Power grid information fusion system state evaluation method and device, terminal and storage medium

Abstract

The application discloses a kind of power system state monitoring and evaluation technical field, a kind of power grid signal fusion system state evaluation method, device, terminal and storage medium, to solve the problem of single dimension limited to physical side or information side in prior art, there is no unified signal fusion index system;Evaluation standard calculation method is single and threshold fixed.The application includes according to the normalization data and pre-constructed power grid signal fusion system operation state evaluation index system, based on diversified threshold setting method, determine the evaluation threshold of each evaluation index;According to the normalization data, based on analytic hierarchy process and entropy weight method, determine the maximum weight of each evaluation index, evaluate the operation state of power grid signal fusion system;The application constructs comprehensive evaluation index system;The system can reflect physical system operation state and information system operation state simultaneously, realize the all-round evaluation of power grid signal fusion system.

Description

TECHNICAL FIELD

[0001] The present application relates to a power grid cyber-physical system state evaluation method and device, a terminal and a storage medium, and belongs to the technical field of power system state monitoring and evaluation. BACKGROUND

[0002] With the continuous expansion of the power grid scale and the rapid development of information technology, the intelligentization and informatization level of the power grid system is continuously improved, and a "cyber-physical fusion system" (i.e., a power grid cyber-physical fusion system) with deep coupling between the physical system and the information system is gradually formed. Under this background, the coordinated operation between the physical side and the information side of the power grid puts higher requirements on the stability and reliability of the system. However, the existing power grid state evaluation methods are often limited to a single dimension of the physical side or the information side, and cannot comprehensively reflect the overall operation condition of the power grid cyber-physical fusion system, making it difficult to timely discover potential system risks. In addition, most of the existing methods lack a unified evaluation index system and weight distribution mechanism, and the state evaluation of each index lacks accuracy and real-time, resulting in a lag in risk monitoring and fault warning, and the existing technology relies on a single data source (such as an automatic monitoring system), lacking comprehensive utilization of multi-source data (manual records, real-time monitoring, fault simulation data). At the same time, the existing evaluation system only makes a comprehensive evaluation of the overall system state in terms of real-time feedback and early warning display, and does not provide real-time feedback and early warning for the state of a single index in the system, making it difficult to quickly locate risks and faults in the system.

[0003] In summary, the existing evaluation method is limited to a single dimension of the physical side or the information side, lacks a unified cyber-physical fusion index system, the evaluation standard calculation method is single and the threshold is fixed, cannot be dynamically adjusted according to different types of indexes and different scenarios and environments, lacks comprehensive utilization of multi-source data, and lacks common early warning and real-time feedback display of single index state evaluation and system comprehensive state evaluation. SUMMARY

[0004] The present application aims to overcome the deficiencies in the prior art and provide a power grid cyber-physical system state evaluation method, device, terminal and storage medium, which expands the evaluation of the power grid operation state from the limitations of a single physical side or information side to a two-dimensional cyber-physical fusion, and constructs a comprehensive evaluation index system. This system can simultaneously reflect the operation state of the physical system and the operation state of the information system, achieving comprehensive evaluation of the power grid cyber-physical fusion system from bottom-up single index state evaluation to system-level state evaluation. This hierarchical evaluation from the bottom up can reduce the risk of misjudgment, improve system robustness, and help managers quickly locate and solve problems.

[0005] To solve the above technical problems, the present application is realized by the following technical scheme:

[0006] In a first aspect, the present application provides a power grid cyber-physical system state evaluation method, comprising:

[0007] According to the pre-constructed power grid cyber-physical system operation state evaluation index system, the real-time data of the power grid cyber-physical system is collected; wherein the power grid cyber-physical system operation state evaluation index system comprises a plurality of evaluation indexes;

[0008] The real-time data of the power grid cyber-physical system is processed and analyzed to determine the normalized data;

[0009] According to the normalized data and the pre-constructed power grid cyber-physical system operation state evaluation index system, the evaluation threshold of each evaluation index is determined based on a diversified threshold setting method;

[0010] According to the power grid cyber-physical system operation state evaluation index system and the normalized data, the maximum weight of each evaluation index is determined based on the analytic hierarchy process and the entropy weight method;

[0011] The real-time data of the power grid cyber-physical system is compared with the evaluation threshold of the corresponding evaluation index, and the first evaluation result is determined according to the comparison result;

[0012] According to the real-time data of the power grid cyber-physical system and the maximum weight of each evaluation index, a comprehensive score is calculated, the comprehensive score is compared with a preset threshold, and a second evaluation result is determined according to the comparison result;

[0013] According to the first evaluation result and the second evaluation result, the operation state of the power grid cyber-physical system is evaluated.

