Affiliations: [a] Department of Electrical and Electronics Engineering, Maria College of Engineering and Technology, Attoor, Thiruvattar, Tamil Nadu, India
| [b] Department of Electrical and Electronics Engineering, KIT-Kalaignar Karunanidhi Institute of Technology, Coimbatore, Tamil Nadu, India
Correspondence:
[*]
Corresponding author. C. Balasubramanian, Assistant Professor, Department of Electrical and Electronics Engineering, Maria College of Engineering and Technology, Attoor, Thiruvattar, Tamil Nadu, India. E-mail: [email protected].
Abstract: This paper proposes an efficient energy management approach for managing the demand response and energy forecasting in a smart grid using Internet of Things (IoT). The proposed energy management approach is the hybrid technique that is the joint execution of adaptive neuro fuzzy inference system (ANFIS) and balancing composite motion optimization (BCMO), thus it is called ANFIS-BCMO technique. An energy management approach is developed using price-based demand response (DR) program for IoT-enabled residential buildings. Then, we devised a approach depends on ANFIS-BCMO technique to systematically manage the energy use of smart devices in IoT-enabled residential buildings by programming to relieve peak-to-average ratio (PAR), diminish electricity cost, and increase user comfort (UC). This maximizes effective energy utilization, which in turn increases the sustainability of IoT-enabled residential buildings on smart cities. The ANFIS-BCMO technique automatically responds to price-based DR programs to combat the main problem of DR programs that is the limitation of the consumer’s knowledge to respond when receiving DR signals. For consumers, the proposed ANFIS-BCMO based strategy programs appliances to exploit benefit based on reduced electricity bill. By then, the proposed method increases the stability of the electrical system by smoothing the demand curve. At last, the proposed model is executed on MATLAB/Simulink platform and the proposed method is compared with existing systems.
Keywords: Energy management, demand response, energy forecast, smart grid, internet of things
