Modelling and analysis of energy footprint at industry level

Electrical, Metal, Plastic & Food are among the major energy consuming industries in the U.S. The U.S Department of Energy has performed assessments through IAC program since 1981. It has collected data related to energy consumption and several other factors like (production quantities, number of employees, etc..) for various types of industries. It is significant to understand the comparison of energy consumption of these industries, since this helps to understand which industry has higher consumption of energy and it also helps the government in making decisions to achieve sustainability. Production cost and environmental impact can be reduced by increasing energy efficiency of any type of industry. To achieve this, we need models to evaluate energy footprints at industry level. With machine learning techniques it is possible to predict the energy consumption at industry level. Probabilistic techniques can be used to benchmark at industry level. This will also help the EPI tool prepared by Energy Star to make more accurate output. Further, we have built classification models using machine learning and deep learning, which will help to make energy efficient decisions at plant level within an industry. With these cluster’s meaningful insights can be derived Advisior: Dr. Vittaldas Prabhu

Files

Metadata

Work Title Modelling and analysis of energy footprint at industry level
Access
Open Access
Creators
  1. Sai Aravind Saraswatula
Keyword
  1. Machine learning
  2. Energy Efficiency
  3. Sustainability
  4. Statistics
License CC BY 4.0 (Attribution)
Work Type Research Paper
Acknowledgments
  1. Dr. Vittaldas Prabhu
  2. Dr. Robert C Voigt
  3. The Pennsylvania State University
Publication Date 2021
Deposited November 17, 2021

Versions

Analytics

Collections

This resource is currently not in any collection.

Work History

Version 1
published

  • Created
  • Updated Acknowledgments Show Changes
    Acknowledgments
    • Dr. Vittaldas Prabhu, Dr. Robert C Voigt
  • Added Creator Sai Aravind Saraswatula
  • Added Frontiers_Template_MS.pdf
  • Updated License Show Changes
    License
    • https://creativecommons.org/licenses/by/4.0/
  • Published
  • Updated

Version 2
published

  • Created
  • Updated Description Show Changes
    Description
    • Electrical, Metal, Plastic & Food are among the major energy consuming industries in the U.S. The U.S Department of Energy has performed assessments through IAC program since 1981. It has collected data related to energy consumption and several other factors like (production quantities, number of employees, etc..) for various types of industries. It is significant to understand the comparison of energy consumption of these industries, since this helps to understand which industry has higher consumption of energy and it also helps the government in making decisions to achieve sustainability. Production cost and environmental impact can be reduced by increasing energy efficiency of any type of industry. To achieve this, we need models to evaluate energy footprints at industry level. With machine learning techniques it is possible to predict the energy consumption at industry level. Probabilistic techniques can be used to benchmark at industry level. This will also help the EPI tool prepared by Energy Star to make more accurate output. Further, we have built classification models using machine learning and deep learning, which will help to make energy efficient decisions at plant level within an industry. With these cluster’s meaningful insights can be derived
    • Electrical, Metal, Plastic & Food are among the major energy consuming industries in the U.S. The U.S Department of Energy has performed assessments through IAC program since 1981. It has collected data related to energy consumption and several other factors like (production quantities, number of employees, etc..) for various types of industries. It is significant to understand the comparison of energy consumption of these industries, since this helps to understand which industry has higher consumption of energy and it also helps the government in making decisions to achieve sustainability. Production cost and environmental impact can be reduced by increasing energy efficiency of any type of industry. To achieve this, we need models to evaluate energy footprints at industry level. With machine learning techniques it is possible to predict the energy consumption at industry level. Probabilistic techniques can be used to benchmark at industry level. This will also help the EPI tool prepared by Energy Star to make more accurate output. Further, we have built classification models using machine learning and deep learning, which will help to make energy efficient decisions at plant level within an industry. With these cluster’s meaningful insights can be derived
    • Advisior: Dr. Vittaldas Prabhu
  • Updated Acknowledgments Show Changes
    Acknowledgments
    • Dr. Vittaldas Prabhu, Dr. Robert C Voigt
    • Dr. Vittaldas Prabhu, Dr. Robert C Voigt, The Pennsylvania State University
  • Published
  • Updated