[0014] Further, the pre-constructed power grid cyber-physical system operation state evaluation index system comprises physical side evaluation indexes and information side evaluation indexes;

[0015] The physical side evaluation indexes include backup capacity margin, independent power supply capability, power quality, load supply capability and fault risk rate; the backup capacity margin includes probability area backup, transformer power margin, generator backup capacity and power structure backup capacity, the independent power supply capability includes partition load balancing degree and partition autonomous power supply rate, the power quality includes voltage deviation, voltage fluctuation, frequency deviation, three-phase voltage imbalance and total harmonic distortion, the load supply capability includes line average load rate, line overload rate and line N-1 passing rate, and the fault risk rate includes line fault rate, distribution transformer fault rate and downtime rate; N is the total number of related lines or elements in the power grid cyber-physical system;

[0016] The information side evaluation indexes include communication reliability, information side core device reliability and information side core device availability; the communication reliability includes average communication delay and communication success rate, the information side core device reliability includes device failure rate and device failure interval time, and the information side core device availability includes device failure repair time, device repair rate and device online duration.

[0017] Further, the real-time data of the power grid information fusion system is collected, including:

[0018] The real-time data of the power grid information fusion system is collected in a manual recording mode, an automatic monitoring system mode and a fault simulation mode.

[0019] Further, the diversified threshold setting method specifically includes:

[0020] Based on the set industry standard and historical data statistics, a customized evaluation threshold setting strategy is set for different types of evaluation indexes, and the evaluation threshold is updated in real time to adapt to the change of environmental conditions.

[0021] Further, the determination of the maximum weight of each evaluation index specifically includes:

[0022] According to the pre-constructed power grid information fusion system operation state evaluation index system, based on the analytic hierarchy process, the subjective weight coefficient of each evaluation index is calculated;

[0023] According to the normalized data and the pre-constructed power grid information fusion system operation state evaluation index system, based on the entropy weight method, the objective weight coefficient of each evaluation index is calculated;

[0024] According to the subjective weight coefficient of each evaluation index and the objective weight coefficient of each evaluation index, the comprehensive weight of each evaluation index is calculated, and the specific expression is as follows:

[0025]

[0026] In the formula: is the comprehensive weight of the i-th evaluation index; is the index of the evaluation index; is the total number of evaluation indexes; is the subjective weight coefficient of the i-th evaluation index; is the objective weight coefficient of the i-th evaluation index.

[0027] Further, the calculation of the comprehensive score specifically includes:

[0028] ​​​Based on the analytic hierarchy process, the pre-constructed power grid C2 system operation state evaluation index system is divided into target layer, criterion layer, sub-criterion layer and scheme layer;

[0029] According to the maximum weight of each evaluation index, the maximum weight of each evaluation index in the scheme layer is obtained;

[0030] According to the real-time data of the power grid C2 system, the score of each evaluation index in the scheme layer is obtained;

[0031] According to the score of each evaluation index in the scheme layer and the maximum weight of each evaluation index in the scheme layer, the comprehensive score is calculated, and the specific expression is as follows:

[0032]

[0033] In the formula: is the comprehensive score, is the index number of the evaluation index in the scheme layer; is the total number of evaluation indexes in the scheme layer; is the maximum weight of the first evaluation index in the scheme layer; is the score of the first evaluation index in the scheme layer.

[0034] Further, the evaluation of the operation state of the power grid C2 system specifically includes:

[0035] The first evaluation result and the second evaluation result both include normal state, alert state and fault state;

[0036] When the first evaluation result and the second evaluation result are both normal state, the power grid C2 system is evaluated as normal state;

[0037] When the first evaluation result and the second evaluation result are both alert state, the power grid C2 system is evaluated as alert state;

[0038] When the first evaluation result and the second evaluation result are both fault state, the power grid C2 system is evaluated as fault state;

[0039] When the first evaluation result and the second evaluation result are normal state and alert state respectively, the power grid C2 system is evaluated as alert state;

[0040] When the first evaluation result and the second evaluation result are normal state and fault state respectively, the power grid C2 system is evaluated as fault state;

[0041] When the first evaluation result and the second evaluation result are alert state and fault state respectively, the power grid C2 system is evaluated as fault state.

[0042] ​​In a second aspect, the present application provides a device for evaluating the operation state of a power grid information fusion system, comprising:

[0043] a data acquisition module for acquiring real-time data of the power grid information fusion system according to a pre-constructed evaluation index system for the operation state of the power grid information fusion system, wherein the evaluation index system for the operation state of the power grid information fusion system comprises a plurality of evaluation indexes;

[0044] a data processing module for processing and analyzing the real-time data of the power grid information fusion system to determine normalized data, and determining evaluation thresholds of the evaluation indexes based on a diversified threshold setting method according to the normalized data and the pre-constructed evaluation index system for the operation state of the power grid information fusion system;

[0045] an index weight calculation module for determining the maximum weights of the evaluation indexes based on an analytic hierarchy process and an entropy weight method according to the evaluation index system for the operation state of the power grid information fusion system and the normalized data;

[0046] a state evaluation module for comparing the real-time data of the power grid information fusion system with the evaluation thresholds of the corresponding evaluation indexes to determine a first evaluation result according to the comparison result, and calculating a comprehensive score according to the real-time data of the power grid information fusion system and the maximum weights of the evaluation indexes, comparing the comprehensive score with a preset threshold, and determining a second evaluation result according to the comparison result;

[0047] a feedback module for evaluating the operation state of the power grid information fusion system according to the first evaluation result and the second evaluation result.

[0048] In a third aspect, the present application provides a terminal comprising a processor and a storage medium.

[0049] The storage medium is used for storing instructions.

[0050] The processor is used for operating according to the instructions to perform the steps of the method according to the first aspect.

[0051] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to the first aspect.

[0052] Compared with the prior art, the present application has the following beneficial effects:

[0053] 1. The present application extends the evaluation of the operation state of the power grid from the limitation of a single physical side or information side to the dual dimensions of information fusion, and constructs a comprehensive evaluation index system; the system can reflect the operation state of the physical system and the operation state of the information system at the same time, and realizes the all-around evaluation of the power grid information fusion system;

[0054] 2. This invention progresses from bottom-up single-indicator status assessment to system-level status assessment. This bottom-up hierarchical assessment can reduce the risk of misjudgment, improve system robustness, and help managers quickly locate and solve problems.

[0055] 3. This invention can not only intuitively display the system's operating status, but also classify the normal state, alert state, and fault state as related to the prevention control, emergency control, and recovery control in power grid safety control. It provides a scientific basis for state analysis, comprehensive risk warning capabilities, and precise recovery guidance strategies for power grid safety control, greatly improving the safety, stability, and intelligence level of power grid operation. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating a method for assessing the state of a power grid information-physical fusion system according to an embodiment of the present invention;

[0057] Figure 2 This is a schematic diagram of the hierarchical structure of the evaluation index system provided in the embodiments of the present invention;

[0058] Figure 3 This is a schematic diagram of the operation status assessment device of a power grid information-physical fusion system provided according to an embodiment of the present invention. Detailed Implementation

[0059] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0060] The term "and / or" simply describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0061] Example 1:

[0062] like Figure 1 As shown, a flowchart illustrating a power grid information-physical fusion system state assessment method provided in this embodiment of the invention includes:

[0063] Based on the pre-constructed power grid information and physical matter fusion system operation status evaluation index system, real-time data of the power grid information and physical matter fusion system is collected; wherein, the power grid information and physical matter fusion system operation status evaluation index system includes multiple evaluation indicators;

[0064] Specifically, the application pre-constructs an index system for evaluating the operation state of a power grid information fusion system, which covers multi-dimensional information on the physical side and the information side to comprehensively reflect the operation state of the system.

