An Explore-Exploit Workload-bounded Strategy for Rare Event Detection in Massive Energy Sensor Time Series

IF 7.2 4区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE ACM Transactions on Intelligent Systems and Technology Pub Date : 2024-04-17 DOI:10.1145/3657641
Lo Pang-Yun Ting, Rong Chao, Chai-Shi Chang, Kun-Ta Chuang
{"title":"An Explore-Exploit Workload-bounded Strategy for Rare Event Detection in Massive Energy Sensor Time Series","authors":"Lo Pang-Yun Ting, Rong Chao, Chai-Shi Chang, Kun-Ta Chuang","doi":"10.1145/3657641","DOIUrl":null,"url":null,"abstract":"<p>With the rise of Internet-of-Things devices, the analysis of sensor-generated energy time series data has become increasingly important. This is especially crucial for detecting rare events like unusual electricity usage or water leakages in residential and commercial buildings, which is essential for optimizing energy efficiency and reducing costs. However, existing detection methods on large-scale data may fail to correctly detect rare events when they do not behave significantly differently from standard events or when their attributes are non-stationary. Additionally, the capacity of computational resources to analyze all time series data generated by an increasing number of sensors becomes a challenge. This situation creates an emergent demand for a workload-bounded strategy. To ensure both effectiveness and efficiency in detecting rare events in massive energy time series, we propose a heuristic-based framework called <i>HALE</i>. This framework utilizes an explore-exploit selection process that is specifically designed to recognize potential features of rare events in energy time series. <i>HALE</i> involves constructing an attribute-aware graph to preserve the attribute information of rare events. A heuristic-based random walk is then derived based on partial labels received at each time period to discover the non-stationarity of rare events. Potential rare event data is selected from the attribute-aware graph, and existing detection models are applied for final confirmation. Our study, which was conducted on three actual energy datasets, demonstrates that the <i>HALE</i> framework is both effective and efficient in its detection capabilities. This underscores its practicality in delivering cost-effective energy monitoring services.</p>","PeriodicalId":48967,"journal":{"name":"ACM Transactions on Intelligent Systems and Technology","volume":null,"pages":null},"PeriodicalIF":7.2000,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Intelligent Systems and Technology","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3657641","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

With the rise of Internet-of-Things devices, the analysis of sensor-generated energy time series data has become increasingly important. This is especially crucial for detecting rare events like unusual electricity usage or water leakages in residential and commercial buildings, which is essential for optimizing energy efficiency and reducing costs. However, existing detection methods on large-scale data may fail to correctly detect rare events when they do not behave significantly differently from standard events or when their attributes are non-stationary. Additionally, the capacity of computational resources to analyze all time series data generated by an increasing number of sensors becomes a challenge. This situation creates an emergent demand for a workload-bounded strategy. To ensure both effectiveness and efficiency in detecting rare events in massive energy time series, we propose a heuristic-based framework called HALE. This framework utilizes an explore-exploit selection process that is specifically designed to recognize potential features of rare events in energy time series. HALE involves constructing an attribute-aware graph to preserve the attribute information of rare events. A heuristic-based random walk is then derived based on partial labels received at each time period to discover the non-stationarity of rare events. Potential rare event data is selected from the attribute-aware graph, and existing detection models are applied for final confirmation. Our study, which was conducted on three actual energy datasets, demonstrates that the HALE framework is both effective and efficient in its detection capabilities. This underscores its practicality in delivering cost-effective energy monitoring services.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
在大规模能量传感器时间序列中检测罕见事件的 "探索-利用 "工作量限制策略
随着物联网设备的兴起,对传感器生成的能源时间序列数据进行分析变得越来越重要。这对于检测住宅和商业建筑中的异常用电或漏水等罕见事件尤为重要,而这对于优化能效和降低成本至关重要。然而,当罕见事件的行为与标准事件无明显差异或其属性为非平稳时,现有的大规模数据检测方法可能无法正确检测到罕见事件。此外,要分析越来越多传感器产生的所有时间序列数据,计算资源的容量也成为了一个挑战。在这种情况下,对有工作量限制的策略提出了新的要求。为了确保在海量能源时间序列中检测罕见事件的有效性和效率,我们提出了一种基于启发式的框架,称为 HALE。该框架采用探索-开发选择流程,专门用于识别能源时间序列中罕见事件的潜在特征。HALE 包括构建一个属性感知图,以保留罕见事件的属性信息。然后,根据每个时间段收到的部分标签推导出基于启发式的随机行走,以发现罕见事件的非平稳性。从属性感知图中选择潜在的罕见事件数据,并应用现有的检测模型进行最终确认。我们在三个实际能源数据集上进行的研究表明,HALE 框架的检测能力既有效又高效。这凸显了它在提供具有成本效益的能源监测服务方面的实用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
ACM Transactions on Intelligent Systems and Technology
ACM Transactions on Intelligent Systems and Technology COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-COMPUTER SCIENCE, INFORMATION SYSTEMS
CiteScore
9.30
自引率
2.00%
发文量
131
期刊介绍: ACM Transactions on Intelligent Systems and Technology is a scholarly journal that publishes the highest quality papers on intelligent systems, applicable algorithms and technology with a multi-disciplinary perspective. An intelligent system is one that uses artificial intelligence (AI) techniques to offer important services (e.g., as a component of a larger system) to allow integrated systems to perceive, reason, learn, and act intelligently in the real world. ACM TIST is published quarterly (six issues a year). Each issue has 8-11 regular papers, with around 20 published journal pages or 10,000 words per paper. Additional references, proofs, graphs or detailed experiment results can be submitted as a separate appendix, while excessively lengthy papers will be rejected automatically. Authors can include online-only appendices for additional content of their published papers and are encouraged to share their code and/or data with other readers.
期刊最新文献
A Survey of Trustworthy Federated Learning: Issues, Solutions, and Challenges DeepSneak: User GPS Trajectory Reconstruction from Federated Route Recommendation Models WC-SBERT: Zero-Shot Topic Classification Using SBERT and Light Self-Training on Wikipedia Categories Self-supervised Text Style Transfer using Cycle-Consistent Adversarial Networks Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1