Probabilistic HVAC Load Forecasting Method Based on Transformer Network Considering Multiscale and Multivariable Correlation
Open Access
- 24 September 2025
- Vol. 18 (19) , 5073
Abstract
Accurate load forecasting for community-level heating, ventilation, and air conditioning (HVAC) plays an important role in determining an efficient strategy for demand response (DR) and the operation of the power grid. However, community-level HVAC includes various building-level HVACs, whose usage patterns and standard parameters vary, causing the challenge of load forecasting. To this end, a novel deep learning model, multiscale and cross-variable transformer (MSCVFormer), is proposed to achieve accurate community-level HVAC probabilistic load forecasting by capturing the various influences of multivariables on the load pattern, providing effective information for the grid operators to develop DR and operation strategies. This approach is combined with the multiscale attention (MSA) and cross-variable attention (CVA) mechanism, capturing the complex temporal patterns of the aggregated load. Specifically, by embedding the time series decomposition into the self-attention mechanism, MSA enables the model to capture the critical features of time series while considering the correlation between multiscale time series. Then, CVA calculates the correlations between the exogenous variable and aggregated load, explicitly utilizing the exogenous variables to enhance the model’s understanding of the temporal pattern. This differs from the usual methods, which do not fully consider the relationship between the exogenous variable and aggregated load. To test the effectiveness of the proposed method, two datasets from Germany and China are used to conduct the experiment. Compared to the benchmarks, the proposed method achieves outperforming probabilistic load forecasting results, where the prediction interval coverage probability (PICP) deviation with the nominal coverage and prediction interval normalized averaged width (PINAW) are reduced by 46.7% and 5.25%, respectively.Keywords
Funding Information
- Southern Power Grid Corporation Technology Project (036000KK52222004(GDKJXM20222117))
This publication has 43 references indexed in Scilit:
- Non-intrusive load monitoring based on process-adaptive multi-target regression and transformer-enabled two-stream input networkApplied Energy, 2025
- Demand response for renewable energy communities: Exploring coordination of prosumer-generated PV and flexible aggregated demand in the Italian frameworkEnergy and Buildings, 2025
- Building plug load mode detection, forecasting and schedulingApplied Energy, 2024
- Short-term cooling load prediction for central air conditioning systems with small sample based on permutation entropy and temporal convolutional networkEnergy and Buildings, 2024
- Total and thermal load forecasting in residential communities through probabilistic methods and causal machine learningApplied Energy, 2023
- Short-term cooling and heating loads forecasting of building district energy system based on data-driven modelsEnergy and Buildings, 2023
- DeepEdge-NILM: A case study of non-intrusive load monitoring edge device in commercial buildingEnergy and Buildings, 2023
- Physics-guided LSTM model for heat load prediction of buildingsEnergy and Buildings, 2023
- Reinforcement learning for whole-building HVAC control and demand responseEnergy and AI, 2020
- Review of modeling methods for HVAC systemsApplied Thermal Engineering, 2014