基于多头注意力卷积网络的电力负荷预测

预测居民用电相当于预测一个多元时间序列.针对多个传感器信号的特定窗口能够利用预测模型提取不同的特征来预测用电量.然而,由于时间序列内部特征存在着不规则的模式,包括电力属性之间隐藏的相关性,使得负荷预测准确率不高.为了提取复杂的不规则电力模式,选择性地学习时空特征以减少电力属性间的平移方差,本文提出了一种基于多头注意力的卷积循环神经网络深度学习模型.相较于单纯的时间序列模型,该模型利用卷积和加权机制对电力属性和有功功率间的局部相关性进行建模.它利用softmax函数和点积运算的注意力分数来模拟电力需求的瞬态和脉冲特性,有效地对瞬时脉冲功耗进行预测.在美国加州大学欧文分校(University of California,Irvine,UCI)家庭用电数据集共2 075 259个时间序列上的实验表明,所提出的模型与现有方法相比,准确率得到了较大提升.

Power load prediction based on multi-headed attentional convolutional network

Predicting residential energy consumption is tantamount to forecasting a multivariate time series.A specific window for several sensor signals can extract various features to forecast the energy consumption by using a prediction model.However,it is still a challenging task because of irregular patterns inside including hidden correlations between power attributes.In order to extract the complicated irregular energy patterns and selectively learn the spatiotemporal features to reduce the translational variance between energy attributes,we propose a deep learning model based on the multi-headed attention with the convolutional recurrent neural network.Compared with the simple time series model,the proposed model uses convolution and weighting mechanism to model the local correlation between power attributes and active power.It exploits the attention scores calculated with softmax and dot product operation in the network to model the transient and impulsive nature of energy demand,predicting the instantaneous pulse power consumption effectively.Experiments with the dataset of University of California,Irvine (UCI) household electric power consumption consisting of a total 2,075,259 time-series show that the proposed model greatly improves the prediction accuracy compared to the state-of-the-art deep learning models.