Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning Techniques
Electricity demand is increasing proportionally to the increase in power usage. Without a doubt, energy efficiency has gained significant importance and attention, with one of the primary concerns being the detection and forecasting of abnormal consumption. In this paper, the authors...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universitas Indonesia
2022-11-01
|
Series: | International Journal of Technology |
Subjects: | |
Online Access: | https://ijtech.eng.ui.ac.id/article/view/5931 |
_version_ | 1797963154984009728 |
---|---|
author | Rawan ELhadad Yi-Fei Tan Wooi-Nee Tan |
author_facet | Rawan ELhadad Yi-Fei Tan Wooi-Nee Tan |
author_sort | Rawan ELhadad |
collection | DOAJ |
description | Electricity
demand is increasing proportionally to the increase in power usage. Without a
doubt, energy efficiency has gained significant importance and attention, with
one of the primary concerns being the detection and forecasting of abnormal
consumption. In this paper, the authors
proposed a method to predict the occurrence of abnormal consumption behavior in
advance. The proposed method utilizes the Isolation Forest algorithm to label
the smart meter electricity consumption readings as normal or abnormal. It
generates a sequence of data with varying lengths. Based on the data sequence, two supervised machine learning algorithms, Random
Forest, and Decision Tree were developed to forecast the occurrence of power
anomaly consumption. Experiment results showed that the proposed methods
consistently detect and predict the abnormal status 30 minutes ahead. There is no significant difference between
Random Forest and Decision Tree performance on different smart meter readings,
dataset sizes, and other data sequence lengths. The proposed methods portray an
alternative approach that is capable of auto-label normal and abnormal data
and, as a result, dealing with the sequence of label data in the prediction
process while avoiding the dynamic behavior of the power consumption data. |
first_indexed | 2024-04-11T01:23:51Z |
format | Article |
id | doaj.art-738ab1226532450c98a9dbd26133d169 |
institution | Directory Open Access Journal |
issn | 2086-9614 2087-2100 |
language | English |
last_indexed | 2024-04-11T01:23:51Z |
publishDate | 2022-11-01 |
publisher | Universitas Indonesia |
record_format | Article |
series | International Journal of Technology |
spelling | doaj.art-738ab1226532450c98a9dbd26133d1692023-01-03T10:44:50ZengUniversitas IndonesiaInternational Journal of Technology2086-96142087-21002022-11-011361317132510.14716/ijtech.v13i6.59315931Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning TechniquesRawan ELhadad0Yi-Fei Tan1Wooi-Nee Tan2Faculty of Engineering, Multimedia University, Persiaran Multimedia, 63100, Cyberjaya, Selangor, MalaysiaFaculty of Engineering, Multimedia University, Persiaran Multimedia, 63100, Cyberjaya, Selangor, MalaysiaFaculty of Engineering, Multimedia University, Persiaran Multimedia, 63100, Cyberjaya, Selangor, MalaysiaElectricity demand is increasing proportionally to the increase in power usage. Without a doubt, energy efficiency has gained significant importance and attention, with one of the primary concerns being the detection and forecasting of abnormal consumption. In this paper, the authors proposed a method to predict the occurrence of abnormal consumption behavior in advance. The proposed method utilizes the Isolation Forest algorithm to label the smart meter electricity consumption readings as normal or abnormal. It generates a sequence of data with varying lengths. Based on the data sequence, two supervised machine learning algorithms, Random Forest, and Decision Tree were developed to forecast the occurrence of power anomaly consumption. Experiment results showed that the proposed methods consistently detect and predict the abnormal status 30 minutes ahead. There is no significant difference between Random Forest and Decision Tree performance on different smart meter readings, dataset sizes, and other data sequence lengths. The proposed methods portray an alternative approach that is capable of auto-label normal and abnormal data and, as a result, dealing with the sequence of label data in the prediction process while avoiding the dynamic behavior of the power consumption data.https://ijtech.eng.ui.ac.id/article/view/5931decision treeisolation forestpower consumption anomalypredictionrandom forest |
spellingShingle | Rawan ELhadad Yi-Fei Tan Wooi-Nee Tan Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning Techniques International Journal of Technology decision tree isolation forest power consumption anomaly prediction random forest |
title | Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning Techniques |
title_full | Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning Techniques |
title_fullStr | Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning Techniques |
title_full_unstemmed | Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning Techniques |
title_short | Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning Techniques |
title_sort | anomaly prediction in electricity consumption using a combination of machine learning techniques |
topic | decision tree isolation forest power consumption anomaly prediction random forest |
url | https://ijtech.eng.ui.ac.id/article/view/5931 |
work_keys_str_mv | AT rawanelhadad anomalypredictioninelectricityconsumptionusingacombinationofmachinelearningtechniques AT yifeitan anomalypredictioninelectricityconsumptionusingacombinationofmachinelearningtechniques AT wooineetan anomalypredictioninelectricityconsumptionusingacombinationofmachinelearningtechniques |