Identifikasi Profil Konsumsi Enegri Listrik untuk Meningkatkan Pendapatan dengan Klustering

Authors

  • Mirza Hamdhani Institut Teknologi Sepuluh Nopember
  • Diana Purwitasari Institut Teknologi Sepuluh Nopember
  • Agus Budi Raharjo Institut Teknologi Sepuluh Nopember

Keywords:

Clustering , Energi Listrik , K-Means , Profil Kelistrikan , Sum Of Square Error

Abstract

Ketersediaan energi listrik pada sistem sulsel lebih dari cukup yakni 602 MW. Sejalan dengan surplusnya energi listrik, kantor pusat memberikan program program peningkataan penjualan kepada unit-unit layanan pelanggan untuk dijalankan. Program tersebut belum memberikan hasil yang baik untuk Key performance indicator penjualan tenaga listrik, karna bahwasannya program tersebut diberikan secara umum untuk seluruh unit layanan pelanggan tanpa memperhatikan kondisi pasar dan karakter pelanggan yang di miliki unit layanan. Profil konsumsi energi listrik sangat penting untuk mendukung pengembangan strategi pemasaran yang dipersonalisasi agar tepat sasaran. Identifikasi profil konsumsi listrik dapat menunjukkan karakteristik pemakaian energi listrik tiap pelanggan. Pada penelitian ini clustering dilakukan permodelan melalui pengolahan data profil konsumsi listrik ditunjukkan dengan variable daya, pemakaian energi, penambahan pelanggan bulanan dari tahun 2019-2021. Selanjutnya dari hasil clustering tersebut menggali informasi karakteristik tiap klusternya untuk dijadikan informasi strategi pemasaran. Diharapkan dari penelitian ini mendapatkan model karakteristik profil konsumsi energi listrik. Hasil dari metode sum of square error mendapatkan k=3 dengan rasio 1,57. Cluster_1 adalah pelanggan dengan kontribusi rupiah penjualan terendah yakni secara komulatif hanya memberikan 18,5%. Cluster_2 berkontribusi sedang secara komulatif pada rupiah pendapatan yakni sebesar 34,86%. Cluster_3 berkontribusi paling tinggi secara komulatif pada rupiah pendapatan yakni sebesar 46,63%. Pada kelompok pelanggan yang berkontribusi terendah perlu dilakukan pemeriksaan persil pelanggan untuk memastikan pemanfaatan energi listrik dan mencurigai adanya pelanggaran penyaluran energi listrik. Pada kelompok pelanggan kontribusi sedang diberikan pendampingan dengan pengenalan alat alat elektronik dengan manfaatnya. Kemudian pada pelanggan kontribusi besar dapat diberikan layanan peendampingan dalam rangka menjaga loyalitas pelanggan, serta memberikan layanan informasi terkait tgihan listrik. Teknik k-means clustering memberikan kemudahan identifikasi karakteristik pelanggan dan visualisasi yang baik untuk perusahaan menganalisa yang kemudian memberikan informasi rekomendasi kebijakan dan strategi peningkatan pendapatan.

References

A. Yusfin, T. Abduh and H. Abubakar, "Pengaruh Bauran Pemasaran Terhadap Peningkatan Penjuallan Tenaga Listrik Pada PT PLN (PERSERO) Unit Pelaksana Pelayanan Pelanggan Pinrang," Indonesian Journal of Business and Management, vol. 3, no. 2460-3767, pp. 115-120, 2021.

Charmicael, Gross, Hanna, Rhodes and Green, "The Demand Response Technology Cluster: Accelerating UK residential consumer engagement with time-of-use tariffs, electric vehicles and smart meters via digital comparison tools," Science Direct-Renewable and Sustainable Energy Reviews, vol. 139, p. 110701, 2021.

S. Ramos, J. Soare, S. S. Cembranel, I. Tavares, Z. Foroozandeh, Z. Vale and R. Fernandes, "Data mining techniques for electricity customer characterization," ScienceDirect-Intelligent Systems, vol. 186, pp. 475-488, 2021.

O. Motlagh, A. Berry and L. O'neil, "Clustering of residential electricity customers using load time series," ScienceDirect- Applied Energy, vol. 237, pp. 11-24, 2019.

A. Rajabi, M. Eskandari, M. Jabbari, L. Li, J. Zhang and P. Siano, "A comparative study of clustering techniques for electrical load pattern segmentation," Science Direct-Renewable and Sustainable Energy Reviews, vol. 120, p. 109628, 2020.

S. Yilmaz, J. Chambers and M. Patel, "Comparison of clustering approaches for domestic electricity load," Science Direct-Energy, vol. 180, pp. 665-677, 2019.

D. Jaiswal, V. Kaushal, P. K. Singh and A. Biswas, "Green market segmentation and consumer profiling: a cluster approach to an emerging consumer market," Eemerald Insight, vol. 28, pp. pp. 792-812, 2021.

J. Alhilman, M. R. M, Wiyono and Marina, "Predicting And Clustering Customer to Improve Customer Loyalty and Company Profit," IEEE, 2014.

E. A. Darko, F. Donkor, S. Adarkwah and E. Kyei, "Management of accounts receivables in utility companies: A focus on Electricity Company of Ghana," International Journal of Academic Research in Business and Social Sciences, pp. 486-518, 2016.

D. Drosos, G. L. Kyriakopoulos, G. Arabatzis and N. Tsotsolas, "Evaluating Customer Satisfaction in Energy Markets Using a Multicriteria Method: The Case of Electricity Market in Greece," MDPI-Sustainability, vol. 12, p. 3862, 2020.

