ADaSci Premium Membership fee will be revised from 1st March 2024. Lock your membership for 1 year at current price.

An Empirical Analysis of Deep Learning Models for Electric Vehicle Load Disaggregation

Author(s): Dilpreet Kaur Rehsi

Abstract

Homeowners increasingly wish to reduce their home energy usage for cost and sustainability reasons. Often, they wish to achieve this by changing their usage of appliances. However, to date homeowners generally lack detailed feedback on electricity usage to understand or track the effect of their changes; a monthly utility bill is often the only feedback they receive. To drive more energy savings in homes it is necessary to provide homeowners with detailed feedback on their appliance usage.

This paper discusses about a low-cost approach for giving homeowners detailed awareness of their energy usage. The approach extracts the individual energy usage of an appliance from the whole home energy at regular intervals, known as load disaggregation. This paper focuses on applying a deep learning algorithm to the whole home energy data to disaggregate the electric vehicle load as an example and can be extended to other loads also.

In this paper, an open-source toolkit called Non-Intrusive Load Monitoring ToolKit is used to review and compare empirically various deep learning algorithms for electric vehicle load disaggregation. The algorithms are evaluated in terms of execution time and performance by performing different experiments.

Access The Research Paper:

The Chartered Data Scientist Designation

Achieve the highest distinction in the data science profession.

Elevate Your Team's AI Skills with our Proven Training Programs

Strengthen Critical AI Skills with Trusted Generative AI Training by Association of Data Scientists

Explore more from Association of Data Scientists