cs.LGApr 4, 2026

GCA-BULF: A Bottom-Up Framework for Short-Term Load Forecasting Using Grouped Critical Appliances

Authors: Yunhao Yao, Jinwei Fang, Puhan Luo, Zhiqiang Wang, Jiahui Hou, Xiang-Yang Li

Organizations: University of Science and Technology of China (USTC)

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

With the rise of time-of-use and tiered electricity pricing, energy consumers are encouraged to adopt peak-shifting strategies by automatically controlling high-power appliances. These help lower energy costs while enhancing the power grid's stability. To support such energy management with high resilience and responsiveness, reliable short-term load forecasting (STLF) plays a critical role. STLF predicts electricity consumption over time horizons ranging from minutes to days, using historical data, temporal patterns, and contextual factors. Traditional top-down forecasting methods struggle to capture the complex consumption patterns of diverse and mixed appliance loads. Although bottom-up methods improve forecasting accuracy by integrating appliance-level data, monitoring all appliances is costly, and many do not meaningfully impact total load prediction. Therefore, we propose GCA-BULF, a bottom-up short-term load forecasting framework based on grouped critical appliances, supported by three key designs. First, the Critical Appliance Filtering module ranks appliances according to their power consumption, switching frequency, and usage pattern periodicity, and identifies critical ones through iterative load decomposition. Next, the Related Appliance Grouping module clusters these appliances based on spatial and temporal correlations for group-level forecasting. Finally, the Collaborative Load Forecasting module refines the total load prediction by combining multiple group-level forecasts. We evaluate GCA-BULF on residential and office building load forecasting tasks. Experimental results reveal that GCA-BULF improves hourly total load forecasting by 20.85%-57.88% compared to existing top-down methods and by 33.03%-92.48% compared to bottom-up methods.

Figures & tables

Fig. 1: System Overview of GCA-BULF.
Fig. 2: Examples of Critical Appliance Filtering on the UK-DALE Dataset.
Fig. 3: Examples of Calculating the Correlation of Critical Appliance Usage.
Fig. 4: The Structure of Our Collaborative Load Forecasting Framework.
ϵ\epsilon0.30.40.50.60.70.80.90.920.940.960.98
τ=3\tau=30.09270.09270.09120.09050.08790.08740.08530.08340.08410.08820.0906
 18.61%18.69%19.07%18.77%17.77%17.94%17.40%17.02%17.11%18.29%18.77%
τ=6\tau=60.08900.08720.08590.08510.08270.08070.07850.07610.07610.08000.0815
 18.06%17.54%18.03%17.15%16.94%16.92%16.21%15.76%15.84%16.58%16.82%
τ=12\tau=120.08220.08170.07960.07640.07410.07340.07330.07000.07020.07490.0794
 16.86%17.17%16.37%15.86%15.54%15.42%15.49%14.50%14.50%15.80%16.50%
TABLE I: MAE (KW) and MAPE of GCA-BULF with Varying Clustering Radius ϵ\epsilon and Time Windows τ\tau on UK-DALE
ϵ\epsilon0.10.20.30.350.40.450.50.60.70.9
τ=3\tau=30.08880.09820.10530.11760.11050.12080.11350.10640.10880.1133
 2.18%2.39%2.56%2.80%2.69%2.93%2.74%2.58%2.61%2.72%
τ=6\tau=60.07900.09070.10970.10890.10560.11920.11390.10850.11220.1136
 1.94%2.25%2.70%2.66%2.55%2.83%2.79%2.64%2.68%2.75%
τ=12\tau=120.07170.09030.10270.11160.09890.11240.10230.11150.10260.1058
 1.79%2.21%2.60%2.79%2.39%2.78%2.48%2.71%2.52%2.57%
TABLE II: MAE (10MW) and MAPE of GCA-BULF with Varying Clustering Radius ϵ\epsilon and Time Windows τ\tau on BST-EC
Table 7
Figure 8
Figure 9
Fig. 9: Case Study: GCA-BULF vs. Existing Top-Down Methods on UK-DALE.
Figure 11
Fig. 12: Case Study: GCA-BULF vs. Existing Bottom-Up Methods on UK-DALE.
More in this topic

Electricity Load Forecasting

Electricity load forecasting predicts future power demand to support grid operation, planning, and energy management.

