این رویداد خاتمه یافته است و اطلاعات موجود در این سایت صرفا جنبه آرشیو دارد
پنجمين دوره كنفرانس بین‌المللی اينترنت اشيا و كاربردها
The 5th International Conference on Internet of Things and Its Application

:: Filter Based Time-Series Anomaly Detection in AMI using AI Approaches


Filter Based Time-Series Anomaly Detection in AMI using AI Approaches

Sina Ramezani

Department of Computer Engineering

Ferdowsi University of Mashhad

Mashhad, Iran

s.ramezani@mail.um.ac.ir

Afshin Shahrestani

Department of Computer Engineering

Ferdowsi University of Mashhad

Mashhad, Iran

afshin.shahrestani@mail.um.ac.ir

Alireza Rahimi

Department of Computer Engineering

Ferdowsi University of Mashhad

Mashhad, Iran

alireza.rahimi@mail.um.ac.ir

Mohammad Hossein Yaghmaee Moghaddam

Department of Computer Engineering

Ferdowsi University of Mashhad

Mashhad, Iran

yaghmaee@ieee.org

Soroush Omidvar Tehrani

Department of Computer Engineering

Ferdowsi University of Mashhad

Mashhad, Iran

omidvar@mail.um.ac.ir

Pedram Zamani

Department of Computer Engineering

Ferdowsi University of Mashhad

Mashhad, Iran

pedram_zamani@mail.um.ac.ir

Detecting anomalies in advanced metering infrastructure can lead to identifying illegal cryptocurrency mining and electricity theft. Successful usage of statistical approaches incorporation with AI models motivated us to propose a combined model on the subject of power consumption in the smart grid. In this paper, we used upper/lower filters to detect sudden and continuous changes in customers’ power usage. To improve the dynamic nature of the filters and their accuracy, we clustered users based on extracted statistical features, and ran the Genetic Algorithm to find the optimal hyperparameters and tune the filter of each cluster. Finally, we performed our proposed approach on a real dataset of 999 industrial users measured in the last year

 






فایل‌های مورد نیاز

فراخوان ویژه

پوستر همایش

© کلیه حقوق این وب سایت محفوظ می باشد .
طراحی و پیاده سازی شده توسط : همایش نگار ( ویرایش 10.0.4)