کنفرانس بین المللی ماشین و محرکه های الکتریکی

صفحه اصلی / The 4th International Conference on Electrical Machines and Drives

A data-driven load shedding method based on generative adversarial networks considering missing data and unlearned fault

نویسندگان :

Nazanin Pourmoradi¹ Sasan Azad² Mohammadtaghi Ameli³

1- دانشگاه شهید بهشتی 2- دانشگاه شهید بهشتی 3- دانشگاه شهید بهشتی

کلمات کلیدی :

Load shedding،generative adversarial،convolutional neural network،Rotor angle stability،missing data،unlearned fault

چکیده :

Event-based load shedding (ELS) is a critical emergency countermeasure against transient rotor angle instability in power systems. ELS based on deep learning has recently achieved promising results. However, in real-world power systems, model input data may be incomplete, and faults may occur that are not in the training database. In this situation, the accuracy of the model decreases. To address these problems, this paper presents a data-driven LS model based on transfer learning. First, the missing data challenge is solved by using a generative adversarial network (GAN), an algorithm for unsupervised deep learning based on two competing neural networks. Then, a convolutional neural network (CNN) model is trained for optimal LS. Finally, when the model encounters unlearned faults in the online application, transfer learning is used to update the model with a small database. The proposed model's test on the IEEE 39 bus system shows its effective performance.

لیست مقالات

لیست مقالات بایگانی شده

Performance Optimization of an Outer Rotor Flux Switching Permanent Magnet Motor Based on Response Surface Methodology

Sadegh Mollaei Saghin - Aghil Ghaheri - Ebrahim Afjei

A Comparision Between PID-PSO and Fuzzy-PID Controllers for Controlling a DC Motor Fed with a Buck-Boost Converter with Continuous Input Current and Semi-Quadric Voltage Gain

Nasim Moradmatak - Seyed Hamid Shahalami

Optimization-Tuned Control of Wireless-Powered BLDC for LVADs under various Medical Conditions

Hawraa Ali - Ali Mahdi - Manal Nawir

Model Predictive Control Based Energy Management of a Grid-Connected Microgrid with Renewable Sources and Electric Vehicles

Milad Maleki - Hamed Gorginpour

3D FE modeling and calculation of electromagnetic torque and eddy current loss in the end region of large synchronous generators

Moein Farhadian - Farshad KIANI - AmirAbbas Vahaj - Hamed Tahanian

An Explainable AI Framework for High-Accuracy Fault Diagnosis and Sound Quality Engineering in Electric Motors

Amirhossein Ghadamossoltani - Mohammadali Sandidzadeh - Mohammad Mosavi Gazafroodi - Farzaad Soleimaani

Design, Modeling, Fabrication, and Analysis of a Double-Input Single-Output Direct DC/AC Converter for Hybrid PV–Battery Systems

Soheil Khosrogorji - Hossein Torkaman - Hao Chen

Halbach-Enhanced Reluctance Magnetic Gear Assisted by Superconductive Flux Channels

Alireza Sohrabzadeh - Aghil Ghaheri

Fault-Tolerant Control of Three-Phase Induction Motor Based on Predictive Feedforward Method

S. Alireza Davari - Mahdi S. Mousavi - Amir Hosein Valiloo - Freddy Flores - Majid Rahmani - Yuzhe Zhang - Zhenbin Zhang - Jose Rodriguez

تعیین تعداد برجستگی بهینه در رتور ریزالور رلوکتانس متغیر لوله‌ای با استفاده از روش مدار معادل مغناطیسی

فاطمه زارع - فرید توتونچیان

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.4