[go: up one dir, main page]

CN120104663A - A data mining method and system serving microgrid control system - Google Patents

A data mining method and system serving microgrid control system Download PDF

Info

Publication number
CN120104663A
CN120104663A CN202510088576.6A CN202510088576A CN120104663A CN 120104663 A CN120104663 A CN 120104663A CN 202510088576 A CN202510088576 A CN 202510088576A CN 120104663 A CN120104663 A CN 120104663A
Authority
CN
China
Prior art keywords
energy storage
inverter
storage battery
microgrid
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202510088576.6A
Other languages
Chinese (zh)
Inventor
迟元峰
李元哲
曹仲明
蒋本帅
王英石
蒋欣伲
杨亚楠
刘忠林
陈超伟
刘海江
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Runtong Technology Co ltd
Original Assignee
Shandong Runtong Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong Runtong Technology Co ltd filed Critical Shandong Runtong Technology Co ltd
Priority to CN202510088576.6A priority Critical patent/CN120104663A/en
Publication of CN120104663A publication Critical patent/CN120104663A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for AC mains or AC distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2474—Sequence data queries, e.g. querying versioned data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for AC mains or AC distribution networks
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
    • H02J2101/24—
    • H02J2101/28—

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Mathematical Physics (AREA)
  • Economics (AREA)
  • Databases & Information Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Power Engineering (AREA)
  • Marketing (AREA)
  • Fuzzy Systems (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

本发明公开了一种服务于微电网控制系统的数据挖掘方法及系统，涉及微电网技术领域，通过收集微电网相关数据，构建微电网数据集合S，并进行特征提取，获取电压稳定性因子Sv(t)、频率偏差因子Sf(t)以及谐波总失真率THD，从而获取电力质量综合评分Qelec，判断微电网是否出现故障，若出现故障，则进行故障定位，并构建储能电池和逆变器的老化模型，对于故障点所在线路和故障点的储能电池和逆变器，获取储能电池剩余使用时间RULb以及逆变器剩余使用时间RULinv，并使用Dijkstra最短路径算法生成最优故障修复路径Popt，进行故障修复，提升了微电网故障检测与修复的效率，延长了设备寿命，降低了维护成本，提高了微电网运行的稳定性和供电可靠性。

The invention discloses a data mining method and system for serving a microgrid control system, and relates to the technical field of microgrids. The invention collects microgrid-related data, constructs a microgrid data set S, performs feature extraction, obtains a voltage stability factor Sv (t), a frequency deviation factor Sf (t) and a total harmonic distortion rate THD, thereby obtaining a comprehensive score of power quality Qelec , judges whether a microgrid fails, locates the fault if a fault occurs, and constructs an aging model of an energy storage battery and an inverter. For the line where the fault point is located and the energy storage battery and the inverter at the fault point, the remaining service life RULb of the energy storage battery and the remaining service life RULinv of the inverter are obtained, and uses the Dijkstra shortest path algorithm to generate an optimal fault repair path Popt to perform fault repair, thereby improving the efficiency of microgrid fault detection and repair, extending the life of equipment, reducing maintenance costs, and improving the stability of microgrid operation and power supply reliability.