E. Kapassa, M. Touloupou and M. Themistocleous, "Local Electricity and Flexibility Markets: SWOT Analysis and Recommendations," in IEEE-International Conference on Smart and Sustainable Technologies, Bol and Split, Croatia, 2021.

"The effect of digital marketing capabilities on business performance enhancement: Mediating the role of customer relationship management (CRM)," Growing Science-International Journal of Data and Network Science, vol. 6, pp. 295-304, 2022.

A. Roihan, P. A. Sunarya and A. S. Rafika, "Pemanfaatan Machine Learning dalam Berbagai Bidang: Riview Paper," Indonesian Journal on Computer and Information Technology, vol. 5, pp. 75-82, 2020.

R. Afthoni, M. Hamdhani, Ardianto, A. F. K and H. Patria, "Pemanfaatan Algoritma Machine Learning untuk Segmentasi Pelanggan Berbasis Data Konsumsi Listrik di PT PLNXYZ," in Seminar Nasional Teknik dan Manajemen Industri dan Call for Paper(SENTEKMI 2021), Bandung, 2021.

Q. Zhao, H. Li, X. Wang, T. Pu and J. Wang, "Analysis of users’ electricity consumption behavior based on ensemble clustering," KeAi-Global Energy Interconnection, vol. 2, pp. 479-488, 2019.

R. S. Rochman, W. E. Y. Retnani and O. Juwita, "Rancang Bangun Aplikasi Analisis Indeks Kepuasan Pelanggan pada PT. PLN (Persero) Area Jember dengan Menggunakan Pendekatan Metode Servqual dan K-Means Clustering," Sainstek 2020, vol. 3, no. 2339-0069, pp. 96-101, 2020.

L. Czetany, V. Vamos, M. Horvath, Z. Szalay, A. Mota, Z. Deme and T. Csoknyai, "Development of electricity consumption profiles of residential buildings based on smart meter data clustering," Science Direct - Energy & Buildings, vol. 252, p. 111376, 2021.

C. Schoer, F. Kruse and J. M. Gomez, "A Systematic Literatur Review on Applying CRISP-DM Process Model," Science Direct, vol. 181, pp. 526-534, 2021.

S. Ramosa, J. Soaresa, S. Cembranela, F. Inês Tavaresa, Z. Vale and R. Piara, "Data mining techniques for electricity customer characterization," Science Direct, vol. 186, pp. 475-488, 2021.

R. Shanker, R. Singh and M. B., "Segmentation of Tumor and Edema Based on K-mean clustering and hierarchical centroid shape descriptor," IEEE, pp. 1105-1109, 2017.

Y. Asri, D. Kuswardani, E. Yosrita and F. H. Wullur, "Clusterization of customer energy usage to detect power shrinkage in an effort to increase the efficiency of electric energy consumption," Indonesian Journal of Electrical Engineering and Computer, vol. 22, no. 2502-4752, pp. p. 10-17, 2021.

R. Menteri ESDM and PLN, Rencana Usaha Penyediaan Tenaga Listrik (RUPTL) PT PLN (PERSERO) 2021-2030, JAKARTA: ESDM dan PT. PLN (Persero), 2021.

S. Alasadi and W. Bhaya, "Review Of Data Preprocessing Techniques in Data Mining," ACADEMIA, vol. 12, no. 1816-949x, pp. 4102-4107, 2017.

Yasirli, Amanda, Fatmawati, Setiani and Rani, "Analysis Clustering of Electricity Usage Profile Using K-Means Algorithm," IOP Science, vol. 105, 2016.

K. Li, Z. Ma, D. Robinson, W. Lin and Z. Li, "A data-driven strategy to forecast next-day electricity usage and peak electricity demand of a building portfolio using cluster analysis, Cubist regression models and Particle Swarm Optimization," ScienceDirect-Journal of Cleaner Production, vol. 273, pp. 115-123, 2020.

K. Zhou, S. Yang and Z. Shao, "Household monthly electricity consumption pattern mining: A fuzzy clustering-based model and a case study," Science Direct-Journal Of Cleaner Production, vol. 141, no. 2016, pp. 900-908, 2016.

A. R. Arsya and E. Listiani, "Efektifitas Personal selling Pada komunikasi pemasaran keliling Listrik Prabayar (Listrik Pintar) PT. PLN (Persero) Di Wilayah Cijaura Bandung," e-Proceeding Of Management, vol. 2, no. 2355-9357, p. 2176, 2015.

S. Balasubramanian and P. Balachandra, "Characterising electricity demand through load curve clustering: A," Science Direct-Computers and Chemical Engineering, vol. 150, p. 107, 2021.

C. Liu, X. Wang, Y. Huang, Y. Liu, R. Li, Y. Li and J. Liu, "A Moving Shape-based Robust Fuzzy K-modes Clustering Algorithm for Electricity Profiles," ScienceDirect-Electric Power Systems Research, vol. 187, p. 106425, 2020.

Downloads

Published

2022-10-31

How to Cite

Hamdhani, M., Purwitasari, D., & Raharjo, A. B. . (2022). Identifikasi Profil Konsumsi Enegri Listrik untuk Meningkatkan Pendapatan dengan Klustering. Journal of Information System,Graphics, Hospitality and Technology, 4(2), 62–70. Retrieved from https://jurnal.stts.edu/index.php/insight/article/view/232