Optimasi Support Vector Machine Particle Swarm Optimization Untuk Prediksi Konsumsi Energi Listrik

Mohamad Ilyas Abas, Irawan Ibrahim

Abstract


Penelitian ini bertujuan untuk menganalisis konsumsi energi listrik di Gorontalo dan melakukan prediksi terhadap penggunaan energi listrik. Konsumsi dan beban listrik di Gorontalo menjadi pokok bahasan dalam penelitian ini. Metode yang digunakan dalam melakukan prediksi yakni SVM dan Optimasi PSO. Algoritma ini dipilih karena memiliki nilai akurasi yang tinggi dengan tingkat error yang rendah. Hasil dari penelitian ini menunjukkan bahwa SVM-PSO mampu melakukan prediksi dengan data time-series dengan error yang kecil. Selain itu, hasil dari penelitian ini dapat digunakan untuk mempersiapkan pasokan listrik jangka panjang serta dapat mensosialisasikan penggunaan listrik yang baik kepada masyarakat. Energi alternatif juga dapat menjadi solusi bagi pemerintah guna menambah pasokan energi listrik sehingga kebutuhan masyarakat akan listrik dapat terpenuhi.


This study aims to analyze the consumption of electrical energy in
Gorontalo and make predictions on the use of electrical energy. Electricity consumption and load in Gorontalo is the subject of this research. The method used in making predictions is SVM and PSO Optimization. This algorithm was chosen because it has a high accuracy value with a low error rate. The results of this study indicate that SVM-PSO is able to make predictions with timeseries data with small errors. In addition, the results of this study can be used to prepare long-term electricity supply and can socialize good use of electricity to the public. Alternative energy can also be a solution for the government to increase the supply of electrical energy so that people's needs for electricity can be met.

Keywords


konsumsi energi listrik; SVM-PSO; prediksi time-series

References


Abas, M. I., & Lasarudin, A. (2019). Prediction of arrival domestic and foreign tourists based on regions using neural network algorithm based on genetic algorithm Prediction of arrival domestic and foreign tourists based on regions using neural network algorithm based on genetic algorithm. IOP Conf. Series: Journal of Physics: Conf. Series (2019) https://doi.org/10.1088/1742-6596/1175/1/012045

Gorontalo, D. E. P. (2018). Wilayah Provinsi Gorontalo. Artikel, (2016).

Juaidi, A., Montoya, F. G., Ibrik, I. H., & Manzano-agugliaro, F. (2016). An overview of renewable energy potential in Palestine. Renewable and Sustainable Energy Reviews, 65, 943–960. https://doi.org/10.1016/j.rser.2016.07.052

Karazmodeh, M., Nasiri, S., & Hashemi, S. M. (2013). Stock Price Forecasting using Support Vector Machines and Improved Particle Swarm Optimization. Journal of Automation and Control Engineering, 1(2), 173–176. https://doi.org/10.12720/joace.1.2.173-176

Purwanto., Eswaran, C., & Logeswaran, R. (2011). Improved Adaptive Neuro-Fuzzy Inference System for HIV/AIDS Time Series Prediction. Informatics Engineering and Information Science, Pt Iii, 253, 1–13. https://doi.org/10.1007/978-3-642-25462-8_1.

Zhang, L., Ge, R., & Chai, J. (2019). Prediction of China’s energy consumption based on robust principal component analysis and PSO- LSSVM optimized by the Tabu Search Algorithm, 1–21. https://doi.org/10.3390/en12010196




DOI: https://doi.org/10.37905/jji.v1i2.2646

Refbacks

  • There are currently no refbacks.



JJIhas been indexed by:
Sinta Crossref Scholar Garuda
Base Dimension ROAD SIS
ASCI







Editorial Office

Department of Informatics Engineering, Universitas Negeri Gorontalo
Engineering Faculty Building, 1st Floor
Jl. Prof. Dr. Ing. B. J. Habibie, Bone Bolango, Gorontalo, 96119, Indonesia. Whatsapp: +6281314270499Email: jji.ft@ung.ac.id


Creative Commons Licence
Jambura Journal of Informatics (JJi), is licensed under a Lisensi Creative Commons Atribusi 4.0 Internasional.