Description

Data mining method and system for serving micro-grid control system
Technical Field
The invention relates to the technical field of micro-grids, in particular to a data mining method and system for serving a micro-grid control system.
Background
The micro-grid technology is an important component of a smart grid, and provides stable and flexible power supply for users in an area through integrated operation of distributed energy sources such as solar energy, wind energy, energy storage equipment and loads, and in the field of micro-grids, power quality management and equipment health maintenance are two core research directions for ensuring efficient and safe operation of a system, and power quality problems such as voltage fluctuation, frequency abnormality and harmonic distortion and equipment operation health conditions such as aging of energy storage batteries and overload of inverters directly affect stability and reliability of the micro-grid, and particularly in modern complex and various energy environments, the problems put higher demands on operation and maintenance of the micro-grid.
In the existing micro-grid system, the abnormal detection of the power quality and the health prediction of the equipment are often separated, the traditional power quality detection mostly adopts an analysis method based on a single index, such as voltage fluctuation amplitude and frequency deviation, so that the power quality problem under multi-factor coupling is difficult to comprehensively reflect, the monitoring of the health state of the equipment is more dependent on regular maintenance and static historical data analysis, the change of the health state of the equipment under the power fluctuation environment is difficult to reflect in real time, the separated monitoring and static analysis means cause the defects that the system is difficult to take optimization measures in time under abnormal conditions, the defects of delayed problem discovery, difficult accurate prediction of equipment aging, low failure recovery efficiency and the like exist, the operation efficiency of the micro-grid is possibly reduced or the system is possibly interrupted, for example, the frequency fluctuation accelerates the aging of an energy storage battery, even causes short-circuit fault, the overload of an inverter possibly causes power interruption due to the fact that the periodical equipment fails to predict in time, in addition, the frequent equipment fault increases maintenance cost, the electricity utilization satisfaction of a user is reduced, the stability and the safety of regional energy supply are also influenced when the problems are serious, and the problems are not popularized, and the sustainable energy supply of the micro-grid is also restricted.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a data mining method and a data mining system for serving a micro-grid control system, and solves the problems in the background art.
The data mining system for the micro-grid control system comprises a data acquisition module, a feature extraction and abnormality assessment module, a fault positioning module, an equipment health monitoring module and an intelligent repairing module;
The data acquisition module is used for collecting related data of the micro-grid in real time and constructing a micro-grid data set S according to the collected related data of the micro-grid;
The feature extraction and anomaly evaluation module is used for preprocessing according to the micro-grid data set S, performing summarization calculation according to the preprocessed micro-grid data set S, acquiring a voltage stability factor S v (t), a frequency deviation factor S f (t) and a harmonic total distortion rate THD, acquiring a power quality comprehensive score Q elec according to the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion rate THD, presetting a power score threshold Q normal, performing comparison analysis on the power score threshold Q normal and the power quality comprehensive score Q elec, evaluating whether the micro-grid is faulty, if Q elec＞Qnormal, indicating that the micro-grid is faulty, and triggering the fault positioning module;
The fault positioning module is used for setting a plurality of data monitoring points in the micro-grid, collecting voltage waveform data of the data monitoring points, determining the positions of fault points according to the traveling wave propagation principle, acquiring information of an energy storage battery and an inverter of a line where the fault points are located, and generating a fault point equipment set G;
The device health monitoring module is used for constructing an energy storage battery aging model and an inverter aging model by using a linear regression algorithm according to the micro-grid data set S and the power quality comprehensive score Q elec to obtain an energy storage battery aging rate And inverter burn-in rateThe energy storage battery health score SoH b (t) and the inverter health score R inv (t) are obtained through calculation, comprehensive calculation is carried out according to the energy storage battery health score SoH b (t) and the inverter health score R inv (t), and the residual use time RUL b of the energy storage battery and the residual use time RUL inv of the inverter are obtained;
The intelligent repairing module is used for obtaining the residual service time RUL b of the energy storage battery and the residual service time RUL inv of the inverter of the line where the fault point is located according to the fault point equipment set G, performing equipment screening to obtain standby equipment, obtaining an optimal fault repairing path P opt from the starting point of the standby equipment to the fault point by using Dijkstra shortest path algorithm, and performing fault repairing according to the optimal fault repairing path P opt.
Preferably, the data acquisition module is used for deploying a smart sensor group on a micro-grid, collecting related data of the micro-grid in real time, and constructing a micro-grid data set S according to the collected related data of the micro-grid, wherein the related data of the micro-grid comprises power quality data and equipment operation data;
the intelligent sensor group comprises a voltage monitor, a current monitor, a frequency detector, a thermal resistance temperature sensor and a power measuring instrument;
the power quality data includes a voltage V, a current I, and a power frequency f;
The device operating data includes a battery state of charge, SOC, energy storage battery load factor, L SOC, energy storage battery operating temperature, T b, inverter operating temperature, T inv, inverter load factor, L inv, and line transmit power, C current.
Preferably, the feature extraction and abnormality evaluation module comprises a feature extraction unit and an evaluation unit;
The feature extraction unit is used for preprocessing according to the micro-grid data set S, and acquiring a voltage stability factor S v (t), a frequency deviation factor S f (t) and a harmonic total distortion (THD) according to the preprocessed micro-grid data set S, wherein preprocessing comprises data cleaning, denoising and data standardization;
The voltage stability factor S v (t) is obtained by the following steps:
wherein T represents a sampling time window, V (θ) represents a voltage at a time point θ, V (θ+Δt) represents a voltage at a time point θ+Δt, θ ε [ T-T, T ], Δt represents a sampling time interval;
The frequency deviation factor S f (t) is obtained by the following steps:
Wherein f (θ) represents a grid frequency value at time θ, and f nom represents a grid standard frequency value;
According to the power quality data in the micro-grid data set S, performing frequency domain decomposition on the voltage V by using fast fourier transform, converting the voltage waveform in the time domain to the frequency domain to obtain a fundamental wave amplitude H 1 and a harmonic wave amplitude H n, and obtaining a harmonic total distortion rate THD according to the fundamental wave amplitude H 1 and the harmonic wave amplitude H n, wherein the specific obtaining mode of the harmonic wave amplitude H n is as follows:
Hn＝n·H1;
wherein H 1 represents the fundamental wave amplitude and n represents the harmonic frequency;
the harmonic total distortion THD acquisition mode is as follows:
Wherein H n represents the harmonic amplitude, and n is more than or equal to 2.
Preferably, the evaluation unit is configured to perform summary calculation according to the voltage stability factor S v (t), the frequency deviation factor S f (t), and the harmonic total distortion ratio THD, to obtain a power quality comprehensive score Q elec, where the power quality comprehensive score Q elec is obtained by:
Qelec＝α1·Sv(t)+α2·Sf(t)+α3·THD+C;
Wherein, α 1、α2 and α 3 respectively represent the weight coefficients of the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion THD, and C represents the first correction constant;
And presetting a power grading threshold Q normal, comparing and analyzing the power grading threshold Q normal with a power quality comprehensive grading Q elec, and evaluating whether the micro-grid fails, if Q elec≤Qnormal, the micro-grid does not fail without intervention, and if Q elec＞Qnormal, the micro-grid fails, and triggering a fault positioning module to perform fault positioning on the micro-grid.
Preferably, the fault positioning module is used for setting a plurality of data monitoring points in the micro-grid, and collecting voltage waveform data of each data monitoring point in real time when the micro-grid fails, wherein the voltage waveform data refers to waveform change of a voltage signal;
According to the obtained voltage waveform data of each data monitoring point, two data monitoring points A and B with the largest amplitude variation of the voltage traveling wave signal are selected, the time difference delta t AB of the voltage traveling wave signal reaching the data monitoring points A and B is obtained, any one data monitoring point is randomly selected from the data monitoring points A and B according to the traveling wave propagation principle, and the distance d between any one data monitoring point in the data monitoring points A and B and the fault point is calculated, wherein the specific calculation mode is as follows:
Wherein v h represents the propagation speed of the traveling wave, and Δt AB represents the time difference between the traveling wave reaching the data monitoring point a and the data monitoring point B;
According to a micro-grid control system, a micro-grid topological graph is obtained, a data monitoring point A and a data monitoring point B are marked in the micro-grid topological graph, a line where a fault point is located in the micro-grid topological graph is positioned and the position of the fault point is marked by combining the distance d between any one of the data monitoring points A and B and the fault point, and energy storage battery data and inverter data of the line where the fault point is located are collected to generate a fault point equipment set G.
Preferably, the device health monitoring module comprises a device aging rate calculating unit and a health state analyzing unit;
the device aging rate calculation unit is configured to construct an energy storage battery aging model and an inverter aging model according to the fault point device set G, the micro-grid data set S and the power quality comprehensive score Q elec for the energy storage battery and the inverter of the line where the fault point is located, and the energy storage battery aging model has the following concrete expression form:
In the formula, Representing the aging rate of the energy storage battery at the current time point T, wherein Q elec (T) represents the comprehensive power quality score at the current time point T, T b (T) represents the running temperature of the energy storage battery at the current time point T, SOC (T) represents the battery charge state of the energy storage battery at the current time point T, and k 1、k2 and k 3 represent regression coefficients;
The inverter aging model has the following concrete expression form:
In the formula, Representing an inverter aging rate at a current time point T, L inv (T) representing an inverter load rate at the current time point T, T inv (T) representing an inverter operation temperature at the current time point T, and m 1、m2 and m 3 representing regression coefficients;
And collecting historical micro-grid operation data, dividing the historical micro-grid operation data into a training set and a testing set, inputting an energy storage battery aging model and an inverter aging model by using the training set for training, fitting parameters of the energy storage battery aging model and the inverter aging model by using a least square method to obtain regression coefficients k 1、k2、k3、m1、m2 and m 3, and verifying the energy storage battery aging model and the inverter aging model by using the testing set.
