An End-to-end Building Load Forecasting Framework with Patch-based Information Fusion Network and Error-weighted Adaptive Loss

2026-04-15

AI Summary

This study addresses the challenges of complex temporal dependencies and high volatility in building load forecasting, which severely limit prediction accuracy. To overcome these issues, the authors propose an end-to-end forecasting framework that first employs Local Outlier Factor and SVM-SHAP for anomaly detection and interpretable feature selection. Subsequently, a Patch-wise Information Fusion Network (PIF-Net) is introduced, integrating patch-based GRU modules, residual connections, and gating mechanisms to dynamically weight and fuse local temporal features. Furthermore, an Error-Weighted Adaptive Loss (EWAL) function is designed to optimize the training process. Experimental results demonstrate that the proposed method significantly outperforms existing approaches in both overall prediction accuracy and robustness under extreme high-volatility conditions.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Intelligent Robots: State Estimation
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Accurate building load forecasting plays a critical role in facilitating demand response aggregation and optimizing energy management. However, the complex temporal dependencies and high volatility of building loads limit the improvement of prediction accuracy. To this end, we propose a novel end-to-end building load forecasting framework. Specifically, the framework can be divided into two main stages. In the two-stage data preprocessing module enhanced by interpretable feature selection, we utilize the Local Outlier Factor (LOF) algorithm to accurately detect and correct anomalies in the original building load series. Furthermore, we employ SVM-SHAP feature analysis to quantify the impact of environmental variables, filtering out critical feature combinations to mitigate redundancy. In the building load forecasting module, we propose the patch-based information fusion network (PIF-Net). This model applies patching technology to process input series into local blocks, extracting temporal features through a shared Gated Recurrent Unit (GRU) network with residual connections. Subsequently, an information fusion module based on a customized gating mechanism integrates the ensemble hidden states to weight the importance of different temporal patches dynamically. Additionally, the framework is trained using a novel Error-weighted Adaptive Loss (EWAL) function. By combining a rational quadratic function and logarithmic loss to dynamically adjust penalty weights based on real-time prediction error distributions, EWAL significantly enhances the model's robustness under extreme load conditions. Finally, extensive experiments demonstrate the effectiveness and superiority of our proposed framework.

Problem

• building load forecasting
• temporal dependencies
• high volatility
• prediction accuracy

Innovation

• Patch-based Information Fusion
• Error-weighted Adaptive Loss
• Gated Recurrent Unit
• Interpretable Feature Selection
• Building Load Forecasting