WO2022021726A1 - 一种基于pmu的电力系统状态估计性能评价方法 - Google Patents

一种基于pmu的电力系统状态估计性能评价方法 Download PDF

Info

Publication number
WO2022021726A1
WO2022021726A1 PCT/CN2020/134406 CN2020134406W WO2022021726A1 WO 2022021726 A1 WO2022021726 A1 WO 2022021726A1 CN 2020134406 W CN2020134406 W CN 2020134406W WO 2022021726 A1 WO2022021726 A1 WO 2022021726A1
Authority
WO
WIPO (PCT)
Prior art keywords
power system
state estimation
pmu
performance evaluation
value
Prior art date
Application number
PCT/CN2020/134406
Other languages
English (en)
French (fr)
Inventor
谢伟
陆超
宋文超
华斌
方陈
林俊杰
Original Assignee
国网上海市电力公司
清华大学
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 国网上海市电力公司, 清华大学 filed Critical 国网上海市电力公司
Priority to AU2020327340A priority Critical patent/AU2020327340B2/en
Publication of WO2022021726A1 publication Critical patent/WO2022021726A1/zh

Links

Images

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • 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
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • 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
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/22—Flexible AC transmission systems [FACTS] or power factor or reactive power compensating or correcting units

Definitions

  • the invention relates to a power system state estimation performance evaluation technology, in particular to a PMU-based power system state estimation performance evaluation method.
  • the power system state estimation performance evaluation method is a key technology for power system operation and control. It can measure key information such as the accuracy of the state estimation result. An accurate and reasonable state estimation result can ensure the correct operation and control of the power system.
  • the linear state estimation based on phasor measurement unit (PMU) can better reflect the current state of the system.
  • PMU error is a key issue that affects the accuracy of linear state estimation. In practical research, it is usually considered that the PMU error obeys a Gaussian distribution.
  • the main indicator for evaluating the performance of state estimation is the pass rate ⁇ , which is defined as:
  • m is the measurement quantity
  • ri is the measurement residual of the measurement point i
  • ⁇ i is the threshold
  • the purpose of the present invention is to provide a PMU-based power system state estimation performance evaluation method in order to overcome the above-mentioned defects in the prior art, which has high accuracy, simple and convenient operation, and saves manpower.
  • a PMU-based power system state estimation performance evaluation method specifically:
  • the measurement values S m of n 2 observation objects are actually measured by the n 2 PMUs of the power system, and the observation objects include one or more of voltage amplitude, voltage phase angle, current amplitude and current phase angle, Obtain the state estimation value S se of each S m through state estimation, input the n 2 groups of S m and S se correspondingly to the n 2 groups of trained classification models, and use the S m and S se given by the n 2 classification models to divide Standard, correspondingly obtain n 2 marked values ⁇ m , calculate the state estimation performance evaluation index ⁇ , and the calculation formula is:
  • p mi and ⁇ mi are the ith classification accuracy p m and the ith label value ⁇ m respectively, and the calculation formula of p m is:
  • n r and n f are the number of correct classifications and the number of incorrect classifications after the classification model is trained;
  • E(X) is the expectation of X
  • var(X) is the variance of X
  • x j is the jth measurement error in X.
  • K is the Gaussian kernel function
  • h is the kernel density estimation window width
  • x j is the jth observation data in X
  • n 1 is the number of samples of X
  • the present invention has the following beneficial effects:
  • the present invention obtains the error characteristics of the PMU measurement data through the power system simulation platform, then superimposes the error characteristics on the true value of the observation object, theoretically calculates the measurement value of the observation object, and forms the training data of the classification model, and finally at a new time
  • the object measurement values and corresponding state estimates of each node of the power system are obtained on the cross-section, and several groups of classification models are input and trained.
  • the state estimation performance evaluation index ⁇ is calculated, and the topology analysis is carried out in combination with the power system simulation platform and machine learning training. It solves the problem of the unknowability of the real state of the power system, and the evaluation results are more objective and accurate. At the same time, it does not require a large number of on-site measured data of the power system, which is easy to operate, saves manpower and material resources, and reduces costs;
