Performance Comparison of ARIMA, LSTM and SVM Models for Electric Energy Consumption Analysis
DOI:
https://doi.org/10.57152/predatecs.v1i2.869Keywords:
ARIMA, Electrical Energy, Machine Learning, SVM, LSTM, RMSEAbstract
The changing needs of electrical energy result in the electrical power needed for everyday life being unstable, so planning and predicting how much electrical load is needed so that the electricity generated is always of good quality. So it is necessary to predict the consumption of electrical energy by using forecasting on the machine learning method. Support Vector Machine (SVM), Autoregressive Integrated Motion Average (ARIMA), and Long Short-Term Memory (LSTM) are models that are often used to overcome patterns in predictions. To find out the best models how to predict electricity consumption in the future and how the SVM, LSTM, and ARIMA algorithms perform in predicting electricity consumption. This research will look for the RMSE value and prediction time, then compare it with the best average value. The results of the study show that the ARIMA model is able to predict electricity usage for the next 1 year period, in the evaluation using the RMSE metric, where SVM shows a much lower value than ARIMA and LSTM. In this case, SVM achieved RMSE of 0.020, while ARIMA and LSTM achieved RMSE of 7.659 and 11.4183, respectively. Even though SVM has a lower RMSE, it is still unable to predict electricity usage for the next 1 year with sufficient accuracy.
References
E. Hossain, MR Tur, S. Padmanaban, S. Ay, and I. Khan, “Analysis and Mitigation of Power Quality Issues in Distributed Generation Systems Using Custom Power Devices,” IEEE Access , vol . 6, no. c, pp. 16816–16833, 2018, doi: 10.1109/ACCESS.2018.2814981.
NS Syam et al. , "Model Support Vector Machine for Predictions on the Use of Electrical Energy in Energy Efficient Homes," J. Inform. , vol. 1, no. 2, pp. 56–59, 2022.
S. Rahayu and JJ Purnama, "Classification of Steel Industry Energy Consumption Using Data Mining Techniques," J. Teknoinfo , vol. 16, no. 2, p. 395, 2022, doi: 10.33365/jti.v16i2.1984.
M. Danus, "Application of the Moving Average Method for Forecasting the Electrical Load of a 20 Kv Distribution Network at the Simpang Tiga Satu Feeder at the Keramasan Substation," J. Ampere , vol. 4, no. 1, p. 252, 2019, doi: 10.31851/ampere.v4i1.2877.
A. González-Briones, G. Hernandez, JM Corchado, S. Omatu, and MS Mohamad, “Machine Learning Models for Electricity Consumption Forecasting: A Review,” 2nd Int. Conf. Comput. appl. inf. Secur. ICCAIS 2019 , 2019, doi: 10.1109/CAIS.2019.8769508.
H. Wibowo, Y. Mulyadi, and AG Abdullah, "Forecasting Classified Short Term Electricity Expenses Based on the Autoregressive Integrated Moving Average Method," Electrans , vol. 11, no. 2, pp. 44–50, 2012.
A. Arfan and L. ETP, "Comparison of Long Short-Term Memory Algorithm with SVR on Stock Price Prediction in Indonesia," Petir , vol. 13, no. 1, pp. 33–43, 2020, doi: 10.33322/petir.v13i1.858.
R. Panggabean, Y. Dewi, and L. Widyasari, “A comparison between Super Vector Regression , Random Forest Regressor , LSTM , and GRU in Forecasting Bitcoin Price,” no. November, pp. 17–19, 2022.
AP Point Rahmawati, Landung Sudarmana, "Application of the Arima Box-Jenkins Method for Forecasting Electricity Consumption," Politeknosains , vol. XIX, no. 1, pp. 6–11, 2020.
MI Abas and I. Ibrahim, "Optimization of Support Vector Machine Particle Swarm Optimization for Predicting Electrical Energy Consumption," Jambura J. Informatics , vol. 1, no. 2, pp. 47–56, 2019, doi: 10.37905/jji.v1i2.2646.
I. Amarulloh, "Forecasting short-term electric power on the Smart Grid Photovoltaic ARIMA method with the effect of temperature in hybrid mode," J. Tek. Electro , vol. 10, no. 3, pp. 769–781, 2021.
Y. Chen and K. Wang, “Prediction of satellite time series data based on long short term memory-autoregressive integrated moving average model (LSTM-ARIMA),” 2019 IEEE 4th Int. Conf. Signal Image Process. ICSIP 2019 , pp. 308–312, 2019, doi: 10.1109/SIPROCESS.2019.8868350.
S. Siami-Namini, N. Tavakoli, and AS Namin, “A Comparison of ARIMA and LSTM in Forecasting Time Series,” Proc. - 17th IEEE Int. Conf. Mach. Learn. appl. ICMLA 2018 , pp. 1394–1401, 2019, doi: 10.1109/ICMLA.2018.00227.
ED Spyrou, I. Tsoulos, and C. Stylios, “Applying and Comparing LSTM and ARIMA to Predict CO Levels for a Time-Series Measurements in a Port Area,” Signals , vol . 3, no. 2, pp. 235–248, 2022, doi: 10.3390/signals3020015.
Y. Guo, Y. Feng, F. Qu, L. Zhang, B. Yan, and J. Lv, “Prediction of hepatitis E using machine learning models,” PLoS One , vol. 15, no. September 9, pp. 1–12, 2020, doi: 10.1371/journal.pone.0237750.
A. Hanifa, SA Fauzan, M. Hikal, and MB Ashfiya, "Comparison of LSTM and GRU (RNN) Methods for Classification of Fake News in Indonesian," Din . Engineering , vol. 17, no. 1, pp. 33–40, 2021.
MA Amrustian, W. Widayat, and AM Wirawan, "Evaluation Sentiment Analysis of Teaching Lecturers in Higher Education Using the LSTM Method," J. Media Inform. Budidarma , vol. 6, no. 1, p. 535, 2022, doi: 10.30865/mib.v6i1.3527.
RN Yusra, OS Sitompul, and Sawaluddin, "Combination of K-Nearest Neighbor (KNN) and Relief-F to Improve Accuracy in Data Classification," InfoTekJar J. Nas. inform. and Technol. Jar. , vol. 1, pp. 0–5, 2021.
Q. Gu, Y. Chang, X. Li, Z. Chang, and Z. Feng, “A novel F-SVM based on FOA for improving SVM performance,” Expert Syst. appl. , vol. 165, p. 113713, 2021, doi: 10.1016/j.eswa.2020.113713.
M. Mohammadi et al. , “A comprehensive survey and taxonomy of the SVM-based intrusion detection systems,” J. Netw. Comput. appl. , vol. 178, no. January, p. 102983, 2021, doi: 10.1016/j.jnca.2021.102983.
SS Durbha, RL King, and NH Younan, “Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer,” Remote Sens. environment. , vol. 107, no. 1–2, pp. 348–361, 2007, doi: 10.1016/j.rse.2006.09.031.