Preferably, the health state analysis unit is configured to obtain an aging rate of the energy storage battery according to the trained aging model of the energy storage battery and the trained aging model of the inverterAnd inverter burn-in rateAnd calculate the energy storage battery health score SoH b (t) and the inverter health score R inv (t), and obtain the remaining use time RUL b of the energy storage battery and the remaining use time RUL inv of the inverter, the energy storage battery health score SoH b (t) and the inverter health score R inv (t) are calculated as follows:
Where SoH b(t0) represents the energy storage battery health score at the initial time point t 0, R inv(t0) represents the inverter health score at the initial time point t 0, The rate of aging of the energy storage battery at time point tau is indicated,Inverter aging rate at time point τ, τ e [ t 0, t ];
The energy storage battery remaining use time RUL b and the inverter remaining use time RUL inv are obtained by the following steps:
Where SoH b,critical represents the energy storage battery health score threshold and R inv,max represents the inverter health score maximum.
Preferably, the intelligent repair module comprises a path planning unit and a fault repair unit;
the path planning unit is configured to obtain an optimal fault repair path P opt according to a microgrid topology map by using a path planning algorithm, where a specific obtaining manner of the optimal fault repair path P opt is as follows:
According to the health equipment monitoring module and the micro-grid data set S, operation data of the energy storage battery and the inverter are obtained, wherein the operation data comprise residual use time RUL b of the energy storage battery, residual use time RUL inv of the inverter, load rate L SOC of the energy storage battery, load rate L inv of the inverter, health score SoH b (t) of the energy storage battery and health score R inv (t) of the inverter;
Converting the micro-grid topological graph into a micro-grid weighted graph F, wherein the micro-grid weighted graph F has the following concrete expression form:
F=(N,E);
N represents nodes in the micro-grid, wherein the nodes comprise an energy storage battery, an inverter and load nodes, E represents edges, and the edges comprise connecting lines among the nodes, wherein the load nodes refer to power consumption ends, namely electric equipment needing power supply and an electric area;
According to the microgrid weighting graph F, for each energy storage battery and inverter, a preset energy storage battery usage time health threshold T (RUL b)min and inverter usage time health threshold T (RUL inv)min, and according to the remaining energy storage battery usage time RUL b and inverter usage time RUL inv, in combination with the preset energy storage battery usage time health threshold T (RUL b)min and inverter usage time health threshold T (RUL inv)min, energy storage battery and inverter screening is performed, and the energy storage batteries and inverters of RUL b＞T(RULb)min and RUL inv＞T(RULinv)min are reserved as standby devices);
According to the operation data of the energy storage battery and the inverter, calculating the weight of each side, wherein the specific calculation process comprises the following steps:
Wherein RUL b,i represents the remaining use time of the energy storage battery of the node i, RUL inv,i represents the remaining use time of the inverter of the node i, L SOC,i represents the load factor of the energy storage battery of the node i, L inv,i represents the load factor of the inverter of the node i, C remaining,ij represents the remaining transmission capacity of the line between the node i and the node j, and beta, gamma, delta, epsilon and epsilon represent weight coefficients;
Using Dijkstra shortest path algorithm, taking a micro-grid weighted graph G as input, carrying out path search, setting a path search target as minimum path total weight, and selecting a path with the minimum path total weight as an optimal fault restoration path P opt, wherein the minimum path total weight has the concrete expression form:
Where W path represents the total weight of path P and e ij represents the edge from node i to node j.
Preferably, the fault repairing unit is configured to perform a fault repairing operation according to the optimal fault repairing path P opt, where the optimal fault repairing path P opt includes a start point device, a pass line and an end point load, the fault repairing operation includes initializing a repairing task, starting a standby device and switching the line, and monitoring related data of the micro grid after the fault repairing operation in real time.
A data mining method for a micro grid control system, comprising the steps of,
Step one, collecting related data of a micro-grid in real time, and constructing a micro-grid data set S according to the collected related data of the micro-grid;
step two, preprocessing is carried out according to the micro-grid data set S, summarizing calculation is carried out according to the preprocessed micro-grid data set S, a voltage stability factor S v (t), a frequency deviation factor S f (t) and a harmonic total distortion THD are obtained, a power quality comprehensive score Q elec is obtained according to the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion THD, a power quality comprehensive score Q normal is preset, a power score threshold Q normal and a power quality comprehensive score Q elec are compared and analyzed, whether the micro-grid fails is evaluated, if Q elec＞Qnormal is judged, the micro-grid fails is indicated, and a fault positioning module is triggered at the moment;
Setting a plurality of data monitoring points in the micro-grid, collecting voltage waveform data of the data monitoring points, determining fault point positions according to a traveling wave propagation principle, acquiring information of an energy storage battery and an inverter of a line where the fault points are located, and generating a fault point equipment set G;
Fourth, according to the micro-grid data set S and the power quality comprehensive score Q elec, an energy storage battery aging model and an inverter aging model are built by using a linear regression algorithm, and an energy storage battery aging rate is obtained And inverter burn-in rateThe energy storage battery health score SoH b (t) and the inverter health score R inv (t) are obtained through calculation, comprehensive calculation is carried out according to the energy storage battery health score SoH b (t) and the inverter health score R inv (t), and the residual use time RUL b of the energy storage battery and the residual use time RUL inv of the inverter are obtained;
Step five, according to the fault point device set G, obtaining the remaining service time RUL b of the energy storage battery and the remaining service time RUL inv of the inverter of the line where the fault point is located, performing device screening to obtain the standby device, obtaining an optimal fault repairing path P opt from the starting point of the standby device to the fault point by using Dijkstra shortest path algorithm, and performing fault repairing according to the optimal fault repairing path P opt.
The invention provides a data mining method and a system for serving a micro-grid control system, which have the following beneficial effects:
(1) Through the feature extraction and anomaly evaluation module, the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion rate THD in the micro-grid are collected and analyzed in real time, the comprehensive power quality score Q elec is comprehensively calculated, the power score threshold Q normal is set, the anomaly state of the micro-grid can be timely found, and compared with a traditional single power quality monitoring mode, the method is based on multi-factor comprehensive evaluation, has higher accuracy and instantaneity, is beneficial to quickly identifying the power fluctuation anomaly condition, and accordingly improves the overall operation stability and power supply quality of the micro-grid.
(2) Through the collaborative work of the fault locating module and the equipment health monitoring module, fault points in the micro-grid can be located rapidly, accurate assessment on equipment states is achieved based on operation data of the energy storage battery and the inverter, such as aging rate, health score and residual service time.
(3) Through the intelligent repair module, the system can generate an optimal fault repair path P opt by combining a micro-grid topological graph, energy storage battery operation data and inverter operation data based on equipment information of a fault point after the fault occurs, and compared with the traditional manual repair scheme, the system optimizes the selection and line switching process of standby equipment on the basis of considering the residual use time RUL b of the energy storage battery, the residual use time RUL inv of the inverter, the load rate L SOC of the energy storage battery, the load rate L inv of the inverter and the line transmission power C current.
Drawings
Fig. 1 is a block diagram of a data mining system serving a microgrid control system in accordance with the present invention.
Fig. 2 is a schematic flow chart of a data mining method serving a micro-grid control system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the invention provides a data mining system serving a micro-grid control system, which comprises a data acquisition module, a feature extraction and abnormality evaluation module, a fault positioning module, an equipment health monitoring module and an intelligent repair module;
The data acquisition module is used for collecting related data of the micro-grid in real time and constructing a micro-grid data set S according to the collected related data of the micro-grid;
The feature extraction and anomaly evaluation module is used for preprocessing according to the micro-grid data set S, performing summarization calculation according to the preprocessed micro-grid data set S, acquiring a voltage stability factor S v (t), a frequency deviation factor S f (t) and a harmonic total distortion rate THD, acquiring a power quality comprehensive score Q elec according to the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion rate THD, presetting a power score threshold Q normal, performing comparison analysis on the power score threshold Q normal and the power quality comprehensive score Q elec, evaluating whether the micro-grid is faulty, if Q elec＞Qnormal, indicating that the micro-grid is faulty, and triggering the fault positioning module;
The fault positioning module is used for setting a plurality of data monitoring points in the micro-grid, collecting voltage waveform data of the data monitoring points, determining the positions of fault points according to the traveling wave propagation principle, acquiring information of an energy storage battery and an inverter of a line where the fault points are located, and generating a fault point equipment set G;
The device health monitoring module is used for constructing an energy storage battery aging model and an inverter aging model by using a linear regression algorithm according to the micro-grid data set S and the power quality comprehensive score Q elec to obtain an energy storage battery aging rate And inverter burn-in rateThe energy storage battery health score SoH b (t) and the inverter health score R inv (t) are obtained through calculation, comprehensive calculation is carried out according to the energy storage battery health score SoH b (t) and the inverter health score R inv (t), and the residual use time RUL b of the energy storage battery and the residual use time RUL inv of the inverter are obtained;
The intelligent repairing module is used for obtaining the residual service time RUL b of the energy storage battery and the residual service time RUL inv of the inverter of the line where the fault point is located according to the fault point equipment set G, performing equipment screening to obtain standby equipment, obtaining an optimal fault repairing path P opt from the starting point of the standby equipment to the fault point by using Dijkstra shortest path algorithm, and performing fault repairing according to the optimal fault repairing path P opt.
In the embodiment, the data acquisition module is used for collecting the power quality data, the equipment operation data and the environment data of the micro-grid in real time, the micro-grid data set S is constructed, comprehensive and accurate data support is provided for subsequent analysis, the feature extraction and anomaly evaluation module can be used for obtaining the voltage stability factor S v (t), the frequency deviation factor S f (t) and the total harmonic distortion THD, calculating the power quality comprehensive score Q elec, accurately evaluating the power quality state of the micro-grid, rapidly identifying abnormal conditions, the fault positioning module is used for combining the traveling wave propagation principle, rapidly positioning fault points and obtaining relevant equipment data, generating the fault point equipment set G, shortening the fault response time, the equipment health monitoring module is used for providing scientific basis for optimizing equipment management and maintenance based on the aging rate model of the energy storage battery and the inverter, the equipment health state is dynamically evaluated, the equipment residual service time is predicted, the intelligent repair module is used for combining the micro-grid topological graph and the equipment health state data, the standby equipment is screened and the optimal fault repair path P opt is obtained by using the Dijkstra shortest path algorithm, the service life and load capacity of the equipment are guaranteed to be prioritized in the repair process, the service life and the load capacity is improved, the fault stability and the service life of the fault can be improved, the fault can be continuously and the fault operation can be guaranteed, the fault is prolonged and the fault is continuously can be continuously and prolonged.