[0065] The real-time data of the power grid information fusion system are processed and analyzed to determine normalized data.

[0066] According to the normalized data and the pre-constructed index system for evaluating the operation state of the power grid information fusion system, evaluation thresholds of each evaluation index are determined based on a diversified threshold setting method.

[0067] According to the index system for evaluating the operation state of the power grid information fusion system and the normalized data, the maximum weights of each evaluation index are determined based on the analytic hierarchy process and the entropy weight method.

[0068] The real-time data of the power grid information fusion system are compared with the evaluation thresholds of the corresponding evaluation indexes, and a first evaluation result is determined according to the comparison result.

[0069] According to the real-time data of the power grid information fusion system and the maximum weights of each evaluation index, a comprehensive score is calculated, the comprehensive score is compared with a preset threshold, and a second evaluation result is determined according to the comparison result.

[0070] According to the first evaluation result and the second evaluation result, the operation state of the power grid information fusion system is evaluated.

[0071] In an embodiment, the pre-constructed index system for evaluating the operation state of the power grid information fusion system includes physical side evaluation indexes and information side evaluation indexes.

[0072] The physical side evaluation indexes include backup capacity margin, independent power supply capability, power quality, load supply capability, and fault risk rate. The backup capacity margin includes probabilistic reserve, transformer power margin, generator backup capacity, and power structure backup capacity. The independent power supply capability includes partition load balancing degree and partition autonomous power supply rate. The power quality includes voltage deviation, voltage fluctuation, frequency deviation, three-phase voltage imbalance, and total harmonic distortion. The load supply capability includes line average load rate, line overload rate, and line N-1 passing rate. The fault risk rate includes 10KV line fault rate, distribution transformer fault rate, and downtime rate.

[0073] The information-side evaluation indicators include communication reliability, information-side core equipment reliability, and information-side core equipment availability; the communication reliability includes average communication latency and communication success rate; the information-side core equipment reliability includes equipment failure rate and equipment failure interval time; and the information-side core equipment availability includes equipment failure repair time, equipment repair rate, and equipment online duration.

[0074] Specifically, each evaluation indicator has a corresponding calculation formula, as follows:

[0075] The reserve capacity margin includes probabilistic area reserve, transformer power margin, generator reserve capacity, and power structure reserve capacity;

[0076] Among them, probabilistic regional reserve: probabilistic regional reserve refers to the reserve capacity that the power grid can provide under a specific probability level, and the specific expression is as follows:

[0077]

[0078] In the formula: S' represents the probability region for future reference. represents the total system capacity, 'a' represents the confidence level, and 'L' represents the current system load.

[0079] Transformer power margin: Transformer power margin refers to the difference between the rated capacity of the transformer and the actual load. The calculation formula is as follows:

[0080]

[0081] In the formula: M represents the power margin of the transformer. This indicates the rated capacity of the transformer.

[0082] Generator standby capacity: Generator standby capacity refers to the additional power capacity that a generator set can provide after meeting the current load; the calculation formula is:

[0083]

[0084] In the formula: Indicates the generator's standby capacity. This indicates the total capacity of the generator.

[0085] Power structure reserve capacity: Power structure reserve capacity refers to the additional power capacity that the entire power system can provide after meeting the current load; the calculation formula is:

[0086]

[0087] In the formula: Indicates the reserve capacity of the power structure. This indicates the total system capacity.

[0088] The independent power supply capability includes a partition load balancing degree and a partition autonomous power supply rate;

[0089] The partition load balancing degree reflects the balancing degree of the load distribution of each node in the partition, and avoids local overload affecting the stability of independent power supply. The calculation formula is:

[0090]

[0091] In the formula, PLBI represents the partition load balancing degree, represents the standard deviation of the load power of each node in the partition, represents the average load power in the partition.

[0092] The partition autonomous power supply rate is the proportion of the local power generation and the energy storage that can meet the load demand in the partition, and represents the short-term independent power supply capability. The calculation formula is:

[0093]

[0094] In the formula, PASR represents the partition autonomous power supply rate, represents the local power generation power of the zth node, represents the maximum discharge power of the energy storage of the zth node, represents the load power of the zth node; and Z represents the total number of nodes.