  • FIG. 1 is a flow chart of the method of the present invention.
  • a PMU-based power system state estimation performance evaluation method as shown in Figure 1, is as follows:
  • each monitoring node is equipped with a PMU.
  • the measurement error data set X of the observation object is obtained through the PMU of the power system simulation platform, and the data set is normalized and calculated.
  • Probability Density Function of X Including the distribution characteristics of PMU measurement error, the true value S t of n 2 groups of observation objects is obtained through the power system simulation platform, and the true value S t of n 2 groups of observation objects is obtained by stacking S t and Theoretically obtain n 2 groups of S m , obtain the state estimated value S se of each S m through state estimation, and judge whether each group of S t , S m and S se satisfies the judgment formula, and if so, the corresponding mark value with a value of 1 is generated ⁇ m , otherwise ⁇ m with a value of 0 is generated, and the judgment formula is as follows:
  • Si m , Si t and Si se are respectively S m , S t and S se of the i-th node;
  • n 2 groups of S t , S m , S se and ⁇ m are used as training data to perform SVM training, and the training kernel function is a Gaussian kernel function, corresponding to n 2 A trained SVM model;
  • n 2 PMUs of the power system actually measure the measured value S m of n 2 observation objects, and the observation objects are voltage amplitude and voltage phase angle, that is, S m includes the measured value of voltage amplitude and voltage
  • the phase angle measurement value obtain the state estimated value S se of each S m through state estimation, input the n 2 groups of S m and S se correspondingly to the n 2 groups of trained classification models, and use the S given by the n 2 classification models.
  • the division criteria of m and S se correspond to n 2 marked values ⁇ m , and the state estimation performance evaluation index ⁇ is calculated.
  • the calculation formula is:
  • p mi and ⁇ mi are the ith classification accuracy p m and the ith label value ⁇ m respectively, and the calculation formula of p m is:
  • n r and n f are the number of correct classifications and the number of incorrect classifications after the classification model is trained;
  • the calculation process of the state estimation is an optimization solution process based on the weighted least squares method, and the calculation formula is as follows:
  • H is the measurement equation, establishing the relationship between S m and S t , w is the measurement error, W is the weight matrix, which is a diagonal sparse matrix, and the diagonal elements are the reciprocal of the corresponding measurement error variance.
  • the acquisition process of the measurement error dataset X is:
  • E(X) is the expectation of X
  • var(X) is the variance of X
  • x j is the jth measurement error in X.
  • K is the Gaussian kernel function
  • h is the kernel density estimation window width
  • x j is the jth observation data in X
  • n 1 is the number of samples of X
  • ⁇ is the standard deviation of X
  • R is the interquartile range of X
  • N is the number of observations in X. If the value of h is too large, or decrease precision, if the value of h is too small, it will cause The fluctuation is large and discontinuous, and the error is large.
  • This embodiment proposes a PMU-based power system state estimation performance evaluation method.
  • the error characteristics of the PMU measurement data are obtained through the power system simulation platform, and then the error characteristics are superimposed on the true value of the observation object, and the measurement of the observation object is theoretically calculated. value, constitute the training data of the SVM model, and finally obtain the object measurement value and the corresponding state estimation value of each node of the power system on the new time section, and input and train several groups of SVM models, and finally calculate the state estimation performance evaluation index ⁇ , does not require a large amount of on-site measured data of the power system, combined with the power system simulation platform and machine learning training for topology analysis, the evaluation results are more objective and accurate.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Power Engineering (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Tourism & Hospitality (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Public Health (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

一种基于PMU的电力系统状态估计性能评价方法，具体为：通过电力系统的PMU实际测得观测对象测量值Sm，获取Sm的状态估计值Sse，将Sm和Sse输入训练好的分类模型，得到分类准确度以及标记值并计算状态估计性能评价指标，训练过程为：通过电力系统仿真平台获取观测对象的测量误差数据集X，对X进行归一化处理并计算X的概率密度函数(I)通过电力系统仿真平台获取St，叠加St和 (I)求得Sm，获取各个Sm的状态估计值Sse，α m取0或1，利用St、Sm、Sse和αm训练分类模型。与现有技术相比，本技术方案具有准确性高、操作简便和节省人力等优点。