Example 2
Referring to fig. 1, the data acquisition module is specifically configured to deploy an intelligent sensor group on a micro-grid, collect micro-grid related data in real time, and construct a micro-grid data set S according to the collected micro-grid related data, where the micro-grid related data includes power quality data and equipment operation data;
the intelligent sensor group comprises a voltage monitor, a current monitor, a frequency detector, a thermal resistance temperature sensor and a power measuring instrument;
the power quality data includes a voltage V, a current I, and a power frequency f;
The equipment operation data comprise battery charge state SOC of the energy storage battery, load rate L SOC of the energy storage battery, operation temperature T b of the energy storage battery, operation temperature T inv of the inverter, load rate L inv of the inverter and line transmission power C current;
The voltage V is obtained through a voltage monitor;
the current I is obtained through a current monitor;
The power frequency f is obtained through a frequency detector;
The battery charge state SOC of the energy storage battery, the load rate L SOC of the energy storage battery and the running temperature T b of the energy storage battery are obtained through a battery management system BMS;
The inverter running temperature T inv is obtained through a thermal resistance temperature sensor;
The inverter load factor L inv and the line transmission power C current are obtained by a power meter.
In the embodiment, through disposing the intelligent sensor group on the micro-grid, the system can acquire power quality data such as voltage V, current I, power frequency f and equipment operation data such as battery charge state SOC of the energy storage battery, energy storage battery load rate L SOC, energy storage battery operation temperature T b, inverter operation temperature T inv, inverter load rate L inv and line transmission power C current in real time, the accurate collection and integration of the multi-source data construct a comprehensive micro-grid data set S, high-quality basic data support is provided for subsequent data analysis and optimization scheduling, compared with a traditional single-parameter monitoring mode, the intelligent sensor group can capture dynamic changes in the micro-grid operation in real time, high efficiency and multiple dimensions, ensure that the system can respond to power grid abnormality or equipment operation deviation in time, through comprehensive data collection, the system can evaluate power quality problems and equipment health status more accurately, the monitoring accuracy and operation stability of the micro-grid are effectively improved, intelligent management and optimization basis of power supply are laid, fault occurrence rate and maintenance cost are reduced, and reliability and sustainability of the system are enhanced.
Example 3
Referring to fig. 1, the feature extraction and anomaly evaluation module includes a feature extraction unit and an evaluation unit;
The feature extraction unit is used for preprocessing according to the micro-grid data set S, and acquiring a voltage stability factor S v (t), a frequency deviation factor S f (t) and a harmonic total distortion (THD) according to the preprocessed micro-grid data set S, wherein preprocessing comprises data cleaning, denoising and data standardization;
The voltage stability factor S v (t) is obtained by the following steps:
Wherein T represents a sampling time window, V (theta) represents a voltage at a time point theta, V (theta+delta T) represents a voltage at a time point theta+delta T, theta epsilon [ T-T, T ] delta T represents a sampling time interval, and the larger the value of S v (T) is, the more severe the voltage fluctuation is, and the worse the stability of the power grid is;
The frequency deviation factor S f (t) is obtained by the following steps:
Wherein f (θ) represents a grid frequency value at time θ, f nom represents a grid standard frequency value, and the more the frequency deviation factor S f (t) tends to zero, the more stable the grid frequency is;
The power grid standard frequency value f nom is obtained through a national power grid operation standard table;
According to the power quality data in the micro-grid data set S, performing frequency domain decomposition on the voltage V by using fast fourier transform, converting the voltage waveform in the time domain to the frequency domain to obtain a fundamental wave amplitude H 1 and a harmonic wave amplitude H n, and obtaining a harmonic total distortion rate THD according to the fundamental wave amplitude H 1 and the harmonic wave amplitude H n, wherein the specific obtaining mode of the harmonic wave amplitude H n is as follows:
Hn＝n·H1;
wherein H 1 represents the fundamental wave amplitude and n represents the harmonic frequency;
the fundamental wave amplitude H 1 refers to the sine wave component with the lowest frequency in the voltage signal, namely the nominal frequency of the power system;
The harmonic amplitude H n refers to a sine wave component of an integral multiple frequency component of the fundamental wave frequency, is a waveform distortion component introduced by nonlinear load and use of power electronic equipment, and is an integral multiple of the fundamental wave amplitude;
the harmonic total distortion THD acquisition mode is as follows:
Wherein H n represents the harmonic amplitude, and n is more than or equal to 2.
The evaluation unit is configured to perform summary calculation according to the voltage stability factor S v (t), the frequency deviation factor S f (t), and the harmonic total distortion ratio THD, and obtain an electric power quality comprehensive score Q elec, where an electric power quality comprehensive score Q elec is obtained by:
Qelec＝α1·Sv(t)+α2·Sf(t)+α3·THD+C;
Wherein, α 1、α2 and α 3 respectively represent the weight coefficients of the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion THD, and C represents the first correction constant, wherein, the value of the weight coefficient is set by the customer according to the actual situation, and 0< α 1<1,0<α2<1,0<α3<1,α1+α2+α3 =1;
And presetting a power grading threshold Q normal, comparing and analyzing the power grading threshold Q normal with a power quality comprehensive grading Q elec, and evaluating whether the micro-grid fails, if Q elec≤Qnormal, the micro-grid does not fail without intervention, and if Q elec＞Qnormal, the micro-grid fails, and triggering a fault positioning module to perform fault positioning on the micro-grid.
In the embodiment, the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion rate THD are extracted by preprocessing the micro-grid data set S and according to the preprocessed micro-grid data set S, the dynamic change characteristics of the power quality can be comprehensively reflected, in addition, the fundamental wave amplitude H 1 and the harmonic wave amplitude H n of the voltage V are extracted by using fast fourier transformation, so that the harmonic total distortion rate THD is calculated, nonlinear loads and harmonic distortion caused by power electronic equipment can be effectively captured, the evaluation unit generates the power quality comprehensive score Q elec by summarizing the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion rate THD, and compares the power quality comprehensive score Q elec with a preset power score threshold Q normal.
Example 4
Referring to fig. 1, the fault location module is specifically configured to set a plurality of data monitoring points in the micro-grid, and collect voltage waveform data of each data monitoring point in real time when the micro-grid fails, where the voltage waveform data refers to waveform variation of a voltage signal;
According to the obtained voltage waveform data of each data monitoring point, two data monitoring points A and B with the largest amplitude variation of the voltage traveling wave signal are selected, the time difference delta t AB of the voltage traveling wave signal reaching the data monitoring points A and B is obtained, any one data monitoring point is randomly selected from the data monitoring points A and B according to the traveling wave propagation principle, and the distance d between any one data monitoring point in the data monitoring points A and B and the fault point is calculated, wherein the specific calculation mode is as follows:
Wherein v h represents the propagation speed of the traveling wave, and Δt AB represents the time difference between the traveling wave reaching the data monitoring point a and the data monitoring point B;
According to a micro-grid control system, a micro-grid topological graph is obtained, a data monitoring point A and a data monitoring point B are marked in the micro-grid topological graph, a line where a fault point is located in the micro-grid topological graph is positioned and the position of the fault point is marked by combining the distance d between any one of the data monitoring points A and B and the fault point, and energy storage battery data and inverter data of the line where the fault point is located are collected to generate a fault point equipment set G.
In the embodiment, through real-time monitoring and accurate analysis of the fault positioning module, the positioning efficiency and accuracy of the micro-grid when faults occur can be effectively improved, firstly, the fault positioning module sets a plurality of data monitoring points, acquires voltage waveform data, can rapidly capture the propagation characteristics of traveling wave signals when the faults occur, so that key monitoring points are selected through amplitude changes, the distance between the fault points and the monitoring points is calculated based on traveling wave propagation principles, compared with the traditional manual investigation and single-point monitoring mode, the method not only improves the fault positioning speed, but also reduces the misjudgment rate, and secondly, through combination with a micro-grid topological graph, the fault points can be accurately mapped to specific line positions, and further related line equipment such as an energy storage battery and an inverter can be obtained, so that a fault point equipment set G is generated, and the multi-dimensional analysis mode combining the power waveform data and equipment operation information can comprehensively evaluate the fault influence range, thereby providing accurate data support for subsequent health monitoring and repairing path planning, finally, the application of the module shortens the fault response time, improves the reliability and stability of the micro-grid operation, and reduces the damage caused by the power supply delay range.
Example 5
Referring to fig. 1, specifically, the device health monitoring module includes a device aging rate calculating unit and a health status analyzing unit;
the device aging rate calculation unit is configured to construct an energy storage battery aging model and an inverter aging model according to the fault point device set G, the micro-grid data set S and the power quality comprehensive score Q elec for the energy storage battery and the inverter of the line where the fault point is located, and the energy storage battery aging model has the following concrete expression form:
In the formula, Representing the aging rate of the energy storage battery at the current time point T, wherein Q elec (T) represents the comprehensive power quality score at the current time point T, T b (T) represents the running temperature of the energy storage battery at the current time point T, SOC (T) represents the battery charge state of the energy storage battery at the current time point T, and k 1、k2 and k 3 represent regression coefficients;
The inverter aging model has the following concrete expression form:
In the formula, Representing an inverter aging rate at a current time point T, L inv (T) representing an inverter load rate at the current time point T, T inv (T) representing an inverter operation temperature at the current time point T, and m 1、m2 and m 3 representing regression coefficients;
