Predicting residential energy consumption is tantamount to forecasting a multivariate time series. A specific window for several sensor signals can induce various features extracted to forecast the energy consumption by using a predic-tion 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 spati-otemporal 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 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 reduces the prediction error by 31.01% compared to the state-of-the-art deep learning model. Especially, the multi-headed attention im-proves the prediction performance even more by up to 27.91% than the single-attention.