Due to the increasing population, a great increase is observed in the number of different centers such as art, entertainment, and industry. The number of such centers is increasing day by day. These areas are naturally the centers where energy is needed at a high rate. Energy consumption data in the specified areas are increasing day by day. At this point, it has become a difficult problem to meet energy needs in all areas where people live and need energy, in addition to the mentioned centers. To eliminate this difficult problem, it has become a necessity to both meet the energy consumption and ensure the effective use of energy. It is observed that there is an increase in artificial intelligence supported housing systems consisting of electronic devices in order to minimize energy consumption in shelters and residences. Taking into account the increase in environmental factors such as global warming, greenhouse gas emissions, carbon dioxide, chemical solvents, and radiation, studies on the efficient use of energy should be increased. In line with the stated objectives and purposes, the data of the United States regional communications organization PJM Interconnection LLC (PJM) named Dominion Virginia Power (DOM) have been used. This dataset shows the hourly data consumption in Mega Watts of the Asian region. On this dataset, the energy estimation results of the recently popular XGBoost, LSTM algorithms, classical linear regression and RANSAC algorithms were compared.

In this study, an automatic solid fuel control algorithm has been developed that provides maximum heating with minimal solid fuel waste in boiler systems. With the algorithm developed using the Atmega16 microcontroller, motors such as stoker, fan, water pump used in boiler control and features such as boiler temperature, temperature sensor, water pump temperature are controlled. In addition to these features, operations such as fuel loading, waiting, fan speed adjustment can be performed with the help of the menu controlled by interrupt functions. The boiler control algorithm developed for real-time control of the system is programmed with the AVR C language. In the system in which the developed algorithm is used, a user-friendly panel with a 7-segment display has been developed to facilitate the work of the users. With the help of this panel, the user will be able to make all adjustments that affect the operation of the boiler in a very short time. As a result of experimental studies, an increase in the life span of the controlled boiler elements has been determined and an annual fuel saving of approximately 20% has been achieved compared to conventional boiler control systems.