Description

一种基于PMU的电力系统状态估计性能评价方法 技术领域
本发明涉及一种力系统状态估计性能评价技术，尤其是涉及一种基于PMU的电力系统状态估计性能评价方法。
背景技术
电力系统状态估计性能评价方法是电力系统运行和控制的关键技术，可以衡量状态估计结果的精度等关键信息，准确合理的状态估计结果可以保证电力系统的正确运行和控制。随着大量可再生能源并网，输电网络复杂以及负荷多样化，电力系统的运行方式迅速变化。基于相量测量单元(PMU)的线性状态估计可以更好地反映系统的当前状态。但是，PMU误差是影响线性状态估计精度的关键问题。在实际研究中，通常认为PMU误差服从高斯分布。但是，影响PMU测量数据精度的因素众多，主要有电压互感器和电流互感器的幅值误差和相角误差、电缆通道传输误差以及同步时钟误差。因此，PMU误差应遵循更复杂的分布。同时，在实际电力系统中，PMU测量点真值和电力系统的真实状态均不可获取，因此实际电力系统中的状态估计性能难以评估。
目前，评估状态估计性能的主要指标为合格率η，其定义为：
Figure PCTCN2020134406-appb-000001
Figure PCTCN2020134406-appb-000002
其中，m是量测数量，r i量测点i的量测残差，为ε i为阈值；
但是合格率取决于区分合格与否的阈值ε i，ε i为根据工程经验设定的常数，没有实际的理论基础；
同时还有研究利用信息论中交叉熵的概念作为状态估计性能评估标准，但其仅反映测量值和估计值之间的关系，并不涉及电力系统的真实状态。
发明内容
本发明的目的就是为了克服上述现有技术存在的缺陷而提供一种基于PMU的电力系统状态估计性能评价方法，准确性高，操作简便，节省人力。
本发明的目的可以通过以下技术方案来实现：
一种基于PMU的电力系统状态估计性能评价方法，具体为：
通过电力系统的n 2个PMU实际测得n 2个观测对象测量值S m，所述的观测对象包括电压幅值、电压相角、电流幅值和电流相角中的一种或多种，通过状态估计获取各个S m的状态估计值S se，将n 2组S m和S se分别对应输入n 2组训练好的分类模型，利用n 2个分类模型给出的S m和S se划分标准，对应得到n 2个标记值α m，计算状态估计性能评价指标λ，计算公式为：
Figure PCTCN2020134406-appb-000003
其中，p mi和α mi分别为第i个分类准确度p m和第i个标记值α m，所述的p m的计算公式为：
Figure PCTCN2020134406-appb-000004
其中，n r和n f分别为分类模型完成训练后的分类正确数量和分类错误数量；
其中，所述的n 2组分类模型的训练过程为：
通过电力系统仿真平台的PMU获取观测对象的测量误差数据集X，为了便于分析与比较，对该X进行归一化处理，并计算X的概率密度函数
Figure PCTCN2020134406-appb-000005
通过电力系统仿真平台获取n 2组观测对象真值S t，通过叠加S t和
Figure PCTCN2020134406-appb-000006
理论求得n 2组S m，通过状态估计获取各个S m的状态估计值S se，判断每组S t、S m和S se是否满足判断公式，若满足则对应生成值为1的标记值α m，否则生成值为0的α m，所述的判断公式如下：
|Si m-Si t|＞|Si se-Si t|
其中Si m、Si t和Si se分别为第i组S m、第i组S t和第i组S se；
将n 2组S t、S m、S se和α m作为训练数据，进行分类模型训练，对应获得n 2个分类模型。
