Augmented robustness in home demand prediction: Integrating statistical loss function with enhanced cross-validation in machine learning hyperparameter optimisation

Sustainable forecasting of home energy demand (SFHED) is crucial for promoting energy efficiency, minimizing environmental impact, and optimizing resource allocation. Machine learning (ML) supports SFHED by identifying patterns and forecasting demand. However, conventional hyperparameter tuning meth...

Full description

Saved in:
Bibliographic Details
Main Authors: Banafshe Parizad, Ali Jamali, Hamid Khayyam
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Energy and AI
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666546825001168
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849389521421991936
author Banafshe Parizad
Ali Jamali
Hamid Khayyam
author_facet Banafshe Parizad
Ali Jamali
Hamid Khayyam
author_sort Banafshe Parizad
collection DOAJ
description Sustainable forecasting of home energy demand (SFHED) is crucial for promoting energy efficiency, minimizing environmental impact, and optimizing resource allocation. Machine learning (ML) supports SFHED by identifying patterns and forecasting demand. However, conventional hyperparameter tuning methods often rely solely on minimizing average prediction errors, typically through fixed k-fold cross-validation, which overlooks error variability and limits model robustness. To address this limitation, we propose the Optimized Robust Hyperparameter Tuning for Machine Learning with Enhanced Multi-fold Cross-Validation (ORHT-ML-EMCV) framework. This method integrates statistical analysis of k-fold validation errors by incorporating their mean and variance into the optimization objective, enhancing robustness and generalizability. A weighting factor is introduced to balance accuracy and robustness, and its impact is evaluated across a range of values. A novel Enhanced Multi-Fold Cross-Validation (EMCV) technique is employed to automatically evaluate model performance across varying fold configurations without requiring a predefined k value, thereby reducing sensitivity to data splits. Using three evolutionary algorithms Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Differential Evolution (DE) we optimize two ensemble models: XGBoost and LightGBM. The optimization process minimizes both mean error and variance, with robustness assessed through cumulative distribution function (CDF) analyses. Experiments on three real-world residential datasets show the proposed method reduces worst-case Root Mean Square Error (RMSE) by up to 19.8% and narrows confidence intervals by up to 25%. Cross-household validations confirm strong generalization, achieving coefficient of determination (R²) of 0.946 and 0.972 on unseen homes. The framework offers a statistically grounded and efficient solution for robust energy forecasting.
format Article
id doaj-art-473e02b90f654a12a30fdb7c17ba8185
institution Kabale University
issn 2666-5468
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Energy and AI
spelling doaj-art-473e02b90f654a12a30fdb7c17ba81852025-08-20T03:41:57ZengElsevierEnergy and AI2666-54682025-09-012110058410.1016/j.egyai.2025.100584Augmented robustness in home demand prediction: Integrating statistical loss function with enhanced cross-validation in machine learning hyperparameter optimisationBanafshe Parizad0Ali Jamali1Hamid Khayyam2School of Engineering, RMIT University, Melbourne, AustraliaSchool of Engineering, RMIT University, Melbourne, AustraliaCorresponding author.; School of Engineering, RMIT University, Melbourne, AustraliaSustainable forecasting of home energy demand (SFHED) is crucial for promoting energy efficiency, minimizing environmental impact, and optimizing resource allocation. Machine learning (ML) supports SFHED by identifying patterns and forecasting demand. However, conventional hyperparameter tuning methods often rely solely on minimizing average prediction errors, typically through fixed k-fold cross-validation, which overlooks error variability and limits model robustness. To address this limitation, we propose the Optimized Robust Hyperparameter Tuning for Machine Learning with Enhanced Multi-fold Cross-Validation (ORHT-ML-EMCV) framework. This method integrates statistical analysis of k-fold validation errors by incorporating their mean and variance into the optimization objective, enhancing robustness and generalizability. A weighting factor is introduced to balance accuracy and robustness, and its impact is evaluated across a range of values. A novel Enhanced Multi-Fold Cross-Validation (EMCV) technique is employed to automatically evaluate model performance across varying fold configurations without requiring a predefined k value, thereby reducing sensitivity to data splits. Using three evolutionary algorithms Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Differential Evolution (DE) we optimize two ensemble models: XGBoost and LightGBM. The optimization process minimizes both mean error and variance, with robustness assessed through cumulative distribution function (CDF) analyses. Experiments on three real-world residential datasets show the proposed method reduces worst-case Root Mean Square Error (RMSE) by up to 19.8% and narrows confidence intervals by up to 25%. Cross-household validations confirm strong generalization, achieving coefficient of determination (R²) of 0.946 and 0.972 on unseen homes. The framework offers a statistically grounded and efficient solution for robust energy forecasting.http://www.sciencedirect.com/science/article/pii/S2666546825001168Demand forecastEnhanced K-fold cross-validationXGBoostLightGBMOptimisationRobust
spellingShingle Banafshe Parizad
Ali Jamali
Hamid Khayyam
Augmented robustness in home demand prediction: Integrating statistical loss function with enhanced cross-validation in machine learning hyperparameter optimisation
Energy and AI
Demand forecast
Enhanced K-fold cross-validation
XGBoost
LightGBM
Optimisation
Robust
title Augmented robustness in home demand prediction: Integrating statistical loss function with enhanced cross-validation in machine learning hyperparameter optimisation
title_full Augmented robustness in home demand prediction: Integrating statistical loss function with enhanced cross-validation in machine learning hyperparameter optimisation
title_fullStr Augmented robustness in home demand prediction: Integrating statistical loss function with enhanced cross-validation in machine learning hyperparameter optimisation
title_full_unstemmed Augmented robustness in home demand prediction: Integrating statistical loss function with enhanced cross-validation in machine learning hyperparameter optimisation
title_short Augmented robustness in home demand prediction: Integrating statistical loss function with enhanced cross-validation in machine learning hyperparameter optimisation
title_sort augmented robustness in home demand prediction integrating statistical loss function with enhanced cross validation in machine learning hyperparameter optimisation
topic Demand forecast
Enhanced K-fold cross-validation
XGBoost
LightGBM
Optimisation
Robust
url http://www.sciencedirect.com/science/article/pii/S2666546825001168
work_keys_str_mv AT banafsheparizad augmentedrobustnessinhomedemandpredictionintegratingstatisticallossfunctionwithenhancedcrossvalidationinmachinelearninghyperparameteroptimisation
AT alijamali augmentedrobustnessinhomedemandpredictionintegratingstatisticallossfunctionwithenhancedcrossvalidationinmachinelearninghyperparameteroptimisation
AT hamidkhayyam augmentedrobustnessinhomedemandpredictionintegratingstatisticallossfunctionwithenhancedcrossvalidationinmachinelearninghyperparameteroptimisation