[0095] The fault risk rate includes a 10KV line fault rate, a distribution transformer fault rate, and a downtime rate;

[0096] The fault risk rate is a 10kV line fault rate, which refers to the probability of failure of a medium-voltage distribution line per unit length or operating time. The calculation formula is:

[0097]

[0098] In the formula, represents the 10kV line fault rate, represents the number of failures, represents the total length of the line, represents the operating time.

[0099] The distribution transformer fault rate represents the frequency of failure of a distribution transformer per unit time. The calculation formula is:

[0100]

[0101] In the formula, represents the distribution transformer fault rate, represents the number of failures, represents the total number of transformers, represents the operating time.

[0102] Downtime: represents the proportion of the total running time that the system is down due to reasons during operation, the calculation formula is:

[0103]

[0104] In the formula: represents the downtime, represents the downtime, represents the total running time.

[0105] The power quality includes voltage deviation, voltage fluctuation, frequency deviation, three-phase voltage imbalance and total harmonic distortion;

[0106] Among them, the voltage deviation: the voltage deviation is usually defined as the difference between the actual voltage and the rated voltage divided by the rated voltage percentage, the calculation formula is:

[0107]

[0108] In the formula: represents the voltage deviation, represents the actual measured voltage value, represents the rated voltage value.

[0109] Voltage fluctuation: voltage fluctuation refers to the change in voltage value in a certain period of time in the power system relative to its rated voltage, the calculation formula is:

[0110]

[0111] In the formula: represents the voltage fluctuation, represents the maximum voltage, represents the minimum voltage; represents the rated voltage.

[0112] Frequency deviation: refers to the difference between the actual frequency and the nominal frequency when the system is running normally, the calculation formula is:

[0113]

[0114] In the formula: represents the frequency deviation, represents the actual frequency, represents the rated frequency.

[0115] Three-phase voltage imbalance: is an important indicator to measure the deviation degree between three-phase voltage amplitudes in the power system, which is defined as the percentage of the maximum deviation value of three-phase voltage (relative to the average voltage), the calculation formula is:

[0116]

[0117] wherein: and respectively represent the maximum and minimum values in the three-phase voltage, represents the average value of the three-phase voltage.

[0118] Total Harmonic Distortion: is an important indicator to measure the degree of harmonic distortion to voltage or current waveform in power system, represents the ratio of the total effective value of harmonic components to the effective value of fundamental component, the calculation formula is:

[0119]

[0120] wherein: THD represents the total harmonic distortion, represents the effective value of the nth harmonic voltage, represents the effective value of the fundamental voltage.

[0121] The load supply capacity includes line average load rate, line overload rate and line N-1 passing rate;

[0122] wherein, the line average load rate: the average load rate of the distribution network line is usually used to measure the degree of use of the line within a certain period of time, represents the ratio of the average load of the line to its maximum load, the calculation formula is:

[0123]

[0124] wherein, ALR represents the average load rate, represents the total power or average load of the line within a certain period of time, represents the maximum carrying capacity or rated capacity of the line.

[0125] Line overload rate: represents the ratio of the actual load degree of the transmission line to its rated capacity, the calculation formula is:

[0126]

[0127] wherein: OR represents the line overload rate, represents the actual load, represents the rated capacity of the line.

[0128] Line N-1 passing rate: represents the load capacity that other lines can still carry when one line fails or is isolated in a power system, the calculation formula is:

[0129]

[0130] wherein: N_1TR represents the N-1 passing rate, is the load capacity lost by the system after N-1 failure, It is the total load capacity of the system under normal operating conditions; N is the total number of related lines or components in the power grid information and physical system.

[0131] The communication reliability includes average communication latency and communication success rate;

[0132] Among them, the communication success rate is the ability of a communication system to successfully transmit data, and the calculation formula is:

[0133]

[0134] In the formula: Indicates the communication success rate; Indicates the number of successful communications; This indicates the total number of communication attempts.

