Estimating electricity consumption at city-level through advanced machine learning methods
An effective energy management system relies on the accurate prediction of electricity consumption, facilitating energy suppliers to optimise energy distribution, reduce energy waste, and avoid overloading the power system. This paper analyses different methods for the estimation of electricity cons...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/09540091.2024.2313852 |
| _version_ | 1797318040454430720 |
|---|---|
| author | Arpad Gellert Lorena-Maria Olaru Adrian Florea Ileana-Ioana Cofaru Ugo Fiore Francesco Palmieri |
| author_facet | Arpad Gellert Lorena-Maria Olaru Adrian Florea Ileana-Ioana Cofaru Ugo Fiore Francesco Palmieri |
| author_sort | Arpad Gellert |
| collection | DOAJ |
| description | An effective energy management system relies on the accurate prediction of electricity consumption, facilitating energy suppliers to optimise energy distribution, reduce energy waste, and avoid overloading the power system. This paper analyses different methods for the estimation of electricity consumption at the level of an urban area. A statistical model based on Trigonometric seasonality, Box-Cox transformation, Auto-Regressive Moving Average errors, Trend and Seasonal components is first presented. Then a model based on fuzzy logic is also proposed. These methods will be optimised and evaluated on a dataset collected by the electric power supply agency of Sibiu, Romania, with the goal of reducing the forecast error. The models are also compared with a Markov stochastic model and with a Long Short-Term Memory neural model. The experiments have shown that our statistical model using a history length of 200 electricity consumption values and a daily seasonality is the most efficient, with the lowest mean absolute error of 3.6 MWh, thus making it a good candidate for integration into a city-level energy management system. |
| first_indexed | 2024-03-08T03:45:43Z |
| format | Article |
| id | doaj.art-419046ca389d4021b8e093f2e1ebad14 |
| institution | Directory Open Access Journal |
| issn | 0954-0091 1360-0494 |
| language | English |
| last_indexed | 2024-03-08T03:45:43Z |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj.art-419046ca389d4021b8e093f2e1ebad142024-02-09T17:37:21ZengTaylor & Francis GroupConnection Science0954-00911360-04942024-12-0136110.1080/09540091.2024.2313852Estimating electricity consumption at city-level through advanced machine learning methodsArpad Gellert0Lorena-Maria Olaru1Adrian Florea2Ileana-Ioana Cofaru3Ugo Fiore4Francesco Palmieri5Computer Science and Electrical Engineering Department, Lucian Blaga University of Sibiu, Sibiu, RomaniaComputer Science and Electrical Engineering Department, Lucian Blaga University of Sibiu, Sibiu, RomaniaComputer Science and Electrical Engineering Department, Lucian Blaga University of Sibiu, Sibiu, RomaniaComputer Science and Electrical Engineering Department, Lucian Blaga University of Sibiu, Sibiu, RomaniaDepartment of Computer Science, University of Salerno, Fisciano, ItalyDepartment of Computer Science, University of Salerno, Fisciano, ItalyAn effective energy management system relies on the accurate prediction of electricity consumption, facilitating energy suppliers to optimise energy distribution, reduce energy waste, and avoid overloading the power system. This paper analyses different methods for the estimation of electricity consumption at the level of an urban area. A statistical model based on Trigonometric seasonality, Box-Cox transformation, Auto-Regressive Moving Average errors, Trend and Seasonal components is first presented. Then a model based on fuzzy logic is also proposed. These methods will be optimised and evaluated on a dataset collected by the electric power supply agency of Sibiu, Romania, with the goal of reducing the forecast error. The models are also compared with a Markov stochastic model and with a Long Short-Term Memory neural model. The experiments have shown that our statistical model using a history length of 200 electricity consumption values and a daily seasonality is the most efficient, with the lowest mean absolute error of 3.6 MWh, thus making it a good candidate for integration into a city-level energy management system.https://www.tandfonline.com/doi/10.1080/09540091.2024.2313852Electricity consumption estimationenergy management systemforecastingTBATSfuzzy controller |
| spellingShingle | Arpad Gellert Lorena-Maria Olaru Adrian Florea Ileana-Ioana Cofaru Ugo Fiore Francesco Palmieri Estimating electricity consumption at city-level through advanced machine learning methods Connection Science Electricity consumption estimation energy management system forecasting TBATS fuzzy controller |
| title | Estimating electricity consumption at city-level through advanced machine learning methods |
| title_full | Estimating electricity consumption at city-level through advanced machine learning methods |
| title_fullStr | Estimating electricity consumption at city-level through advanced machine learning methods |
| title_full_unstemmed | Estimating electricity consumption at city-level through advanced machine learning methods |
| title_short | Estimating electricity consumption at city-level through advanced machine learning methods |
| title_sort | estimating electricity consumption at city level through advanced machine learning methods |
| topic | Electricity consumption estimation energy management system forecasting TBATS fuzzy controller |
| url | https://www.tandfonline.com/doi/10.1080/09540091.2024.2313852 |
| work_keys_str_mv | AT arpadgellert estimatingelectricityconsumptionatcitylevelthroughadvancedmachinelearningmethods AT lorenamariaolaru estimatingelectricityconsumptionatcitylevelthroughadvancedmachinelearningmethods AT adrianflorea estimatingelectricityconsumptionatcitylevelthroughadvancedmachinelearningmethods AT ileanaioanacofaru estimatingelectricityconsumptionatcitylevelthroughadvancedmachinelearningmethods AT ugofiore estimatingelectricityconsumptionatcitylevelthroughadvancedmachinelearningmethods AT francescopalmieri estimatingelectricityconsumptionatcitylevelthroughadvancedmachinelearningmethods |