Building Electricity Load Forecasting Considering Climate Change Impacts: A Multi-Factor Deep Learning Approach

Accurate electricity load forecasting is crucial for efficient power system operation and planning, especially in urban environments where building energy dynamics play a significant role. This study focuses on improving building load forecasting by accounting for the differences between indoor and outdoor climate conditions, which significantly influence energy consumption patterns in buildings. In this paper, a comprehensive comparative study was conducted to assess the performance of several deep neural network models, with multi-factors incorporated to enhance forecast performance. The input features considered in this paper include the input sequence structures, lagged correlation-based temperature conditions, calendar information and categorical Building-Adjusted Internal Temperature (BAIT) index. The proposed approach innovatively integrates the disparities between indoor and outdoor climatic conditions to better capture the complexities of energy demand influenced by building characteristics and external weather conditions. The proposed method was tested on Singapore EMA load data from 2019 to 2022. The experimental outcomes demonstrate that the BAIT-enhanced models exhibit strong performance across various metrics, which yields superior predictions.