14. Savetovanje o elektrodistributivnim mrežama Srbije, sa regionalnim učešćem (2024), Broj rada: I-5.03
АУТОР / AUTHOR(S): Sofija Krstev, Dragoljub Krneta
DOI: 10.46793/CIRED24.I-5.03SK
САЖЕТАК / ABSTRACT:
Povećana složenost modernih energetskih sistema zahteva napredne metode za efikasnu kontrolu i menadžment distribucije. Ovaj rad istražuje definisanje ključnih indikatora performansi (KPI-ova) koristeći modele mašinskog učenja za predikciju potrošnje energije, s ciljem poboljšanja kontrole distribucije i ukupne performanse sistema za održivi energetski menadžment.
КЉУЧНЕ РЕЧИ / KEYWORDS:
predviđanje, KPI, mašinsko učenje, energija, distribucija
ЛИТЕРАТУРА / REFERENCES:
[1] Ghaffarian Hoseini A, et al, 2017, “IoT-based smart energy grid with renewable energy sources (RES).”“Energy Procedia”, “143”, 277-282
[2] Ahmad T, and Jamshed I C, 2013, “A study on energy consumption prediction using machine learning techniques.”, “Journal of Renewable and Sustainable Energy”, “5.2”, 023119
[3] Amasyali K, and El-Gohary N M, 2018 “A review of data-driven building energy consumption prediction studies.”, “Renewable and Sustainable Energy Reviews”, “81”, 1194-1205
[4] Oldewurtel F, et al., 2012. “Data-driven predictive control for building energy management.”, “Proceedings of the IEEE”, “100.1”, 240-253.
[5] Kong W, et al., 2018, “Short-term residential load forecasting based on LSTM recurrent neural network.”, “IEEE Transactions on Smart Grid”, “10.4”, 841-850.
[6] Al-Ati J A, Iqbal M A, Benkrid K, 2021, “Forecasting Energy Consumption using Hybrid Machine Learning Techniques”, “IEEE Access”, “9”, 10606-10620
[7] Bucciarelli M, Bellini A, Ciampi A, and Pezzotta G, 2020, “Smart Predictive Management of Distributed Renewable Energy Sources with Machine Learning”, “Energy reports”, “6”, 441-456
[8] Sayed-Mouchaweh M, Lughofer E and Schirru M, 2020, “Evaluation of Machine Learning Algorithms for Energy Heuristic Performance Prediction”, “Applied Energy”, “260”
[9] Wang J, Li K, Tan J and Jian X, 2020, “Machine Learning-Based Predictive Modeling and Intelligent Energy Management of Renewable Energy Systems”, “IEEE Transactions on Sustainable Energy”, “11.3”, 1630-1638
[10] Krstev S, Forcan J and Krneta D, 2023, “An Overview of Forecasting Methods for Monthly Electricity Consumption”, “Technical Gazette”, “30.3”, 993-1001
[11] Wang B, Wang H, Xiao Y, Peng Y and Zhu Z, 2015, “Electric load forecasting using an improved PSObased LSSVM model”, “Energy”, “90.2”, 1599-1607
[12] Amini M H, Haghbin S and Kargarian A, 2021, “Techniques for evaluating electric power grid data and reducing energy losses through machine learning”, “IEEE Transactions on Smart Grid”, “12.3”, 2345-2356
[13] Khatib T, Mohamed A and Mustafa M W, 2018, “Enhancing the Efficiency of Electric Power Distribution using Machine Learning Models”, “Applied Energy”, “230”, 1595-1603
[14] Zhang Y, Hodge B M and Lu S, 2020, “Improving Power System Reliability with Predictive Maintenance Using Machine Learning”, “Renewable and Sustainable Energy Reviews”, “127”, 109398
[15] Praktiknjo A and Erdmann G, 2016, “Renewable electricity and backup capacities: An (un) resolvable problem?”, “Journal of Energy”, “114”, 1106-1117
[16] Chicco G and Mancarella P, 2009, “Assessment of the greenhouse gas emissions from cogeneration and trigeneration systems. Part II: Analysis techniques and application cases”, “Energy”, “34.3”, 359-367