Energy Disaggregation via Deep Temporal Dictionary Learning
Energy Disaggregation via Deep Temporal Dictionary Learning
复制标题
DOI：
10.1109/tnnls.2019.2921952
复制
发表时间：
2020-05-01
影响因子：
10.4
通讯作者：
Wang, Zhaoyu
中科院分区：
文献类型：
--
作者：
Khodayar, Mahdi;Wang, Jianhui;Wang, Zhaoyu
本文提出了一种新的非线性字典学习（DL）模型来解决能量分解（艾德）问题，将家庭的电信号分解到其操作设备。首先，艾德被建模为一个新的时间DL问题，其中一组字典原子被学习以捕获电信号的最具代表性的时间特征。对应于这些原子的稀疏代码显示了每个设备在总耗电量中的贡献。为了学习强大的原子，提出了一种新的深时间DL（DTDL）模型，该模型在长短期记忆自动编码器（LSTM-AE）的潜在空间中计算复杂的非线性字典。虽然LSTM-AE捕获了电信号的深时间流形，但DTDL模型在该流形中找到了最具代表性的原子。为了同时优化字典和深时态流形，提出了一种新的优化算法，该算法在寻找最佳LSTM-AE和最佳字典之间交替进行。据作者所知，DTDL是唯一理解数据深层时态结构的DL模型。在参考艾德数据集上的实验表明，与最近的国家的最先进的算法相比，在精度，召回率，准确率和F-得分的出色表现。
This paper presents a novel nonlinear dictionary learning (DL) model to address the energy disaggregation (ED) problem, i.e., decomposing the electricity signal of a home to its operating devices. First, ED is modeled as a new temporal DL problem where a set of dictionary atoms is learned to capture the most representative temporal features of electricity signals. The sparse codes corresponding to these atoms show the contribution of each device in the total electricity consumption. To learn powerful atoms, a novel deep temporal DL (DTDL) model is proposed that computes complex nonlinear dictionaries in the latent space of a long short-term memory autoencoder (LSTM-AE). While the LSTM-AE captures the deep temporal manifold of electricity signals, the DTDL model finds the most representative atoms inside this manifold. To simultaneously optimize the dictionary and the deep temporal manifold, a new optimization algorithm is proposed that alternates between finding the optimal LSTM-AE and the optimal dictionary. To the best of authors' knowledge, DTDL is the only DL model that understands the deep temporal structures of the data. Experiments on the Reference ED Data Set show an outstanding performance compared with the recent state-of-the-art algorithms in terms of precision, recall, accuracy, and F-score.