进一步地，所述的分类模型包括SVM模型、二叉树模型或神经网络模型，训练分类模型的核函数为高斯核函数。
进一步地，所述的测量误差数据集X的获取过程为：
通过电力系统仿真平台的节点上的PMU测得观测对象观测值S m，通过仿真软件查询电力系统仿真平台上节点的S t，通过计算S m和S t的差值求得测量误差，由若干组测量误构成X。
进一步地，所述的归一化处理的公式为：
Figure PCTCN2020134406-appb-000007
其中，
Figure PCTCN2020134406-appb-000008
为第j个归一化后的测量误差，E(X)为X的期望，var(X)为X的方差，x j为X中的第j个测量误差。
进一步地，所述的
Figure PCTCN2020134406-appb-000009
的计算公式如下：
Figure PCTCN2020134406-appb-000010
其中，K为高斯核函数，h为核密度估计窗宽，x j为X中的第j个观测数据，n 1为X的样本数量；
所述的核密度估计窗宽h的计算公式为：
Figure PCTCN2020134406-appb-000011
其中，σ是X的标准差，R为X的四分位距，N为X中观测数据的数量，如果h取值过大，或降低
Figure PCTCN2020134406-appb-000012
的精度，如果h取值过小，会导致
Figure PCTCN2020134406-appb-000013
起伏大且不连续，误差大。
进一步地，所述的状态估计算法能够减小测量误差，增加量测数据准确性和可用率，其基本思想基于加权最小二乘法，求解一个优化问题：
Figure PCTCN2020134406-appb-000014
s.t.S m＝H(S t)+w
其中，H为量测方程，所述的H建立S m和S t的关系，w为量测误差，W为权重矩阵，所述的W为对角稀疏矩阵，对角线元素为对应量测误差方差的倒数。
与现有技术相比，本发明具有以如下有益效果：
(1)本发明通过电力系统仿真平台获取PMU测量数据的误差特性，然后在观测对象真值上叠加该误差特性，理论计算出观测对象测量值，组成分类模型的训练数据，最后在新的时间断面上获取电力系统各个节点的对象测量值和对应的状态估计值，并输入训练好若干组分类模型，最后计算出状态估计性能评价指标λ，结 合电力系统仿真平台和机器学习训练进行拓扑分析，解决了电力系统真实状态的不可知性的问题，评估结果更加客观和准确，同时不需要大量的电力系统的现场实测数据，操作简便，节省人力和物力，降低成本；
(2)本发明可采用SVM模型、二叉树模型或神经网络模型作为分类模型，应用范围广。
附图说明
图1为本发明的方法流程图。
具体实施方式
下面结合附图和具体实施例对本发明进行详细说明。本实施例以本发明技术方案为前提进行实施，给出了详细的实施方式和具体的操作过程，但本发明的保护范围不限于下述的实施例。
一种基于PMU的电力系统状态估计性能评价方法，如图1，具体为：
电力系统上设有n 2个监测节点，每个监测节点上设有PMU，通过电力系统仿真平台的PMU获取观测对象的测量误差数据集X，并对该数据集进行归一化处理，并计算X的概率密度函数
Figure PCTCN2020134406-appb-000015
包含了PMU测量误差分布特性，通过电力系统仿真平台获取n 2组观测对象真值S t，通过叠加S t和
Figure PCTCN2020134406-appb-000016
理论求得n 2组S m，通过状态估计获取各个S m的状态估计值S se，判断每组S t、S m和S se是否满足判断公式，若满足则对应生成值为1的标记值α m，否则生成值为0的α m，判断公式如下：
|Si m-Si t|＞|Si se-Si t|
