Dormitory Non-intrusive Load Identification Algorithm Based on Penalty Function

Non-intrusive load identification technology can provide household electricity data for power companies without installing indoor measuring equipment, and its modification design is more acceptable to users. A non-intrusive load identification algorithm which is specifically designed for dormitory electrical equipment has not yet been proposed. An identification algorithm based on penalty function is proposed in this paper. First, the working characteristic indicators of electrical equipment is selected. Next, whether the current signal is in a steady state is judged. If it is, a matrix equation for multiple power equipment which is working in the system at the same time is established. Then the least norm generalized squares solution is used to judge the working condition of the electrical equipment in the dormitory. Finally, a large number is introduced into the penalty function to improve the accuracy of identification. The experimental results show that the method proposed in this paper has good recognition accuracy and stability, and can be applied in the dormitory electricity environment.