Sign In


College of Computing and Mathematics


Information & Computer Science Department


Presents an Online Seminar


"Data Requirements for Applying Machine Learning to Energy Disaggregation"



Date: Monday, 14th November 2022

Time:  2:30 – 3:45 PM

Location: Bldg. 59 Room 1005



Mr. Mohammed Ayub


King Fahd University of Petroleum & Minerals



Energy disaggregation, also known as nonintrusive load monitoring (NILM), is a technology that separates aggregate electricity consumption data into appliance-wise consumption in a household's smart meter. Although this technology was developed in 1992, its practical application and mass deployment have been limited, possibly due to the inadequacy of commonly used datasets for NILM research. In this paper, the authors presented the results of a newly collected dataset containing 10 Hz sampling data for 58 houses. The dataset includes aggregate measurements as well as individual appliance measurements for three different types of appliances. They demonstrated that NILM performance can be significantly limited when the data sampling rate is too low or the number of distinct houses in the dataset is too small by applying three classification algorithms (vanilla DNN (Deep Neural Network), ML (Machine Learning) with feature engineering, and CNN (Convolutional Neural Network) with hyper-parameter tuning) and a recent regression algorithm (Subtask Gated Network) to the new dataset. These requirements are not met by the well-known NILM datasets that are popular in the research community. The findings suggest that higher-quality datasets should be used to accelerate NILM research.


Short bio of presenter:

Mr. MOHAMMED AYUB received his MS in Computer Science, and is currently pursuing his PhD in computer science at King Fahd University of Petroleum and Minerals (KFUPM), Saudi Arabia. He has also been working as a Computer Engineer at Apollo General Trading LLC, United Arab Emirates (UAE). His research interest includes Deep and Machine Learning, Signal Processing, Information Security, Renewable Energy and Smart Grid. Google Scholar profile:



All faculty, researchers and graduate students are invited to attend.


Information & Computer Science Department, College of Computing and Mathematics

Telephone: +966 (13) 860 2175, Email:, Website:


Copyright © 2014 King Fahd University of Petroleum & Minerals



14 Nov 2022


02:30 PM to 03:45 PM