And collecting historical micro-grid operation data, dividing the historical micro-grid operation data into a training set and a testing set, inputting an energy storage battery aging model and an inverter aging model by using the training set for training, fitting parameters of the energy storage battery aging model and the inverter aging model by using a least square method to obtain regression coefficients k 1、k2、k3、m1、m2 and m 3, and verifying the energy storage battery aging model and the inverter aging model by using the testing set.
The health state analysis unit is used for obtaining the aging rate of the energy storage battery according to the trained aging model of the energy storage battery and the trained aging model of the inverterAnd inverter burn-in rateAnd calculate the energy storage battery health score SoH b (t) and the inverter health score R inv (t), and obtain the remaining use time RUL b of the energy storage battery and the remaining use time RUL inv of the inverter, the energy storage battery health score SoH b (t) and the inverter health score R inv (t) are calculated as follows:
Where SoH b(t0) represents the energy storage battery health score at the initial time point t 0, R inv(t0) represents the inverter health score at the initial time point t 0, The rate of aging of the energy storage battery at time point tau is indicated,Inverter aging rate at time point τ, τ e [ t 0, t ];
The energy storage battery remaining use time RUL b and the inverter remaining use time RUL inv are obtained by the following steps:
Where SoH b,critical represents the energy storage battery health score threshold and R inv,max represents the inverter health score maximum.
The energy storage battery health score critical value SoH b,critical is obtained through manufacturing trademark data, and the inverter health score maximum value R inv,max is set to 1.
In the embodiment, through the cooperative work of the equipment aging rate calculation unit and the health state analysis unit, the operation safety of the micro-grid and the precision of equipment maintenance are improved, firstly, an aging model of an energy storage battery and an inverter is built through a linear regression algorithm, the aging rate of equipment under different operation conditions can be dynamically quantified, the dynamic analysis method breaks through the limitation of traditional static evaluation, so that the change of the health state of the equipment can be captured in real time, and secondly, the aging rate of the energy storage battery is utilized through the health state analysis unitAnd inverter burn-in rateThe method for dynamically monitoring the health state of the micro-grid based on the health score and the residual life provides reliable basis for accurate maintenance and scheduling of the energy storage battery and the inverter, effectively avoids sudden faults caused by deterioration of the health state of the micro-grid, and in addition, the scheduling strategy of the micro-grid is optimized by combining the health data of the equipment, so that the equipment with good health state can be preferentially used under the power fluctuation scene, the equipment load is lightened, the service life of the equipment is prolonged, and in sum, the module can effectively reduce the operation cost of the micro-grid through accurate health monitoring and life assessment, improve the power supply stability, provide timely and scientific data support for fault restoration, and be a key guarantee for efficient and safe operation of the micro-grid.
Example 6
Referring to fig. 1, specifically, the intelligent repair module includes a path planning unit and a fault repair unit;
the path planning unit is configured to obtain an optimal fault repair path P opt according to a microgrid topology map by using a path planning algorithm, where a specific obtaining manner of the optimal fault repair path P opt is as follows:
According to the health equipment monitoring module and the micro-grid data set S, operation data of the energy storage battery and the inverter are obtained, wherein the operation data comprise residual use time RUL b of the energy storage battery, residual use time RUL inv of the inverter, load rate L SOC of the energy storage battery, load rate L inv of the inverter, health score SoH b (t) of the energy storage battery and health score R inv (t) of the inverter;
Converting the micro-grid topological graph into a micro-grid weighted graph F, wherein the micro-grid weighted graph F has the following concrete expression form:
F=(N,E);
N represents nodes in the micro-grid, wherein the nodes comprise an energy storage battery, an inverter and load nodes, E represents edges, and the edges comprise connecting lines among the nodes, wherein the load nodes refer to power consumption ends, namely electric equipment needing power supply and an electric area;
According to the microgrid weighting graph F, for each energy storage battery and inverter, a preset energy storage battery usage time health threshold T (RUL b)min and inverter usage time health threshold T (RUL inv)min, and according to the remaining energy storage battery usage time RUL b and inverter usage time RUL inv, in combination with the preset energy storage battery usage time health threshold T (RUL b)min and inverter usage time health threshold T (RUL inv)min, energy storage battery and inverter screening is performed, and the energy storage batteries and inverters of RUL b＞T(RULb)min and RUL inv＞T(RULinv)min are reserved as standby devices);
According to the operation data of the energy storage battery and the inverter, calculating the weight of each side, wherein the specific calculation process comprises the following steps:
Wherein RUL b,i represents the remaining usage time of the energy storage battery of the node i, RUL inv,i represents the remaining usage time of the inverter of the node i, L SOC,i represents the load factor of the energy storage battery of the node i, L inv,i represents the load factor of the inverter of the node i, C remaining,ij represents the remaining transmission capacity of the line between the node i and the node j, wherein the remaining transmission power C remaining,ij of the line between the node i and the node j is obtained by subtracting the transmission power C current of the line from the maximum transmission power C current,max of the line, β, γ, δ, ε and e represent weight coefficients, the data of which are set by the client according to the specific situation, 0< β <1,0< γ <1,0< δ <1,0< ε <1, β+γ+δ+ε=1;
Using Dijkstra shortest path algorithm, taking a micro-grid weighted graph G as input, carrying out path search, setting a path search target as minimum path total weight, and selecting a path with the minimum path total weight as an optimal fault restoration path P opt, wherein the minimum path total weight has the concrete expression form:
Where W path represents the total weight of path P and e ij represents the edge from node i to node j.
The fault repairing unit is configured to execute a fault repairing operation according to the optimal fault repairing path P opt, where the optimal fault repairing path P opt includes a start point device, a pass line and an end point load, the fault repairing operation includes initializing a repairing task, starting a standby device and switching the line, and monitors related data of the micro grid after the fault repairing operation in real time.
In the embodiment, through the cooperative work of the path planning unit and the fault repairing unit, the scheme can quickly generate the optimal fault repairing path P opt after the micro-grid fault occurs and efficiently execute repairing tasks, effectively improve the running reliability and repairing efficiency of the micro-grid, the path planning unit combines a health equipment monitoring module and a micro-grid data set S, acquires the residual service time RUL b of an energy storage battery, the residual service time RUL inv of an inverter, the load rate L SOC of the energy storage battery, the load rate L inv of the inverter, the health score SoH b (t) of the energy storage battery and the health score R inv (t) of the inverter, generates a micro-grid weighting graph F based on a micro-grid topological graph, and calculates the weight of each side by screening the energy storage equipment and the inverter with good health status as standby equipment, comprehensively considering factors such as equipment health state, load rate, line residual transmission capacity and the like, ensuring scientificity and high efficiency of repair path selection, finally using Dijkstra shortest path algorithm, taking the total weight of a minimized path as a target, selecting an optimal fault repair path P opt from a standby device to a fault point, executing repair operation by a fault repair unit according to the optimal fault repair path P opt, monitoring fault repair effect in real time, ensuring normal operation of a system, dynamically optimizing the repair path by a path planning algorithm, fully considering equipment health condition and line load condition, avoiding occurrence of repeated faults, improving repair efficiency, reducing extra burden of the standby device, simultaneously reducing influence of fault repair on integral operation of a power grid, the safety and stability of the micro-grid are guaranteed.
Referring to fig. 2, in particular, a data mining method for serving a micro grid control system, includes the steps of,
Step one, collecting related data of a micro-grid in real time, and constructing a micro-grid data set S according to the collected related data of the micro-grid;
step two, preprocessing is carried out according to the micro-grid data set S, summarizing calculation is carried out according to the preprocessed micro-grid data set S, a voltage stability factor S v (t), a frequency deviation factor S f (t) and a harmonic total distortion THD are obtained, a power quality comprehensive score Q elec is obtained according to the voltage stability factor S v (t), the frequency deviation factor S f (t) and the harmonic total distortion THD, a power quality comprehensive score Q normal is preset, a power score threshold Q normal and a power quality comprehensive score Q elec are compared and analyzed, whether the micro-grid fails is evaluated, if Q elec＞Qnormal is judged, the micro-grid fails is indicated, and a fault positioning module is triggered at the moment;
Setting a plurality of data monitoring points in the micro-grid, collecting voltage waveform data of the data monitoring points, determining fault point positions according to a traveling wave propagation principle, acquiring information of an energy storage battery and an inverter of a line where the fault points are located, and generating a fault point equipment set G;
Fourth, according to the micro-grid data set S and the power quality comprehensive score Q elec, an energy storage battery aging model and an inverter aging model are built by using a linear regression algorithm, and an energy storage battery aging rate is obtained And inverter burn-in rateThe energy storage battery health score SoH b (t) and the inverter health score R inv (t) are obtained through calculation, comprehensive calculation is carried out according to the energy storage battery health score SoH b (t) and the inverter health score R inv (t), and the residual use time RUL b of the energy storage battery and the residual use time RUL inv of the inverter are obtained;
Step five, according to the fault point device set G, obtaining the remaining service time RUL b of the energy storage battery and the remaining service time RUL inv of the inverter of the line where the fault point is located, performing device screening to obtain the standby device, obtaining an optimal fault repairing path P opt from the starting point of the standby device to the fault point by using Dijkstra shortest path algorithm, and performing fault repairing according to the optimal fault repairing path P opt.
In the embodiment, the micro-grid data set S is constructed by collecting related data of the micro-grid in real time, comprehensive diagnosis and optimal scheduling of power quality and equipment health status are achieved, in power quality assessment, voltage stability factor S v (t), frequency deviation factor S f (t) and harmonic total distortion rate THD are utilized, multi-factor joint analysis is carried out, power quality comprehensive score Q elec is obtained, abnormal conditions of the micro-grid are accurately detected, traveling wave propagation principles are adopted for fault location problems, fault point positions are rapidly determined, fault point equipment information is obtained by combining a micro-grid topological graph, a foundation is laid for follow-up health status analysis and path planning, residual service time RUL b of an energy storage battery and residual service time RUL inv of the inverter are dynamically obtained through ageing model and health status prediction of the energy storage battery, and in fault restoration, the optimal fault restoration path P opt is generated through Dijkstra shortest path algorithm.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (10)

