Real-Time Energy Disaggregation Algorithm Based on Multi-Channels DCNN and Autoregressive Model

Abstract

Energy disaggregation refers to the process of obtaining the energy consumption of several appliances in a house by disaggregating the aggregate power consumption measured by an electrical meter. Currently, deep learning methods are widely applied in this field. Real-time energy disaggregation is an important branch of energy disaggregation. Based on the Short Sequence-to-Point (Short Seq2point) (Odysseas) network structure, a real-time energy disaggregation algorithm based on multi-channels deep convolutional neural networks(MC-DCNN) and autoregressive model(AR) is proposed in this paper, which obtains the energy consumption of appliances at the current time point by disaggregating the historical aggregate power consumption to achieve delivering disaggregation results in real-time. The proposed method takes the original aggregate power sequence and differential power signal as the input of the network, and extracts the information of different time lengths in the sequence using multi-channels deep convolutional neural networks with a modified concatenate layer, so that the network can adapt to different appliances with different operating modes. In addition, the traditional autoregressive model is added as the linear component for solving the problem that the scale of the output is insensitive to the scale of the input in the neural network model. Finally, the proposed method was tested on the UK-DALE and REDD datasets, and the experimental results show that the method has good disaggregation performance on both datasets, has a small number of parameters and achieves fast inference.

Load Energy Decomposition Algorithm Based on Improved Bidirectional Transformer Combined With Time-Sensing Self-Attention

“…They used CNNs to extract load features and predict the midpoint values of signals, which improved decomposition accuracy while reducing model computational complexity. Deng et al [14] proposed a multichannel convolutional neural network combined with an autoregressive model, based on the short S2P framework. The model used the aggregated power signal and the differential power signal as inputs to extract information of different time lengths, thereby enhancing the disaggregation accuracy.…”