Skip to content
Open access

Effects of Operational-State Features on One-Week-Ahead Building Electricity Demand Forecasting Using a Temporal Fusion Transformer

Sep 2026 · Energies · 0 citations · 23 references

Abstract

Accurate one-week-ahead building electricity demand forecasting is essential for building energy management, yet representing future building operational characteristics remains challenging because such information is generally unavailable in advance. This study investigates the effectiveness of representing building operational characteristics using cluster labels derived from daily electricity consumption patterns for medium-term electricity demand forecasting. Cluster labels obtained by k-means clustering were incorporated as operational-state features into a Temporal Fusion Transformer (TFT) together with historical electricity consumption, meteorological variables, and calendar information. Forecasting performance was evaluated for a training facility and three university buildings using walk-forward validation under different feature reference periods. Under an idealized information condition in which meteorological variables and cluster labels corresponding to the forecasting period were provided as known future inputs, this forecasting pattern achieved the highest accuracy for all investigated buildings. Under the same idealized condition, variable importance analysis indicated that the cluster label exhibited the highest importance among the known future inputs, exceeding that of calendar variables and most meteorological variables. In addition, the TFT outperformed Long Short-Term Memory (LSTM) and Multi-Layer Perceptron (MLP) models. These findings indicate the potential value of the proposed operational-state representation for improving one-week-ahead building electricity demand forecasting and provide interpretable insights into the contribution of operational-state features.

Read PDF

Similar papers

Open access Sep 2026

Machine learning framework for short- and medium-term building energy consumption forecasting

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, M. Yurtseven · 0 citations
#machine learning Preprint Sep 2026

Medium-Term Multi-Resolution Electric Load Forecasting using Economic Data and Foundation Model

Accurate medium-term, from a few months to a few years, electricity load forecasts are crucial for informed decision-making in power plant maintenance scheduling, load dispatch and price settlement. Being comprised between Long-Term Load Forecasting (LTLF) which uses mostly economic projections and appliances developme...

Lindas Eloi, G. Yannig, Ciais Philippe · 0 citations
Open access Aug 2026

Joint probabilistic forecasting of electricity and heat demand in residential buildings using LSTM and weather-driven features

A probabilistic forecasting framework designed to jointly predict hourly electricity and heat demand for a residential building using deep learning is presented, based on a Long Short-Term Memory neural network trained using look-back windows of 48 h.

H. S, S. Radhakrishnan · 0 citations
Open access Sep 2026

Impact of Forecasting Uncertainty on Hybrid Renewable Energy System Sizing in Water Utilities

Water utilities are energy-intensive municipal systems, yet high-resolution operational data for planning on-site renewable generation remain scarce. This study assesses the influence of short-term load forecasting accuracy on the sizing of hybrid renewable energy systems that integrate photovoltaics, wind turbines, an...

Kalsoom Bano, Thomas Liberski, Przemysław Janik et al. · 0 citations
Open access Sep 2026

An Improved Informer-Based Load Forecasting Method Incorporating Electricity Consumption Profiling

An electricity-use-aware load forecasting method that integrates user behavior profiling with an improved Informer model and indicates that combining electricity-use behavior profiling with multiscale temporal modeling can effectively improve residential demand-side load forecasting.

Jin Wang, Ying Shi, Lei Zhang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.