Comprehensive multi-type and multi-unit appliance (CMTMU) dataset

Citation Author(s):: Wenbin Yu (Nanjing University of Information Science and Technology)

Louyang Yu (Nanjing University of Information Science and Technology)

Gaozhenyang Wang (Nanjing University of Information Science and Technology)

Zhengju Ren (Nanjing University of Information Science and Technology)

Konglin Zhu (the Department of Electrical and Computer Engineering, Michigan State University)

Hanmiao Cheng (Marketing Service Center of State Grid Jiangsu Electric Power Co., LTD.)

Yadang Chen (Nanjing University of Information Science and Technology)

Alex Liu (Midea Group)
Submitted by:: Wenbin Yu
Last updated:: Mon, 05/12/2025 - 05:30
DOI:: 10.21227/r6re-e340

21 views

Categories:

Smart Grid

Keywords:

Non Intrusive Load Monitoring (NILM)

ACCESS DATASET CITE

Abstract

To facilitate real-world deployment of non-intrusive load monitoring (NILM), we introduce the CMTMU dataset. Based on REFIT consumption data, CMTMU simulates realistic residential power-use scenarios featuring both multiple appliance types and concurrent units of the same type. It includes a variety of devices—refrigerators, electric kettles, washing machines, dishwashers, and more—comprehensively capturing load variations and operational overlaps. Experimental results show that using CMTMU significantly improves the load-disaggregation and appliance-count identification accuracy of state-of-the-art NILM models under complex operating conditions, providing robust data support for the advancement of smart energy systems.

Get Password

To obtain the password for the compressed CMTMU dataset package, please send an email application to ywb@nuist.edu.cn in the following required format. Applications not conforming to this format may be ignored.

Title of Mail:
- CMTMU: your_organization: your_name

Note that: The string of 'CMTMU' can not be empty. It is the fixed form and a special sign we use to identifying your downloading intention from other disturbers like spams.

Body of Mail:
- Organization Detail: Your Organization Details
- Main Works: Your Main Works
- Usages: YourUsages About This Data Set

Instructions:

The CMTMU dataset is a crucial resource for non-intrusive load monitoring (NILM) research, specifically designed to address the challenges of identifying multiple appliances in a household setting. It contains power consumption data that simulates scenarios where residents with similar usage habits operate multiple identical appliances simultaneously. This dataset builds on the REFIT load data to simulate realistic multi-appliance operating scenarios without specifying the underlying generation process. The dataset is primarily intended for researchers working on NILM algorithms, enabling them to train and evaluate models for identifying the operating states of individual appliances from the total household power consumption signal. For example, machine learning and deep learning models can be trained on this dataset to predict whether an appliance is on or off at a given time. The dataset is also helpful in developing methods to identify the number of identical appliances operating simultaneously, a challenging task in NILM. The CMTMU dataset provides the necessary data to test and improve algorithms for this purpose.