1.一种服务于微电网控制系统的数据挖掘系统，其特征在于：包括数据采集模块、特征提取与异常评估模块、故障定位模块、设备健康监测模块以及智能修复模块；1. A data mining system serving a microgrid control system, characterized by: comprising a data acquisition module, a feature extraction and anomaly assessment module, a fault location module, an equipment health monitoring module and an intelligent repair module; 所述数据采集模块用于实时收集微电网相关数据，并依据收集的微电网相关数据，构建微电网数据集合S；The data acquisition module is used to collect microgrid related data in real time, and construct a microgrid data set S based on the collected microgrid related data; 所述特征提取与异常评估模块用于依据所述微电网数据集合S，进行预处理，并依据预处理后的微电网数据集合S，进行汇总计算，获取电压稳定性因子Sv(t)、频率偏差因子Sf(t)以及谐波总失真率THD，并依据所述电压稳定性因子Sv(t)、频率偏差因子Sf(t)以及谐波总失真率THD，获取电力质量综合评分Qelec，并预设电力评分阈值Qnormal，将电力评分阈值Qnormal与电力质量综合评分Qelec进行对比分析，评估微电网是否发生故障，若Qelec＞Qnormal，则表明微电网发生故障，此时触发故障定位模块；The feature extraction and abnormality assessment module is used to perform preprocessing according to the microgrid data set S, and perform summary calculation according to the preprocessed microgrid data set S to obtain a voltage stability factor S v (t), a frequency deviation factor S f (t) and a total harmonic distortion rate THD, and obtain a comprehensive power quality score Q elec according to the voltage stability factor S v (t), the frequency deviation factor S f (t) and the total harmonic distortion rate THD, and preset a power score threshold Q normal , compare and analyze the power score threshold Q normal with the comprehensive power quality score Q elec , and evaluate whether a microgrid fault occurs. If Q elec >Q normal , it indicates that a microgrid fault occurs, and the fault location module is triggered at this time; 所述故障定位模块用于在微电网中设置若干数据监测点，并收集数据监测点的电压波形数据，依据行波传播原理确定故障点位置，并获取故障点所在线路的储能电池和逆变器信息，生成故障点设备集合G；The fault location module is used to set a number of data monitoring points in the microgrid, collect voltage waveform data of the data monitoring points, determine the location of the fault point according to the principle of traveling wave propagation, and obtain the energy storage battery and inverter information of the line where the fault point is located, and generate a fault point device set G; 所述设备健康监测模块用于依据所述微电网数据集合S和电力质量综合评分Qelec，使用线性回归算法构建储能电池老化模型和逆变器老化模型，获取储能电池老化速率和逆变器老化速率并计算得到储能电池健康评分SoHb(t)和逆变器健康评分Rinv(t)，依据储能电池健康评分SoHb(t)和逆变器健康评分Rinv(t)，进行综合计算，获取储能电池剩余使用时间RULb以及逆变器剩余使用时间RULinv；The equipment health monitoring module is used to construct an energy storage battery aging model and an inverter aging model based on the microgrid data set S and the power quality comprehensive score Q elec using a linear regression algorithm to obtain the energy storage battery aging rate and inverter aging rate And calculate the energy storage battery health score SoH b (t) and the inverter health score R inv (t), and perform comprehensive calculation based on the energy storage battery health score SoH b (t) and the inverter health score R inv (t) to obtain the remaining use time RUL b of the energy storage battery and the remaining use time RUL inv of the inverter; 所述智能修复模块用于依据故障点设备集合G，获取故障点所在线路的储能电池剩余使用时间RULb以及逆变器剩余使用时间RULinv，进行设备筛选，获取备用设备，并使用Dijkstra最短路径算法，获取从备用设备起点到故障点的最优故障修复路径Popt，并依据最优故障修复路径Popt进行故障修复。The intelligent repair module is used to obtain the remaining service life RUL b of the energy storage battery and the remaining service life RUL inv of the inverter of the line where the fault point is located according to the fault point device set G, perform device screening, obtain spare devices, and use the Dijkstra shortest path algorithm to obtain the optimal fault repair path P opt from the starting point of the spare device to the fault point, and perform fault repair according to the optimal fault repair path P opt . 2.根据权利要求1所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：所述数据采集模块用于在微电网上部署智能传感器组，实时收集微电网相关数据，并依据收集的微电网相关数据，构建微电网数据集合S，其中，微电网相关数据包括电力质量数据和设备运行数据；2. A data mining system serving a microgrid control system according to claim 1, characterized in that: the data acquisition module is used to deploy an intelligent sensor group on the microgrid, collect microgrid-related data in real time, and construct a microgrid data set S based on the collected microgrid-related data, wherein the microgrid-related data includes power quality data and equipment operation data; 所述智能传感器组包括电压监测仪、电流监测仪、频率检测仪、热电阻温度传感器以及功率测量仪；The intelligent sensor group includes a voltage monitor, a current monitor, a frequency detector, a thermal resistance temperature sensor and a power measuring instrument; 所述电力质量数据包括电压V、电流I和电力频率f；The power quality data includes voltage V, current I and power frequency f; 所述设备运行数据包括储能电池的电池荷电状态SOC、储能电池负载率LSOC、储能电池运行温度Tb、逆变器运行温度Tinv、逆变器负载率Linv以及线路传输功率Ccurrent。The equipment operation data includes a battery state of charge SOC of the energy storage battery, an energy storage battery load rate L SOC , an energy storage battery operation temperature T b , an inverter operation temperature T inv , an inverter load rate L inv and a line transmission power C current . 3.根据权利要求2所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：所述特征提取与异常评估模块包括特征提取单元和评估单元；3. A data mining system serving a microgrid control system according to claim 2, characterized in that: the feature extraction and abnormality assessment module comprises a feature extraction unit and an assessment unit; 所述特征提取单元用于依据所述微电网数据集合S，进行预处理，并依据预处理后的微电网数据集合S，获取电压稳定性因子Sv(t)、频率偏差因子Sf(t)以及谐波总失真率THD，其中，预处理包括数据清洗、去噪和数据标准化；The feature extraction unit is used to perform preprocessing according to the microgrid data set S, and obtain a voltage stability factor S v (t), a frequency deviation factor S f (t) and a total harmonic distortion rate THD according to the preprocessed microgrid data set S, wherein the preprocessing includes data cleaning, denoising and data standardization; 所述电压稳定性因子Sv(t)获取方式为：The voltage stability factor S v (t) is obtained as follows: 式中，T表示采样时间窗口，V(θ)表示时间点θ时的电压，V(θ+Δt)表示时间点θ+Δt时的电压，θ∈[t-T，t]，Δt表示采样时间间隔；Where T represents the sampling time window, V(θ) represents the voltage at time point θ, V(θ+Δt) represents the voltage at time point θ+Δt, θ∈[t-T, t], Δt represents the sampling time interval; 所述频率偏差因子Sf(t)获取方式为：The frequency deviation factor S f (t) is obtained in the following manner: 式中，f(θ)表示时间θ时的电网频率值，fnom表示电网标准频率值；In the formula, f(θ) represents the grid frequency value at time θ, and f nom represents the grid standard frequency value; 依据所述微电网数据集合S中的电力质量数据，使用快速傅里叶变换对电压V进行频域分解，将时间域的电压波形转换到频域，以获取基波幅值H1和谐波幅值Hn，并依据基波幅值H1和谐波幅值Hn，获取谐波总失真率THD，其中，谐波幅值Hn具体获取方式如下：According to the power quality data in the microgrid data set S, the voltage V is decomposed in the frequency domain using fast Fourier transform, and the voltage waveform in the time domain is converted to the frequency domain to obtain the fundamental amplitude H1 and the harmonic amplitude Hn , and the total harmonic distortion THD is obtained according to the fundamental amplitude H1 and the harmonic amplitude Hn, wherein the harmonic amplitude Hn is specifically obtained as follows: Hn＝n·H1；H n = n·H 1 ; 式中，H1表示基波幅值，n表示谐波次数；In the formula, H1 represents the fundamental amplitude, and n represents the harmonic order; 所述谐波总失真率THD获取方式为：The total harmonic distortion THD is obtained as follows: 式中，Hn表示谐波幅值，n≥2。Where Hn represents the harmonic amplitude, n≥2. 4.根据权利要求3所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：所述评估单元用于依据所述电压稳定性因子Sv(t)、频率偏差因子Sf(t)以及谐波总失真率THD，进行汇总计算，获取电力质量综合评分Qelec，所述电力质量综合评分Qelec获取方式为：4. A data mining system serving a microgrid control system according to claim 3, characterized in that: the evaluation unit is used to perform summary calculation based on the voltage stability factor S v (t), the frequency deviation factor S f (t) and the total harmonic distortion rate THD to obtain a comprehensive power quality score Q elec , and the comprehensive power quality score Q elec is obtained in the following manner: Qelec＝α1·Sv(t)+α2·Sf(t)+α3·THD+C；Q elec =α 1 ·S v (t)+α 2 ·S f (t)+α 3 ·THD+C; 式中，α1、α2和α3分别表示电压稳定性因子Sv(t)、频率偏差因子Sf(t)和谐波总失真率THD的权重系数，C表示第一修正常数；Wherein, α 1 , α 2 and α 3 represent the weight coefficients of the voltage stability factor S v (t), the frequency deviation factor S f (t) and the total harmonic distortion rate THD respectively, and C represents the first correction constant; 预设电力评分阈值Qnormal，并将电力评分阈值Qnormal与电力质量综合评分Qelec进行对比分析，评估微电网是否发生故障，若Qelec≤Qnormal，则表明微电网未发生故障，无需进行干预；若Qelec＞Qnormal，则表明微电网发生故障，此时触发故障定位模块，对微电网进行故障定位。The power scoring threshold Q normal is preset, and the power scoring threshold Q normal is compared and analyzed with the comprehensive power quality score Q elec to evaluate whether the microgrid has a fault. If Q elec ≤Q normal , it indicates that the microgrid has not a fault and no intervention is required; if Q elec ＞Q normal , it indicates that the microgrid has a fault, and the fault location module is triggered to locate the fault of the microgrid. 5.根据权利要求4所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：所述故障定位模块用于在微电网中设置若干数据监测点，在微电网发生故障时，实时采集各个数据监测点的电压波形数据，其中，电压波形数据指电压信号的波形变化；5. A data mining system serving a microgrid control system according to claim 4, characterized in that: the fault location module is used to set a number of data monitoring points in the microgrid, and when a fault occurs in the microgrid, the voltage waveform data of each data monitoring point is collected in real time, wherein the voltage waveform data refers to the waveform change of the voltage signal; 依据获取的各个数据监测点电压波形数据，选择电压行波信号幅值变化最大的两个数据监测点A和B，并获取电压行波信号到达数据监测点A和B的时间差ΔtAB，并依据行波传播原理，随机从数据监测点A和B中选取出任意一个数据监测点，并计算数据监测点A和B中任意一个数据监测点与故障点间的距离d，具体计算方式如下：According to the voltage waveform data obtained at each data monitoring point, select the two data monitoring points A and B with the largest change in the amplitude of the voltage traveling wave signal, and obtain the time difference Δt AB between the voltage traveling wave signal reaching the data monitoring points A and B. According to the traveling wave propagation principle, randomly select any data monitoring point from the data monitoring points A and B, and calculate the distance d between any data monitoring point A and B and the fault point. The specific calculation method is as follows: 式中，vh表示行波的传播速度，ΔtAB表示行波到达数据监测点A和数据监测点B的时间差；In the formula, v h represents the propagation speed of the traveling wave, and Δt AB represents the time difference between the traveling wave reaching the data monitoring point A and the data monitoring point B; 依据微电网控制系统，获取微电网拓扑图，并在微电网拓扑图中标记数据监测点A和数据监测点B，结合数据监测点A和B中任意一个数据监测点与故障点间的距离d，在微电网拓扑图中定位故障点所在线路并标记故障点位置，并收集故障点所在线路的储能电池数据和逆变器信息，生成故障点设备集合G。According to the microgrid control system, the microgrid topology map is obtained, and the data monitoring point A and the data monitoring point B are marked in the microgrid topology map. Combined with the distance d between any data monitoring point A and B and the fault point, the line where the fault point is located is located in the microgrid topology map and the position of the fault point is marked. The energy storage battery data and inverter information of the line where the fault point is located are collected to generate the fault point device set G. 6.