Online household load power utilization combination identification and power consumption prediction method

Abstract

The invention discloses an online household load power utilization combination identification and power consumption prediction method. The method comprises the following steps: converting a time domain signal of load feature data into a frequency spectrum image through employing a time-frequency conversion technology, and achieving the online precise identification of a household load power utilization combination through combining with the technologies of deep learning, reinforcement learning, structure traction and algorithm optimization; and for the prediction of the power consumption of the household power consumption load, monitoring the power consumption of the power consumption load in real time according to the periodicity and time sequence characteristics of the user power consumption monitoring data, and predicating the power consumption condition and power consumption behavior trend of users in the future. Online accurate identification of household load power utilization combination is realized, the power consumption of the power utilization load is monitored in real time, and the power consumption condition and the power utilization behavior trend of future users are predicted; and the method can be widely applied to accurate combination prediction of household electrical load combination online scenes.

Description

technical field [0001] The invention belongs to the technical field of household electricity consumption, and in particular relates to an online household load electricity combination identification and electricity consumption prediction method. Background technique [0002] The main technical problems of the existing methods for household load combination identification and power consumption prediction are: the actual household loads are various, the working status is complex and diverse, the existing load collection technology has large errors in online data collection, and the data is in the In the process of dimensionality reduction, it is easy to cause the loss of original signal features; using mathematical optimization methods, the number of clusters needs to be determined in advance, which is highly dependent on prior verification knowledge and requires a large amount of calculation; the traditional artificial neural network algorithm has a high recognition accuracy ...

AI Technical Summary

Problems solved by technology

[0002] The main technical problems of the existing methods for household load combination identification and power consumption prediction are: the actual household loads are various, the working status is complex and diverse, the existing load collection technology has large errors in online data collection, and the data is in the In the process of dimensionality reduction, it is easy to cause the loss of original signal features; using mathematical optimization methods, the number of clusters needs to be determined in advance, which is highly dependent on prior verification knowledge and requires a large amount of calculation; the traditional artificial neural network algorithm has a high recognition accuracy , but its scalability is weak, its convergence is poor, and it is easy to fall into local optimum; in the process of load feature extraction, only a single feature information is collected, and it is impossible to capture the changes in the instantaneous process of household load combination opening and closing in real time; Most of the power forecasting methods are analyzed on a single time scale. This method is only suitable for simulating short-term dependence, and there is no corresponding solution for long-term trend and periodicity.

Images