Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks
The availability of constant electricity supply is a crucial factor to the performance of any industry. Nevertheless, the unstable supply of electricity in Cameroon has led to countless periods of electricity load shedding, hence, making the management of the telecom industry to fall on backup power...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2020-01-01
|
Series: | Applied Artificial Intelligence |
Online Access: | http://dx.doi.org/10.1080/08839514.2019.1691839 |
_version_ | 1797684892105965568 |
---|---|
author | Jecinta Mulongo Marcellin Atemkeng Theophilus Ansah-Narh Rockefeller Rockefeller Gabin Maxime Nguegnang Marco Andrea Garuti |
author_facet | Jecinta Mulongo Marcellin Atemkeng Theophilus Ansah-Narh Rockefeller Rockefeller Gabin Maxime Nguegnang Marco Andrea Garuti |
author_sort | Jecinta Mulongo |
collection | DOAJ |
description | The availability of constant electricity supply is a crucial factor to the performance of any industry. Nevertheless, the unstable supply of electricity in Cameroon has led to countless periods of electricity load shedding, hence, making the management of the telecom industry to fall on backup power supply such as diesel generators. The fuel consumption of these generators remain a challenge due to some perturbations in the mechanical fuel level gauges and lack of maintenance at the base stations resulting to fuel pilferage. In order to overcome these effects, we detect anomalies in the recorded data by learning the patterns of the fuel consumption using four classification techniques namely; support vector machines (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR), and MultiLayer Perceptron (MLP) and then compare the performance of these classification techniques on a test data. In this paper, we show the use of supervised machine learning classification based techniques in detecting anomalies associated with the fuel consumed dataset from TeleInfra base stations using the generator as a source of power. Here, we perform the normal feature engineering, selection, and then fit the model classifiers to obtain results and finally, test the performance of these classifiers on a test data. The results of this study show that MLP has the best performance in the evaluation measurement recording a score of $$96{\kern 1pt} \% $$ in the K-fold cross validation test. In addition, because of class imbalance in the observation, we use the precision-recall curve instead of the ROC curve and registered the probability of the Area Under Curve (AUC) as $$0.98$$. |
first_indexed | 2024-03-12T00:36:18Z |
format | Article |
id | doaj.art-90078f445f574857bd33ba9adcaa72b2 |
institution | Directory Open Access Journal |
issn | 0883-9514 1087-6545 |
language | English |
last_indexed | 2024-03-12T00:36:18Z |
publishDate | 2020-01-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | Applied Artificial Intelligence |
spelling | doaj.art-90078f445f574857bd33ba9adcaa72b22023-09-15T09:33:57ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452020-01-01341647910.1080/08839514.2019.16918391691839Anomaly Detection in Power Generation Plants Using Machine Learning and Neural NetworksJecinta Mulongo0Marcellin Atemkeng1Theophilus Ansah-Narh2Rockefeller Rockefeller3Gabin Maxime Nguegnang4Marco Andrea Garuti5African Institute for Mathematical Sciences (AIMS)Rhodes UniversityGhana Atomic Energy Commission (GAEC)African Institute for Mathematical Sciences (AIMS)African Institute for Mathematical Sciences (AIMS)African Institute for Mathematical Sciences (AIMS)The availability of constant electricity supply is a crucial factor to the performance of any industry. Nevertheless, the unstable supply of electricity in Cameroon has led to countless periods of electricity load shedding, hence, making the management of the telecom industry to fall on backup power supply such as diesel generators. The fuel consumption of these generators remain a challenge due to some perturbations in the mechanical fuel level gauges and lack of maintenance at the base stations resulting to fuel pilferage. In order to overcome these effects, we detect anomalies in the recorded data by learning the patterns of the fuel consumption using four classification techniques namely; support vector machines (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR), and MultiLayer Perceptron (MLP) and then compare the performance of these classification techniques on a test data. In this paper, we show the use of supervised machine learning classification based techniques in detecting anomalies associated with the fuel consumed dataset from TeleInfra base stations using the generator as a source of power. Here, we perform the normal feature engineering, selection, and then fit the model classifiers to obtain results and finally, test the performance of these classifiers on a test data. The results of this study show that MLP has the best performance in the evaluation measurement recording a score of $$96{\kern 1pt} \% $$ in the K-fold cross validation test. In addition, because of class imbalance in the observation, we use the precision-recall curve instead of the ROC curve and registered the probability of the Area Under Curve (AUC) as $$0.98$$.http://dx.doi.org/10.1080/08839514.2019.1691839 |
spellingShingle | Jecinta Mulongo Marcellin Atemkeng Theophilus Ansah-Narh Rockefeller Rockefeller Gabin Maxime Nguegnang Marco Andrea Garuti Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks Applied Artificial Intelligence |
title | Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks |
title_full | Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks |
title_fullStr | Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks |
title_full_unstemmed | Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks |
title_short | Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks |
title_sort | anomaly detection in power generation plants using machine learning and neural networks |
url | http://dx.doi.org/10.1080/08839514.2019.1691839 |
work_keys_str_mv | AT jecintamulongo anomalydetectioninpowergenerationplantsusingmachinelearningandneuralnetworks AT marcellinatemkeng anomalydetectioninpowergenerationplantsusingmachinelearningandneuralnetworks AT theophilusansahnarh anomalydetectioninpowergenerationplantsusingmachinelearningandneuralnetworks AT rockefellerrockefeller anomalydetectioninpowergenerationplantsusingmachinelearningandneuralnetworks AT gabinmaximenguegnang anomalydetectioninpowergenerationplantsusingmachinelearningandneuralnetworks AT marcoandreagaruti anomalydetectioninpowergenerationplantsusingmachinelearningandneuralnetworks |