COMPARISON OF SHORT-TERM FORECASTING METHODS OF ELECTRICITY CONSUMPTION IN MICROGRIDS
Keywords:Microgrid, machine learning, LSTM model, AR model, forecasting, electricity consumption
Context. The current stage of development of the electric power industry is characterized by an intensive process of microgrid development and management. The feasibility of using a microgrid is determined by the fact that it has a number of advantages compared to classical methods of energy generation, transmission, and distribution. It is much easier to ensure the reliability of electricity supply within the microgrid than in large energy systems. Energy consumers in a microgrid can affect the power balancing process by regulating their loads, generating, storing, and releasing electricity. One of the main tasks of the microgrid is to provide consumers with electrical energy in a balance between its generation and consumption. This is achieved thanks to the intelligent management of the microgrid operation, which uses energy consumption forecasting data. This allows to increase the efficiency of energy infrastructure management.
Objective. The purpose of this work is to develop short-term electricity consumption forecasting models for various types of microgrid electricity consumers, which will improve the efficiency of energy infrastructure management and reduce electricity consumption.
Method. The SARIMA autoregressive model and the LSTM machine learning model are used to obtain forecast values of electricity consumption. AIC and BIC information criteria are used to compare autoregressive models. The accuracy of forecasting models is evaluated using MAE, RMSE, MAPE errors.
Results. The experiments that forecast the amount of electricity consumption for the different types of consumers were conducted. Forecasting was carried out for both LSTM and AR models on formed data sets at intervals of 6 hours, 1 day, and 3 days. The forecasting results of the LSTM model met the forecasting requirements, providing better forecasting quality compared to AR models.
Conclusions. The conducted study of electricity consumption forecasting made it possible to find universal forecasting models that meet the requirements of forecasting quality. A comparative analysis of developed time series forecasting models was performed, as a result of which the advantages of ML models over AR models were revealed. The predictive quality of the LSTM model showed the accuracy of the MAPE of forecasting electricity consumption for a private house – 0.1%, a dairy plant – 3.74%, and a gas station – 3.67%. The obtained results will allow to increase the efficiency of microgrid management, the distribution of electricity between electricity consumers to reduce the amount of energy consumption and prevent peak loads on the power grid.
Issa Walid, Al-naemi Faris, Konstantopoulos George Stability analysis and control of a microgrid against circulating power between parallel inverters [Electronic resource], Energy procedia, 2019, Volume 157, pp. 1061– 1070. – Mode of access: https://doi.org/10.1016/j.egypro.2018.11.273. (date of access: 24.11.2022).
Sonam Parashar [et al.] Multiobjective optimal sizing of battery energy storage in grid-connected microgrid [Electronic resource], The journal of engineering, 2019, Vol. 2019, No. 18, pp. 5280–5283. Mode of access: https://doi.org/10.1049/joe.2018.9237 (date of access: 24.11.2022).
Barzegarkhoo Reza, Farhangi Majid, Sze Lee Sing NineLevel Nine-Switch Common-Ground Switched-Capacitor Inverter Suitable for High-Frequency AC-Microgrid Applications [Electronic resource], IEEE transactions on power electronics, 2022, Vol. 37, No. 5, pp. 6132–6143. Mode of Access: https://doi.org/10.1109/TPEL.2021.3131847 (date of access: 24.11.2022).
Shendryk Vira [et al.] Modeling techniques of electricity consumption forecasting [Electronic resource], AIP conference proceedings, 2022, No. 2570, 030004. Mode of access: https://doi.org/10.1063/5.0100123 (date of access: 24.11.2022).
Dhabi Abu Electricity storage valuation framework. [Electronic resource]. IRENA, 2020. Mode of access: https://www.irena.org//media/Files/IRENA/Agency/Publication/2020/Mar/IRENA _storage_valuation_2020.pdf (date of access: 24.11.2022).
Lianyong Qi, Wanchun Dou, Wenping Wang Dynamic mobile crowdsourcing selection for electricity load forecasting [Electronic resource], IEEE access, 2018, pp. 256–263. Mode of access: https://doi.org/10.1109/ACCESS.2018.2866641 (date of access: 24.11.2022).
Stanislaw Czapp, Hanan Tariq, Seweryn Szultka Electrical safety in low-voltage DC microgrids with B-type residual current devices [Electronic resource], Eksploatacja i niezawodnosc – maintenance and reliability, 2022, pp. 346– 358. Mode of access: https://doi.org/10.17531/ein.2022.2.16 (date of access: 24.11.2022).
Potapov Viktor, Khamitov Rustam, Makarov Vladimir Short-Term Forecast of Electricity Load for LLC “Omsk Energy Retail Company” Using Neural Network [Electronic resource], Dynamics of Systems, Mechanisms and Machines, 2018, pp. 1–5. Mode of access: https://doi.org/10.1109/Dynamics.2018.8601430 (date of access: 24.11.2022).
Brancucci Carlo, Martinez-Anido Brancucci, Botor Benjamin, Florita Anthony The value of day-ahead solar power forecasting improvement [Electronic resource] / // Solar Energy, 2016. pp. 192–203. Access mode: https://doi.org/10.1016/j.solener.2016.01.049 (date of access: 24.11.2022).
Mehrnaz Anvari, Elisavet Proedrou, Benjamin Schäfer Datadriven load profiles and the dynamics of residential electricity consumption, Nature Communications, 2022, pp. 1711–1723. Access mode: https://doi.org/10.1038/s41467-022-31942-9 (date of access: 24.11.2022).
Yao Zhenpeng, Lum Yanwei, Johnston Andrew Machine learning for a sustainable energy future [Electronic resource], Nature reviews. Materials, 2022, pp. 1–14. Access mode: https://doi.org/10.1038/s41578-022-00490-5 (date of access: 24.11.2022).
Guillermo Hernández, Juan M. Corchado, Sigeru Omatu Machine Learning Models for Electricity Consumption Forecasting: A Review [Electronic resource], International Conference on Computer Applications & Information Security, 2019, pp. 1–6. Access mode: https://doi.org/10.1109/CAIS.2019.8769508. (date of access: 24.11.2022).
Hyung-Jun Moon, Seok-Jun Bu, Sung-Bae Cho Learning Disentangled Representation of Residential Power Demand Peak via Convolutional-Recurrent Triplet Network [Electronic resource], International Conference on Data Mining Workshops (ICDMW), 2020, pp. 757–761. Access mode: https://doi.org/10.1109/ICDMW51313.2020.00110 (date of access: 24.11.2022).
Ngoc-Tri Ngo, Anh-Duc Pham, Thi Thu Truong Developing a hybrid time-series artificial intelligence model to forecast energy use in buildings [Electronic resource], Scientific Reports, 2022, Vol. 12, No. 1, pp. 2045–2053. Access mode: https://doi.org/10.1038/s41598-022-19935-6 (date of access: 24.11.2022).
Gers Felix, Cummins Fred Understanding LSTM Networks [Electronic resource]. https://colah.github.io/. Mode of access: https://colah.github.io/posts/2015-08-UnderstandingLSTMs/ (date of access: 24.11.2022).
Robert H. Shumway, David S. Stoffer Time series analysis and its applications (springer texts in statistics). [S. l.]. Springer, 2005, 562 p.
John Lu Z. Q. The elements of statistical learning: data mining, inference, and prediction [Electronic resource], Journal of the royal statistical society: series A (statistics in society), 2010, Vol. 173, No. 3, pp. 693–694. Mode of access: https://doi.org/10.1111/j.1467-985x.2010.00646_6.x (date of access: 24.11.2022).
Asterios Papageorgiou [et al.] Climate change impact of integrating a solar microgrid system into the Swedish electricity grid [Electronic resource], Applied energy, 2020. Vol. 268, pp. 164–181. Mode of access: https://doi.org/10.1016/j.apenergy.2020.114981 (date of access: 24.11.2022).
Pramode K. Verma, Mayssaa El Rifai, Kam Wai Clifford Chan Application of the multi-stage protocol in IEEE 802.11i [Electronic resource], Multi-photon quantum secure communication. Singapore, 2018, pp. 143–159. Mode of access: https://doi.org/10.1007/978-981-10-8618-2_9 (date of access: 24.11.2022).
Sherin A. Helal [et al.] Energy management system for smart hybrid AC/DC microgrids in remote communities [Electronic resource], Electric power components and systems, 2019, Vol. 47, No. 11–12, pp. 1012–1024. Mode of access: https://doi.org/10.1080/15325008.2019.1629512 (date of access: 24.11.2022)
Changbin Hu [et al.] Coordinative optimization control of microgrid based on model predictive control [Electronic resource], Research anthology on smart grid and microgrid development, [S. l.], 2022, pp. 233–252. Mode of access: https://doi.org/10.4018/978-1-6684-3666-0.ch012 (date of access: 24.11.2022)
Kosarev V. S. Neural network approach to the electricity market forecasting with different-frequency data among the explanatory variables [Electronic resource], 2022 III international conference on neural networks and neurotechnologies (neuront). Saint Petersburg, Russian Federation, 16 June 2022, [S. l.], 2022. Mode of access: https://doi.org/10.1109/neuront55429.2022.9805538 (date of access: 24.11.2022).
Kinanti Hanugera Gusti, Irhamah Irhamah, Heri Kuswanto Hybrid double seasonal ARIMA and support vector regression in short-term electricity load forecasting [Electronic resource], IPTEK journal of proceedings series, 2021, No. 6, pp. 322–341. Mode of access: https://doi.org/10.12962/j23546026.y2020i6.11117 (date of access: 24.11.2022).
How to Cite
Copyright (c) 2023 Yu. V. Parfenenko, V. V. Shendryk, Ye. P. Kholiavka, P. M. Pavlenko
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.