Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integration

Forecasting household energy consumption is crucial for sustainable energy management and grid stability. Traditional models often struggle with complex data characteristics. This study introduces a TinyML-optimized multivariate LSTM model designed for resource-constrained environments, leveraging s...

Full description

Saved in:
Bibliographic Details
Main Authors: Aditya Pai H, Kritika Kumari Mishra, Mahesh T R, J V Muruga Lal Jeyan, Anu Sayal
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025025812
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850070733661667328
author Aditya Pai H
Kritika Kumari Mishra
Mahesh T R
J V Muruga Lal Jeyan
Anu Sayal
author_facet Aditya Pai H
Kritika Kumari Mishra
Mahesh T R
J V Muruga Lal Jeyan
Anu Sayal
author_sort Aditya Pai H
collection DOAJ
description Forecasting household energy consumption is crucial for sustainable energy management and grid stability. Traditional models often struggle with complex data characteristics. This study introduces a TinyML-optimized multivariate LSTM model designed for resource-constrained environments, leveraging self-supervised learning to enhance predictive accuracy with minimal computational overhead. By integrating environmental factors like weather, the model offers a scalable solution for smart home applications, achieving significant improvements in key metrics while operating within the memory and power limitations typical of edge computing devices. This research contributes to the state of the art by using a structured data preprocessing pipeline that includes normalization, day resampling, and advanced feature engineering methods to prepare the input for LSTM networks in an optimal way. This work initiates the application of Self-Supervised Learning (SSL) for preprocessing and enriching weather-related features from remote sensing data to enhance the predictive capability of the LSTM. Empirical outcomes prove a considerable improvement over traditional forecasting models, which reach a Mean Squared Error (MSE) of 0.02063 and a Root Mean Squared Error (RMSE) of 0.14363, a Mean Absolute Error (MAE) of 0.107, a Mean Absolute Percentage Error (MAPE) of 0.155, and a Coefficient of Determination (R²) of 0.724. This work uniquely combines Self-Supervised Learning (SSL) with multivariate LSTM models, significantly improving feature extraction and alleviating limitations witnessed in current hybrid models, most notably with respect to handling intricate temporal dependencies and mitigating computational overhead within resource-limited settings.
format Article
id doaj-art-0cc42d5b253b4e1fb6769833f6426b24
institution DOAJ
issn 2590-1230
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-0cc42d5b253b4e1fb6769833f6426b242025-08-20T02:47:28ZengElsevierResults in Engineering2590-12302025-09-012710651210.1016/j.rineng.2025.106512Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integrationAditya Pai H0Kritika Kumari Mishra1Mahesh T R2J V Muruga Lal Jeyan3Anu Sayal4Department of CSE, MIT School of Computing MIT Art, Design and Technology University, Pune, 412201, IndiaDepartment of Computer Science and Engineering, JAIN (Deemed-to-be University), Bengaluru, 562112, IndiaDepartment of Computer Science and Engineering, JAIN (Deemed-to-be University), Bengaluru, 562112, India; Corresponding authors.LIPS Research & DLCARD, European International University, Paris, FranceSchool of Accounting and Finance, Faculty of Business and Law, Taylor's University, Subang Jaya, 47500, Malaysia; Corresponding authors.Forecasting household energy consumption is crucial for sustainable energy management and grid stability. Traditional models often struggle with complex data characteristics. This study introduces a TinyML-optimized multivariate LSTM model designed for resource-constrained environments, leveraging self-supervised learning to enhance predictive accuracy with minimal computational overhead. By integrating environmental factors like weather, the model offers a scalable solution for smart home applications, achieving significant improvements in key metrics while operating within the memory and power limitations typical of edge computing devices. This research contributes to the state of the art by using a structured data preprocessing pipeline that includes normalization, day resampling, and advanced feature engineering methods to prepare the input for LSTM networks in an optimal way. This work initiates the application of Self-Supervised Learning (SSL) for preprocessing and enriching weather-related features from remote sensing data to enhance the predictive capability of the LSTM. Empirical outcomes prove a considerable improvement over traditional forecasting models, which reach a Mean Squared Error (MSE) of 0.02063 and a Root Mean Squared Error (RMSE) of 0.14363, a Mean Absolute Error (MAE) of 0.107, a Mean Absolute Percentage Error (MAPE) of 0.155, and a Coefficient of Determination (R²) of 0.724. This work uniquely combines Self-Supervised Learning (SSL) with multivariate LSTM models, significantly improving feature extraction and alleviating limitations witnessed in current hybrid models, most notably with respect to handling intricate temporal dependencies and mitigating computational overhead within resource-limited settings.http://www.sciencedirect.com/science/article/pii/S2590123025025812TinyMLEdge computingSmart home energy managementLSTM networksSelf-supervised learning in IoTEnergy consumption prediction
spellingShingle Aditya Pai H
Kritika Kumari Mishra
Mahesh T R
J V Muruga Lal Jeyan
Anu Sayal
Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integration
Results in Engineering
TinyML
Edge computing
Smart home energy management
LSTM networks
Self-supervised learning in IoT
Energy consumption prediction
title Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integration
title_full Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integration
title_fullStr Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integration
title_full_unstemmed Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integration
title_short Enhanced household energy consumption forecasting using multivariate long short-term memory (LSTM) networks with weather data integration
title_sort enhanced household energy consumption forecasting using multivariate long short term memory lstm networks with weather data integration
topic TinyML
Edge computing
Smart home energy management
LSTM networks
Self-supervised learning in IoT
Energy consumption prediction
url http://www.sciencedirect.com/science/article/pii/S2590123025025812
work_keys_str_mv AT adityapaih enhancedhouseholdenergyconsumptionforecastingusingmultivariatelongshorttermmemorylstmnetworkswithweatherdataintegration
AT kritikakumarimishra enhancedhouseholdenergyconsumptionforecastingusingmultivariatelongshorttermmemorylstmnetworkswithweatherdataintegration
AT maheshtr enhancedhouseholdenergyconsumptionforecastingusingmultivariatelongshorttermmemorylstmnetworkswithweatherdataintegration
AT jvmurugalaljeyan enhancedhouseholdenergyconsumptionforecastingusingmultivariatelongshorttermmemorylstmnetworkswithweatherdataintegration
AT anusayal enhancedhouseholdenergyconsumptionforecastingusingmultivariatelongshorttermmemorylstmnetworkswithweatherdataintegration