Muhammad, Sadli and Wahyu, Fuadi and Ermatita, Ermatita and Iwan, Pahendra (2019) Implementation of Clustering K-Means Algorithm classification of the need of Electricity power for each region at PT Lhokseumawe. Mulia International Journal in Science and Technical - MULTICA, 1 (1). pp. 1-8. ISSN 2776-2386
Preview |
Text
Implementation of Clustering K-Means Algorithm classification of the need of El.pdf Download (863kB) | Preview |
Abstract
PLN (State Electricity Company) is in charge of providing stock of needs for the grouping of electrical power and classification for each region in Lhokseumawe City. The area that were grouped based on the amount of power consists of the four subdistricts, namely Banda Sakti, Blang Mangat, Muara Dua and Muara Satu, each of which is sourced from the village. The importance of clusters is to separate each data between data in the villages that will be input into sub-district data. Furthermore, the K-Means Clustering Classification was used in determining the grouping of electrical power needs in each region in the Lhokseumawe City where this system classify the electricity stock needs in each region categorized into a cluster. In this study, Clustering Classification of K-Means variables include job (V1), overall income (V2), house area (V3), number of rooms (V4), number of electronic equipment (V5) and total of power usage (V6). Results of grouping of C1 system = Subsidy R-1/450 VA, C2 = Subsidy R-1/900 VA, C3 = Non Subsidy R-1/900, C4 = Non Subsidy R-1/1300, C5 = Non Subsidy R- 1/2200 VA. The purpose of this study is to be able to predict the classification of each electric power requirement for each region based on the input data per district. This has an impact on the community and PLN's stock of electricity needs in order to remain stable. It is found out from the Clustering K-Means Classification that there is a new cluster for Banda Sakti. The last step in determining Clustering K- Means stopped at the the iteration 3 until the cluster is optimal. The results of this study are in the form of grouping of PLN Customers from each region displayed in the system in the form of classification of electrical power in each subdistrictdistrict. Furthermore, the grouping can be recommended to predict the power needs of each sub�district and belong to the cluster provided by the PLN
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | : Clustering, K-Means, Electricity Needs |
| Subjects: | Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA75.5.A142 Computer science. Information society. Information technology. |
| Divisions: | 09-Faculty of Computer Science > 57201-Information Systems (S1) |
| Depositing User: | Dr Ermatita zuhairi |
| Date Deposited: | 15 Mar 2022 08:02 |
| Last Modified: | 15 Mar 2022 08:02 |
| URI: | http://repository.unsri.ac.id/id/eprint/66187 |
Actions (login required)
 |
View Item |