[0135] Average communication delay: Average communication delay refers to the average delay time of each communication attempt over multiple communication attempts. The calculation formula is as follows:

[0136]

[0137] In the formula: Indicates average communication delay. Indicates the first The delay of this communication.

[0138] The reliability of the core equipment on the information side includes the equipment failure rate and the equipment failure interval time.

[0139] Among them, equipment failure rate: used to measure the frequency of failures of important information-side equipment during operation, and the calculation formula is:

[0140]

[0141] In the formula: Indicates the switchgear failure rate. Indicates the number of failures; Indicates the runtime.

[0142] Intermittent Failure Time: This measures the average uptime of critical information-side equipment between two failures. The calculation formula is as follows:

[0143]

[0144] In the formula: This indicates the interval between equipment failures.

[0145] The availability of the core information-side equipment includes equipment failure repair time, equipment repair rate, and equipment online duration.

[0146] Among them, the device fault repair time: indicates the average time required for the device to fail to be completely repaired and put into use again, and the calculation formula is:

[0147]

[0148] In the formula: Indicates the fault repair time of the information side important device, Indicates the total repair time of the important device, Indicates the total number of faults of the important device.

[0149] Device repair rate: indicates the ratio of the number of successful device fault repairs to the total number of device fault repair attempts within a certain time, and the calculation formula is:

[0150]

[0151] In the formula: Indicates the device fault repair rate, Indicates the number of successful repairs, Indicates the total number of repair attempts.

[0152] Device online duration: indicates the ratio of the normal operation duration of the device within a certain time to the total operation duration, and the calculation formula is:

[0153]

[0154] Among them, Indicates the device online duration, Indicates the normal operation time of the device, Indicates the total operation time of the information side device.

[0155] Because there are many evaluation indexes, different scale and operation scene power grids have different needs for evaluation indexes, therefore, the application allows to flexibly select evaluation index content according to the actual power grid operation situation, so as to ensure the applicability and effectiveness of evaluation.

[0156] An embodiment, the collection power grid signal fusion system real-time data, comprising:

[0157] Adopt manual recording mode, automatic monitoring system mode and fault simulation mode to collect real-time data of power grid signal fusion system.

[0158] Specifically, the above-mentioned manual recording data collection mode is mainly for some factory parameters of the device, which needs to manually input data in the evaluation system; the data collected by the automatic monitoring system is mainly for real-time data in system operation; the fault simulation collection mode is mainly to collect data in abnormal state.

[0159] An embodiment, data processing and analysis of real-time data of the power grid signal fusion system, determine the normalized data, according to the normalized data and pre-built power grid signal fusion system operation state evaluation index system, based on the diversification threshold setting method, determine the evaluation threshold of each evaluation index, specifically including:

[0160] Data processing and analysis of collected data, based on the diversification threshold setting method, set the evaluation criteria of the operating state, alert state and fault state for each evaluation index in the index system.

[0161] The collected real-time data may have abnormal values, noise or missing problems, which need to be preprocessed before formal analysis.

[0162] Missing value processing: use interpolation method or other statistical methods to fill in missing data to avoid affecting the analysis results.

[0163] Data alignment and time synchronization: align the time stamps of data from different sources (such as physical side and information side data) to ensure data synchronization.

[0164] Data normalization: to eliminate the influence of different index dimensions, all evaluation indexes are normalized to obtain normalized evaluation indexes X'; evaluation indexes X' are divided into positive indexes and negative indexes, the larger the positive index value is, the better, the smaller the negative index value is, the better, and the positive and negative index normalization formulas are as follows:

[0165]

[0166]

[0167] In the formula: X' represents the normalized value of the positive index, X' represents the normalized value of the negative index, X represents the original data, and are the upper limit value and the lower limit value of the normal state of the index, respectively.

[0168] State classification algorithm, used to divide each evaluation index into operating state, alert state and fault state; normal state index value is in the safe range, the system does not need to be intervened, the alert state index value is close to the critical point, triggering the pre-warning and starting the preparatory measures; the fault state index value exceeds the tolerance limit value, and the protection action must be performed.

