Implementation of Clustering K-Means Algorithm classification of the need of Electricity power for each region at PT Lhokseumawe

  • Muhammad Sadli Universitas Malikussaleh
  • Wahyu Fuadi Universitas Mulia
  • Fajriana Universitas Malikussaleh
  • Ermatita Universitas Sriwijaya
  • Iwan Pahendra Universitas Sriwijaya
  • Mutammimul Ula Universitas Malikussaleh
  • Richki Hardi Universitas Mulia
Keywords: Clustering, K-Means, Electricity Needs

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.

References

Antonov, B. M., Baranov, N. N. and Kryukov, K. V. (2015) ‘A direct current converter for power supply systems with alternative energy sources’, Russian Electrical Engineering. doi: 10.3103/S1068371215070020.

Hardi, R. (2015) ‘Client Server Based Antivirus Development’, Telematika.

Hendriana, Y. and Hardi, R. (2017) ‘Remote control system as serial communications mobile using a microcontroller’, in 2016 International Conference on Information Technology Systems and Innovation, ICITSI 2016 - Proceedings. doi: 10.1109/ICITSI.2016.7858212.

II, R. X. and D. C. W. (2009) Clustering, Computational Intelligence. doi:10.1002/9780470382776.

Ipmawati, J., Kusrini and Luthfi, E. T. (2017) ‘Komparasi Teknik Klasifikasi Teks Mining Pada Analisis Sentimen’, ijns.org Indonesian Journal on Networking and Security.

Larose, G. L. and D’Auteuil, A. (2006) ‘On the Reynolds number sensitivity of the aerodynamics of bluff bodies with sharp edges’, Journal of Wind Engineering and Industrial Aerodynamics. doi: 10.1016/j.jweia.2006.01.011.

Shang, L. H. (2011) ‘ftsa : An R Package for Analyzing Functional Time Series’, The R Journal Vol.

Sheng, J. et al. (2013) ‘PT-symmetric optical potentials in a coherent atomic medium’, Physical Review A - Atomic, Molecular, and Optical Physics. doi: 10.1103/PhysRevA.88.041803.

Tampubolon, W. and Reinhardt, W. (2014) ‘UAV data processing for large scale topographical mapping’, in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives. doi: 10.5194/isprsarchives-XL-5-565-2014.

Ula, M. et al. (2017) ‘An expert system for early diagnose of vitamins and minerals deficiency on the body’, in 2016 International Conference on Information Technology Systems and Innovation, ICITSI 2016 - Proceedings. doi: 10.1109/ICITSI.2016.7858225.

Vaswani, A. et al. (2013) ‘Decoding with Large-Scale Neural Language Models Improves Translation’, Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP 2013). doi: 10.1.1.637.2567.

Published
2019-10-23
Section
Articles