DyAt Nets: Dynamic Attention Networks for State Forecasting in Cyber-Physical Systems
DyAt Nets: Dynamic Attention Networks for State Forecasting in Cyber-Physical Systems
复制标题
DyAt Nets：用于网络物理系统状态预测的动态注意力网络
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Naren Ramakrishnan
中科院分区：
文献类型：
--
作者：
N. Muralidhar;S. Muthiah;Naren Ramakrishnan
多元时间序列预测是网络物理系统（CPS）状态预测的一项重要任务。 CPS 中的状态预测对于系统能源利用的优化规划和了解系统的正常运行特性至关重要，从而实现异常检测。预测模型还可用于识别次优或磨损的组件，从而有助于整体系统监控。大多数现有工作仅执行单步预测，但在 CPS 中，必须预测下一个系统状态序列（即曲线预测）。在本文中，我们提出了 DyAt（动态注意力）网络，这是一种新颖的深度学习序列到序列（Seq2Seq）模型，具有用于长期时间序列状态预测的新颖的分层注意力机制。我们在几个 CPS 状态预测和电力负荷预测任务上评估了我们的方法，发现我们提出的 DyAt 模型与其他最先进的预测基线相比，CPS 状态预测任务的性能提高了至少 13.69%，电力负荷预测任务的性能提高了至少 18.83%。我们对 DyAt 模型的几个变体进行了严格的实验，并证明与具有或不具有传统注意力机制的模型相比，DyAt 模型确实在整个长期预测过程中学习到了更好的表示。所有数据和源代码均已在线提供。
Multivariate time series forecasting is an important task in state forecasting for cyber-physical systems (CPS). State forecasting in CPS is imperative for optimal planning of system energy utility and understanding normal operational characteristics of the system thus enabling anomaly detection. Forecasting models can also be used to identify sub-optimal or worn out components and are thereby useful for overall system monitoring. Most existing work only performs single step forecasting but in CPS it is imperative to forecast the next sequence of system states (i.e curve forecasting). In this paper, we propose DyAt (Dynamic Attention) networks, a novel deep learning sequence to sequence (Seq2Seq) model with a novel hierarchical attention mechanism for long-term time series state forecasting. We evaluate our method on several CPS state forecasting and electric load forecasting tasks and find that our proposed DyAt models yield a performance improvement of at least 13.69% for the CPS state forecasting task and a performance improvement of at least 18.83% for the electric load forecasting task over other state-of-the-art forecasting baselines. We perform rigorous experimentation with several variants of the DyAt model and demonstrate that the DyAt models indeed learn better representations over the entire course of the long term forecast as compared to their counterparts with or without traditional attention mechanisms. All data and source code has been made available online.