Method and system for identifying transient process of non-intrusive load

Abstract

The invention belongs to the field of load power use monitoring and energy management, and particularly relates to a method and system for identifying transient process of a non-intrusive load. The method comprises the following steps: by virtue of transient power waveform characteristics of multiple types, measuring similarity of a transient power waveform characteristic parameter sample sequence of an unfixed length and a template sequence by using a dynamic time warping algorithm within a time domain, on the basis, establishing a load transient process classification identification scheme based on a nearest neighbor classification strategy, and confirming power use equipment with the load transient process, thereby achieving artificial working state identification on the non-intrusive type power use equipment. The method and the system have the beneficial effects that accuracy and robustness of power load transient process identification can be improved, the cost of a monitoring system can be effectively controlled, and the practicability of the monitoring system can be effectively improved, therefore, practical popularization of an NILM (Non-Intrusive Load monitoring) technique can be greatly improved.

Description

technical field [0001] The invention belongs to the field of electric load monitoring and energy management, and in particular relates to a non-invasive electric load transient process identification method and system. Background technique [0002] The global energy and environmental crisis has triggered an upsurge of innovations in energy-saving and emission-reduction technologies and implementation schemes, and the first step in realizing energy-saving and emission-reduction is to understand the specific details of energy consumption. With the continuous improvement of electrification and digitalization in various fields of society, electric energy will gradually become the most important form of terminal energy in modern society [1] , so knowing the details of electricity consumption is very important to improve energy efficiency and achieve energy saving and emission reduction [2] . Power consumption details refer to the power consumption information such as the workin...

AI Technical Summary

Problems solved by technology

[0011] Although, the existing methods have good classification recognition performance in their respective research scenarios [11,13-21] , however, none of them have studied the randomness of the moment of transient disturbance, load background fluctuation (time-varying nature of the working state of the online running electrical equipment) and the influence of system noise on the power waveform of the transient process; the actual situation is, Under these complex and changeable actual operating conditions, through load event detection, the extracted transient power waveforms of similar electrical equipment load events often have position shifts and / or local scale scaling in time, which will have a negative impact on The identification effect of existing methods has a great impact

In addition, the power output frequency of the order of 100Hz ~ 1000Hz [13,15,18-21] , complex time-frequency analysis techniques [19-21] , as well as the parameterization method and identification technology of transient power waveform characteristics with a large amount of calculation [18] , all require the monitoring system to have high processing performance and make the system cost higher

At the same time, some of these methods also require a lot of parameter learning and training work [15-19,21]

Images