A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction

Transformers are essential for voltage regulation and power distribution in electrical systems, and monitoring their top-oil temperature is crucial for detecting potential faults. High oil temperatures are directly linked to insulation degradation, a primary cause of transformer failures. Therefore,...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuemin Huang, Xiaoliang Zhuang, Fangyuan Tian, Zheng Niu, Yujie Chen, Qian Zhou, Chao Yuan
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/6/1432
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342094236188672
author Xuemin Huang
Xiaoliang Zhuang
Fangyuan Tian
Zheng Niu
Yujie Chen
Qian Zhou
Chao Yuan
author_facet Xuemin Huang
Xiaoliang Zhuang
Fangyuan Tian
Zheng Niu
Yujie Chen
Qian Zhou
Chao Yuan
author_sort Xuemin Huang
collection DOAJ
description Transformers are essential for voltage regulation and power distribution in electrical systems, and monitoring their top-oil temperature is crucial for detecting potential faults. High oil temperatures are directly linked to insulation degradation, a primary cause of transformer failures. Therefore, accurate oil temperature prediction is important for proactive maintenance and preventing failures. This paper proposes a hybrid time series forecasting model combining ARIMA, LSTM, and XGBoost to predict transformer oil temperature. ARIMA captures linear components of the data, while LSTM models complex nonlinear dependencies. XGBoost is used to predict the overall oil temperature by learning from the complete dataset, effectively handling complex patterns. The predictions of these three models are combined through a linear-regression stacking approach, improving accuracy and simplifying the model structure. This hybrid method outperforms traditional models, offering superior performance in predicting transformer oil temperature, which enhances fault detection and transformer reliability. Experimental results demonstrate the hybrid model’s superiority: In 5000-data-point prediction, it achieves an MSE = 0.9908 and MAPE = 1.9824%, outperforming standalone XGBoost (MSE = 3.2001) by 69.03% in error reduction and ARIMA-LSTM (MSE = 1.1268) by 12.08%, while surpassing naïve methods 1–2 (MSE = 1.7370–1.6716) by 42.94–40.74%. For 500-data-point scenarios, the hybrid model (MSE = 1.9174) maintains 22.40–35.53% lower errors than XGBoost (2.4710) and ARIMA-LSTM (3.6481) and outperforms naïve methods 1–2 (2.8611–2.9741) by 32.97–35.53%. These results validate the approach’s effectiveness across data scales. The proposed method contributes to more effective predictive maintenance and improved safety, ensuring the long-term performance of transformer equipment.
format Article
id doaj-art-9fcde55a92d240d3bb9f257df24d9d42
institution Kabale University
issn 1996-1073
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-9fcde55a92d240d3bb9f257df24d9d422025-08-20T03:43:30ZengMDPI AGEnergies1996-10732025-03-01186143210.3390/en18061432A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature PredictionXuemin Huang0Xiaoliang Zhuang1Fangyuan Tian2Zheng Niu3Yujie Chen4Qian Zhou5Chao Yuan6China Southern Power Grid Extra-High Voltage Transmission Company, Guangzhou Bureau, Guangzhou 510663, ChinaChina Southern Power Grid Extra-High Voltage Transmission Company, Guangzhou Bureau, Guangzhou 510663, ChinaChina Southern Power Grid Extra-High Voltage Transmission Company, Guangzhou Bureau, Guangzhou 510663, ChinaChina Southern Power Grid Extra-High Voltage Transmission Company, Guangzhou Bureau, Guangzhou 510663, ChinaSchool of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaSchool of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaSchool of Electrical and Information Engineering, Hunan University, Changsha 410082, ChinaTransformers are essential for voltage regulation and power distribution in electrical systems, and monitoring their top-oil temperature is crucial for detecting potential faults. High oil temperatures are directly linked to insulation degradation, a primary cause of transformer failures. Therefore, accurate oil temperature prediction is important for proactive maintenance and preventing failures. This paper proposes a hybrid time series forecasting model combining ARIMA, LSTM, and XGBoost to predict transformer oil temperature. ARIMA captures linear components of the data, while LSTM models complex nonlinear dependencies. XGBoost is used to predict the overall oil temperature by learning from the complete dataset, effectively handling complex patterns. The predictions of these three models are combined through a linear-regression stacking approach, improving accuracy and simplifying the model structure. This hybrid method outperforms traditional models, offering superior performance in predicting transformer oil temperature, which enhances fault detection and transformer reliability. Experimental results demonstrate the hybrid model’s superiority: In 5000-data-point prediction, it achieves an MSE = 0.9908 and MAPE = 1.9824%, outperforming standalone XGBoost (MSE = 3.2001) by 69.03% in error reduction and ARIMA-LSTM (MSE = 1.1268) by 12.08%, while surpassing naïve methods 1–2 (MSE = 1.7370–1.6716) by 42.94–40.74%. For 500-data-point scenarios, the hybrid model (MSE = 1.9174) maintains 22.40–35.53% lower errors than XGBoost (2.4710) and ARIMA-LSTM (3.6481) and outperforms naïve methods 1–2 (2.8611–2.9741) by 32.97–35.53%. These results validate the approach’s effectiveness across data scales. The proposed method contributes to more effective predictive maintenance and improved safety, ensuring the long-term performance of transformer equipment.https://www.mdpi.com/1996-1073/18/6/1432transformer top-oil temperaturehybrid time series forecasting modelARIMA-LSTM-XGBoostprediction accuracyfault detection
spellingShingle Xuemin Huang
Xiaoliang Zhuang
Fangyuan Tian
Zheng Niu
Yujie Chen
Qian Zhou
Chao Yuan
A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction
Energies
transformer top-oil temperature
hybrid time series forecasting model
ARIMA-LSTM-XGBoost
prediction accuracy
fault detection
title A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction
title_full A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction
title_fullStr A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction
title_full_unstemmed A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction
title_short A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction
title_sort hybrid arima lstm xgboost model with linear regression stacking for transformer oil temperature prediction
topic transformer top-oil temperature
hybrid time series forecasting model
ARIMA-LSTM-XGBoost
prediction accuracy
fault detection
url https://www.mdpi.com/1996-1073/18/6/1432
work_keys_str_mv AT xueminhuang ahybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT xiaoliangzhuang ahybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT fangyuantian ahybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT zhengniu ahybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT yujiechen ahybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT qianzhou ahybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT chaoyuan ahybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT xueminhuang hybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT xiaoliangzhuang hybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT fangyuantian hybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT zhengniu hybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT yujiechen hybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT qianzhou hybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction
AT chaoyuan hybridarimalstmxgboostmodelwithlinearregressionstackingfortransformeroiltemperatureprediction