其中Si m、Si t和Si se分别为第i个节点的S m、S t和S se；
由于无法获取实际的电力系统的观测对象真值，故将n 2组S t、S m、S se和α m作为训练数据，进行SVM训练，训练的核函数为高斯核函数，对应获得n 2个训练好的SVM模型；
在需要评估的时间断面上通过电力系统的n 2个PMU实际测得n 2个观测对象测量值S m，观测对象为电压幅值和电压相角，即S m包括电压幅值测量值和电压相角测量值，通过状态估计获取各个S m的状态估计值S se，将n 2组S m和S se分别对应输入n 2组训练好的分类模型，利用n 2个分类模型给出的S m和S se划分标准，对应得到n 2个标记值α m，计算状态估计性能评价指标λ，计算公式为：
Figure PCTCN2020134406-appb-000017
其中，p mi和α mi分别为第i个分类准确度p m和第i个标记值α m，p m的计算公式为：
Figure PCTCN2020134406-appb-000018
其中，n r和n f分别为分类模型完成训练后的分类正确数量和分类错误数量；
状态估计的计算过程为基于加权最小二乘法的优化求解过程，计算公式如下：
Figure PCTCN2020134406-appb-000019
s.t.S m＝H(S t)+w
其中，H为量测方程，建立S m和S t的关系，w为量测误差，W为权重矩阵，为对角稀疏矩阵，对角线元素为对应量测误差方差的倒数。
测量误差数据集X的获取过程为：
通过电力系统仿真平台的节点上的PMU测得观测对象观测值S m，通过仿真软件查询电力系统仿真平台上节点的S t，通过计算S m和S t的差值求得测量误差，由若干组测量误构成X。
归一化处理的公式为：
Figure PCTCN2020134406-appb-000020
其中，
Figure PCTCN2020134406-appb-000021
为第j个归一化后的测量误差，E(X)为X的期望，var(X)为X的方差，x j为X中的第j个测量误差。
Figure PCTCN2020134406-appb-000022
的计算公式如下：
Figure PCTCN2020134406-appb-000023
其中，K为高斯核函数，h为核密度估计窗宽，x j为X中的第j个观测数据，n 1为X的样本数量；
核密度估计窗宽h的计算公式为：
Figure PCTCN2020134406-appb-000024
其中，σ是X的标准差，R为X的四分位距，N为X中观测数据的数量，如果h取值过大，或降低
Figure PCTCN2020134406-appb-000025
的精度，如果h取值过小，会导致
Figure PCTCN2020134406-appb-000026
起伏大且不连续， 误差大。
本实施例提出了一种基于PMU的电力系统状态估计性能评价方法，首先通过电力系统仿真平台获取PMU测量数据的误差特性，然后在观测对象真值上叠加该误差特性，理论计算出观测对象测量值，组成SVM模型的训练数据，最后在新的时间断面上获取电力系统各个节点的对象测量值和对应的状态估计值，并输入训练好若干组SVM模型，最后计算出状态估计性能评价指标λ，不需要大量的电力系统的现场实测数据，结合电力系统仿真平台和机器学习训练进行拓扑分析，评估结果更加客观和准确。
以上详细描述了本发明的较佳具体实施例。应当理解，本领域的普通技术人员无需创造性劳动就可以根据本发明的构思作出诸多修改和变化。因此，凡本技术领域中技术人员依本发明的构思在现有技术的基础上通过逻辑分析、推理或者有限的实验可以得到的技术方案，皆应在由权利要求书所确定的保护范围内。

