Unlock instant, AI-driven research and patent intelligence for your innovation.

Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis

A fault tree analysis, data center technology, applied in digital transmission systems, transmission systems, data processing applications, etc., can solve the problems of performance dependence, control data center damage, etc., to achieve simple use, eliminate negative effects, and high prediction accuracy. Effect

Pending Publication Date: 2020-09-01
ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The performance of the system depends on the availability of the machines, and if failures are not handled properly, the entire regulated data center can be easily compromised

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
  • Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis
  • Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis
  • Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] figure 1 It is a schematic flow diagram of the method for locating faults in service characteristics of power grid control data centers based on time series and fault tree analysis provided by Embodiment 1 of the present invention, as shown in figure 1 As shown, the time series and fault tree analysis-based fault location method for business characteristics of power grid regulation data centers provided in this embodiment may include:

[0045] Establish a fault tree model; obtain a set of variable data corresponding to each device in the power control data center, and normalize the variable data with maximum and minimum values; use the MARA adaptive prediction model to predict the future state of the obtained variable data, And store the predicted data in the database; compare the predicted data with the threshold value, and output the predicted data after binary conversion when the predicted data meets the threshold value; receive the binary predicted data, and conduct...

Embodiment 2

[0050] On the basis of Embodiment 1, this Embodiment 2 provides a method for quickly locating faults of power grid regulation data center business characteristics based on time series and fault tree analysis, and the future state prediction of the acquired variable data is performed through the MARA adaptive prediction model. , and store the predicted data in the database, which may specifically include:

[0051] Create a MARA model; create a multi-step MARA model and train it in an adaptive manner to obtain a MARA adaptive prediction model based on variable data; predict the future state of the acquired variable data, when the MARA adaptive prediction model obtains the future moment The predicted data value of , and store the predicted data value in the database.

[0052] image 3 It is a schematic diagram of the circuit structure of the grid control data center business characteristic fault location system based on time series and fault tree analysis provided by Embodiment ...

Embodiment 3

[0062] On the basis of Embodiment 1, this Embodiment 3 provides a method for quickly locating faults in power grid control data center business characteristics based on time series and fault tree analysis. The establishment of a fault tree model may specifically include:

[0063] Create the top business to represent the system state, and split the top business to obtain the lower terminal business, and split the lower terminal business step by step, and end the split when reaching the maximum value of the explainable resolution;

[0064] Use the Boolean logic gate index to connect the lower terminal business with the top business, establish a Boolean expression corresponding to each sub-business, and a Boolean expression corresponding to the top business;

[0065] The receiving binary prediction data and performing availability analysis through the fault tree model may specifically include:

[0066] The fault tree model decomposes the binary forecast data and simplifies it int...

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 provides a power grid regulation and control data center service characteristic fault positioning method and system based on a time sequence and fault tree analysis. The method comprises: establishing a fault tree model; obtaining a group of variable data corresponding to each device in the power regulation and control data center, and performing maximum and minimum normalization processing on the variable data; performing future state prediction on the acquired variable data through an MARA adaptive prediction model, and storing prediction data into a database; performing threshold comparison on the prediction data, and when the prediction data meets a threshold, performing binary conversion on the prediction data and outputting the prediction data; receiving binary prediction data, and performing availability analysis through the fault tree model; receiving a fault signal sent by a fault node possibly existing in the future, marking, organizing and executing a migrationoperation. The method has the beneficial effect of rapid and accurate positioning, and is suitable for the field of data center fault positioning.

Description

technical field [0001] The invention relates to the technical field of fault location, in particular to a fault location method and system for business characteristics of a power grid control data center based on time series and fault tree analysis. Background technique [0002] In the power system, accurate fault location of equipment in the power control data center computer room can help operation and maintenance personnel and managers improve work efficiency and control capabilities, and ultimately provide support for actual operation and maintenance operations and management. [0003] Grid-regulated data centers have a large number of servers and components interconnected in a complex fabric, often with high failure rates, and long-running applications and heavy workloads are common in these facilities. The performance of the system depends on the availability of the machines, and if failures are not properly handled, the entire regulated data center can be easily compr...

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
IPC IPC(8): H04L12/24G06F16/21G06Q50/06
CPCG06Q50/06G06F16/214H04L41/0663H04L41/0677H04L41/145H04L41/147
Inventor 张秀丽王其兵何志方闫磊赵文娜李远姚非石新聪王婷汪文全赵金郝伟吴攀李晋泉强彦贾培伟吕金顺
Owner ELECTRIC POWER RES INST STATE GRID SHANXI ELECTRIC POWER