A short-term load forecasting scheme based on auto-encoder and random forest

Minjae Son, Jihoon Moon, Seungwon Jung, Een Jun Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recently, the smart grid has been attracting much attention as a viable solution to the power shortage problem. One of critical issues for improving its operational efficiency is to predict the short-term electric load accurately. So far, many works have been done to construct STLF (Short-Term Load Forecasting) models using a variety of machine learning algorithms. By taking many influential variables into account, they gave satisfactory results in predicting overall electric load pattern. But, they are still lacking in predicting minute electric load patterns. To overcome this problem, in this paper, we propose a new STLF model that combines Auto-Encoder (AE) based feature extraction and Random Forest (RF) and show its performance by carrying out several experiments for the actual power consumption data collected from diverse types of building clusters.

Original languageEnglish
Title of host publicationApplied Physics, System Science and Computers III - Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers APSAC 2018
EditorsAnca Croitoru, Klimis Ntalianis, George Vachtsevanos, Pierre Borne
PublisherSpringer Verlag
Pages138-144
Number of pages7
ISBN (Print)9783030215064
DOIs
Publication statusPublished - 2019 Jan 1
Event3rd International Conference on Applied Physics, System Science and Computers, APSAC 2018 - Dubrovnik, Croatia
Duration: 2018 Sep 262018 Sep 28

Publication series

NameLecture Notes in Electrical Engineering
Volume574
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference3rd International Conference on Applied Physics, System Science and Computers, APSAC 2018
CountryCroatia
CityDubrovnik
Period18/9/2618/9/28

Fingerprint

Electric loads
Learning algorithms
Learning systems
Feature extraction
Electric power utilization
Experiments

Keywords

  • Auto-encoder
  • Feature extraction
  • Random forest
  • Short-term load forecasting
  • Smart grid

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Son, M., Moon, J., Jung, S., & Hwang, E. J. (2019). A short-term load forecasting scheme based on auto-encoder and random forest. In A. Croitoru, K. Ntalianis, G. Vachtsevanos, & P. Borne (Eds.), Applied Physics, System Science and Computers III - Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers APSAC 2018 (pp. 138-144). (Lecture Notes in Electrical Engineering; Vol. 574). Springer Verlag. https://doi.org/10.1007/978-3-030-21507-1_21

A short-term load forecasting scheme based on auto-encoder and random forest. / Son, Minjae; Moon, Jihoon; Jung, Seungwon; Hwang, Een Jun.

Applied Physics, System Science and Computers III - Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers APSAC 2018. ed. / Anca Croitoru; Klimis Ntalianis; George Vachtsevanos; Pierre Borne. Springer Verlag, 2019. p. 138-144 (Lecture Notes in Electrical Engineering; Vol. 574).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Son, M, Moon, J, Jung, S & Hwang, EJ 2019, A short-term load forecasting scheme based on auto-encoder and random forest. in A Croitoru, K Ntalianis, G Vachtsevanos & P Borne (eds), Applied Physics, System Science and Computers III - Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers APSAC 2018. Lecture Notes in Electrical Engineering, vol. 574, Springer Verlag, pp. 138-144, 3rd International Conference on Applied Physics, System Science and Computers, APSAC 2018, Dubrovnik, Croatia, 18/9/26. https://doi.org/10.1007/978-3-030-21507-1_21
Son M, Moon J, Jung S, Hwang EJ. A short-term load forecasting scheme based on auto-encoder and random forest. In Croitoru A, Ntalianis K, Vachtsevanos G, Borne P, editors, Applied Physics, System Science and Computers III - Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers APSAC 2018. Springer Verlag. 2019. p. 138-144. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-3-030-21507-1_21
Son, Minjae ; Moon, Jihoon ; Jung, Seungwon ; Hwang, Een Jun. / A short-term load forecasting scheme based on auto-encoder and random forest. Applied Physics, System Science and Computers III - Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers APSAC 2018. editor / Anca Croitoru ; Klimis Ntalianis ; George Vachtsevanos ; Pierre Borne. Springer Verlag, 2019. pp. 138-144 (Lecture Notes in Electrical Engineering).
@inproceedings{15de1cf2cb18468bb11e1694669613bf,
title = "A short-term load forecasting scheme based on auto-encoder and random forest",
abstract = "Recently, the smart grid has been attracting much attention as a viable solution to the power shortage problem. One of critical issues for improving its operational efficiency is to predict the short-term electric load accurately. So far, many works have been done to construct STLF (Short-Term Load Forecasting) models using a variety of machine learning algorithms. By taking many influential variables into account, they gave satisfactory results in predicting overall electric load pattern. But, they are still lacking in predicting minute electric load patterns. To overcome this problem, in this paper, we propose a new STLF model that combines Auto-Encoder (AE) based feature extraction and Random Forest (RF) and show its performance by carrying out several experiments for the actual power consumption data collected from diverse types of building clusters.",
keywords = "Auto-encoder, Feature extraction, Random forest, Short-term load forecasting, Smart grid",
author = "Minjae Son and Jihoon Moon and Seungwon Jung and Hwang, {Een Jun}",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-030-21507-1_21",
language = "English",
isbn = "9783030215064",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "138--144",
editor = "Anca Croitoru and Klimis Ntalianis and George Vachtsevanos and Pierre Borne",
booktitle = "Applied Physics, System Science and Computers III - Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers APSAC 2018",

}

TY - GEN

T1 - A short-term load forecasting scheme based on auto-encoder and random forest

AU - Son, Minjae

AU - Moon, Jihoon

AU - Jung, Seungwon

AU - Hwang, Een Jun

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Recently, the smart grid has been attracting much attention as a viable solution to the power shortage problem. One of critical issues for improving its operational efficiency is to predict the short-term electric load accurately. So far, many works have been done to construct STLF (Short-Term Load Forecasting) models using a variety of machine learning algorithms. By taking many influential variables into account, they gave satisfactory results in predicting overall electric load pattern. But, they are still lacking in predicting minute electric load patterns. To overcome this problem, in this paper, we propose a new STLF model that combines Auto-Encoder (AE) based feature extraction and Random Forest (RF) and show its performance by carrying out several experiments for the actual power consumption data collected from diverse types of building clusters.

AB - Recently, the smart grid has been attracting much attention as a viable solution to the power shortage problem. One of critical issues for improving its operational efficiency is to predict the short-term electric load accurately. So far, many works have been done to construct STLF (Short-Term Load Forecasting) models using a variety of machine learning algorithms. By taking many influential variables into account, they gave satisfactory results in predicting overall electric load pattern. But, they are still lacking in predicting minute electric load patterns. To overcome this problem, in this paper, we propose a new STLF model that combines Auto-Encoder (AE) based feature extraction and Random Forest (RF) and show its performance by carrying out several experiments for the actual power consumption data collected from diverse types of building clusters.

KW - Auto-encoder

KW - Feature extraction

KW - Random forest

KW - Short-term load forecasting

KW - Smart grid

UR - http://www.scopus.com/inward/record.url?scp=85068593594&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068593594&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-21507-1_21

DO - 10.1007/978-3-030-21507-1_21

M3 - Conference contribution

SN - 9783030215064

T3 - Lecture Notes in Electrical Engineering

SP - 138

EP - 144

BT - Applied Physics, System Science and Computers III - Proceedings of the 3rd International Conference on Applied Physics, System Science and Computers APSAC 2018

A2 - Croitoru, Anca

A2 - Ntalianis, Klimis

A2 - Vachtsevanos, George

A2 - Borne, Pierre

PB - Springer Verlag

ER -