Özet:

Depending on the growth of energy consumption data in energy-consumption centers in different areas such as economy, art, entertainment and industry, the amount of energy to be produced will increase further in the coming years. There was an increase in artificial intelligence-backed housing systems consisting of electronic devices to minimize energy consumption in shelters and houses. Given the increase in environmental factors such as global warming, greenhouse gas emissions, carbon dioxide, chemical solvents, radiation, work towards energy efficiency should be increased. For this purpose, a set of data is used to indicate the hourly data consumption of the Mega Watt of the Asian region, obtained from the website of the U.S. regional communications agency PJM Interconnection LLC (PJM), as Dominion Virginia Power (DOM) data. XGBoost, which is recently popular on this data set, has been compared with LSTM algorithms, classic Linear regression and Ransac algorithms using DOM data set. The differences between the scaled and non-scaled version of the data set used during the comparison were studied between the training and test results.

Anahtar Kelimeler:

Özet:

Depending on the growth of energy consumption data in centers consuming energy in different fields such as economy, art, entertainment and industry, the amount of energy that needs to be produced will increase even more in the coming years. It has been observed that there has been an increase in artificial intelligence supported housing systems consisting of electronic devices in order to minimize energy consumption in shelters and residences. Considering the increase in environmental factors such as global warming, greenhouse gas emissions, carbon dioxide, chemical solvents, and radiation, studies should be increased for the efficient use of energy. For this purpose, the data set showing the hourly data consumption in Mega Watts of the Dominion Virginia Power (DOM) data of the Asian region obtained from the website of the United States regional communication organization PJM Interconnection LLC (PJM) was used. On this dataset, the recently popular XGBoost, LSTM algorithms, classical Linear regression and Ransac algorithms are compared using the DOM dataset. The differences between the training and test results between the scaled and unscaled version of the data set used during the comparison were examined.