TY - JOUR A2 - Cai, Ning AU - Deng, Zhuofu AU - Wang, Binbin AU - Guo, Heng AU - Chai, Chengwei AU - Wang, Yanze AU - Zhu，基于时间认知的统一分位数回归深度神经网络的概率住宅负荷预测但单户住宅的荷载分布具有较大的波动性和不确定性。由于难以产生可靠的点预测，概率负荷预测由于通过间隔、密度或分位数来捕捉波动和不确定性而变得更加流行。本文提出了一种统一的时间认知分位数回归深度神经网络来解决这一具有挑战性的问题。首先，设计多尺度卷积神经网络，从历史负荷序列中提取更多的行为特征;此外，还采用了一种新的周期编码方法对模型进行标记，提高了模型捕获规则负载模式的能力。然后，将两个子网络生成的特征融合并以端到端方式输入预测模型。此外，全局可微的分位数损失函数约束了整个网络进行训练。最后，在一个镜头中直接生成多个分位数的预测。 With ablation experiments, the proposed model achieved the best results in the AQS, AACE, and inversion error, and especially the average of the AACE is grown by 34.71%, 75.22%, and 32.44% compared with QGBRT, QCNN, and QLSTM, respectively, indicating that our method has excellent reliability and robustness rather than the state-of-the-art models obviously. Meanwhile, great performances of efficient time response demonstrate that our proposed work has promising prospects in practical applications. SN - 1076-2787 UR - https://doi.org/10.1155/2020/9147545 DO - 10.1155/2020/9147545 JF - Complexity PB - Hindawi KW - ER -