专栏名称: AEii国际应用能源
发布应用能源领域资讯,介绍国际应用能源创新研究院工作,推广应用能源优秀项目,增进应用能源领域合作
目录
相关文章推荐
EETOP  ·  深空芯片的4种未来 ·  12 小时前  
ZOL中关村在线  ·  iPhone ... ·  2 天前  
EETOP  ·  FPGA 线上技术交流 ·  3 天前  
EETOP  ·  ISSCC2025|IEDM|JSSC|Ho ... ·  3 天前  
51好读  ›  专栏  ›  AEii国际应用能源

【Applied Energy最新原创论文】使用序列条件变分自编码器感知光伏系统中的异常

AEii国际应用能源  · 公众号  ·  · 2023-11-15 18:30

正文

原文信息

Sensing anomaly of photovoltaic systems with sequential conditional variational autoencoder

原文链接:

https://www.sciencedirect.com/science/article/pii/S0306261923014885

Highlights

(1) 提出了一个适用于多样化环境条件下分布式光伏系统的异常检测方法。

(2) 提出了一个具有创新性的时间序列无监督异常检测模型。

(3) 提出了一套真实光伏场景下的数据处理流程,并且开源了一个有标注的合成数据集。

摘要

城市分布式光伏系统(DPV)市场预计将在未来十年蓬勃发展。然而,这些系统往往受制于复杂的城市环境和欠优的发电条件,需要可扩展的综合解决方案来检测其是否发生性能不佳的情况。近年来,在异常检测领域,深度生成模型(DGMs)在处理常见的高维时间序列数据方面表现出色。然而,现有的应用在光伏领域的深度生成模型仍没有考虑环境信息,从而限制了其在复杂多样的环境条件下的性能。本研究提出了序列条件变分自编码器(SCVAE),它可以考虑环境对光伏发电的时序性影响。利用从中国的 30 个屋顶光伏发电站收集到的实际数据,本文提出了一套数据处理流程来构建训练数据集,使得训练集中大部分是正常样本,用于SCVAE 模型的无监督训练。这项工作还参照了分布式光伏系统领域的专业见解和工程实践,构建了一个包含各种异常的人工合成数据集。经过专家的检查和筛选,该合成数据集最终可用于验证异常检测模型的效果。结果表明,SCVAE模型优于现有的最先进的无监督异常检测模型,并能有效地推广到未见过的光伏站点。此外,SCVAE的隐变量可用于识别分布式光伏系统的故障类型,从而对异常的发生进行更有针对性的诊断。

Abstr act

The market for urban distributed photovoltaics (DPV) is expected to take off in the next decade. However, these systems are often subject to complex urban contexts and sub-optimal conditions, requiring scalable and comprehensive solutions to detect their underperformances. In recent years, deep generative models (DGMs) have exhibited outstanding performance in the anomaly detection domain, dealing with generic high-dimensional time series data. Nevertheless, the existing applications of DGMs in the photovoltaic (PV) sector are still unable to account for environmental information, limiting their performance under various environmental conditions. This study proposes the Sequential Conditional Variational Autoencoder (SCVAE), which can cope with the sequential impacts of the environment on PV power generation. Using real-world data collected from 30 rooftop PV sites located across China, a data processing pipeline is developed to construct the training datasets which contain mostly normal samples for unsupervised SCVAE model training. This work also constructs a synthetic dataset with a wide variety of artificial anomalies in reference to the domain insights and engineering practice of DPV systems. After checking and refining by experts, the synthetic dataset can finally be used to validate the anomaly detection models. The results demonstrate that the SCVAE model outperforms existing state-of-the-art unsupervised anomaly detection models and can be effectively generalized to unseen PV sites. Moreover, the latent variables of SCVAE could be used to identify the type of DPV failure, thereby enabling more targeted diagnostics of anomaly mechanisms.

Keywords

Anomaly detection

Anomaly diagnosis

Photovoltaic (PV) system

Time series

Deep generative model

Conditional variational auto-encoder

Graphics

Fig. 6. Proposed PV anomaly detection framework.

Fig. 8. Training procedure combining with the model design of SCVAE.

Fig. 14. Clustering result using TSNE.







请到「今天看啥」查看全文