An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple Features

Accurate prediction of natural gas purchase volumes is crucial for both the economy and the environment. It not only facilitates the rational allocation of resources for companies but also helps to reduce operational costs. Although existing prediction methods have achieved some success in addressin...

Full description

Saved in:
Bibliographic Details
Main Authors: Junjie Wang, Lei Jiang, Le Zhang, Yaqi Liu, Qihong Yu, Yuheng Bu
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/2/778
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832589164882690048
author Junjie Wang
Lei Jiang
Le Zhang
Yaqi Liu
Qihong Yu
Yuheng Bu
author_facet Junjie Wang
Lei Jiang
Le Zhang
Yaqi Liu
Qihong Yu
Yuheng Bu
author_sort Junjie Wang
collection DOAJ
description Accurate prediction of natural gas purchase volumes is crucial for both the economy and the environment. It not only facilitates the rational allocation of resources for companies but also helps to reduce operational costs. Although existing prediction methods have achieved some success in addressing the nonlinear relationships in natural gas purchases, there remains potential for further improvement. To address this issue, a stacking ensemble learning model was developed to enhance the ability to handle complex nonlinear problems. This model integrates diverse algorithms and incorporates weather factors, while regionalizing characteristics of natural gas usage, thereby achieving accurate forecasts of natural gas purchase volumes. We selected three distinctly different base models—Informer, multiple linear regression (MLR), and support vector regression (SVR)—for our research. By conducting four different feature combination experiments for each base model, including weather, time, regional, and usage features, we constructed 12 foundational models. Subsequently, we integrated these base models using a meta-learner to form the final stacking ensemble model. The experimental results indicate that the stacking ensemble model outperforms individual models across key metrics, including <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>, MRE, and RMSE. Notably, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> values improved by 4–15% compared to the 12 base models. The model was subsequently applied to predict natural gas purchase volumes in Pi County, Chengdu, China. In November 2024, a side-by-side comparison of the predicted and actual data revealed a maximum error of just 5.39%. This exceptional accuracy effectively meets forecasting requirements, underscoring the model’s predictive strength in the energy sector.
format Article
id doaj-art-14c5bc88b9b4488fa8be464f712e469c
institution Kabale University
issn 2076-3417
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-14c5bc88b9b4488fa8be464f712e469c2025-01-24T13:20:47ZengMDPI AGApplied Sciences2076-34172025-01-0115277810.3390/app15020778An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple FeaturesJunjie Wang0Lei Jiang1Le Zhang2Yaqi Liu3Qihong Yu4Yuheng Bu5School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaSchool of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411201, ChinaChengdu Pidu District Xingneng Natural Gas Co., Ltd., Pidu District, Chengdu 611730, ChinaChengdu Pidu District Xingneng Natural Gas Co., Ltd., Pidu District, Chengdu 611730, ChinaChengdu Pidu District Xingneng Natural Gas Co., Ltd., Pidu District, Chengdu 611730, ChinaChengdu Pidu District Xingneng Natural Gas Co., Ltd., Pidu District, Chengdu 611730, ChinaAccurate prediction of natural gas purchase volumes is crucial for both the economy and the environment. It not only facilitates the rational allocation of resources for companies but also helps to reduce operational costs. Although existing prediction methods have achieved some success in addressing the nonlinear relationships in natural gas purchases, there remains potential for further improvement. To address this issue, a stacking ensemble learning model was developed to enhance the ability to handle complex nonlinear problems. This model integrates diverse algorithms and incorporates weather factors, while regionalizing characteristics of natural gas usage, thereby achieving accurate forecasts of natural gas purchase volumes. We selected three distinctly different base models—Informer, multiple linear regression (MLR), and support vector regression (SVR)—for our research. By conducting four different feature combination experiments for each base model, including weather, time, regional, and usage features, we constructed 12 foundational models. Subsequently, we integrated these base models using a meta-learner to form the final stacking ensemble model. The experimental results indicate that the stacking ensemble model outperforms individual models across key metrics, including <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula>, MRE, and RMSE. Notably, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> values improved by 4–15% compared to the 12 base models. The model was subsequently applied to predict natural gas purchase volumes in Pi County, Chengdu, China. In November 2024, a side-by-side comparison of the predicted and actual data revealed a maximum error of just 5.39%. This exceptional accuracy effectively meets forecasting requirements, underscoring the model’s predictive strength in the energy sector.https://www.mdpi.com/2076-3417/15/2/778natural gas purchase predictionstacking ensembleInformermultiple linear regressionsupport vector regression
spellingShingle Junjie Wang
Lei Jiang
Le Zhang
Yaqi Liu
Qihong Yu
Yuheng Bu
An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple Features
Applied Sciences
natural gas purchase prediction
stacking ensemble
Informer
multiple linear regression
support vector regression
title An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple Features
title_full An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple Features
title_fullStr An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple Features
title_full_unstemmed An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple Features
title_short An Integrated Stacking Ensemble Model for Natural Gas Purchase Prediction Incorporating Multiple Features
title_sort integrated stacking ensemble model for natural gas purchase prediction incorporating multiple features
topic natural gas purchase prediction
stacking ensemble
Informer
multiple linear regression
support vector regression
url https://www.mdpi.com/2076-3417/15/2/778
work_keys_str_mv AT junjiewang anintegratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT leijiang anintegratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT lezhang anintegratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT yaqiliu anintegratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT qihongyu anintegratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT yuhengbu anintegratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT junjiewang integratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT leijiang integratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT lezhang integratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT yaqiliu integratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT qihongyu integratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures
AT yuhengbu integratedstackingensemblemodelfornaturalgaspurchasepredictionincorporatingmultiplefeatures