CN-121814548-B - Low-voltage distribution network fault diagnosis method based on trusted access of optical storage equipment

CN121814548BCN 121814548 BCN121814548 BCN 121814548BCN-121814548-B

Abstract

The invention discloses a low-voltage distribution network fault diagnosis method based on trusted access of optical storage equipment, which belongs to the technical field of power grid fault diagnosis and comprises the steps of carrying out protocol deep analysis on data packets of the optical storage equipment in a trusted computing environment constructed by a security chip to obtain reliable standardized data, dynamically selecting a minimum feature subset required by fault diagnosis based on a maximum correlation minimum redundancy algorithm, acquiring encryption transmission to obtain high-efficiency perception data, fusing the high-efficiency perception data with historical fault cases to construct an edge fault diagnosis knowledge unit, and executing fast fault type recognition and power supply restoration potential pre-assessment based on the edge fault diagnosis knowledge unit in parallel when faults occur. The invention adopts a protocol deep analysis and trusted computing environment, can ensure the integrity and the safety of nonstandard access data, dynamically optimizes the dimension of measured data through a maximum correlation minimum redundancy algorithm, and improves the real-time performance and the efficiency of rapid fault type identification and power supply recovery potential pre-evaluation.

Inventors

Yang Xizai
ZHAN XINRUI
CHEN XINGYUAN
LEI WEI
CUI BING
MA QINQIN
GUO YIMING
WANG LINNAN
LI YIFAN
Pang Bingyao
HUO YONGBO
YANG LE
ZHU YU

Assignees

国网陕西省电力有限公司信息通信公司

Dates

Publication Date: 20260508
Application Date: 20260312

Claims (8)

1. The low-voltage distribution network fault diagnosis method based on the trusted access of the optical storage equipment is characterized by comprising the following steps: S1, in a trusted computing environment constructed by a security chip, carrying out application layer protocol deep analysis on a data packet acquired from optical storage equipment to obtain analyzed data; S2, carrying out standardized conversion on the analyzed data, and adding data branding containing a time stamp and an integrity check code to the analyzed data by utilizing a trusted computing environment to obtain trusted standardized data; S3, acquiring target variables for distinguishing different distribution network fault types, and dynamically selecting features from the bearable standardized data by using a maximum correlation minimum redundancy algorithm based on the target variables to obtain a minimum feature subset; S4, collecting and encrypting transmission is carried out on the measurement data corresponding to the minimum feature subset, and high-efficiency perception data are obtained; S5, acquiring historical fault case data, fusing the historical fault case data with high-efficiency perception data, and constructing to obtain an edge fault diagnosis knowledge unit, wherein the method comprises the following steps: taking a real-time characteristic value in the high-efficiency perception data as a query index; performing pattern matching and association analysis in the historical fault case data, and screening out a historical fault case similar to the current power grid state; Integrating the screened historical fault cases and the high-efficiency perception data into a composite data structure to generate an edge fault diagnosis knowledge unit; and S6, when the fault occurs, the fault type is rapidly identified and the power restoration potential is pre-estimated in parallel based on the edge fault diagnosis knowledge unit, so that diagnosis and estimation results are obtained, and the diagnosis and estimation results are reported to the upper-layer master station.
2. The method for diagnosing a low-voltage distribution network fault based on trusted access of optical storage equipment according to claim 1, wherein in S1, obtaining the parsed data includes: The method comprises the steps of obtaining data packets of the optical storage equipment in parallel through a power line communication channel and a wireless communication channel; acquiring a protocol feature library for identifying a communication mechanism and a data format of an application layer protocol; In a trusted computing environment, parsed data is generated by prefix and suffix matching of application layer content of a data packet with a protocol feature library.
3. The method for diagnosing a low-voltage distribution network fault based on trusted access of optical storage equipment according to claim 1, wherein in S2, obtaining the trusted standardized data includes: Obtaining a mapping rule base for unifying data fields, and performing format unification processing on the parsed data based on the mapping rule base to generate a standardized data stream; calculating an integrity check code for the standardized data stream using a hardware cryptography engine in a trusted computing environment; And packaging the time stamp and the integrity check code into a standardized data stream to generate bearable standardized data.
4. The method for diagnosing a low-voltage distribution network fault based on trusted access of optical storage equipment according to claim 1, wherein in S3, obtaining the minimum feature subset includes: calculating mutual information of each feature and a target variable in the trusted standardized data to obtain a feature correlation index; Calculating mutual information among the features to obtain a feature redundancy index; and iteratively selecting the features based on the feature correlation index and the feature redundancy index, and constructing a minimum feature subset.
5. The method for diagnosing a low-voltage distribution network fault based on trusted access of optical storage equipment according to claim 1, wherein in S3, after obtaining the minimum feature subset, the method further comprises a process of updating the minimum feature subset, specifically: Acquiring operation parameters representing the current distribution network state; based on the operation parameters, adjusting the target variable through decision logic to obtain a new target variable; Based on the new target variable, the feature correlation index and the feature redundancy index are recalculated, and the minimum feature subset is updated.
6. The method for diagnosing a low-voltage distribution network fault based on trusted access of optical storage equipment according to claim 1, wherein in S4, obtaining efficient sensing data comprises: extracting corresponding voltage, current and power measurement data from the minimum feature subset; acquiring a symmetric encryption key for encrypting the measurement data; Encrypting the measured data by using the symmetric encryption key to generate encrypted measured data; and transmitting the encrypted measurement data to edge processing to obtain high-efficiency perception data.
7. The method for diagnosing a low-voltage distribution network fault based on trusted access of optical storage equipment according to claim 1, wherein in S6, obtaining the diagnosis and evaluation result comprises: Taking high-efficiency sensing data captured in the moment of the current fault as a real-time query mode; identifying short circuit, broken line or grounding fault types by comparing the similarity of the real-time query mode and the historical fault mode in the edge fault diagnosis knowledge unit; Acquiring capacity and distribution data of real-time optical storage equipment, and pre-calculating a reliability index of power supply recovery based on the data; and integrating the fault type and the reliability index to generate diagnosis and evaluation results.
8. The method for diagnosing a low-voltage distribution network fault based on trusted access of optical storage equipment according to claim 1, wherein in S6, after obtaining the diagnosis and evaluation result, further comprises: acquiring topology information of a power distribution network depicting a connection relationship in a station area; Performing downstream tracking analysis based on the topology information of the distribution network and the edge fault diagnosis knowledge unit, and evaluating to obtain a fault influence range; Acquiring important load grade information, and calculating to obtain a recovery scheduling priority based on the important load grade information, the fault influence range and the real-time optical storage capacity data; And integrating the fault influence range and the recovery scheduling priority into the diagnosis and evaluation results.

