Short-term power load prediction system based on DTW algorithm

Abstract

The invention discloses a short-term power load prediction system based on a DTW algorithm, which comprises a household electric energy meter and a non-intrusive load detection module which are uniformly installed at a user wire inlet, and is characterized in that the output end of the electric energy meter is connected to the input end of the non-intrusive load detection module; the output end of the non-intrusive load detection module is connected with a household distribution box, and the household distribution box is electrically connected with household appliances. The system has the beneficial effects that the transient waveform and the power change value when the household load is turned on and turned off are taken as characteristic quantities, and the similarity between the test template and the reference template is calculated by using the DTW algorithm, so that various load data of household power consumption can be effectively identified. The power consumption conditions of different types of electric appliances in a period of time can be known, so that a user can more reasonably arrange the use of the electric appliances, manage the load of the electric appliances and formulate an energy-saving plan to save expenditure, thereby reasonably utilizing electricity and saving energy.

Description

technical field [0001] The invention relates to the technical field of power load forecasting, in particular to a short-term power load forecasting system based on a DTW algorithm. Background technique [0002] The development momentum of load monitoring technology is booming, and the identification of power consumption behavior of power customers has become an urgent problem to be solved. Electric load monitoring can be roughly divided into two forms. One is the traditional intrusive load monitoring system (IntrusiveLoad Monitoring Sys-tem, ILM), and the other is the non-intrusive load monitoring system (Non-intrusiveLoad Monitoring system, NILM). The traditional intrusive load monitoring system needs to install modules such as data acquisition and sensors on each electrical equipment, and then transmit the data of each equipment to the data processing center. The hardware installation and maintenance costs are very high, and the installation process requires Entering int...

AI Technical Summary

Problems solved by technology

The traditional intrusive load monitoring system needs to install modules such as data acquisition and sensors on each electrical equipment, and then transmit the data of each equipment to the data processing center. The hardware installation and maintenance costs are very high, and the installation process requires Entering into the load will cause inconvenience to the normal life of the user and even affect the operation of the system

Images