Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) Network Models for Forecasting Energy Consumptions
##plugins.themes.bootstrap3.article.sidebar##
PDF
Submitted Apr 18, 2022
Published May 21, 2022
Published May 21, 2022
DOI
Abstract viewed = 100 times
Issue
Section
Articles
##plugins.themes.bootstrap3.article.main##
Unlike other sources of energy, electricity can't be stored. Therefore, an estimation of Energy Consumption (EC) with good accuracy is required to manage demand and supply in the smart grid. Not only good accuracy, but reliability is also on-demand in the prediction model to optimize resource allocation. Therefore, in this study we have implemented and examine two different models: a machine learning model, Autoregressive Integrated Moving Average (ARIMA), and a deep learning-based model Long Short-Term Memory (LSTM). Although ARIMA showed powerful statistical analysis and less robustness, LSTM demonstrated highly accurate results which may stop us to lead false alarming of over-demand and low consumption of energy. In last, we have concluded our result by presenting significant improvement in forecasting energy by LSTM using various evaluation criteria e.g., Mean Square Error (MSE), Root Mean Square Error (RMSE), and other normalized matrices.
Keywords: ARIMA; Demand-Supply; Energy Consumptions; Forecasting; LSTM
References
International Energy Agency. Energy and Air Pollution. World Energy Outlook – Spec. Rep., p. 266, 2016.
Mouli G. R. C., Venugopal P. and Bauer P. Future of electric vehicle charging. 2017 International Symposium on Power Electronics (EE), 2017, pp. 1-7, doi: 10.1109/PEE.2017.8171657.
Saqib M., Hussain M., Alam M. S., Beg M. M. S., and Sawant A. Public Opinion on Viability of xEVs in India. In ISGW 2017: Compendium of Technical Papers, 2018.
Saqib, M., Hussain, M.M., Alam, M.S. et al. Smart electric vehicle charging through cloud monitoring and management. Technol Econ (Smart Grids Sustain Energy, 2017;17(2):218. https://doi.org/10.1007/s40866-017-0035-4.
Kim T. Y. and Cho S. B. Predicting residential energy consumption using CNN-LSTM neural networks. Energy, 2019:182:72–81.
Xu Y., Ahokangas P., and Louis J. Electricity Market Empowered by Artificial Intelligence: A Platform Approach. 2019.
Seyedzadeh, S., Rahimian, F., Glesk, I. et al. Machine learning for estimation of building energy consumption and performance: a review. Vis. in Eng. 2018;6(5). https://doi.org/10.1186/s40327-018-0064-7 Çamurdan Z. and Ganiz M. C. Machine Learning based Electricity Demand Forecasting. UBMK 17 Int. conf. Comput. Sci., 2017.
Strategic I., Conference M., Demirel O. F., and Zaim S. Forecasting Electricity Consumption with Neural Networks and Support Vector Regression. 8th Int. Strateg. Manag. Conf., 2012;58:1576–1585.
Puspita V. and Ermatita. Time Series Forecasting for Electricity Consumption using Kernel Principal Component Analysis ( kPCA ) and Support Vector Machine Time Series Forecasting for Electricity Consumption using Kernel Principal Component Analysis ( kPCA ) and Support Vector Mac. IOP Conf. Ser. J. Phys. Conf. Ser., 2019.
Berriel R. F., Lopes A. T., Rodrigues A., Varejao F. M., and Oliveira-Santos T. Monthly energy consumption forecast: A deep learning approach. Proc. Int. Jt. Conf. Neural Networks, 2017;2017–May:4283–4290.
Muzaffar S., Afshari A., and Muzaffar S. ScienceDirect ScienceDirect ScienceDirect Short-Term Load Forecasts Using LSTM Networks on District and Cooling Short-Term Load Forecasts LSTM feasibility of using the heat demand-outdoor Masdar for. Energy Procedia, 2019;158:2922–2927.
Suganthi L. and Samuel A. A. Energy models for demand forecasting — A review. Renew. Sustain. Energy Rev., 2012;16(2):1223–1240.
Downloads
Download data is not yet available.
##plugins.themes.bootstrap3.article.details##
How to Cite
[1]
Shariff, S.M. 2022. Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) Network Models for Forecasting Energy Consumptions. European Journal of Electrical Engineering and Computer Science. 6, 3 (May 2022), 7–10. DOI:https://doi.org/10.24018/ejece.2022.6.3.435.
This work is licensed under a Creative Commons Attribution 4.0 International License.