Description

Low-voltage distribution network fault diagnosis method based on trusted access of optical storage equipment Technical Field The invention belongs to the technical field of power grid fault diagnosis, and particularly relates to a low-voltage distribution network fault diagnosis method based on trusted access of optical storage equipment. Background Along with the transformation of energy structures, the construction of novel power systems is accelerating, wherein a low-voltage distribution network is used as a key link for bearing clean energy access such as distributed photovoltaic and energy storage, and the intelligent management level of the low-voltage distribution network is increasingly important. At the end of the low voltage distribution area, the large-scale access of distributed Photovoltaic (PV) and energy storage (ESS) devices enables the transformation of distribution networks from traditional unidirectional radiant networks to complex networks with source-network-load-storage multiple interactions. In order to realize effective bearing, efficient consumption and safe and stable operation of the dispersed heterogeneous resources, unified and accurate data acquisition, state monitoring and flexible regulation and control of the terminal optical storage equipment are required. In the prior art, CN119231510a discloses an intelligent management system for optical storage devices, which comprises a photovoltaic device, a photovoltaic inverter, an energy storage system, a load, a power distribution network, a transformer and an optical storage management platform. The technical scheme mainly focuses on performance prediction and optimal scheduling of an upper management platform, and relies on deep learning and improved particle swarm optimization algorithm to achieve minimization of economic cost. However, in practical low-voltage area application, the types of terminal optical storage devices are multiple, the types of communication protocols are complex, and a large number of nonstandard protocols exist, so that the unified specification of bottom data acquisition and communication is lacked, and high-efficiency and reliable acquisition of heterogeneous resource data is difficult to realize. Meanwhile, the existing research fails to fully consider the safety and the integrity of the data source, the credibility of the collected electric variable data cannot be effectively verified, and once the bottom layer data is tampered, the accuracy of upper layer optimal scheduling and fault diagnosis is directly reduced. Especially in the complex scene of the rapid recovery after the power failure of the distribution network, the reliable edge diagnosis capability of the state, the fault type and the power supply potential of the optical storage equipment is lacking, and the rapid and accurate response decision is difficult to make for the emergency, so that the improvement of the intelligent management level of the distribution network and the improvement of the power consumption satisfaction of users are limited. Disclosure of Invention In order to solve the problems, the invention aims to provide a low-voltage distribution network fault diagnosis method based on trusted access of optical storage equipment, which adopts a protocol deep analysis and trusted computing environment, can ensure the integrity and safety of nonstandard access data, dynamically optimizes the dimension of measured data through a maximum relevant minimum redundancy algorithm, and improves the real-time performance and efficiency of rapid fault type identification and power supply recovery potential pre-evaluation. In order to achieve the above purpose, the application adopts the following technical scheme: The low-voltage distribution network fault diagnosis method based on the trusted access of the optical storage equipment comprises the following steps: S1, in a trusted computing environment constructed by a security chip, carrying out application layer protocol deep analysis on a data packet acquired from optical storage equipment to obtain analyzed data; S2, carrying out standardized conversion on the analyzed data, and adding data branding containing a time stamp and an integrity check code to the analyzed data by utilizing a trusted computing environment to obtain trusted standardized data; S3, acquiring target variables for distinguishing different distribution network fault types, and dynamically selecting features from the bearable standardized data by using a maximum correlation minimum redundancy algorithm based on the target variables to obtain a minimum feature subset; S4, collecting and encrypting transmission is carried out on the measurement data corresponding to the minimum feature subset, and high-efficiency perception data are obtained; S5, acquiring historical fault case data, fusing the historical fault case data with high-efficiency perception data, and constructing an edge fault diagnosis knowledge unit; an