural Load Forecasting: A Dynamic Feature Selection Approach](https://mlsanity.com/paper/2108.11763/) (2021)
- [Federated Short-Term Load Forecasting with Personalization Layers for Heterogeneous Clients](https://mlsanity.com/paper/2309.13194/) (2023)

## Built on by (most cited first, 1 of 1)

- [Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers](https://mlsanity.com/paper/2603.19544/) (2026)

## Abstract (arXiv)

The widespread adoption of smart meters provides access to detailed and localized load consumption data, suitable for training building-level load forecasting models. To mitigate privacy concerns stemming from model-induced data leakage, federated learning (FL) has been proposed. This paper addresses the performance challenges of short-term load forecasting models trained with FL on heterogeneous data, emphasizing privacy preservation through model obfuscation. Our proposed algorithm, Privacy Preserving Federated Learning (PPFL), incorporates personalization layers for localized training at each smart meter. Additionally, we employ a differentially private mechanism to safeguard against data leakage from shared layers. Simulations on the NREL ComStock dataset corroborate the effectiveness of our approach.