# Towards Real-world Deployment of NILM Systems: Challenges and Practices

arXiv: https://arxiv.org/abs/2409.14821 · HTML: https://mlsanity.com/paper/2409.14821/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Recurrent Neural Network Regularization](https://mlsanity.com/paper/1409.2329/) (2014)
- [Sequence-to-point learning with neural networks for nonintrusive load monitoring](https://mlsanity.com/paper/1612.09106/) (2016)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [FedNILM: Applying Federated Learning to NILM Applications at the Edge](https://mlsanity.com/paper/2106.07751/) (2021)
- [Microservices in Practice: A Survey Study](https://mlsanity.com/paper/1808.04836/) (2018)

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

- [Prompting Large Language Models for Training-Free Non-Intrusive Load Monitoring](https://mlsanity.com/paper/2505.06330/) (2025)

## Abstract (arXiv)

Non-intrusive load monitoring (NILM), as a key load monitoring technology, can much reduce the deployment cost of traditional power sensors. Previous research has largely focused on developing cloud-exclusive NILM algorithms, which often result in high computation costs and significant service delays. To address these issues, we propose a three-tier framework to enhance the real-world applicability of NILM systems through edge-cloud collaboration. Considering the computational resources available at both the edge and cloud, we implement a lightweight NILM model at the edge and a deep learning based model at the cloud, respectively. In addition to the differential model implementations, we also design a NILM-specific deployment scheme that integrates Gunicorn and NGINX to bridge the gap between theoretical algorithms and practical applications. To verify the effectiveness of the proposed framework, we apply real-world NILM scenario settings and implement the entire process of data acquisition, model training, and system deployment. The results demonstrate that our framework can achieve high decomposition accuracy while significantly reducing the cloud workload and communication overhead under practical considerations.