Electric energy consumption prediction by deep learning with state explainable autoencoder

Jin Young Kim, Sung-Bae Cho

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

As energy demand grows globally, the energy management system (EMS) is becoming increasingly important. Energy prediction is an essential component in the first step to create a management plan in EMS. Conventional energy prediction models focus on prediction performance, but in order to build an efficient system, it is necessary to predict energy demand according to various conditions. In this paper, we propose a method to predict energy demand in various situations using a deep learning model based on an autoencoder. This model consists of a projector that defines an appropriate state for a given situation and a predictor that forecasts energy demand from the defined state. The proposed model produces consumption predictions for 15, 30, 45, and 60 min with 60-min demand to date. In the experiments with household electric power consumption data for five years, this model not only has a better performance with a mean squared error of 0.384 than the conventional models, but also improves the capacity to explain the results of prediction by visualizing the state with t-SNE algorithm. Despite unsupervised representation learning, we confirm that the proposed model defines the state well and predicts the energy demand accordingly.

Original languageEnglish
Article number739
JournalEnergies
Volume12
Issue number4
DOIs
Publication statusPublished - 2019 Feb 22

Fingerprint

Energy Consumption
Energy utilization
Prediction
Energy
Energy Management
Energy management systems
Predict
Essential Component
Model
Energy Model
Performance Prediction
Projector
Mean Squared Error
Prediction Model
Power Consumption
Forecast
Learning
Demand
Deep learning
Predictors

All Science Journal Classification (ASJC) codes

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

Cite this

@article{c4533e949b874b13a22ed60ffd4b4a01,
title = "Electric energy consumption prediction by deep learning with state explainable autoencoder",
abstract = "As energy demand grows globally, the energy management system (EMS) is becoming increasingly important. Energy prediction is an essential component in the first step to create a management plan in EMS. Conventional energy prediction models focus on prediction performance, but in order to build an efficient system, it is necessary to predict energy demand according to various conditions. In this paper, we propose a method to predict energy demand in various situations using a deep learning model based on an autoencoder. This model consists of a projector that defines an appropriate state for a given situation and a predictor that forecasts energy demand from the defined state. The proposed model produces consumption predictions for 15, 30, 45, and 60 min with 60-min demand to date. In the experiments with household electric power consumption data for five years, this model not only has a better performance with a mean squared error of 0.384 than the conventional models, but also improves the capacity to explain the results of prediction by visualizing the state with t-SNE algorithm. Despite unsupervised representation learning, we confirm that the proposed model defines the state well and predicts the energy demand accordingly.",
author = "Kim, {Jin Young} and Sung-Bae Cho",
year = "2019",
month = "2",
day = "22",
doi = "10.3390/en12040739",
language = "English",
volume = "12",
journal = "Energies",
issn = "1996-1073",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "4",

}

Electric energy consumption prediction by deep learning with state explainable autoencoder. / Kim, Jin Young; Cho, Sung-Bae.

In: Energies, Vol. 12, No. 4, 739, 22.02.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Electric energy consumption prediction by deep learning with state explainable autoencoder

AU - Kim, Jin Young

AU - Cho, Sung-Bae

PY - 2019/2/22

Y1 - 2019/2/22

N2 - As energy demand grows globally, the energy management system (EMS) is becoming increasingly important. Energy prediction is an essential component in the first step to create a management plan in EMS. Conventional energy prediction models focus on prediction performance, but in order to build an efficient system, it is necessary to predict energy demand according to various conditions. In this paper, we propose a method to predict energy demand in various situations using a deep learning model based on an autoencoder. This model consists of a projector that defines an appropriate state for a given situation and a predictor that forecasts energy demand from the defined state. The proposed model produces consumption predictions for 15, 30, 45, and 60 min with 60-min demand to date. In the experiments with household electric power consumption data for five years, this model not only has a better performance with a mean squared error of 0.384 than the conventional models, but also improves the capacity to explain the results of prediction by visualizing the state with t-SNE algorithm. Despite unsupervised representation learning, we confirm that the proposed model defines the state well and predicts the energy demand accordingly.

AB - As energy demand grows globally, the energy management system (EMS) is becoming increasingly important. Energy prediction is an essential component in the first step to create a management plan in EMS. Conventional energy prediction models focus on prediction performance, but in order to build an efficient system, it is necessary to predict energy demand according to various conditions. In this paper, we propose a method to predict energy demand in various situations using a deep learning model based on an autoencoder. This model consists of a projector that defines an appropriate state for a given situation and a predictor that forecasts energy demand from the defined state. The proposed model produces consumption predictions for 15, 30, 45, and 60 min with 60-min demand to date. In the experiments with household electric power consumption data for five years, this model not only has a better performance with a mean squared error of 0.384 than the conventional models, but also improves the capacity to explain the results of prediction by visualizing the state with t-SNE algorithm. Despite unsupervised representation learning, we confirm that the proposed model defines the state well and predicts the energy demand accordingly.

UR - http://www.scopus.com/inward/record.url?scp=85065911918&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065911918&partnerID=8YFLogxK

U2 - 10.3390/en12040739

DO - 10.3390/en12040739

M3 - Article

VL - 12

JO - Energies

JF - Energies

SN - 1996-1073

IS - 4

M1 - 739

ER -