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

TL;DR

This paper introduces an innovative end-to-end building load forecasting framework that combines anomaly correction, feature analysis, a patch-based neural network, and an adaptive loss function to improve prediction accuracy and robustness.

Contribution

The framework's novel integration of anomaly detection, feature filtering, patch-based neural architecture, and adaptive loss function offers a comprehensive solution for accurate building load forecasting.

Findings

The proposed framework outperforms existing methods in accuracy.

The patch-based network effectively captures local temporal features.

The adaptive loss improves robustness under extreme load conditions.

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.