Forecasting power consumption for higher educational institutions based on machine learning

Jihoon Moon, Jinwoong Park, Een Jun Hwang, Sanghoon Jun

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Electric power consumption is affected by diverse factors. In particular, a university campus, which is one of the highest power consuming institutions, shows a wide variation of electric load depending on time and environment. For stable operation of such institution, reliable electric power supply should be guaranteed. One of possible methods to do that is to forecast the electric load accurately and supply power accordingly. Even though various influencing factors of power consumption have been discovered for educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative forecasting of their electric load. In this paper, we build a power consumption forecasting model using various machine learning algorithms. To evaluate their effectiveness, we consider four building clusters in a university and collect their power consumption data of 15-min interval over more than one year. For the data, we first extract features based on the periodic characteristic and then perform the principal component analysis and factor analysis for the features. We build two electric load forecasting models using artificial neural network and support vector regression. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to actual electric load. The experimental results show that the two forecasting models can achieve average error rate of 3.46–10 % for all clusters.

Original languageEnglish
Pages (from-to)1-23
Number of pages23
JournalJournal of Supercomputing
DOIs
Publication statusAccepted/In press - 2017 Mar 29

Fingerprint

Power Consumption
Electric loads
Learning systems
Forecasting
Machine Learning
Electric power utilization
Load Forecasting
Electric load forecasting
Support Vector Regression
Evaluate
Performance Prediction
Factor Analysis
Cross-validation
Model
High Power
Principal Component Analysis
Factor analysis
Artificial Neural Network
Error Rate
Forecast

Keywords

  • Artificial neural network
  • Forecasting model
  • Machine learning
  • Power consumption prediction
  • Principal component analysis
  • Support vector regression

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Software
  • Information Systems
  • Hardware and Architecture

Cite this

Forecasting power consumption for higher educational institutions based on machine learning. / Moon, Jihoon; Park, Jinwoong; Hwang, Een Jun; Jun, Sanghoon.

In: Journal of Supercomputing, 29.03.2017, p. 1-23.

Research output: Contribution to journalArticle

@article{58c6d6105174460f9e11b71e8ede82d5,
title = "Forecasting power consumption for higher educational institutions based on machine learning",
abstract = "Electric power consumption is affected by diverse factors. In particular, a university campus, which is one of the highest power consuming institutions, shows a wide variation of electric load depending on time and environment. For stable operation of such institution, reliable electric power supply should be guaranteed. One of possible methods to do that is to forecast the electric load accurately and supply power accordingly. Even though various influencing factors of power consumption have been discovered for educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative forecasting of their electric load. In this paper, we build a power consumption forecasting model using various machine learning algorithms. To evaluate their effectiveness, we consider four building clusters in a university and collect their power consumption data of 15-min interval over more than one year. For the data, we first extract features based on the periodic characteristic and then perform the principal component analysis and factor analysis for the features. We build two electric load forecasting models using artificial neural network and support vector regression. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to actual electric load. The experimental results show that the two forecasting models can achieve average error rate of 3.46–10 {\%} for all clusters.",
keywords = "Artificial neural network, Forecasting model, Machine learning, Power consumption prediction, Principal component analysis, Support vector regression",
author = "Jihoon Moon and Jinwoong Park and Hwang, {Een Jun} and Sanghoon Jun",
year = "2017",
month = "3",
day = "29",
doi = "10.1007/s11227-017-2022-x",
language = "English",
pages = "1--23",
journal = "The Journal of Supercomputing",
issn = "0920-8542",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Forecasting power consumption for higher educational institutions based on machine learning

AU - Moon, Jihoon

AU - Park, Jinwoong

AU - Hwang, Een Jun

AU - Jun, Sanghoon

PY - 2017/3/29

Y1 - 2017/3/29

N2 - Electric power consumption is affected by diverse factors. In particular, a university campus, which is one of the highest power consuming institutions, shows a wide variation of electric load depending on time and environment. For stable operation of such institution, reliable electric power supply should be guaranteed. One of possible methods to do that is to forecast the electric load accurately and supply power accordingly. Even though various influencing factors of power consumption have been discovered for educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative forecasting of their electric load. In this paper, we build a power consumption forecasting model using various machine learning algorithms. To evaluate their effectiveness, we consider four building clusters in a university and collect their power consumption data of 15-min interval over more than one year. For the data, we first extract features based on the periodic characteristic and then perform the principal component analysis and factor analysis for the features. We build two electric load forecasting models using artificial neural network and support vector regression. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to actual electric load. The experimental results show that the two forecasting models can achieve average error rate of 3.46–10 % for all clusters.

AB - Electric power consumption is affected by diverse factors. In particular, a university campus, which is one of the highest power consuming institutions, shows a wide variation of electric load depending on time and environment. For stable operation of such institution, reliable electric power supply should be guaranteed. One of possible methods to do that is to forecast the electric load accurately and supply power accordingly. Even though various influencing factors of power consumption have been discovered for educational institutions by analyzing power consumption patterns and usage cases, further studies are required for the quantitative forecasting of their electric load. In this paper, we build a power consumption forecasting model using various machine learning algorithms. To evaluate their effectiveness, we consider four building clusters in a university and collect their power consumption data of 15-min interval over more than one year. For the data, we first extract features based on the periodic characteristic and then perform the principal component analysis and factor analysis for the features. We build two electric load forecasting models using artificial neural network and support vector regression. We evaluate the prediction performance of each forecasting model by 5-fold cross-validation and compare the prediction result to actual electric load. The experimental results show that the two forecasting models can achieve average error rate of 3.46–10 % for all clusters.

KW - Artificial neural network

KW - Forecasting model

KW - Machine learning

KW - Power consumption prediction

KW - Principal component analysis

KW - Support vector regression

UR - http://www.scopus.com/inward/record.url?scp=85016420609&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016420609&partnerID=8YFLogxK

U2 - 10.1007/s11227-017-2022-x

DO - 10.1007/s11227-017-2022-x

M3 - Article

AN - SCOPUS:85016420609

SP - 1

EP - 23

JO - The Journal of Supercomputing

JF - The Journal of Supercomputing

SN - 0920-8542

ER -