PREDVIĐANjE POTROŠNjE ELEKTRIČNE ENERGIJE KORIŠĆENjEM LGBM ALGORITMA U ML.NET-U I PYTHON-U
Ključne reči:
LGBM, ML.NET, Python, Mašinsko učenje, Algoritam
Apstrakt
Predviđanjem potrošnje električne energije, elektrodistribucije mogu efikasnije da planiraju režim upotrebe generatorskih postrojenja, redovna održavanja elemenata mreže kao i potencijalnu trgovinu na marketu električne energije. Algoritmi mašinskog učenja mogu poslužiti kao alat za precizno predviđanje potrošnje u elektroenergetskim sistemima. Kroz ovaj rad implementirana su dva softverska rešenja za prognozu potrošnje električne energije na osnovu podataka vremenskih prilika koristeći LGBM algoritam u ML.NET-u i Pythonu-u, dok su rezultati predikcija su opisani i analizirani.
Reference
Zhao, Hai-xiang & Magoulès, Frédéric, „A review on the prediction of building energy consumption“, Renewable and Sustainable Energy Reviews. 16. 3586-3592. 10.1016/j.rser.2012.02.049.
[2] J. Kolter,J. Ferreira, „A Large-Scale Study on Predicting and Contextualizing Building Energy Usage“, AAAI, vol. 25, no. 1, pp. 1349-1356, Aug. 2011.
[3] Slobodan Ilić, „Kratkoročno predviđanje potrošnje električne energije u velikim elektroenergetskim sistemima“, Fakultet tehničkih nauka, Univerzitet u Novom Sadu.
[4] Sebastijan Stoja, „Arhitektura softverskog sistema za elektroenergetske proračune zasnovana na mikroservisima“, Fakultet tehničkih nauka, Univerzitet u Novom Sadu.
[5] Gama João, Rodrigues Pedro, „Stream-Based Electricity Load Forecast“, 446-453. 10.1007/978-3-540-74976-9_45, 2007.
[6] Khuntia, Swasti R. & Rueda, José & Meijden, Mart, „Forecasting the Load of Electrical Power Systems in Mid- and Long-term Horizons - A Review“, IET Generation Transmission & Distribution. 10, 2016. 10.1049/iet-gtd.2016.0340.
[7] J. W. Taylor, „An evaluation of methods for very short-term load forecasting using minute-by-minute British data“, International Journal of Forecasting, vol. 24, no. 4, pp. 645-658, 2008.
[8] G. Gross, F.D. Galiana, „Short-term load forecasting“, Proceedings of the IEEE, vol. 75, no.12, pp. 1558-1572, 1987.
[9] N. Amjady, F. Keynia, „Mid-term load forecasting of power systems by a new prediction method“, Energy Conversion and Management, vol. 49, no. 10, pp. 2678-2687, 2008.
[10] H. Daneshi, M. Shahidehpour, A. L. Choobbar, „Long-term load forecasting in electricity market“, IEEE International Conference on Electro/Information Technology, USA, 2008.
[11] Harsh H. Patel, Purvi Prajapati, „Study and Analysis of Decision Tree Base Classification Algorithms“, Dept. Of Information Technology, CSPIT, Charotar University of Science and Technology, Changa, Gujarat, India.
[12] Lior Rokach, Oded Maimon, „The Data Mining and Knowledhe Discovery Handbook Chapter:Decision Trees“, DOI:10.1007/-387-25465-X_9.
[13] https://lightgbm.readthedocs.io/en/v3.3.2/ (pristupljeno u martu 2023.)
[14] https://data.cityofnewyork.us/Housing-Development/Electric-Consumption-And-Cost-2010-April-2020-/jr24-e7cr (pristupljeno u martu 2023.)
[15] https://www.ncdc.noaa.gov/cdo-web/datasets/GSOM/locations/CITY:US360019/detail (pristupljeno u martu 2023.)
[16] https://dotnet.microsoft.com/en-us/apps/machinelearning-ai/ml-dotnet/model-builder (pristupljeno u martu 2023.)
[17] https://lightgbm.readthedocs.io/en/latest/index.html (pristupljeno u martu 2023.)
[2] J. Kolter,J. Ferreira, „A Large-Scale Study on Predicting and Contextualizing Building Energy Usage“, AAAI, vol. 25, no. 1, pp. 1349-1356, Aug. 2011.
[3] Slobodan Ilić, „Kratkoročno predviđanje potrošnje električne energije u velikim elektroenergetskim sistemima“, Fakultet tehničkih nauka, Univerzitet u Novom Sadu.
[4] Sebastijan Stoja, „Arhitektura softverskog sistema za elektroenergetske proračune zasnovana na mikroservisima“, Fakultet tehničkih nauka, Univerzitet u Novom Sadu.
[5] Gama João, Rodrigues Pedro, „Stream-Based Electricity Load Forecast“, 446-453. 10.1007/978-3-540-74976-9_45, 2007.
[6] Khuntia, Swasti R. & Rueda, José & Meijden, Mart, „Forecasting the Load of Electrical Power Systems in Mid- and Long-term Horizons - A Review“, IET Generation Transmission & Distribution. 10, 2016. 10.1049/iet-gtd.2016.0340.
[7] J. W. Taylor, „An evaluation of methods for very short-term load forecasting using minute-by-minute British data“, International Journal of Forecasting, vol. 24, no. 4, pp. 645-658, 2008.
[8] G. Gross, F.D. Galiana, „Short-term load forecasting“, Proceedings of the IEEE, vol. 75, no.12, pp. 1558-1572, 1987.
[9] N. Amjady, F. Keynia, „Mid-term load forecasting of power systems by a new prediction method“, Energy Conversion and Management, vol. 49, no. 10, pp. 2678-2687, 2008.
[10] H. Daneshi, M. Shahidehpour, A. L. Choobbar, „Long-term load forecasting in electricity market“, IEEE International Conference on Electro/Information Technology, USA, 2008.
[11] Harsh H. Patel, Purvi Prajapati, „Study and Analysis of Decision Tree Base Classification Algorithms“, Dept. Of Information Technology, CSPIT, Charotar University of Science and Technology, Changa, Gujarat, India.
[12] Lior Rokach, Oded Maimon, „The Data Mining and Knowledhe Discovery Handbook Chapter:Decision Trees“, DOI:10.1007/-387-25465-X_9.
[13] https://lightgbm.readthedocs.io/en/v3.3.2/ (pristupljeno u martu 2023.)
[14] https://data.cityofnewyork.us/Housing-Development/Electric-Consumption-And-Cost-2010-April-2020-/jr24-e7cr (pristupljeno u martu 2023.)
[15] https://www.ncdc.noaa.gov/cdo-web/datasets/GSOM/locations/CITY:US360019/detail (pristupljeno u martu 2023.)
[16] https://dotnet.microsoft.com/en-us/apps/machinelearning-ai/ml-dotnet/model-builder (pristupljeno u martu 2023.)
[17] https://lightgbm.readthedocs.io/en/latest/index.html (pristupljeno u martu 2023.)
Objavljeno
2023-07-08
Sekcija
Elektrotehničko i računarsko inženjerstvo
