A nonintrusive load identification method for residential applications based on quadratic programming

• A novel nonintrusive load identification method is proposed in this paper.
• The proposed method is modeled with quadratic binary programming.
• Test results show that the recognition is highly accurate (>90%).
• Test results also show that it is highly resilient to interferences.

The decomposition of household power consumption is highly desired for scheduling household appliances and reducing home energy consumption. This paper presents a novel nonintrusive load identification method based on quadratic programming. Extensive simulation and laboratory tests have demonstrated that the proposed technique can provide adequate load identification accuracy for residential energy monitoring such that it is suitable for nonintrusive load monitoring (NILM) systems in residential and commercial buildings.