A Framework for Prediction Using Rough Set and Real Coded Genetic Algorithm

2017 ◽  
Vol 43 (8) ◽  
pp. 4215-4227 ◽  
Author(s):  
R. Rathi ◽  
D. P. Acharjya
Keyword(s):  
Genetic Algorithm ◽  
Rough Set ◽  
Real Coded Genetic Algorithm

Flexible Genetic Algorithm Based Optimal Power Flow of Power Systems

2018 ◽  
Vol 24 (3) ◽  
pp. 84
Author(s):  
Hassan Abdullah Kubba ◽  
Mounir Thamer Esmieel
Keyword(s):  
Genetic Algorithm ◽  
Objective Function ◽  
Power Flow ◽  
Optimal Power Flow ◽  
Reactive Power ◽  
Test System ◽  
Multi Objective ◽  
Optimal Power ◽  
Blending Method ◽  
Real Coded Genetic Algorithm

Nowadays, the power plant is changing the power industry from a centralized and vertically integrated form into regional, competitive and functionally separate units. This is done with the future aims of increasing efficiency by better management and better employment of existing equipment and lower price of electricity to all types of customers while retaining a reliable system. This research is aimed to solve the optimal power flow (OPF) problem. The OPF is used to minimize the total generations fuel cost function. Optimal power flow may be single objective or multi objective function. In this thesis, an attempt is made to minimize the objective function with keeping the voltages magnitudes of all load buses, real output power of each generator bus and reactive power of each generator bus within their limits. The proposed method in this thesis is the Flexible Continuous Genetic Algorithm or in other words the Flexible Real-Coded Genetic Algorithm (RCGA) using the efficient GA's operators such as Rank Assignment (Weighted) Roulette Wheel Selection, Blending Method Recombination operator and Mutation Operator as well as Multi-Objective Minimization technique (MOM). This method has been tested and checked on the IEEE 30 buses test system and implemented on the 35-bus Super Iraqi National Grid (SING) system (400 KV). The results of OPF problem using IEEE 30 buses typical system has been compared with other researches.     

scholarly journals Multi-dimensional optimization of In0.53Ga0.47As thermophotovoltaic cell using real coded genetic algorithm

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Mansur Mohammed Ali Gamel ◽  
Pin Jern Ker ◽  
Hui Jing Lee ◽  
Wan Emilin Suliza Wan Abdul Rashid ◽  
M. A. Hannan ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Output Power ◽  
Waste Heat ◽  
Antireflection Coating ◽  
Base Layer ◽  
Average Percentage ◽  
Cell Efficiency ◽  
Design Variables ◽  
Real Coded Genetic Algorithm ◽  
Dimensional Optimization

AbstractThe optimization of thermophotovoltaic (TPV) cell efficiency is essential since it leads to a significant increase in the output power. Typically, the optimization of In0.53Ga0.47As TPV cell has been limited to single variable such as the emitter thickness, while the effects of the variation in other design variables are assumed to be negligible. The reported efficiencies of In0.53Ga0.47As TPV cell mostly remain < 15%. Therefore, this work develops a multi-variable or multi-dimensional optimization of In0.53Ga0.47As TPV cell using the real coded genetic algorithm (RCGA) at various radiation temperatures. RCGA was developed using Visual Basic and it was hybridized with Silvaco TCAD for the electrical characteristics simulation. Under radiation temperatures from 800 to 2000 K, the optimized In0.53Ga0.47As TPV cell efficiency increases by an average percentage of 11.86% (from 8.5 to 20.35%) as compared to the non-optimized structure. It was found that the incorporation of a thicker base layer with the back-barrier layers enhances the separation of charge carriers and increases the collection of photo-generated carriers near the band-edge, producing an optimum output power of 0.55 W/cm2 (cell efficiency of 22.06%, without antireflection coating) at 1400 K radiation spectrum. The results of this work demonstrate the great potential to generate electricity sustainably from industrial waste heat and the multi-dimensional optimization methodology can be adopted to optimize semiconductor devices, such as solar cell, TPV cell and photodetectors.

A Performance Study of Real Coded Genetic Algorithm on Gear Design Optimization

2012 ◽  
Vol 622-623 ◽  
pp. 64-68 ◽  
Author(s):  
S. Padmanabhan ◽  
M. Chandrasekaran ◽  
P. Asokan ◽  
V. Srinivasa Raman
Keyword(s):  
Genetic Algorithm ◽  
Power Efficiency ◽  
Mechanical Design ◽  
Design Solution ◽  
Functional Requirements ◽  
Performance Study ◽  
Gear Design ◽  
Adverse Result ◽  
Real Coded Genetic Algorithm ◽  
Comparative Results

he major problem that deals with practical engineers is the mechanical design and creativeness. Mechanical design can be defined as the choice of materials and geometry, which satisfies, specified functional requirements of that design. A good design has to minimize the most significant adverse result and to maximize the most significant desirable result. An evolutionary algorithm offers efficient ways of creating and comparing a new design solution in order to complete an optimal design. In this paper a type of Genetic Algorithm, Real Coded Genetic Algorithm (RCGA) is used to optimize the design of helical gear pair and a combined objective function with maximizes the Power, Efficiency and minimizes the overall Weight, Centre distance. The performance of the proposed algorithms is validated through LINGO Software and the comparative results are analyzed.

Sign in / Sign up

Export Citation Format

Share Document