Claims (10)

  1. 一种基于PMU的电力系统状态估计性能评价方法，其特征在于，具体为：
    通过电力系统的n 2个PMU实际测得n 2个观测对象测量值S m，通过状态估计获取各个S m的状态估计值S se，将n 2组S m和S se分别对应输入n 2组训练好的分类模型，对应得到n 2个标记值α m，计算状态估计性能评价指标λ，计算公式为：
    Figure PCTCN2020134406-appb-100001
    其中，p mi和α mi分别为第i个分类准确度p m和第i个标记值α m，所述的p m的计算公式为：
    Figure PCTCN2020134406-appb-100002
    其中，n r和n f分别为分类模型完成训练后的分类正确数量和分类错误数量；
    其中，所述的n 2组分类模型的训练过程为：
    通过电力系统仿真平台的PMU获取观测对象的测量误差数据集X，并对X进行归一化处理，并计算X的概率密度函数
    Figure PCTCN2020134406-appb-100003
    通过电力系统仿真平台获取n 2组观测对象真值S t，通过叠加S t和
    Figure PCTCN2020134406-appb-100004
    理论求得n 2组S m，通过状态估计获取各个S m的状态估计值S se，判断每组S t、S m和S se是否满足判断公式，若满足则对应生成值为1的标记值α m，否则生成值为0的α m，所述的判断公式如下：
    |Si m-Si t|＞|Si se-Si t|
    其中Si m、Si t和Si se分别为第i组S m、第i组S t和第i组S se；
    利用n 2组S t、S m、S se和α m进行分类模型训练，对应获得n 2个分类模型。
  2. 根据权利要求1所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，所述的状态估计的计算公式为：
    Figure PCTCN2020134406-appb-100005
    s.t.S m＝H(S t)+w
    其中，H为量测方程，w为量测误差，W为权重矩阵。
  3. 根据权利要求1所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，所述的
    Figure PCTCN2020134406-appb-100006
    的计算公式如下：
    Figure PCTCN2020134406-appb-100007
    其中，K为核密度函数，h为核密度估计窗宽，x j为X中的第j个观测数据，n 1为X的样本数量。
  4. 根据权利要求3所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，所述的核密度估计窗宽h的计算公式为：
    Figure PCTCN2020134406-appb-100008
    其中，σ是X的标准差，R为X的四分位距，N为X中观测数据的数量。
  5. 根据权利要求3所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，所述的K为高斯核函数。
  6. 根据权利要求1所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，所述的观测对象包括电压幅值、电压相角、电流幅值和电流相角中的一种或多种。
  7. 根据权利要求1所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，训练所述分类模型的核函数为高斯核函数。
  8. 根据权利要求1所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，所述的测量误差数据集X的获取过程为：
    通过电力系统仿真平台的PMU测得观测对象观测值S m，通过电力系统仿真平台查询观测对象真值S t，通过计算S m和S t的差值求得测量误差，由若干组测量误构成X。
  9. 根据权利要求1所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，所述的归一化处理的公式为：
    Figure PCTCN2020134406-appb-100009
    其中，
    Figure PCTCN2020134406-appb-100010
    为第j个归一化后的测量误差，E(X)为X的期望，var(X)为X的方差，x j为X中的第j个测量误差。
  10. 根据权利要求1所述的一种基于PMU的电力系统状态估计性能评价方法，其特征在于，所述的分类模型包括SVM模型、二叉树模型或神经网络模型。
PCT/CN2020/134406 2020-07-29 2020-12-08 一种基于pmu的电力系统状态估计性能评价方法 WO2022021726A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2020327340A AU2020327340B2 (en) 2020-07-29 2020-12-08 Method for evaluating state estimation performance of power system based on PMU

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010746249.2 2020-07-29
CN202010746249.2A CN111900731B (zh) 2020-07-29 2020-07-29 一种基于pmu的电力系统状态估计性能评价方法

Publications (1)

Publication Number Publication Date
WO2022021726A1 true WO2022021726A1 (zh) 2022-02-03

Family

ID=73182638

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/134406 WO2022021726A1 (zh) 2020-07-29 2020-12-08 一种基于pmu的电力系统状态估计性能评价方法

Country Status (3)

Country Link
CN (1) CN111900731B (zh)
AU (1) AU2020327340B2 (zh)
WO (1) WO2022021726A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110705887A (zh) * 2019-10-10 2020-01-17 国网湖北省电力有限公司计量中心 一种基于神经网络模型的低压台区运行状态综合评价方法
CN115379551A (zh) * 2022-08-19 2022-11-22 合肥联信电源有限公司 一种应用于储能式应急电源的时钟校准方法
CN115480204A (zh) * 2022-09-29 2022-12-16 武汉格蓝若智能技术有限公司 基于大数据推演的电流互感器运行误差在线评估优化方法
CN115859690A (zh) * 2023-02-15 2023-03-28 西安热工研究院有限公司 一种设备电磁威胁的多等级qmu评估方法及系统
CN115906353A (zh) * 2022-11-17 2023-04-04 国网上海市电力公司 一种基于节点评估的配电网pmu优化配置方法
CN116840765A (zh) * 2023-08-31 2023-10-03 武汉格蓝若智能技术股份有限公司 一种基于多元时序分析的电压互感器误差状态评估方法
CN117039893A (zh) * 2023-10-09 2023-11-10 国网天津市电力公司电力科学研究院 配电网状态确定方法、装置及电子设备

