Distribution transformer heavy overload prediction method and system based on Prophet-LSTM combinatorial algorithm

A technology of distribution transformers and combined algorithms, applied in forecasting, information technology support systems, instruments, etc., can solve the problems of not taking into account and low forecasting accuracy.

Pending Publication Date: 2021-05-11
STATE GRID SHANDONG ELECTRIC POWER +1
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current public distribution transformer heavy overload prediction methods do not take into account the influence of the above factors on the prediction results, resulting in low prediction accuracy

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Distribution transformer heavy overload prediction method and system based on Prophet-LSTM combinatorial algorithm
  • Distribution transformer heavy overload prediction method and system based on Prophet-LSTM combinatorial algorithm
  • Distribution transformer heavy overload prediction method and system based on Prophet-LSTM combinatorial algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029]In one or more embodiments, a multi-LSTM combination algorithm is disclosed, with referencefigure 1, Including the following steps:

[0030](1) Get the historical load data of the power distribution transformer and pretreatment;

[0031]Specifically, a method of performing data pretreatment includes:

[0032]1) Repair of missing load data

[0033]If the data in a certain day has a lot of missing or bad data, it is considered that the data of this day is invalid data, and it is necessary to supplement by normal data in neighborhood. The supplement formula is as follows:

[0034]

[0035]Where x (d, t) is the load value of the power distribution transformer, X (d, X (D)i, t) is the load value of several date T times with the same date and the day similar to the day D, ΩiIn order to weigh the average weight.

[0036]2) Vertical processing of data

[0037]The transformer load has a certain periodic period, although the load is different at different times, but the load at the same time of the adjacent da...

Embodiment 2

[0105]In one or more embodiments, a multi-PROPHET-LSTM combination algorithm is disclosed, including:

[0106]Data acquisition module: Used to obtain historical load data for distribution transformers and pretreatment;

[0107]Feature Factor Screening Module: It is used to determine the influencing factors that have correlation with the power-on transformer weight value, as a feature factor predicted by the distribution transformer;

[0108]Data Decomposition Module: Decompose the power distribution transformer load data into trend components, periodical components, and data mutation components;

[0109]Load prediction module: Establish a corresponding predictive model for each component to predict, and integrate the predicted value of each component to obtain a predicted value of the power distribution transformer load data.

[0110]It will be described herein that the specific implementation of the above modules is implemented in the method disclosed in the first embodiment, but is not limited t...

Embodiment 3

[0114]This embodiment also provides a terminal device including: one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected to a memory, the above one or more computer programs are Stored in the memory, when the electronic device is run, the processor performs one or more computer programs stored in the memory to enable the electronic device to perform the method described above.

[0115]It should be understood that in the present embodiment, the processor may be a central processing unit CPU, and the processor can also be other general purpose processors, digital signal processor DSP, dedicated integrated circuit ASIC, ready-made programmable gate array FPGA or other programmable logic devices. , Discrete door or transistor logic devices, discrete hardware components, and the like. The general purpose processor can be a microprocessor or the processor can also be any conventional processor or the like.

[0116]The memory can includ...

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

No PUM Login to view more

Abstract

The invention discloses a distribution transformer heavy overload prediction method and system based on a Prophet-LSTM combinatorial algorithm. The method comprises the steps of obtaining and preprocessing historical load data of a distribution transformer; determining influence factors having correlation with the heavy and overload load values of the distribution transformer as characteristic factors for prediction of the distribution transformer; decomposing the load data of the distribution transformer into a trend component, a periodic component and a data mutation item component; and respectively establishing a corresponding prediction model for each component for prediction, and integrating predicted values of each component to obtain a predicted value of the load data of the distribution transformer. The invention provides a new algorithm of the distribution transformer load data cleaning and processing method, the periodicity, the missing property and the continuity of the data are considered, the data can be restored to the maximum extent, and the preprocessing precision of the data is improved.

Description

Technical field[0001]The present invention relates to the field of weight overload prediction techniques of distribution transformers, and more particularly to a high-end overload prediction method and system of distribution transformers based on Prophet-LSTM combined algorithm.Background technique[0002]The statement of this section is merely the background technology information associated with the present invention, which is not necessarily constituted in prior art.[0003]Power quality and power supply are important factors in measuring the level of distribution network. At present, the matching area is used as the last level of power supply unit facing low-voltage users, and the operating state of the field power supply equipment directly affects the supply quality in the area. The heavy overload operation of the device is one of the main reasons for fault power failure, and heavy overload is usually accompanied by other problems such as three-phase imbalance, voltage offset, and ...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06G06N3/04G06F17/18
CPCG06Q10/04G06Q50/06G06N3/049G06F17/18G06N3/044Y04S10/50
Inventor 霍凌宇王兴照张建文邓影王健张岩刘函铭刘超王耀黄亚磊李小萱徐珂田晓彤林朋辉代桃桃
Owner STATE GRID SHANDONG ELECTRIC POWER
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap