Sep 2026· 2026 3rd International Conference on Technology Innovation and Its Applications (ICTIIA)· pp. 1-6· 0 citations· 14 references
Abstract
Accurate forecasting of household appliance energy consumption is essential for supporting smart-home energy management and residential electricity efficiency. This study compares the forecasting performance of Linear Models (LM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) using a multivariate dataset. Performance was assessed using RMSE, R2, and MAE alongside a Naive Persistence baseline, with statistical significance evaluated using the DM test. Results indicate that LM achieved the highest single-step accuracy (RMSE = 61.15 Wh, R2 = 0.5447, MAE = 28.48 Wh) and was the only model to significantly outperform the naive baseline (p < 0.01), while XGBoost demonstrated superior performance at longer forecast horizons beyond 8 hours. These findings highlight that simpler linear models can outperform ensemble methods in short-term settings, and that horizon-dependent model selection offers practical value for residential energy planning and demand response applications.
The LSTM model’s superior accuracy supports its integration into Building Energy Management Systems (BEMS) for demand response, anomaly detection, and predictive control, enabling professionals to reduce operational energy costs, enhance occupant comfort, and advance sustainability targets within modern building portfo...
Nadia Ahbab, Shahrad Samankan, Mustafa Berker Yurtseven· Building Services Engineerin...· 0 citations
A comparative analysis of two independent forecasting approaches: a statistical Seasonal AutoRegressive Integrated Moving Average with eXogenous variables (SARIMAX) model and a feature-enhanced gradient descent (GD) based learning model demonstrates that the gradient-based learning approach captures short-term load var...
Rinu Sarah Mathews, A. Linsley, T. Symon· International Journal of Dru...· 0 citations
This study assessed how the selected seasonal test period, training-window strategy, and hyperparameter selection were associated with differences in XGBoost day-ahead forecast accuracy and interpretation for approximately 300 G11-tariff households in Poland. Sixteen configurations combined four 31-day periods, sliding...
P. Szeląg, T. Popławski, M. Adamusiński· Energies· 0 citations
The hybrid ensemble model accomplished the highest forecasting accuracy of the electricity bill with MAE, RMSE, MSE, MASE and R2 of 0.97978 when compared to other models.
T. Adefarati, Gulshan Sharma, P. Bokoro et al.· Energies· 0 citations
One-hour-ahead electricity-load forecasting offers a potential reference for near-term demand monitoring, while its practical implementation requires a balance between predictive performance and input-data requirements. This study develops one-hour-ahead forecasting models using 3,504,000 hourly observations from 400 p...
Dongfang Yang, Kai Li, Yu-Hang Zhang et al.· Buildings· 0 citations
The experimental findings indicate that Linear Regression (LR) model is better than the Artificial Neural Network (ANN) model because it has a small Root Mean Square Error (RMSE), which means that the underlying data set is more linear in nature and in this case, simpler models can be more effective than the more compl...
Shorya Mittal, N. Saxena, K. Gandhi et al.· Journal of Electrical System...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
