Statistical estimation method for medium and long term energy consumption in non-invasive electrical load monitoring

Abstract

The invention discloses a statistical estimation method for medium and long-term energy consumption in non-invasive electrical load monitoring. A Gaussian mixture model and a Bayesian classifier are used for equipment identification of non-invasive electrical load monitoring. More accurate energy consumption estimation can be obtained indeed through accumulation of confidence coefficients of a single event for statistics of medium and long-term electricity consumption of electric appliances; therefore, the problems of electric appliance feature overlapping, noise in measurement and electric appliance use and the like are solved, the problems of electric appliance feature random distribution and feature overlapping are solved, more reasonable power distribution can be given under the condition of probability medium and long-term accumulation, and the accuracy of a long-term estimation result in a non-intrusive load monitoring algorithm is remarkably improved. Under the condition of limited types of electric appliances, the accuracy is more than 80%. Edge computing is adopted, so that the cloud data processing burden is reduced. Medium and long-term energy consumption is estimated based on a probability load monitoring result, and optimization of a user-side energy consumption structure is facilitated.

Description

technical field [0001] The invention belongs to the technical field of smart grid and big data analysis, and in particular relates to a method for estimating medium and long-term energy consumption of non-intrusive load monitoring in an actual power consumption environment. Background technique [0002] Non-intrusive load monitoring (NILM) refers to a new detailed monitoring and analysis technology of electric load, that is, without large-scale arrangement of measurement points at the end of electric load, the algorithm can be used Based on the measurement of bus power consumption data, identify the energy consumption of different electrical appliances connected under the bus, so that users can obtain more specific power consumption data, and use this as a basis to achieve user demand side management, energy structure optimization, etc. It is of great significance to save energy and reduce costs. [0003] Compared with the traditional intrusive power load monitoring technol...

AI Technical Summary

Problems solved by technology

Using this scheme, although it is impossible to provide users with accurate identification results of a single power consumption event, in terms of statistics on the medium and long-term power consumption of electrical appliances, more accurate information can be obtained by accumulating the confidence of a single event. Energy consumption estimation, so as to solve the problems of electrical appliance feature overlap, measurement and use noise, etc., thereby significantly improving the accuracy of long-term estimation results in non-intrusive load monitoring algorithms

Images