根据权利要求5所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：所述设备健康监测模块包括设备老化速率计算单元和健康状态分析单元；6. A data mining system serving a microgrid control system according to claim 5, characterized in that: the equipment health monitoring module comprises an equipment aging rate calculation unit and a health status analysis unit; 所述设备老化速率计算单元用于依据所述故障点设备集合G，对于故障点所在线路和故障点所在线路的储能电池和逆变器，依据微电网数据集合S和电力质量综合评分Qelec，使用线性回归算法构建储能电池老化模型和逆变器老化模型，所述储能电池老化模型具体表现形式如下：The device aging rate calculation unit is used to construct an energy storage battery aging model and an inverter aging model based on the fault point device set G, for the line where the fault point is located and the energy storage battery and inverter of the line where the fault point is located, according to the microgrid data set S and the comprehensive power quality score Q elec , using a linear regression algorithm. The specific expression of the energy storage battery aging model is as follows: 式中，表示当前时间点t时的储能电池老化速率，Qelec(t)表示当前时间点t时的电力质量综合评分，Tb(t)表示当前时间点t时的储能电池运行温度，SOC(t)表示当前时间点t时储能电池的电池荷电状态，k1、k2和k3表示回归系数；In the formula, represents the aging rate of the energy storage battery at the current time point t, Q elec (t) represents the comprehensive score of the power quality at the current time point t, T b (t) represents the operating temperature of the energy storage battery at the current time point t, SOC(t) represents the battery state of charge of the energy storage battery at the current time point t, k 1 , k 2 and k 3 represent regression coefficients; 所述逆变器老化模型具体表现形式如下：The inverter aging model is specifically expressed as follows: 式中，表示当前时间点t时的逆变器老化速率，Linv(t)表示当前时间点t时的逆变器负载率，Tinv(t)表示当前时间点t时的逆变器运行温度，m1、m2和m3表示回归系数；In the formula, represents the inverter aging rate at the current time point t, Linv (t) represents the inverter load rate at the current time point t, Tinv (t) represents the inverter operating temperature at the current time point t, m1 , m2 and m3 represent regression coefficients; 收集历史微电网运行数据，并将历史微电网运行数据划分为训练集和测试集，使用训练集输入储能电池老化模型和逆变器老化模型进行训练，并使用最小二乘法拟合储能电池老化模型和逆变器老化模型的参数，得到回归系数k1、k2、k3、m1、m2以及m3，并使用测试集验证储能电池老化模型和逆变器老化模型。Historical microgrid operation data are collected and divided into training set and test set. The training set is used to input the energy storage battery aging model and the inverter aging model for training. The least squares method is used to fit the parameters of the energy storage battery aging model and the inverter aging model to obtain the regression coefficients k 1 , k 2 , k 3 , m 1 , m 2 and m 3 , and the test set is used to verify the energy storage battery aging model and the inverter aging model. 7.根据权利要求6所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：所述健康状态分析单元用于依据训练后的储能电池老化模型和逆变器老化模型，获取储能电池老化速率和逆变器老化速率并计算储能电池健康评分SoHb(t)和逆变器健康评分Rinv(t)，并获取储能电池剩余使用时间RULb以及逆变器剩余使用时间RULinv，所述储能电池健康评分SoHb(t)和逆变器健康评分Rinv(t)计算方式为：7. A data mining system serving a microgrid control system according to claim 6, characterized in that: the health status analysis unit is used to obtain the aging rate of the energy storage battery based on the trained energy storage battery aging model and inverter aging model and inverter aging rate The energy storage battery health score SoH b (t) and the inverter health score R inv (t) are calculated, and the remaining use time RUL b of the energy storage battery and the remaining use time RUL inv of the inverter are obtained. The energy storage battery health score SoH b (t) and the inverter health score R inv (t) are calculated as follows: 式中，SoHb(t0)表示初始时间点t0时的储能电池健康评分，Rinv(t0)表示初始时间点t0时的逆变器健康评分，表示时间点τ时的储能电池老化速率，表示时间点τ时的逆变器老化速率，τ∈[t0，t]；In the formula, SoH b (t 0 ) represents the health score of the energy storage battery at the initial time point t 0 , R inv (t 0 ) represents the health score of the inverter at the initial time point t 0 , represents the aging rate of the energy storage battery at time point τ, represents the inverter aging rate at time point τ, τ∈[t 0 ,t]; 所述储能电池剩余使用时间RULb以及逆变器剩余使用时间RULinv获取方式为：The remaining usage time RUL b of the energy storage battery and the remaining usage time RUL inv of the inverter are obtained as follows: 式中，SoHb，critical表示储能电池健康评分临界值，Rinv，max表示逆变器健康评分最大值。Where, SoH b,critical represents the critical value of the energy storage battery health score, and R inv,max represents the maximum value of the inverter health score. 8.根据权利要求7所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：所述智能修复模块包括路径规划单元和故障修复单元；8. A data mining system serving a microgrid control system according to claim 7, characterized in that: the intelligent repair module includes a path planning unit and a fault repair unit; 所述路径规划单元用于依据微电网拓扑图，使用路径规划算法获取最优故障修复路径Popt，所述最优故障修复路径Popt具体获取方式如下：The path planning unit is used to obtain an optimal fault repair path P opt using a path planning algorithm according to the microgrid topology diagram. The optimal fault repair path P opt is specifically obtained in the following manner: 依据健康设备监测模块和微电网数据集合S，获取储能电池和逆变器的运行数据，包括储能电池剩余使用时间RULb、逆变器剩余使用时间RULinv、储能电池负载率LSOC、逆变器负载率Linv、储能电池健康评分SoHb(t)以及逆变器健康评分Rinv(t)；According to the health equipment monitoring module and the microgrid data set S, the operation data of the energy storage battery and the inverter are obtained, including the remaining use time of the energy storage battery RUL b , the remaining use time of the inverter RUL inv , the energy storage battery load rate L SOC , the inverter load rate L inv , the energy storage battery health score SoH b (t) and the inverter health score R inv (t); 将微电网拓扑图转换为微电网加权图F，所述微电网加权图F具体表现形式为：The microgrid topology diagram is converted into a microgrid weighted graph F, and the microgrid weighted graph F is specifically expressed as follows: F＝(N，E)；F = (N, E); 其中，N表示微电网中的节点，包括储能电池、逆变器和负载节点，E表示边，包括节点间的连接线路，其中，负载节点指电力消耗端，即需要供电的用电设备和用电区域；Where N represents the nodes in the microgrid, including energy storage batteries, inverters and load nodes, and E represents the edges, including the connection lines between nodes. The load nodes refer to the power consumption ends, that is, the power consumption equipment and power consumption areas that need power supply; 依据所述微电网加权图F，对于每个储能电池和逆变器，预设储能电池使用时间健康阈值T(RULb)min和逆变器使用时间健康阈值T(RULinv)min，并依据储能电池剩余使用时间RULb以及逆变器剩余使用时间RULinv，结合预设的储能电池使用时间健康阈值T(RULb)min和逆变器使用时间健康阈值T(RULinv)min，进行储能电池和逆变器筛选，保留RULb＞T(RULb)min和RULinv＞T(RULinv)min的储能电池和逆变器，作为备用设备；According to the microgrid weighted graph F, for each energy storage battery and inverter, a healthy threshold value T(RUL b ) min of the energy storage battery usage time and a healthy threshold value T(RUL inv ) min of the inverter usage time are preset, and according to the remaining usage time RUL b of the energy storage battery and the remaining usage time RUL inv of the inverter, combined with the preset healthy threshold value T(RUL b ) min of the energy storage battery usage time and the healthy threshold value T(RUL inv ) min of the inverter usage time, the energy storage batteries and inverters are screened, and the energy storage batteries and inverters with RUL b >T(RUL b ) min and RUL inv >T(RUL inv ) min are retained as backup equipment; 依据储能电池和逆变器的运行数据，计算每条边的权重，具体计算过程包括：The weight of each edge is calculated based on the operating data of the energy storage battery and inverter. The specific calculation process includes: 式中，RULb，i表示节点i的储能电池剩余使用时间，RULinv，i表示节点i的逆变器剩余使用时间，LSOC，i表示节点i的储能电池负载率，Linv，i表示节点i的逆变器负载率，Cremaining，ij表示节点i和节点j之间线路剩余传输容量，β、γ、δ、ε和∈表示权重系数；Where, RUL b,i represents the remaining service life of the energy storage battery at node i, RUL inv,i represents the remaining service life of the inverter at node i, L SOC,i represents the load rate of the energy storage battery at node i, L inv,i represents the load rate of the inverter at node i, C remaining,ij represents the remaining transmission capacity of the line between node i and node j, β, γ, δ, ε and ∈ represent weight coefficients; 使用Dijkstra最短路径算法，以微电网加权图G作为输入，进行路径搜索，并设定路径搜索目标为最小化路径总权重，选择路径总权重最小的路径作为最优故障修复路径Popt，所述最小化路径总权重具体表现形式为：The Dijkstra shortest path algorithm is used to perform path search with the microgrid weighted graph G as input, and the path search goal is set to minimize the total path weight. The path with the smallest total path weight is selected as the optimal fault repair path P opt . The specific form of minimizing the total path weight is: 式中，Wpath表示路径P的总权重，eij表示从节点i到节点j的边。Where W path represents the total weight of path P, and e ij represents the edge from node i to node j. 9.根据权利要求8所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：所述故障修复单元用于依据所述最优故障修复路径Popt，执行故障修复作业，其中，所述最优故障修复路径Popt包括起点设备、经过线路和终点负载，故障修复作业包括初始化修复任务、启用备用设备和切换线路，并实时监测故障修复作业后的微电网相关数据。9. A data mining system serving a microgrid control system according to claim 8, characterized in that: the fault repair unit is used to perform a fault repair operation according to the optimal fault repair path P opt , wherein the optimal fault repair path P opt includes a starting device, a passing line and an end load, and the fault repair operation includes initializing the repair task, enabling backup equipment and switching lines, and real-time monitoring of microgrid related data after the fault repair operation. 10.一种服务于微电网控制系统的数据挖掘方法，用于实现上述权利要求1～9任一项所述的一种服务于微电网控制系统的数据挖掘系统，其特征在于：包括以下步骤，10. A data mining method serving a microgrid control system, used to implement a data mining system serving a microgrid control system as claimed in any one of claims 1 to 9, characterized in that it comprises the following steps: 步骤一、实时收集微电网相关数据，并依据收集的微电网相关数据，构建微电网数据集合S；Step 1: Collect microgrid related data in real time, and construct a microgrid data set S based on the collected microgrid related data; 步骤二、依据所述微电网数据集合S，进行预处理，并依据预处理后的微电网数据集合S，进行汇总计算，获取电压稳定性因子Sv(t)、频率偏差因子Sf(t)以及谐波总失真率THD，并依据所述电压稳定性因子Sv(t)、频率偏差因子Sf(t)以及谐波总失真率THD，获取电力质量综合评分Qelec，并预设电力评分阈值Qnormal，将电力评分阈值Qnormal与电力质量综合评分Qelec进行对比分析，评估微电网是否发生故障，若Qelec＞Qnormal，则表明微电网发生故障，此时触发故障定位模块；Step 2: Preprocessing is performed based on the microgrid data set S, and summary calculation is performed based on the preprocessed microgrid data set S to obtain a voltage stability factor S v (t), a frequency deviation factor S f (t) and a total harmonic distortion rate THD, and a comprehensive power quality score Q elec is obtained based on the voltage stability factor S v (t), the frequency deviation factor S f (t) and the total harmonic distortion rate THD, and a power score threshold Q normal is preset, and the power score threshold Q normal is compared and analyzed with the comprehensive power quality score Q elec to evaluate whether a microgrid fault occurs. If Q elec >Q normal , it indicates that a microgrid fault occurs, and a fault location module is triggered at this time; 步骤三、在微电网中设置若干数据监测点，并收集数据监测点的电压波形数据，依据行波传播原理确定故障点位置，并获取故障点所在线路的储能电池和逆变器信息，生成故障点设备集合G；Step 3: Set up several data monitoring points in the microgrid, collect voltage waveform data at the data monitoring points, determine the fault point location based on the traveling wave propagation principle, obtain the energy storage battery and inverter information of the line where the fault point is located, and generate the fault point device set G; 步骤四、依据所述微电网数据集合S和电力质量综合评分Qelec，使用线性回归算法构建储能电池老化模型和逆变器老化模型，获取储能电池老化速率和逆变器老化速率并计算得到储能电池健康评分SoHb(t)和逆变器健康评分Rinv(t)，依据储能电池健康评分SoHb(t)和逆变器健康评分Rinv(t)，进行综合计算，获取储能电池剩余使用时间RULb以及逆变器剩余使用时间RULinv；Step 4: Based on the microgrid data set S and the comprehensive power quality score Q elec , a linear regression algorithm is used to construct an energy storage battery aging model and an inverter aging model to obtain the energy storage battery aging rate. and inverter aging rate And calculate the energy storage battery health score SoH b (t) and the inverter health score R inv (t), and perform comprehensive calculation based on the energy storage battery health score SoH b (t) and the inverter health score R inv (t) to obtain the remaining use time RUL b of the energy storage battery and the remaining use time RUL inv of the inverter; 步骤五、依据故障点设备集合G，获取故障点所在线路的储能电池剩余使用时间RULb以及逆变器剩余使用时间RULinv，进行设备筛选，获取备用设备，并使用Dijkstra最短路径算法，获取从备用设备起点到故障点的最优故障修复路径Popt，并依据最优故障修复路径Popt进行故障修复。Step 5: According to the fault point device set G, the remaining service life RUL b of the energy storage battery and the remaining service life RUL inv of the inverter of the line where the fault point is located are obtained, and the equipment is screened to obtain the backup equipment. The Dijkstra shortest path algorithm is used to obtain the optimal fault repair path P opt from the starting point of the backup equipment to the fault point, and the fault is repaired according to the optimal fault repair path P opt .
CN202510088576.6A 2025-01-21 2025-01-21 A data mining method and system serving microgrid control system Pending CN120104663A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510088576.6A CN120104663A (en) 2025-01-21 2025-01-21 A data mining method and system serving microgrid control system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510088576.6A CN120104663A (en) 2025-01-21 2025-01-21 A data mining method and system serving microgrid control system

