عبداله یونسی
دانشگاه محقق اردبیلی - دانشکده فنی و مهندسی - گروه مهندسی برق
[ 1 ] - کنترل‌کننده مقاوم تطبیقی بار فرکانس مبتنی بر یادگیری تقویتی برای یک سیستم قدرت به‌هم‌پیوسته شامل SMES
هدف از این مقاله استفاده از یادگیری تقویتی برای طراحی کنترل‌کننده‌های PID و SMES مقاوم و تطبیقی برای کنترل بار فرکانسی در یک سیستم قدرت دو ناحیه‌ای حرارتی است. ابتدا تنظیم پارامترهای کنترل‌کننده‌های PID و SMES به‌صورت یک مسئله بهینه‌سازی مدل‌شده توسط الگوریتم تدریس - یادگیری اصلاح‌شده حل می‌شود. سپس عملکرد هم‌زمان آن‌ها با استفاده از الگوریتم پیشنهادی مبتنی بر یادگیری تقویتی بهینه می‌گردد. کنتر...
[ 2 ] - A Robust Discrete FuzzyP+FuzzyI+FuzzyD Load Frequency Controller for Multi-Source Power System in Restructuring Environment
In this paper a fuzzy logic (FL) based load frequency controller (LFC) called discrete FuzzyP+FuzzyI+FuzzyD (FP+FI+FD) is proposed to ensure the stability of a multi-source power system in restructured environment. The whale optimization algorithm (WOA) is used for optimum designing the proposed control strategy to reduce fuzzy system effort and achieve the best performance of LFC task. Further...
[ 3 ] - Diagnosis of Different Types of Air-Gap Eccentricity Fault in Switched Reluctance Motors Using Transient Finite Element Method
This paper presents a method for diagnosis of eccentricity fault in a switched-reluctance motor (SRM) during offline and standstill modes. In this method, the fault signature is differential induced voltage (DIV) achieved by injecting diagnostic pulses to the motor windings. It will be demonstrated by means of results that there is a correlation between differential induced voltage and eccentri...
[ 4 ] - طراحی پایدارساز PSS3B بر اساس الگوریتم KH و Q-learning برای میراسازی نوسانات فرکانس پایین سیستم قدرت تک‌ماشینه
The main purpose of this paper is to develop a supplementary signal using reinforcement learning (RL) to improve the performance of power system stabilizer (PSS). RL is one of the most important issues in the field of artificial intelligence and is the popular method for solving Markov decision procedure (MDP). In this paper, a control method is developed based on Q-learning and used to improve...
[ 5 ] - An Online Q-learning Based Multi-Agent LFC for a Multi-Area Multi-Source Power System Including Distributed Energy Resources
This paper presents an online two-stage Q-learning based multi-agent (MA) controller for load frequency control (LFC) in an interconnected multi-area multi-source power system integrated with distributed energy resources (DERs). The proposed control strategy consists of two stages. The first stage is employed a PID controller which its parameters are designed using sine cosine optimization (SCO...
Co-Authors