Document Type : Research Article
Authors
- Mr. Sasikumar Selvam 1
- Dr.C. Kalaivanan 2
- Mr. Rituraj Jain 3
- Er. Murali. S 4
- Dr Thendral Puyalnithi 5
- Dr. Jaishri Gothania 6
1 Assistant Professor, Construction Technology and management, Wachemo University, SNNPR region, Ethiopia.
2 Assistant Professor, Electrical and Electronics Engineering, Sona College of Technology, Salem, Tamilnadu, India.
3 Lecturer, Department of Electrical & Computer Engineering, College of Engineering & Technology, Wollega University, Nekemte, Oromia Regional State, Ethiopia
4 Assistant Professor, Department of Electrical and Electronics Engineering, SRM University Haryana, Delhi-NCR, Sonepat, Haryana, India.
5 Associate Professor, Department of Computer Science and Engineering, Kalasalingam Academy of Research and Education, Krishnankoil, Virudhunagar, Tamil Nadu, India.
6 Assistant Professor, Department of Computer Science & Engineering, School of Engineering & Technology, Lingaya's Vidyapeeth, Nachauli, Faridabad, Haryana, India.
Abstract
Dramatic increase in heating, ventilation, and air conditioning (HVAC) units leads to 40% of total energy consumption in a building. The HVAC system shares largest among other devices the energy consumption and it tends to increase further with steady increasing HVAC systems. Optimal management of HVAC operations is hence required to reduce the consumption of energy among the buildings. Certain advancements are hence required to avoid degradation associated with existing equipment and poor control. Optimal control strategy and fault diagnostics needs to be improved further in order to provide higher efficient thermal comfort. In this paper, we design an Artificial Intelligence (AI) powered system to control the cooling load demand and temperature maintenance with maximum thermal efficiency. AI powered system uses Recurrent Neural Network (RNN) to offer cost-effective estimation with temperature conditions as input to the system. The thermal efficiency on the building is maintained using RNN with high level energy consumption. The experimental results reveal that the AI powered module estimates the cooling capacity of entire building with reduced error, which is lesser than 4.34%.
Keywords
)