See all 46 papers

Explore similar work

CardsList
Sep 16, 2026

Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels

For distribution system operators, short-term load forecasting (STLF) supports congestion management, voltage control, and asset protection. Most existing approaches focus on overall accuracy across all time steps and neglect performance during high-demand (HD) periods, where larger forecast errors can increase the risk of congestion and voltage violations. In this paper, we study peak-aware STLF across three operator-relevant distribution grid aggregation levels, area codes (AC), secondary substations (SUB), and low-voltage (LV) feeders, using open datasets from the United Kingdom and Switzerland. We compare statistical baselines, machine learning models (LightGBM and XGBoost), and recent time-series foundation models (Chronos Bolt and Chronos-2) under a peak-aware evaluation framework that reports both overall and HD forecasting performance using NMAE and MAPE. The results show that Chronos-2 achieves the best HD performance across all aggregation levels, with HD-NMAE and HD-MAPE of 0.039 and 4.53% at AC, 0.080 and 9.45% at SUB, and 0.138 and 16.14% at LV, while Chronos-Bolt consistently ranks second best. Compared with the gradient boosted ML models, Chronos-2 reduces mean HD-NMAE by about 20-51% across levels while remaining best or near-best on the overall metrics. A quantile analysis of the probabilistic Chronos outputs further identifies aggregation-specific operating points, and runtime measurements indicate that foundation model inference is fast enough for practical deployment. Overall, the findings highlight peak-aware evaluation and aggregation specific quantile selection as a practical pathway toward more operationally relevant STLF in distribution networks.

Souhardya Chattopadhyay, Julian Oelhaf, Antonia Schoening +5

Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg · Siemens AG, Smart Infrastructure · Department of Electrical Engineering, Media and Computer Science, Ostbayerische Technische Hochschule Amberg-Weiden

Time Series ForecastingElectricity Load ForecastingTime-Series Foundation ModelsPower Systems
AskPDF
Jul 17, 2026

A Benchmark for Electrical Load Forecasting Across Grid Levels: Time-Series Transformers Outperform Established Methods

Accurate load forecasting at multiple grid levels is essential for future smart grids, ranging from aggregated control area forecasts for balancing supply and demand to forecasts of individual end-consumer loads for demand-side management and energy management systems. We present a comprehensive benchmark for load forecasting across grid levels, comprising three datasets that represent a transmission system operator control area, low-voltage grid feeders, and individual end consumers. We evaluate ten methods for short-term load forecasting and find that Transformer-based approaches consistently outperform established methods, reducing forecast error by 6.6-10.7 %. To analyze the impact of architectural design, we introduce YAformer, a flexible Transformer architecture that integrates modifications from prior work and is optimized via hyperparameter optimization. However, the standard Transformer achieves superior performance, suggesting that these architectural modifications are not required for accurate load forecasting. We further evaluate the Transformer-based time-series foundation model Chronos-2, which demonstrates competitive zero-shot performance on two datasets but fails to accurately capture special events in the TSO data. Detailed analyses reveal model-specific strengths and weaknesses, and ablation studies highlight the importance of long input contexts, covariates and continuous retraining - aspects that are often overlooked in the time-series forecasting literature.

Matthias Hertel, Sebastian Pütz, Jonathan Kolar +3

Karlsruhe Institute of Technology, Germany · Helmholtz AI, Germany

Time Series ForecastingForecasting BenchmarksElectricity Load ForecastingTime Series TransformersTime-Series Foundation ModelsPower Systems
AskPDF
Jul 2, 2026

Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics

Low-voltage load forecasting is an important component in current and future energy systems with a high degree of electrification and decentralized generation. However, current forecasting methods require significant manual effort, often lack uncertainty estimation and proper peak prediction, and they are often not adequately evaluated in terms of grid requirements. In the present study, we provide an extensive evaluation of short-term net load forecasts of 200 real-world low-voltage feeders with a focus on the rapidly evolving time series foundation models. Our study compares Chronos-Bolt, Chronos-2 and TabPFN-TS to six baseline models and demonstrates superior performance, in particular for Chronos-2. An ablation study, in which weather covariates are omitted, shows that time series foundation models adapt to increased uncertainty, despite the importance of weather information. A novel application-oriented metric links the model's forecasting capabilities in peak prediction to the trade-off in grid asset planning and operation between cost reduction and minimizing the risk of failure.

Benedikt Kaas, Manuel Treutlein, Hannes Benedikt Gerber +5

Karlsruhe Institute of Technology (KIT), Germany and Netze BW GmbH, Germany · Netze BW GmbH, Germany · Karlsruhe Institute of Technology (KIT), Germany

Time Series ForecastingElectricity Load ForecastingTime-Series Foundation ModelsProbabilistic Time Series Forecasting
AskPDF