Hybrid short-term load forecasting scheme using random forest and multilayer perceptron

Jihoon Moon, Yongsung Kim, Minjae Son, Een Jun Hwang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

A stable power supply is very important in the management of power infrastructure. One of the critical tasks in accomplishing this is to predict power consumption accurately, which usually requires considering diverse factors, including environmental, social, and spatial-temporal factors. Depending on the prediction scope, building type can also be an important factor since the same types of buildings show similar power consumption patterns. A university campus usually consists of several building types, including a laboratory, administrative office, lecture room, and dormitory. Depending on the temporal and external conditions, they tend to show a wide variation in the electrical load pattern. This paper proposes a hybrid short-term load forecast model for an educational building complex by using random forest and multilayer perceptron. To construct this model, we collect electrical load data of six years from a university campus and split them into training, validation, and test sets. For the training set, we classify the data using a decision tree with input parameters including date, day of the week, holiday, and academic year. In addition, we consider various configurations for random forest and multilayer perceptron and evaluate their prediction performance using the validation set to determine the optimal configuration. Then, we construct a hybrid short-term load forecast model by combining the two models and predict the daily electrical load for the test set. Through various experiments, we show that our hybrid forecast model performs better than other popular single forecast models.

Original languageEnglish
Article number3283
JournalEnergies
Volume11
Issue number12
DOIs
Publication statusPublished - 2018 Dec 1

Fingerprint

Short-term Load Forecasting
Random Forest
Multilayer neural networks
Perceptron
Multilayer
Forecast
Test Set
Power Consumption
Electric power utilization
Model
Predict
Configuration
Environmental Factors
Performance Prediction
Decision trees
Date
Decision tree
Infrastructure
Classify
Tend

Keywords

  • Electrical load forecasting
  • Hybrid forecast model
  • Multilayer perceptron
  • Random forest
  • Time series analysis

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Energy Engineering and Power Technology
  • Energy (miscellaneous)
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

Hybrid short-term load forecasting scheme using random forest and multilayer perceptron. / Moon, Jihoon; Kim, Yongsung; Son, Minjae; Hwang, Een Jun.

In: Energies, Vol. 11, No. 12, 3283, 01.12.2018.

Research output: Contribution to journalArticle

Moon, Jihoon ; Kim, Yongsung ; Son, Minjae ; Hwang, Een Jun. / Hybrid short-term load forecasting scheme using random forest and multilayer perceptron. In: Energies. 2018 ; Vol. 11, No. 12.
@article{8a6319bac1a04f93b033bdfd9c5dfae0,
title = "Hybrid short-term load forecasting scheme using random forest and multilayer perceptron",
abstract = "A stable power supply is very important in the management of power infrastructure. One of the critical tasks in accomplishing this is to predict power consumption accurately, which usually requires considering diverse factors, including environmental, social, and spatial-temporal factors. Depending on the prediction scope, building type can also be an important factor since the same types of buildings show similar power consumption patterns. A university campus usually consists of several building types, including a laboratory, administrative office, lecture room, and dormitory. Depending on the temporal and external conditions, they tend to show a wide variation in the electrical load pattern. This paper proposes a hybrid short-term load forecast model for an educational building complex by using random forest and multilayer perceptron. To construct this model, we collect electrical load data of six years from a university campus and split them into training, validation, and test sets. For the training set, we classify the data using a decision tree with input parameters including date, day of the week, holiday, and academic year. In addition, we consider various configurations for random forest and multilayer perceptron and evaluate their prediction performance using the validation set to determine the optimal configuration. Then, we construct a hybrid short-term load forecast model by combining the two models and predict the daily electrical load for the test set. Through various experiments, we show that our hybrid forecast model performs better than other popular single forecast models.",
keywords = "Electrical load forecasting, Hybrid forecast model, Multilayer perceptron, Random forest, Time series analysis",
author = "Jihoon Moon and Yongsung Kim and Minjae Son and Hwang, {Een Jun}",
year = "2018",
month = "12",
day = "1",
doi = "10.3390/en11123283",
language = "English",
volume = "11",
journal = "Energies",
issn = "1996-1073",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "12",

}

TY - JOUR

T1 - Hybrid short-term load forecasting scheme using random forest and multilayer perceptron

AU - Moon, Jihoon

AU - Kim, Yongsung

AU - Son, Minjae

AU - Hwang, Een Jun

PY - 2018/12/1

Y1 - 2018/12/1

N2 - A stable power supply is very important in the management of power infrastructure. One of the critical tasks in accomplishing this is to predict power consumption accurately, which usually requires considering diverse factors, including environmental, social, and spatial-temporal factors. Depending on the prediction scope, building type can also be an important factor since the same types of buildings show similar power consumption patterns. A university campus usually consists of several building types, including a laboratory, administrative office, lecture room, and dormitory. Depending on the temporal and external conditions, they tend to show a wide variation in the electrical load pattern. This paper proposes a hybrid short-term load forecast model for an educational building complex by using random forest and multilayer perceptron. To construct this model, we collect electrical load data of six years from a university campus and split them into training, validation, and test sets. For the training set, we classify the data using a decision tree with input parameters including date, day of the week, holiday, and academic year. In addition, we consider various configurations for random forest and multilayer perceptron and evaluate their prediction performance using the validation set to determine the optimal configuration. Then, we construct a hybrid short-term load forecast model by combining the two models and predict the daily electrical load for the test set. Through various experiments, we show that our hybrid forecast model performs better than other popular single forecast models.

AB - A stable power supply is very important in the management of power infrastructure. One of the critical tasks in accomplishing this is to predict power consumption accurately, which usually requires considering diverse factors, including environmental, social, and spatial-temporal factors. Depending on the prediction scope, building type can also be an important factor since the same types of buildings show similar power consumption patterns. A university campus usually consists of several building types, including a laboratory, administrative office, lecture room, and dormitory. Depending on the temporal and external conditions, they tend to show a wide variation in the electrical load pattern. This paper proposes a hybrid short-term load forecast model for an educational building complex by using random forest and multilayer perceptron. To construct this model, we collect electrical load data of six years from a university campus and split them into training, validation, and test sets. For the training set, we classify the data using a decision tree with input parameters including date, day of the week, holiday, and academic year. In addition, we consider various configurations for random forest and multilayer perceptron and evaluate their prediction performance using the validation set to determine the optimal configuration. Then, we construct a hybrid short-term load forecast model by combining the two models and predict the daily electrical load for the test set. Through various experiments, we show that our hybrid forecast model performs better than other popular single forecast models.

KW - Electrical load forecasting

KW - Hybrid forecast model

KW - Multilayer perceptron

KW - Random forest

KW - Time series analysis

UR - http://www.scopus.com/inward/record.url?scp=85059411542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059411542&partnerID=8YFLogxK

U2 - 10.3390/en11123283

DO - 10.3390/en11123283

M3 - Article

AN - SCOPUS:85059411542

VL - 11

JO - Energies

JF - Energies

SN - 1996-1073

IS - 12

M1 - 3283

ER -