[论文解读] Filling time-series gaps using image techniques: Multidimensional context autoencoder approach for building energy data imputation

Chun Fu, Matías Quintana+2 more|arXiv (Cornell University)|Jul 12, 2023

Building Energy and Comfort Optimization参考文献 57被引用 5

一句话总结

本研究提出了一种基于图像的深度学习方法——部分卷积（PConv）——的多维上下文自编码器，通过将一维时间序列重塑为二维空间网格，以填补缺失的建筑能效数据。该方法在1,479个全球电表上的表现优于一维卷积神经网络（1D-CNN）和每周持续性基线模型，将均方误差（MSE）降低了20%–30%，显著提升了在不同电表类型和缺失数据模式下的插补准确性和泛化能力。

ABSTRACT

Building energy prediction and management has become increasingly important in recent decades, driven by the growth of Internet of Things (IoT) devices and the availability of more energy data. However, energy data is often collected from multiple sources and can be incomplete or inconsistent, which can hinder accurate predictions and management of energy systems and limit the usefulness of the data for decision-making and research. To address this issue, past studies have focused on imputing missing gaps in energy data, including random and continuous gaps. One of the main challenges in this area is the lack of validation on a benchmark dataset with various building and meter types, making it difficult to accurately evaluate the performance of different imputation methods. Another challenge is the lack of application of state-of-the-art imputation methods for missing gaps in energy data. Contemporary image-inpainting methods, such as Partial Convolution (PConv), have been widely used in the computer vision domain and have demonstrated their effectiveness in dealing with complex missing patterns. To study whether energy data imputation can benefit from the image-based deep learning method, this study compared PConv, Convolutional neural networks (CNNs), and weekly persistence method using one of the biggest publicly available whole building energy datasets, consisting of 1479 power meters worldwide, as the benchmark. The results show that, compared to the CNN with the raw time series (1D-CNN) and the weekly persistence method, neural network models with reshaped energy data with two dimensions reduced the Mean Squared Error (MSE) by 10% to 30%. The advanced deep learning method, Partial convolution (PConv), has further reduced the MSE by 20-30% than 2D-CNN and stands out among all models.

研究动机与目标

• 解决建筑能效数据缺失和不一致这一关键挑战，因为此类问题会削弱能源预测与管理中机器学习模型的性能。
• 评估最先进的图像修复技术（特别是部分卷积，PConv）在时间序列能效数据插补中的适用性。
• 基于来自多个来源和电表类型的1,479个建筑电表的大型多样化数据集，建立用于评估插补方法的基准。
• 在学术与工业应用中，展示重塑为二维的深度学习模型在真实世界能效数据插补中的泛化性与可扩展性。

提出的方法

• 将一维建筑能效时间序列重塑为二维空间网格（例如，按日或周模式），以利用类似于图像数据的空间规律性。
• 应用原本为图像修复开发的部分卷积（PConv）神经网络架构，学习上下文模式并在二维能效网格中重建缺失值。
• 在标准化的1,479个电表基准数据集上，对PConv模型与一维卷积神经网络（1D-CNN）及每周持续性基线模型进行训练与评估。
• 使用均方误差（MSE）和决定系数（R²）作为主要指标，比较在不同缺失数据率和模式（随机缺失与连续缺失）下的插补性能。
• 在多种电表类型（如分支电表、整体建筑电表）和数据源上测试模型的鲁棒性，以评估其泛化能力。
• 将数据重塑与多维上下文自编码器框架相结合，以保留能耗中的时间与周期性模式。

Figure 1 : The one-dimensional time series of energy data can be reshaped into a two-dimensional heatmap image for testing different imputation methods. Comparisons are made between the one- and two-dimensional imputation, including baseline model, 1D- and 2D-CNN, and advanced deep learning techniqu

实验结果

研究问题

• RQ1 将一维建筑能效时间序列重塑为二维空间表示，是否能提升深度学习模型在填补缺失数据方面的性能？
• RQ2 在多种建筑能效数据集中，部分卷积（PConv）模型在MSE和R²方面与1D-CNN及每周持续性基线相比表现如何？
• RQ3 所提出的基于图像的插补方法是否能在真实世界建筑能效数据中，泛化到不同电表类型和数据源？
• RQ4 当连续缺失数据超过10%时，PConv方法在处理长期连续缺失数据方面存在哪些局限性？

主要发现

• 将一维能效时间序列重塑为二维网格显著提升了插补性能，相比1D-CNN和每周持续性基线，MSE降低了10%–30%。
• 部分卷积（PConv）模型表现最佳，相比二维卷积神经网络（2D-CNN）进一步将MSE降低了20%–30%，证明了先进图像驱动深度学习在此任务中的优越性。
• PConv在多种电表类型中均保持了稳定的高精度，证实了该方法在不同建筑能效数据源和配置下的泛化能力。
• 当缺失数据以连续块形式超过10%时，PConv的平均R²降至0.7以下，表明其在长期连续缺失数据插补中性能有所下降。
• 本研究首次基于全球1,479个电表建立了大规模基准，为真实世界条件下插补方法的严格评估提供了支持。
• 所提出的方法具备可扩展性，可应用于建筑环境中其他时间序列数据，如暖通空调（HVAC）、照明和电器能耗。

Figure 2 : Overview of the proposed framework and different phases in the working pipeline.