14. Savetovanje o elektrodistributivnim mrežama Srbije, sa regionalnim učešćem (2024), Broj rada: R-5.01
АУТОР / AUTHOR(S): Darko Šošić, Mileta Žarković, Goran Dobrić
DOI: 10.46793/CIRED24.R-5.01DS
САЖЕТАК / ABSTRACT:
Ovaj rad predstavlja model za prognozu opterećenja izvoda srednjenaponske distributivne mreže. Pomoću ovog modela se vrši prognoza opterećenja izvoda sa 15-to minutnom rezolucijom. Za kreiranje modela korišćena je neuralna mreža koja je obučavana pomoću meteoroloških podataka koji su relevantni za analiziranu lokaciju, i istorijskih podataka o potrošnji električne energije na posmatranom izvodu. Da bi se smanjila greška prognoze određeni su karakteristični dijagrami opterećenja posmatranih izvoda. Prvu grupu sačinjavaju dijagrami opterećenja koji odgovaraju karakterističnom radnom i neradnom danu za svaki pojedinačni mesec. Druga grupa dijagrama koja je korišćena u obuci neuralne mreže je sačinjena za radni i neradni dan u okviru sezone, pri čemu je godina podeljena na tri sezone (zima, prelazni period i leto). Podela podataka na grupe za obuku, validaciju i testiranje je izvršena nakon klasterovanja k-mean metodom, gde je broj klastera odabiran na osnovu visine Dejvis Bouldinovog indeksa. Procena tačnosti prognoze je vršena upotrebom standardnih statističkih mera: MAPE (Mean Absolute Percentage Error), RMSE (Root Mean Square Deviation), CV-RMSE (Coefficient of Variation of RMSE). U ovom radu će biti razmatran jedan srednjenaponski izvod koji napaja potrošače sa centralnim grejanjem.
КЉУЧНЕ РЕЧИ / KEYWORDS:
prognoza opterećenja izvoda, neuralne mreže, srednjenaponska distributivna mreža, klasterovanje
ЛИТЕРАТУРА / REFERENCES:
[1] Pertl M, Heussen K, Gehrke O, Rezkalla M, 2016, “Voltage Estimation in Active Distribution Grids Using Neural Networks”, 2016 IEEE Power and Energy Society General Meeting (PESGM), Boston, USA[2] Weng G, Zhu S, Gong Y, Ma T, Xie F, Fang M, 2017, “Research on Power Quality Prediction for DG Integrated Smart Grid Based on Neural Network”, 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2), Beijing, China
[3] Hong G, Kim Y-S, 2020, “Supervised Learning Approach for State Estimation of Unmeasured Points of Distribution Network”, IEEE Access, Vol. 8, pp. 113918 – 113931
[4] Faiazy M, Ebtehaj M, 2013, “Short Term Load Prediction of a Distribution Network based on an Artificial Intelligent Method”, 22nd International Conference and Exhibition on Electricity Distribution (CIRED 2013), Stockholm
[5] Tziolis G, Spanias C, Theodoride M, Theocharides S, Lopez-Lorente J, Livera A, Makrides G, Georghiou GE, 2023, “Short-term electric net load forecasting for solar-integrated distribution systems based on Bayesian neural networks and statistical post-processing”, Energy, Vol 271, , 127018
[6] Chu Y, Pedro H, Kaur A, Kleissl J, Coimbra C, 2017,”Net load forecasts for solar-integrated operational grid feeders”, Solar Energy, Vol. 158, pp. 236-246
[7] Išlić M, Sučić S, Havelka J, Marušić A, 2020, “0” Sustainable Energy, Grids and Networks, Volume 22, 100331
[8] Liu B, Dong J, Lian J, Kuruganti T, Wang X, Li F, 2023, “Enhanced deep neural networks with transfer learning for distribution LMP considering load and PV uncertainties”, Electrical Power and Energy Systems, Vol. 147, 108780
[9] Berrisch J, Narajewski M, Ziel F, 2023, “High-resolution peak demand estimation using generalized additive models and deep neural networks”, Energy and AI, vol. 13, 100236
[10] Kobylinski P, Wierzbowski M, Piotrowski K, 2020, “High-resolution net load forecasting for microneighbourhoods with high penetration of renewable energy sources”, Electrical Power and Energy Systems, Vol. 117, 105635
[11] Cao Z, Han X, Lyons W, O’Rourke F, 2021, “Energy management optimisation using a combined Long Short-Term Memory recurrent neural network – Particle Swarm Optimisation model”, Journal of Cleaner Production, Vol. 326, 129246
[12] Schlager E, Feichtinger G, Gursch H, 2023, “Development and comparison of local solar split models on the example of Central Europe”, Energy and AI, Vol. 12, 100226
[13] Kakhki IN, Taherian H, Aghaebrahimi MR, 2013, “Short-Term Price Forecasting Under High Penetration of Wind Generation Units in Smart Grid Environment”, 3rd International Conference on Computer and Knowledge Engineering (ICCKE 2013), Ferdowsi University of Mashhad.
[14] Sepasi S, Reihani E, Howlader A, Roose L, Matsuura M, 2017, “Very short term load forecasting of a distribution system with high PV penetration”, Renewable Energy, Vol. 106, pp. 142–148
[15] Chang WY, 2014, “A Literature Review of Wind Forecasting Methods”, Journal of Power and Energy Engineering, pp161 – 168
[16] Asare-Bediako B, Kling WL, Ribeiro PF, 2013, “Day-Ahead Residential Load Forecasting with Artificial Neural Networks using Smart Meter Data”, Power Tech (POWERTECH), Grenoble
[17] Wang J, Li L, Niu D, Tan Z, 2012, “An annual load forecasting model based on support vector regression with differential evolution algorithm”, Journal of Applied Energy, vol. 95, pp 65 – 70
[18] Huyghues-Beaufond N, Tindemans S, Falugi P, Sun M, Strbac G, 2020, “Robust and automatic data cleansing method for short-term load forecasting of distribution feeders”, Applied Energy, Vol. 261, 114405
[19] Aggarwal CC, 2013, “Outlier analysis”, Springer
[20] Hampel FR, 1974, “The influence curve and its role in robust estimation”, Journal of the American Statistical Association, vol 69 (346), pp. 383–93
[21] Hampel FR, 1971, “A general qualitative definition of robustness”. Ann Math Stat, vol 42(6), pp.1887–96
[22] Hoaglin DC, Iglewicz B, Tukey JW, 1986, “Performance of some resistant rules for outlier labeling”, Journal of the American Statistical Association, vol 81(396), pp. 991–9
[23] Ye C, Ding Y, Wang P, et al, 2019, “A data-driven bottom-up approach for spatial and temporal electric load forecasting”, IEEE Trans Power Syst, vol 34(3), pp. 1966–79
[24] Zhou B, Meng Y, Huang W, Wang H, Deng L, Huang S, Wei J, 2021, “Multi-energy net load forecasting for integrated local energy systems with heterogeneous prosumers”, Electrical Power and Energy Systems, Vol. 126, 106542
[25] Karsoliya S, 2112, “Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture”, Int J Eng Trends Technol, vol. 3(6)
[26] Ahmed M, Abdelrazek S, Kamalasadan S, Enslin J, Fenimore T, 2016, “Weather Forecasting Based Intelligent Distribution Feeder Load Prediction”, 2016 IEEE Power and Energy Society General Meeting (PESGM), Boston, USA