No abstract

Taking into account energy management and fire safety, electric bicycles are one of the most significant household loads that require real-time sensing for nonintrusive load monitoring. V–I trajectories, power quantities, and harmonic characteristics are the basic selection in feature space for appliance identification. Based on the study of the charging mode of electric bicycles, this study expands the V–I trajectory into V-△I trajectory for gaining the load signature with multi appliances working simultaneously. We perform linear interpolation and pixelation to obtain a bitmap of the V-△I trajectory. Meanwhile, active and harmonic features are encoded and combined to form a hybrid feature bitmap, which is unique to compensate for the high harmonic feature loss caused by the pixelation of the V-△I trajectory. Furthermore, we trained the DeiT model on the self-built dataset and UK-DALE dataset and performed two experiments under single and superposition working conditions for electric bicycles. Our case results indicate that the DeiT model using hybrid feature bitmap offers better overall precision in the prediction of electric bicycles, against other deep convolutional neural networks.