PENJADWALAN PEMADAMAN NODE SERVER PADA SERVER CLUSTER BERDASARKAN KLASTERISASI DATA UPTIME
The problem of server clusters is the use of electrical power. The data center, as a place to keep server clusters, in Indonesia consumed 1.5% of the national generating capacity in 2014. This percentage increased in 2017 to 2% of the national generating capacity or equivalent to the consumption of...
Saved in:
Main Author: | |
---|---|
Format: | Academic Paper |
Published: |
2018-08-27.
|
Subjects: | |
Online Access: | http://repository.upi.edu/38226/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 04592 am a22003013u 4500 | ||
---|---|---|---|
001 | repoupi_38226 | ||
042 | |a dc | ||
100 | 1 | 0 | |a Ginanjar Aji Sudarsono, - |e author |
245 | 0 | 0 | |a PENJADWALAN PEMADAMAN NODE SERVER PADA SERVER CLUSTER BERDASARKAN KLASTERISASI DATA UPTIME |
260 | |c 2018-08-27. | ||
500 | |a http://repository.upi.edu/38226/1/S_KOM_1204929_Title.pdf | ||
500 | |a http://repository.upi.edu/38226/2/S_KOM_1204929_Abstract.pdf | ||
500 | |a http://repository.upi.edu/38226/3/S_KOM_1204929_table_of_content.pdf | ||
500 | |a http://repository.upi.edu/38226/4/S_KOM_1204929_Chapter1.pdf | ||
500 | |a http://repository.upi.edu/38226/5/S_KOM_1204929_Chapter2.pdf | ||
500 | |a http://repository.upi.edu/38226/6/S_KOM_1204929_Chapter3.pdf | ||
500 | |a http://repository.upi.edu/38226/7/S_KOM_1204929_Chapter4.pdf | ||
500 | |a http://repository.upi.edu/38226/8/S_KOM_1204929_Chapter5.pdf | ||
500 | |a http://repository.upi.edu/38226/9/S_KOM_1204929_Bibliography.pdf | ||
500 | |a http://repository.upi.edu/38226/10/S_KOM_1204929_Appendix.pdf | ||
520 | |a The problem of server clusters is the use of electrical power. The data center, as a place to keep server clusters, in Indonesia consumed 1.5% of the national generating capacity in 2014. This percentage increased in 2017 to 2% of the national generating capacity or equivalent to the consumption of generating capacity for a combination of Jambi, Riau and West Sumatra.To solve this problem is to turn off the server node on the server cluster. With the turn off server nodes on server clusters scheduling, it is expected to determine the time and duration of turning off server nodes so that they can efficiently use electricity and maintain maximum server quality. In this study server cluster will use the least connection load balancing method. When the server cluster is running, data retrieval takes one, five and 15 minutes average load which is done every minute. Then the collected data is clustered using a combination of average linkage hierarchical clustering and K-Means clustering. The results of this clustering produce three cluster load averages that are "low", "medium" and "high". Load averages that included into the "low" category are sorted by the time of data retrieval to get the time and duration to turn off at each node. The results of the research result in scheduling turning off node one is 14.09 - 14.28, at node two is 14.47 - 06.57 and at node three is 06.57 - 07.18. Turn off server node scheduling is reduces the use of electrical power from 2,528 kWh to 2,519 kWh and does not affect availability, throughput and packet loss as server quality parameters.;---Permasalahan server cluster adalah penggunaan daya listrik. Data center, sebagai tempat menyimpan server cluster, di Indonesia mengkonsumsi 1.5% kapasitas pembangkit nasional pada tahun 2014. Presentase ini meningkat pada tahun 2017 menjadi 2% kapasitas pembangkit nasional atau setara dengan konsumsi kapasitas pembangkit untuk gabungan Jambi, Riau dan Sumatera Barat. Salah satu cara menanggulangi masalah ini adalah memadamkan node server pada server cluster. Dengan diadakannya penjadwalan pemadaman node server pada server cluster diharapkan dapat menentukan waktu dan durasi pemadaman sehingga dapat mengefisiensi penggunaan listrik dan menjaga kualitas server secara maksimal. Pada penelitian ini server cluster akan menggunakan metode load balancing least connection. Saat server cluster berjalan, setiap menit dilakukan pengambilan data load average satu, lima dan 15 menit. Kemudian data yang terkumpul diklasterisasi menggunakan gabungan algoritma average linkage hierarchical clustering dan K-Means. Hasil dari klasterisasi tersebut menghasilkan tiga cluster load average yaitu "rendah", "sedang" dan "tinggi". Load average yang termasuk ke dalam kategori "rendah" diurutkan berdasarkan waktu pengambilan data sehingga mendapatkan waktu dan durasi pemadaman pada setiap node. Hasil penelitian menghasilkan waktu penjadwalan pemadaman pada node satu adalah 14.09 - 14.28, pada node dua adalah 14.47 - 06.57 dan pada node tiga adalah 06.57 - 07.18. Penjadwalan pemadaman mengurangi penggunaan daya listrik sebesar dari 2.528 kWh menjadi 2.519 kWh dan tidak mempengaruhi availability, throughput dan packet loss sebagai parameter kualitas server. | ||
546 | |a en | ||
690 | |a QA75 Electronic computers. Computer science | ||
655 | 7 | |a Thesis |2 local | |
655 | 7 | |a NonPeerReviewed |2 local | |
787 | 0 | |n http://repository.upi.edu/38226/ | |
787 | 0 | |n http://repository.upi.edu | |
856 | 4 | 1 | |u http://repository.upi.edu/38226/ |