Publications (1)

Publication Number Publication Date
CN120104663A true CN120104663A (en) 2025-06-06

Family

ID=95880065

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510088576.6A Pending CN120104663A (en) 2025-01-21 2025-01-21 A data mining method and system serving microgrid control system

Country Status (1)

Country Link
CN (1) CN120104663A (en)

Similar Documents

Publication Publication Date Title
CN116069079B (en) Intelligent heat dissipation control method and system for intelligent switch cabinet
JP6467186B2 (en) System and method for detecting, correcting, and inspecting bad data in a data stream
CN101493491B (en) Substation ground network defect synthesis diagnosis method and diagnosis system thereof
KR101327225B1 (en) Fault diagnosis method of grid-connected photovoltaic system and apparatus thereof
WO2018028005A1 (en) Fault detection algorithm for battery panel in large-scale photovoltaic power station
CN110311709B (en) Fault judgment method for electricity consumption information acquisition system
JP2023500167A (en) Method and apparatus for recognizing operating state of photovoltaic string and storage medium
CN118839866B (en) Power line state evaluation method and system based on artificial intelligence
CN117078017A (en) An intelligent decision-making analysis system for power grid equipment monitoring
CN110689252A (en) Capacitive voltage transformer metering error situation sensing system
CN119382168B (en) Transient voltage instability identification method based on Koopman operator
CN117674249A (en) A fault self-healing control and evaluation method for distribution network containing distributed photovoltaics
CN119944624A (en) Power quality monitoring system and method for distributed photovoltaic grid-connected distribution network
CN109613372B (en) Power grid fault diagnosis method based on multi-element power grid database
CN117394311B (en) A distribution network resilience assessment and emergency control method based on multi-source information fusion
CN117150216B (en) Regression analysis method and system for power data
CN103928923B (en) A kind of network stationary power quality method for early warning based on sensitivity analysis
CN120074012B (en) Low-voltage power distribution cabinet monitoring method and system comprising electric leakage monitoring
CN118157325B (en) Real-time monitoring method and system for new energy power
CN120104663A (en) A data mining method and system serving microgrid control system
CN118413000A (en) A digital-analog integrated substation relay protection load test system
Bozorg et al. Model-less/Measurement-based computation of voltage sensitivities in unbalanced electrical distribution networks: experimental validation
CN119154799B (en) A method for detecting the adaptability of photovoltaic power generation to weak grid
CN119408439B (en) Electric vehicle charging safety monitoring method and device
CN120705807A (en) DC transmission data processing method, system and equipment based on multimodal data fusion

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination