Main Page
Deanship
The Dean
Dean's Word
Curriculum Vitae
Contact the Dean
Vision and Mission
Organizational Structure
Vice- Deanship
Vice- Dean
KAU Graduate Studies
Research Services & Courses
Research Services Unit
Important Research for Society
Deanship's Services
FAQs
Research
Staff Directory
Files
Favorite Websites
Deanship Access Map
Graduate Studies Awards
Deanship's Staff
Staff Directory
Files
Researches
Contact us
عربي
English
About
Admission
Academic
Research and Innovations
University Life
E-Services
Search
Deanship of Graduate Studies
Document Details
Document Type
:
Thesis
Document Title
:
EFFICIENT LOAD FREQUENCY CONTROL OF RENEWABLE INTEGRATED POWER SYSTEM USING ARTIFICIAL INTELLIGENCE TECHNIQUES
التحكم الفعال في تردد الحمل لنظام الطاقة المتكاملة المتجددة باستخدام تقنيات الذكاء الاصطناعي
Subject
:
Faculty of Engineering
Document Language
:
Arabic
Abstract
:
Since the integration of renewable energy sources into conventional power systems is emerging, it is becoming more challenging for modern grids to maintain the power quality and power flow between interconnected areas. A minor unexpected load shift in one of the interconnected areas causes the frequencies of all areas to vary, as well as the tie-line power variation. This study investigates the load frequency control (LFC) of two area systems to control the frequency dynamics and tie-line power of a hybrid system. The main goals of LFC are to maintain the desired frequency and power output in the power system, as well as to limit the variations in tie-line power between interconnected areas. As a result, an LFC scheme primarily entails a suitable control system that is capable of restoring the frequency and tie-line power of each region to appropriate setpoint levels following a sudden load shift. In this thesis, for a more realistic approach, both areas comprise different unequal power systems, and generation rate constraint (GRC) is also considered for hydro and thermal power systems. Initially, a genetic algorithm-based optimization technique is used to tune the proportional integral derivative (PID) controller parameters. Further, fuzzy logic controller and artificial neural network controller are implemented in the proposed model. After that, some recent reinforcement learning techniques are applied to tune the PID controller parameters, and then an improved twin delayed deep deterministic policy gradient (TD3) based scheme is proposed to effectively obtain the PID gain values. The proposed TD3 approach is proven the best technique among the considered techniques. The effectiveness of all these controlling techniques is investigated under continuous variation of renewable energy. The comparison of different evaluations demonstrates the performances of all these controllers for the interconnected hybrid system. Finally, the sensitive analysis of the proposed TD3 scheme is performed to check the robustness of the approach.
Supervisor
:
Prof. Makbul Anwari Muhammad Ramli
Thesis Type
:
Master Thesis
Publishing Year
:
1444 AH
2023 AD
Added Date
:
Tuesday, March 7, 2023
Researchers
Researcher Name (Arabic)
Researcher Name (English)
Researcher Type
Dr Grade
Email
جونيد خالد محمود
Mehmood, Junaid Khalid
Researcher
Master
Files
File Name
Type
Description
49094.pdf
pdf
Back To Researches Page