Open Access

ARTICLE

A MCG-GFAM-MRDCM Model for Accurate Building Electricity Load Forecasting

Chuan Lin^*, Weixian Chen, Guangtao Hao^*
College of Intelligent Manufacturing, Putian University, Putian, China
* Corresponding Author: Chuan Lin. Email: ; Guangtao Hao. Email:

Energy Engineering https://doi.org/10.32604/ee.2026.080605

Received 12 February 2026; Accepted 08 April 2026; Published online 05 May 2026

Abstract

Accurate building electricity load forecasting (BELF) can provide a regulatory basis for building energy management systems and promote the transition of buildings toward low-carbon and intelligent operation modes. However, building electricity load is influenced by historical loads, as well as outside environmental conditions such as humidity and temperature, which reduces the prediction accuracy of models. To tackle these challenges, this study presents a BELF model, which consists of a modal component grouping approach, grouped feature attention mechanism, and multi-scale residual depthwise convolution memory module. First, the modal component grouping method analyzes building electricity load in the time domain, frequency domain (via fast fourier transform, FFT), and complexity (via sample entropy, SE), and then performs clustering to achieve precise decomposition of load components with different fluctuation characteristics. Second, the grouped feature attention mechanism assigns suitable importance to various input features to emphasize key factors affecting prediction accuracy. Third, the multi-scale residual depthwise convolution memory module mitigates the impact of long and short-term load variations on BELF by employing residual blocks of depthwise convolution layers with different kernel sizes. Meanwhile, gated recurrent units are used to identify the time-dependent trends of building load. Experimental results on public buildings show that the proposed model outperforms existing models, achieving more than 2.4% improvement in MAPE prediction performance.

---

Keywords

Building electricity load forecasting; modal component grouping method; depthwise convolutional neural network; attention mechanism

---