TY - GEN
T1 - An Efficient Load Balancing Using Genetic Algorithm in Cloud Computing
AU - Saputra, Vriza Wahyu
AU - Wibowo, Della
AU - Pratomo, Baskoro Adi
AU - Rishika, Ravi Vendra
AU - Bagaskara, Aditya
AU - Shiddiqi, Ary Mazharuddin
AU - Solekhah, Mirotus
AU - Ayatullah, Ahmad
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Distributing jobs to servers is an essential factor affecting the performance of a cluster server. Load balancing is a method to distribute jobs to a group of computers to optimize resource utilization, throughput, or response time. A large number of requests increase the load on the cloud. The load has to be balanced to distribute the dynamic workload throughout a couple of nodes to make sure that no single resource is both crushed or underutilized. Machine learning is used to automate the decision of the load balancing algorithm, and machine learning is considered to provide advantages in load balancing. Various strategies can be used inside the Genetic Algorithm (GA) approach selection procedure on the problem. Selection techniques used depend on the problem to be solved. This paper proposes GA with Tournament Selection and Roulette Wheel Selection. These two selection techniques have been proposed as load balancing techniques for cloud computing to find global optimal processors for tasks in the cloud. The result of this research is that the GA using Tournament Selection is better than the GA using the Roulette Wheel Selection.
AB - Distributing jobs to servers is an essential factor affecting the performance of a cluster server. Load balancing is a method to distribute jobs to a group of computers to optimize resource utilization, throughput, or response time. A large number of requests increase the load on the cloud. The load has to be balanced to distribute the dynamic workload throughout a couple of nodes to make sure that no single resource is both crushed or underutilized. Machine learning is used to automate the decision of the load balancing algorithm, and machine learning is considered to provide advantages in load balancing. Various strategies can be used inside the Genetic Algorithm (GA) approach selection procedure on the problem. Selection techniques used depend on the problem to be solved. This paper proposes GA with Tournament Selection and Roulette Wheel Selection. These two selection techniques have been proposed as load balancing techniques for cloud computing to find global optimal processors for tasks in the cloud. The result of this research is that the GA using Tournament Selection is better than the GA using the Roulette Wheel Selection.
KW - Genetic algorithm
KW - load balancing
KW - roulette wheel selection
KW - tournament selection
UR - http://www.scopus.com/inward/record.url?scp=85140648854&partnerID=8YFLogxK
U2 - 10.1109/EECCIS54468.2022.9902925
DO - 10.1109/EECCIS54468.2022.9902925
M3 - Conference contribution
AN - SCOPUS:85140648854
T3 - Proceedings - 11th Electrical Power, Electronics, Communications, Control, and Informatics Seminar, EECCIS 2022
SP - 298
EP - 303
BT - Proceedings - 11th Electrical Power, Electronics, Communications, Control, and Informatics Seminar, EECCIS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 11th Electrical Power, Electronics, Communications, Control, and Informatics Seminar, EECCIS 2022
Y2 - 23 August 2022 through 25 August 2022
ER -