This paper proposes a generalised and robust multi-factor Gated Recurrent Unit (GRU) based Deep Learning (DL) model to forecast electricity load in distribution networks during wildfire seasons. The flexible modelling methods consider data input structure, calendar effects and correlation-based leading temperature conditions. Compared to the regular use of instantaneous temperature, the Mean Absolute Percentage Error (MAPE) is decreased by 30.73% by using the proposed input feature selection and leading temperature relationships. Our model is generalised and applied to eight real distribution networks in Victoria, Australia, during the wildfire seasons of 2015-2020. We demonstrate that the GRU-based model consistently outperforms another DL model, Long Short-Term Memory (LSTM), at every step, giving average improvements in Mean Squared Error (MSE) and MAPE of 10.06% and 12.86%, respectively. The sensitivity to large-scale climate variability in training data sets, e.g. El Ni\~no or La Ni\~na years, is considered to understand the possible consequences for load forecasting performance stability, showing minimal impact. Other factors such as regional poverty rate and large-scale off-peak electricity use are potential factors to further improve forecast performance. The proposed method achieves an average forecast MAPE of around 3%, giving a potential annual energy saving of AU\$80.46 million for the state of Victoria.

翻译：本文提出一种基于门控循环单元（GRU）的广义鲁棒多因子深度学习（DL）模型，用于预测野火季节配电网电力负荷。该灵活建模方法综合考虑数据输入结构、日历效应及基于相关性的领先温度条件。相较于常规瞬时温度输入，采用本文提出的输入特征选择与领先温度关系后，平均绝对百分比误差（MAPE）降低30.73%。该模型具有广义性，已应用于澳大利亚维多利亚州2015-2020年野火季节期间的八个实际配电网。实验证明，基于GRU的模型在每个评估步骤上均持续优于另一种深度学习模型——长短期记忆网络（LSTM），在均方误差（MSE）和MAPE指标上分别平均提升10.06%和12.86%。研究同时考虑训练数据集中大规模气候变率（如厄尔尼诺或拉尼娜年份）对负荷预测性能稳定性的潜在影响，结果表明其影响极小。区域贫困率与大规模非高峰用电等其它因素，可作为进一步提升预测性能的潜在因子。所提方法实现约3%的平均预测MAPE，可为维多利亚州每年节省约8046万澳元的潜在能源成本。