Skip to main content
QUICK REVIEW

[论文解读] Energy Disaggregation via Deep Temporal Dictionary Learning

Mahdi Khodayar, Jianhui Wang|arXiv (Cornell University)|Sep 10, 2018
Smart Grid Energy Management被引用 4
一句话总结

本文提出了一种名为深度时序字典学习(DTDL)的新方法,用于能量分解,该方法结合长短期记忆自编码器(LSTM-AE)与非线性字典学习,以建模家庭用电信号中的时间模式。通过从深度时序特征中学习非线性字典,DTDL在REDD数据集上实现了最先进的性能,显著提升了现有方法的能量分解准确率和F值。

ABSTRACT

This paper addresses the energy disaggregation problem, i.e. decomposing the electricity signal of a whole home to its operating devices. First, we cast the problem as a dictionary learning (DL) problem where the key electricity patterns representing consumption behaviors are extracted for each device and stored in a dictionary matrix. The electricity signal of each device is then modeled by a linear combination of such patterns with sparse coefficients that determine the contribution of each device in the total electricity. Although popular, the classic DL approach is prone to high error in real-world applications including energy disaggregation, as it merely finds linear dictionaries. Moreover, this method lacks a recurrent structure; thus, it is unable to leverage the temporal structure of energy signals. Motivated by such shortcomings, we propose a novel optimization program where the dictionary and its sparse coefficients are optimized simultaneously with a deep neural model extracting powerful nonlinear features from the energy signals. A long short-term memory auto-encoder (LSTM-AE) is proposed with tunable time dependent states to capture the temporal behavior of energy signals for each device. We learn the dictionary in the space of temporal features captured by the LSTM-AE rather than the original space of the energy signals; hence, in contrast to the traditional DL, here, a nonlinear dictionary is learned using powerful temporal features extracted from our deep model. Real experiments on the publicly available Reference Energy Disaggregation Dataset (REDD) show significant improvement compared to the state-of-the-art methodologies in terms of the disaggregation accuracy and F-score metrics.

研究动机与目标

  • 为解决传统线性字典学习在能量分解中的局限性,后者无法捕捉电能信号中的复杂时间模式。
  • 克服经典字典学习中缺乏循环结构的问题,后者限制了其对能耗数据中序列依赖关系的建模能力。
  • 通过从LSTM自编码器提取的深度时间感知特征中学习非线性字典,提升分解准确率。
  • 通过在深度时序特征空间中联合优化字典与稀疏系数,实现更精确的设备级能耗估计。

提出的方法

  • 训练一个长短期记忆自编码器(LSTM-AE),以从原始电能信号中提取强大且与时间相关的表征。
  • 将LSTM-AE学习到的时间特征用作字典学习的输入空间,从而在设备级能耗中发现非线性模式。
  • 提出一种联合优化框架,以同时学习非线性字典与稀疏系数,确保每个设备的贡献被准确表示。
  • 在LSTM-AE的潜在空间中学习字典,使其能够捕捉线性模型所遗漏的复杂时间动态。
  • 该方法将每个设备的能耗信号建模为学习到的时间模式的稀疏线性组合,从而实现精确的分解。
  • 优化过程被制定为在强制系数稀疏性的同时最小化重构误差,以提升可解释性与准确性。

实验结果

研究问题

  • RQ1与传统线性模型相比,具有循环结构的深度神经网络是否能更好地表征家庭用电信号中的时间模式?
  • RQ2在LSTM自编码器的特征空间中学习非线性字典,是否相比在原始信号空间中进行线性字典学习,能带来更好的能量分解性能?
  • RQ3在深度时序特征空间中联合优化字典与稀疏系数,对分解准确率和F值指标有何影响?
  • RQ4通过LSTM-AE引入时间依赖性,与最先进方法相比,能在多大程度上降低设备级能耗估计的误差?

主要发现

  • 所提出的DTDL方法在公开的REDD数据集上,与最先进方法相比,显著提升了能量分解准确率。
  • 设备级能耗分解的F值明显高于基线方法,表明在识别单个电器使用情况方面具有更高的精确率与召回率。
  • 使用LSTM-AE特征使模型能够捕捉能量信号中的长期时间依赖性,而线性模型则无法实现这一点。
  • 在深度特征空间中联合优化字典与稀疏系数,带来了更准确且更鲁棒的设备活动检测。
  • 从时间特征中学得的非线性字典在建模家用电器复杂且非平稳的耗电行为方面,优于线性字典。
  • 实证结果证实,所提方法降低了重构误差,并增强了分解后能耗信号的可解释性。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。