Electric Load Forecasting Using Artificial Neural Network Method with Limited Data
Abstract
As time changes, electric load demand forecasting is one of the vital things in generation and distribution planning. Various ways can be implemented in forecasting electrical energy demands, one of which is by using the artificial neural network method, which is a method that mimics the ability of the human brain to receive an input and then carry out processing between the neurons within to produce information based on the processes that occur within the neurons. This research uses a neural network method to forecast the electric load in Jayawijaya Regency. This research builds a neural network architecture suitable to the data obtained from National Electricity Company (Perusahaan Listrik Negara, PT PLN Indonesia) UP 3 Wamena to find an architecture model suitable with high accuracy. Due to the limited data owned to forecast electric load, an interpolation method based on the owned original data was carried out to increase the amount of the existing data. In this way, more data can be used as input, allowing the model to forecast load requirements more accurately. These propagated data were used as input data in the artificial neural network model. After conducting iterative testing using a neural network, it is found that the model that fitted the data was feed-forward long short-term memory (LSTM) network, this model can obtain errors in accordance with the standards of a model to perform forecasts of 0.04% with nine epochs.
References
Q. Feng and S. Qian, “Research on Power Load Forecasting Model of Economic Development Zone Based on Neural Network,” Energy Rep., Vol. 7, pp. 1447–1452, Nov. 2021, doi: 10.1016/j.egyr.2021.09.098.
W. Kong et al., “Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network,” IEEE Trans. Smart Grid, Vol. 10, No. 1, pp. 841–851, Jan. 2019, doi: 10.1109/TSG.2017.2753802.
S.N. Fallah, M. Ganjkhani, S. Shamshirband, and K.-W. Chau, “Computational Intelligence on Short-Term Load Forecasting: A Methodological Overview,” Energies, Vol. 12, No. 3, pp. 1–21, Jan. 2019, doi: 10.3390/en12030393.
“Kabupaten Jayawijaya dalam Angka 2017,” Badan Pusat Statistik Kabupaten Jayawijaya, 2017.
Y. Liang, D. Niu, and W.-C. Hong, “Short Term Load Forecasting Based on Feature Extraction and Improved General Regression Neural Network Model,” Energy, Vol. 166, pp. 653–663, Jan. 2019, doi: 10.1016/j.energy.2018.10.119.
J. Kim, J. Moon, E. Hwang, and P. Kang, “Recurrent Inception Convolution Neural Network for Multi Short-Term Load Forecasting,” Energy, Build., Vol. 194, pp. 328–341, Jul. 2019, doi: 10.1016/j.enbuild.2019.04.034.
X. Liu, Z. Zhang, and Z. Song, “A Comparative Study of the Data-Driven Day-Ahead Hourly Provincial Load Forecasting Methods: From Classical Data Mining to Deep Learning,” Renew. Sustain. Energy Rev., Vol. 119, pp. 1–17, Mar. 2020, doi: 10.1016/j.rser.2019.109632.
L. Yin, Z. Sun, F. Gao, and H. Liu, “Deep Forest Regression for Short-Term Load Forecasting of Power Systems,” IEEE Access, Vol. 8, pp. 49090–49099, Mar. 2020, doi: 10.1109/ACCESS.2020.2979686.
P. Singh, P. Dwivedi, and V. Kant, “A Hybrid Method Based on Neural Network and Improved Environmental Adaptation Method Using Controlled Gaussian Mutation with Real Parameter for Short-Term Load Forecasting,” Energy, Vol. 174, pp. 460–477, May. 2019, doi: 10.1016/j.energy.2019.02.141.
L. Wu, C. Kong, X. Hao, and W. Chen, “A Short-Term Load Forecasting Method Based on GRU-CNN Hybrid Neural Network Model,” Math. Probl. Eng., Vol. 2020, pp. 1–10, Mar. 2020, doi: 10.1155/2020/1428104.
C. Tian, J. Ma, C. Zhang, and P. Zhan, “A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network,” Energies, Vol. 11, No. 12, pp. 1–13, Dec. 2018, doi: 10.3390/en11123493.
A. Sherstinsky, “Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network,” Phys. D Nonlinear Phenom., Vol. 404, pp. 1–28, Mar. 2020, doi: 10.1016/j.physd.2019.132306.
M.S. Hossain and H. Mahmood, “Short-Term Load Forecasting Using an LSTM Neural Network,” 2020 IEEE Power Energy Conf. Illinois (PECI), 2020, pp. 1–6, doi: 10.1109/PECI48348.2020.9064654.
L. Sehovac and K. Grolinger, “Deep Learning for Load Forecasting: Sequence to Sequence Recurrent Neural Networks with Attention,” IEEE Access, Vol. 8, pp. 36411–36426, Feb. 2020, doi: 10.1109/ACCESS.2020.2975738.
J. Ma et al., “A Temporal-Spatial Interpolation and Extrapolation Method Based on Geographic Long Short-Term Memory Neural Network for PM2.5,” J. Clean. Prod., Vol. 237, pp. 1–11, Nov. 2019, doi: 10.1016/j.jclepro.2019.117729.
Y. Sun, T. Yang, and Z. Liu, “A Whale Optimization Algorithm Based on Quadratic Interpolation for High-Dimensional Global Optimization Problems,” Appl. Soft Comput., Vol. 85, Dec. 2019, doi: 10.1016/j.asoc.2019.105744.
Z. Deng et al., “Multi-Scale Convolutional Neural Network with Time-Cognition for Multi-Step Short-Term Load Forecasting,” IEEE Access, Vol. 7, pp. 88058–88071, Jul. 2019, doi: 10.1109/ACCESS.2019.2926137.
S. Muzaffar and A. Afshari, “Short-Term Load Forecasts Using LSTM Networks,” Energy Procedia, Vol. 158, pp. 2922–2927, Feb. 2019, doi: 10.1016/j.egypro.2019.01.952.
O.I. Abiodun et al., “State-of-the-Art in Artificial Neural Network Applications: A Survey,” Heliyon, Vol. 4, No. 11, pp. 1–41, Nov. 2018, doi: 10.1016/j.heliyon.2018.e00938.
A. Tealab, “Time Series Forecasting Using Artificial Neural Networks Methodologies: A Systematic Review,” Future Comput., Inform. J., Vol. 3, No. 2, pp. 334–340, Dec. 2018, doi: 10.1016/j.fcij.2018.10.003.
S.M.J. Jalali et al., “A Novel Evolutionary-Based Deep Convolutional Neural Network Model for Intelligent Load Forecasting,” IEEE Trans. Ind. Inform., Vol. 17, No. 12, pp. 8243-8253, Dec. 2021, doi: 10.1109/TII.2021.3065718.
B.-S. Kwon, R.-J. Park, and K.-B. Song, “Short-Term Load Forecasting Based on Deep Neural Networks Using LSTM Layer,” J. Elect. Eng., Technol., Vol. 15, pp. 1501–1509, Jul. 2020, doi: 10.1007/s42835-020-00424-7.
M.A. Al Amin and M.A. Hoque, “Comparison of ARIMA and SVM for Short-Term Load Forecasting,” 2019 9th Annu. Inf. Technol. Electromech. Eng., Microelectron. Conf. (IEMECON), 2019, pp. 205–210, doi: 10.1109/IEMECONX.2019.8877077.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
