A load event detection method, system and storage medium
An event detection and load technology, applied in electrical components, data processing applications, instruments, etc., can solve the problem of low detection accuracy, and achieve the effect of delaying the decline of statistical function values and improving detection accuracy.
Active Publication Date: 2021-09-21
STATE GRID JIANGSU ELECTRIC POWER CO ELECTRIC POWER RES INST +2
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Aiming at the deficiencies of the prior art, the object of the present invention is to provide a load event detection method, system and storage medium to solve the problem of low detection accuracy existing in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0058] In order to deepen the knowledge and understanding of the present invention, the solution will be further introduced below in conjunction with the accompanying drawings and specific embodiments.
[0059] Such as Figure 7 As shown, a load event detection method,
[0060] Obtain frequency reduction data of load events;
[0061] calculating an adaptive shrinkage coefficient of the down-frequency data;
[0062] calculating the statistical function value of the down-frequency data according to the self-adaptive contraction coefficient;
[0063] The nature of the load event is judged according to the statistical function value.
[0064] Such as figure 1 As shown, the present invention uses a set of active power data with a duration of 15 minutes and a sampling rate of 1600HZ, including wall-mounted fixed-frequency air conditioners, wall-mounted frequency conversion air conditioners, microwave ovens, and electric kettles, as calculation example data to illustrate and explai...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a load event detection method, system and storage medium. Kalman filtering of sliding window is performed on high-frequency sampling data of residents' access buses, and an improved two-way CUSUM detection algorithm is used to detect the changing point time of residents' load operation, thereby Determine whether a load event occurs. The entire data window is divided into multiple filtering windows, and Kalman filtering is performed sequentially by sliding. An adaptive shrinkage parameter is introduced into the bidirectional CUSUM algorithm, so that the statistical function is linked with the load event, and the positive and negative cumulative statistical function value of each data point is calculated. The load events are marked by comparing the positive and negative statistical values with the threshold value, and the load events are automatically classified into and out. The invention has the advantages of filtering and denoising while retaining the characteristics of load mutation, and has strong anti-interference ability; it has the ability to detect load events adaptive to different power levels and switching characteristics, and has high detection accuracy.
Description
technical field [0001] The invention relates to a load event detection method, system and storage medium, and belongs to the technical field of non-intervention load identification. Background technique [0002] With the improvement of the living standards of urban residents in my country, the electricity load of residential users is growing rapidly, and at the same time, residents' demand for precise and lean energy use services is increasing day by day. Non-intrusive load identification technology is a brand-new intelligent perception technology of electricity consumption information on the residential user side. It only uses high-frequency voltage and current sampling data on the household side to identify residential electricity loads locally in real time and intelligently sense various residential loads. The start-stop time, power consumption and other multi-dimensional power consumption information of the system can be analyzed in detail to analyze the energy consumpti...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/06G06Q50/06H02J3/00
CPCG06Q10/0639G06Q50/06H02J3/00
Inventor 黄奇峰杨世海方凯杰纪峰黄艺璇程含渺赵双双夏国芳曹晓冬李波段梅梅
Owner STATE GRID JIANGSU ELECTRIC POWER CO ELECTRIC POWER RES INST