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111900731B (zh) * 2020-07-29 2021-10-08 国网上海市电力公司 一种基于pmu的电力系统状态估计性能评价方法

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101615213A (zh) * 2009-07-21 2009-12-30 清华大学 基于扩展不确定度的电力系统状态估计结果评价方法
CN108182257A (zh) * 2017-12-29 2018-06-19 东北电力大学 一种基于区域密度统计方法优化的gsa不良数据检测与辨识方法
CN110490378A (zh) * 2019-08-07 2019-11-22 中国南方电网有限责任公司 基于云scada大数据的电网状态估计精度的计算方法
CN110543720A (zh) * 2019-09-03 2019-12-06 北京交通大学 基于sdae-elm伪量测模型的状态估计方法
CN110942109A (zh) * 2019-12-17 2020-03-31 浙江大学 一种基于机器学习的pmu防御虚假数据注入攻击方法
US10635519B1 (en) * 2017-11-30 2020-04-28 Uptake Technologies, Inc. Systems and methods for detecting and remedying software anomalies
CN111221811A (zh) * 2020-02-15 2020-06-02 光一科技股份有限公司 一种基于集抄系统的低压配电网络线路参数估计方法
CN111900731A (zh) * 2020-07-29 2020-11-06 国网上海市电力公司 一种基于pmu的电力系统状态估计性能评价方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011156403A1 (en) * 2010-06-07 2011-12-15 Abb Research Ltd. Systems and methods for power line event zone identification
GB201314611D0 (en) * 2013-08-15 2013-10-02 Univ The Of Birmingham Power system control
CN103489009B (zh) * 2013-09-17 2016-08-17 北方信息控制集团有限公司 基于自适应修正神经网络的模式识别方法
CN104866714A (zh) * 2015-05-14 2015-08-26 同济大学 一种电力系统自适应核密度抗差状态估计方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101615213A (zh) * 2009-07-21 2009-12-30 清华大学 基于扩展不确定度的电力系统状态估计结果评价方法
US10635519B1 (en) * 2017-11-30 2020-04-28 Uptake Technologies, Inc. Systems and methods for detecting and remedying software anomalies
CN108182257A (zh) * 2017-12-29 2018-06-19 东北电力大学 一种基于区域密度统计方法优化的gsa不良数据检测与辨识方法
CN110490378A (zh) * 2019-08-07 2019-11-22 中国南方电网有限责任公司 基于云scada大数据的电网状态估计精度的计算方法
CN110543720A (zh) * 2019-09-03 2019-12-06 北京交通大学 基于sdae-elm伪量测模型的状态估计方法
CN110942109A (zh) * 2019-12-17 2020-03-31 浙江大学 一种基于机器学习的pmu防御虚假数据注入攻击方法
CN111221811A (zh) * 2020-02-15 2020-06-02 光一科技股份有限公司 一种基于集抄系统的低压配电网络线路参数估计方法
CN111900731A (zh) * 2020-07-29 2020-11-06 国网上海市电力公司 一种基于pmu的电力系统状态估计性能评价方法

