Prediksi Konsumsi Energi Pada Bangunan Menggunakan Metode Support Vector Machice Berbasis Algoritma Genetika

Wida Prima Mustika(1*),

(1) Sekolah Tinggi Manajemen Informatika dan Komputer Nusa Mandiri (STMIK Nusa Mandiri)
(*) Corresponding Author

Abstract


Energy consumption is a demand for the amount of energy that must supply the building at any given time. Building energy consumption has continued increased over the last few decades all over the world, and Heating, Ventilating, and Air-Conditioning (HVAC), which has a catalytic role in regulating the temperature in the room, mostly accounted for of building energy use. Models created for in this study support vector machine and support vector machine-based models of genetic algorithm to obtain the value of accuracy or error rate or the smallest error value Root Mean Square Error (RMSE) in predicting energy consumption in buildings is more accurate. After testing the two models of support vector machines and support vector machines based on the genetic algorithm is the testing results obtained by using support vector machines where RMSE value obtained was 2,613. Next was the application of genetic algorithms to the optimization parameters C and γ values obtained RMSE error of 1.825 and a genetic algorithm for feature selection error RMSE values obtained for 1,767 of the 7 predictor variables and the selection attribute or feature resulting in the election of three attributes used. After that is done the optimization parameters and the importance of the value of feature selection mistake or error of the smallest RMSE of 1.537. Thus the support vector machine algorithm based on genetic algorithm can give a solution to the problems in the prediction of energy consumption rated the smallest mistake or error.

Full Text:

PDF

References


Wu, L., Kaiser, G., Solomon, D., Winter, R., Boulanger, A., & Anderson, R. (2011). Improving Efficiency and Reliability of Building Systems Using Machine Learning and Automated Online Evaluation.

Tsanas, A., & Xifara, A. (2012). Accurate quantitative estimation of energy performance of residential buildin using statistical machine learning tools. Energy and Buildings, 560-567.

Xiang, Hai Zhao, frederic M. (2009). Parallel Support Vector Machines Applied to the Prediction of Multiple Buildings Energy Consumption, 4(2), 1–17.

Zhao, H., & Magoulès, F. (2012). A review on the prediction of building energy consumption. Renewable and Sustainable Energy Reviews, 16(6), 3586–3592.

Yu, Z., Haghighat, F., Fung, B. C. M., & Yoshino, H. (2010). A decision tree method for building energy demand modeling. Energy and Buildings, 42(10), 1637–1646.

Ekonomou, L. (2010). Greek long-term energy consumption prediction using artificial neural networks. Energy, 35(2), 512–517. ScienceDirect.

Li, Q., Meng, Q., Cai, J., Yoshino, H., & Mochida, A. (2009). Applying support vector machine to predict hourly cooling load in the building. Applied Energy, 86(10).

Yu, Z., Haghighat, F., Fung, B. C. M., & Yoshino, H. (2010). A decision tree method for building energy demand modeling. Energy and Buildings, 42(10), 1637–1646.

Yuxia, H., & Hongtao, Z. (2012). Chaos Optimization Method of SVM Parameters Selection for Chaotic Time Series Forecasting. Physics Procedia, 25, 588–594.

Wang, S., & Meng, B. (2011). Parameter Selection Algorithm for Support Vector Machine. Procedia Environmental Sciences, 11, 538–544.

Huang, C.-L., & Wang, C.-J. (2006). A GA-based feature selection and parameters optimizationfor support vector machines. Expert Systems with Applications, 31(2).

Lin, S.-W., Chen, S.-C., Wu, W.-J., & Chen, C.-H. (2009). Parameter determination and feature selection for back-propagation network by particle swarm optimization. Knowledge and Information Systems, 21(2), 249–266.

Witten, I. H., Frank, E., & Hall, M. A. (2011). Data Mining Practical

Machine Learning Tools And Techniques. Burlington, Usa: Morgan

Kaufmann Publishers.

Santosa, Budi (2007). Data Mining: Teknik Pemanfaatan Data Untuk Keperluan Bisnis. Yogyakarta: Graha Ilmu

Zhao, H. (2011). New Parallel Support Vector Regression for Predicting Building Energy Consumption. IEEE Symposium Series on Computational Intelligence. Paris : Chatenay Malabry.

Larose, D. T. (2007). Data Mining Methods And Models. New Jersey: A John Wiley & Sons.

Berndtsson, Hansson, Olsson, & Lundell. (2008). Thesis Projects. A Guide For Students In Computer Science and Information Systems. London: Springer.

UCI (2012). Energy Efficiency. November 30. http://archive.ics.uci.edu/ml/machine-learningdatabase/00242/ENB2012_data.xlsx

Vercellis, C. (2009). Business Intelligence Data Mining And Optimization For Decision Making. United Kingdom: A John Wiley And Sons, Ltd.,Publication.




DOI: http://dx.doi.org/10.30645/jurasik.v2i1.14

DOI (PDF): http://dx.doi.org/10.30645/jurasik.v2i1.14.g11

Refbacks

  • There are currently no refbacks.



JURASIK (Jurnal Riset Sistem Informasi dan Teknik Informatika)
Published Papers Indexed/Abstracted By:

Jumlah Kunjungan : View My Stats