Genetic algorithm based hydrothermal generation scheduling

Anuradha, .; Sinha, Samarth

doi:10.1109/rdcape.2015.7281419

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have been conducted to solve short-term scheduling problems using genetic algorithms as observed in the application of ant colony optimization [13] and one other example that is more relevant is Economic Generation in Diesel Power Units where the use of the genetic algorithm method in this study is based on the presence of several weaknesses when using conventional methods. If viewed from the objectives to be achieved, the previous research mentioned above with this research has the same goal, namely to minimize the total cost of generation.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Thermal Power Plant Operations Using Genetic Algorithms

Sapto Nisworo,

Hasibuan,

Syafii

2023

JNTE

View full text Add to dashboard Cite

Accurate scheduling of capacity and operating time for electricity generation is intended to be able to determine the start and end periods of electricity generation operations and produce power output that can meet load requirements. In this research, the goal to be achieved is to know the existence of power plants when to start operating and when to stop operations and to minimize operational costs by dividing the value of the power that will be generated at each power plant. Genetic algorithms are applied to thermal power plant data patterns to design a scheduling plan. The process involves combining the six power generating units to be tested into three different samples. It was found that the total power load and total cost for Sample 1 was 78,109 MW and IDR 200,285, 66.26, Sample 2 was 74,497 MW and IDR 149,774,156.41, and Sample 3 was 78,681 MW and IDR 156,297,893, respectively. 08. This shows that the cost of sample 1 compared to sample 2 decreased by 25.22%, then in sample 2 when compared to sample 3 it increased by 4.17%. The data also shows that a higher number of generations results in lower costs. Therefore, genetic algorithms produce better solutions from one generation to the next.

show abstract

Section: Introductionmentioning

confidence: 99%