| Title |
Development of Variable Duty Cycle Control Method for Air Conditioner using Artificial Neural Networks |
| Authors |
김형중(Kim, Hyeong-Jung) ; 두석배(Doo, Seog-Bae) ; 신중린(Shin, Joong-Rin) ; 박종배(Park, Jong-Bae) |
| Keywords |
Air-Conditioner ; Direct Load Control ; Variable Duty Cycle ; Artificial Neural Networks |
| Abstract |
This paper presents a novel method for satisfying the thermal comfort of indoor environment and reducing the summer peak demand power by minimizing the power consumption for an Air-conditioner within a space. Korea Electric Power Corporation (KEPCO) use the fixed duty cycle control method regardless of the indoor thermal environment. However, this method has disadvantages that energy saving depends on the set-point value of the Air-Conditioner and direct load control (DLC) has no net effects on Air-conditioners if the appliance has a lower operating cycle than the fixed duty cycle. In this paper, the variable duty cycle control method is proposed in order to compensate the weakness of conventional fixed duty cycle control method and improve the satisfaction of residents and the reduction of peak demand. The proposed method estimates the predict mean vote (PMV) at the next step with predicted temperature and humidity using the back propagation neural network model. It is possible to reduce the energy consumption by maintaining the Air-conditioner's OFF state when the PMV lies in the thermal comfort range. To verify the effectiveness of the proposed variable duty cycle control method, the case study is performed using the historical data on Sep. 7th, 2001 acquired at a classroom in Seoul and the obtained results are compared with the fixed duty cycle control method. |