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110705887A (zh) * 2019-10-10 2020-01-17 国网湖北省电力有限公司计量中心 一种基于神经网络模型的低压台区运行状态综合评价方法
CN115379551A (zh) * 2022-08-19 2022-11-22 合肥联信电源有限公司 一种应用于储能式应急电源的时钟校准方法
CN115379551B (zh) * 2022-08-19 2024-05-17 合肥联信电源有限公司 一种应用于储能式应急电源的时钟校准方法
CN115480204A (zh) * 2022-09-29 2022-12-16 武汉格蓝若智能技术有限公司 基于大数据推演的电流互感器运行误差在线评估优化方法
CN115906353A (zh) * 2022-11-17 2023-04-04 国网上海市电力公司 一种基于节点评估的配电网pmu优化配置方法
CN115906353B (zh) * 2022-11-17 2023-08-08 国网上海市电力公司 一种基于节点评估的配电网pmu优化配置方法
CN115859690A (zh) * 2023-02-15 2023-03-28 西安热工研究院有限公司 一种设备电磁威胁的多等级qmu评估方法及系统
CN116840765A (zh) * 2023-08-31 2023-10-03 武汉格蓝若智能技术股份有限公司 一种基于多元时序分析的电压互感器误差状态评估方法
CN116840765B (zh) * 2023-08-31 2023-11-07 武汉格蓝若智能技术股份有限公司 一种基于多元时序分析的电压互感器误差状态评估方法
CN117039893A (zh) * 2023-10-09 2023-11-10 国网天津市电力公司电力科学研究院 配电网状态确定方法、装置及电子设备
CN117039893B (zh) * 2023-10-09 2024-01-26 国网天津市电力公司电力科学研究院 配电网状态确定方法、装置及电子设备

Also Published As

Publication number Publication date
CN111900731B (zh) 2021-10-08
AU2020327340B2 (en) 2022-03-24
CN111900731A (zh) 2020-11-06
AU2020327340A1 (en) 2022-02-17

Similar Documents

Publication Publication Date Title
WO2022021726A1 (zh) 一种基于pmu的电力系统状态估计性能评价方法
CN110417011B (zh) 一种基于互信息与迭代随机森林的在线动态安全评估方法
CN109308571B (zh) 配电线路线变关系检测方法
CN111628494B (zh) 一种基于逻辑回归法的低压配电网拓扑识别方法及系统
CN109088407B (zh) 基于深度信念网络伪量测建模的配电网状态估计方法
CN108336739A (zh) 一种基于rbf神经网络的概率潮流在线计算方法
Minli et al. Research on the application of artificial neural networks in tender offer for construction projects
CN110363334B (zh) 基于灰色神经网络模型的光伏并网的电网线损预测方法
CN107741578A (zh) 一种用于智能电能表运行误差远程校准的原始抄表数据处理方法
CN108520310A (zh) 基于G-L混合噪声特性v-支持向量回归机的风速预报方法
CN109711435A (zh) 一种基于遗传算法的支持向量机在线电压稳定性监测方法
CN110674984A (zh) 一种基于Tri-Training-Lasso-BP网络的静态电压稳定裕度预测方法
CN106372440B (zh) 一种并行计算的配电网自适应抗差状态估计方法及装置
CN113612237A (zh) 一种在海上风电场中定位谐振诱发的次同步振荡源的方法
CN116432123A (zh) 一种基于cart决策树算法的电能表故障预警方法
CN104021315A (zh) 基于bp神经网络的电厂厂用电率计算方法
CN115146538A (zh) 基于消息传递图神经网络的电力系统状态估计方法
CN114662989A (zh) 电力系统的暂态稳定自适应评估方法及装置
CN107204616B (zh) 基于自适应稀疏伪谱法的电力系统随机状态估计方法
CN109684749B (zh) 一种考虑运行特性的光伏电站等值建模方法
CN114462684B (zh) 耦合数值天气预报与实测数据的风速多点同步预测方法
Jiang et al. Discharge estimation based on machine learning
CN116702629B (zh) 一种具备可迁移能力的电力系统暂态稳定评估方法
Wang et al. Reliability Assessment Study of Typical Connection Mode Medium Voltage Distribution Networks using Neural Network based on MIV and MEA
Guo et al. Power engineering cost prediction based on Fuzzy Neural Network

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2020327340

Country of ref document: AU

Date of ref document: 20201208

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20947622

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20947622

Country of ref document: EP

Kind code of ref document: A1