Location
Presentation- Allen E. Paulson College of Engineering and Computing
Document Type and Release Option
Thesis Presentation (Restricted to Georgia Southern)
Faculty Mentor
Rami Haddad
Faculty Mentor Email
rhaddad@georgiasouthern.edu
Presentation Year
2021
Start Date
26-4-2021 12:00 AM
End Date
30-4-2021 12:00 AM
Keywords
Pico-micro grid, electronics, energy consumption, device identification
Description
Technology continues to improve, and people buy more electronics day by day. Therefore, something very important is to be smart about how much energy one uses. Being smart about how one uses electricity can decrease their environmental footprint and decrease their electric bill. Therefore, the Pico-Micro Grid Power Energy Management System (PEMS) is an important tool that will help one to monitor how much energy they are using as well as how they are using it. In order to monitor how much energy each device is consuming, identifying the device is vital. This project focuses on finding the best method to use in order to identify a device. Some methods explored are a single large ANN, applying principal component analysis (PCA) with different methods, and a Bi-directional Long Short-Term Memory (Bi-LSTM) network. The best method is found to be the Bi-LSTM network, once this was discovered, tests were ran for five different devices and the resulting data for each device was collected and verified the findings that the best method of classification is through the use of a Bi-LSTM network.
Academic Unit
Allen E. Paulson College of Engineering and Computing
Pico-Micro Grid Power Management Energy Systems
Presentation- Allen E. Paulson College of Engineering and Computing
Technology continues to improve, and people buy more electronics day by day. Therefore, something very important is to be smart about how much energy one uses. Being smart about how one uses electricity can decrease their environmental footprint and decrease their electric bill. Therefore, the Pico-Micro Grid Power Energy Management System (PEMS) is an important tool that will help one to monitor how much energy they are using as well as how they are using it. In order to monitor how much energy each device is consuming, identifying the device is vital. This project focuses on finding the best method to use in order to identify a device. Some methods explored are a single large ANN, applying principal component analysis (PCA) with different methods, and a Bi-directional Long Short-Term Memory (Bi-LSTM) network. The best method is found to be the Bi-LSTM network, once this was discovered, tests were ran for five different devices and the resulting data for each device was collected and verified the findings that the best method of classification is through the use of a Bi-LSTM network.
Comments
This work is archived and distributed under the repository's standard copyright and reuse license, available here. Under this license, end-users may copy, store, and distribute this work without restriction. For questions related to additional reuse of this work, please contact the copyright owner.