[0169] The diversified threshold setting method specifically includes: based on established industry standards and historical data statistics, etc., customized assessment threshold setting strategies are adopted for different types of assessment indicators, and data is monitored in real time to update the assessment thresholds to adapt to changes in environmental conditions; the threshold setting method for each specific indicator mainly includes: based on relevant industry standards, based on historical data statistics, etc., different threshold setting methods are adopted for different types of indicators, and dynamic adjustment is supported to adapt to system changes.

[0170] In one embodiment, determining the final weight of each evaluation indicator specifically includes:

[0171] Based on the pre-constructed power grid information and physical system fusion system operation status evaluation index system, the subjective weight coefficients of each evaluation index are calculated using the analytic hierarchy process (AHP).

[0172] Based on the normalized data and the pre-constructed power grid information-physical fusion system operation status evaluation index system, the objective weight coefficients of each evaluation index are calculated using the entropy weight method.

[0173] Based on the subjective weight coefficient and the objective weight coefficient of each evaluation indicator, the comprehensive weight of each evaluation indicator is calculated, as shown in the following expression:

[0174]

[0175] In the formula: For the first The overall weight of each evaluation indicator; The labels for the evaluation indicators; The total number of evaluation indicators; For the first Subjective weighting coefficients for each evaluation indicator; For the first Objective weighting coefficients for each evaluation indicator.

[0176] Specifically, based on the pre-constructed power grid information-physical fusion system operation status evaluation index system, and using the analytic hierarchy process (AHP), the subjective weight coefficients of each evaluation index are calculated, including:

[0177] The analytic hierarchy process (AHP) is used to calculate the subjective weight coefficients of the operational status evaluation indicators for each power grid information-physical fusion system; the implementation process is as follows:

[0178] First, according to Figure 2 The diagram shown is a hierarchical structure diagram of the evaluation index system provided in an embodiment of the present invention. The index system can be divided into: target layer, criterion layer, sub-criterion layer and scheme layer.

[0179] Next, a judgment matrix is ​​constructed. Based on expert opinions, the relative importance of indicators at the same upper level within the hierarchical structure is compared. The importance ratio between each pair of indicators is determined through pairwise comparisons. The Saaty scale is then used for assignment, typically employing a scale of 1-9. The meaning of the importance of the scale values ​​is shown in Table 1.

[0180]

[0181] In the table, Ai and Aj refer to the two indicators in the pairwise comparison;

[0182] For each pairwise comparison matrix, compute its eigenvector W and the largest eigenvalue. The eigenvectors are normalized to obtain the weight values ​​of the indicators, while the largest eigenvalue... Used for consistency checks; to ensure the rationality of the judgment matrix, a consistency check is required. The formulas for calculating the consistency index CI and the consistency ratio CR are as follows:

[0183]

[0184]

[0185] In the formula: To determine the largest eigenvalue of a matrix, n is the order of the matrix, and RI is obtained by looking up the random consistency index (RI) table; if CR < 0.1, the comparison matrix is ​​considered to have satisfactory consistency; otherwise, the comparison matrix needs to be adjusted.

[0186] Suppose the eigenvector W of the pairwise comparison matrix is ; Let represent the transpose; then, the set of local weight coefficients of the evaluation indicators for the comparison matrix calculated using the analytic hierarchy process is as follows:

[0187]

[0188] In the formula: s is the evaluation index label in the current comparison matrix, The sum of the eigenvectors; Let be the local weight coefficient of the s-th evaluation indicator.

[0189] Assume w up Given the weights of the higher-level indicators in the current set, the final set of subjective weights for the current evaluation indicators is as follows:

[0190]

[0191] Based on the set of final subjective weight coefficients of multiple comparison matrices, obtain the first... Subjective weighting coefficients of each evaluation indicator .

[0192] An entropy weight method is used to calculate objective weight coefficients of each power grid information fusion system operation state evaluation index; the implementation process is as follows:

[0193] According to the normalized data and the pre-constructed power grid information fusion system operation state evaluation index system, the proportion of each evaluation index in each sample is calculated, and the calculation formula of the proportion is:

[0194]

[0195] In the formula: is the proportion of the ith index in the jth sample; n is the total number of samples.

[0196] Secondly, for each index, the information entropy thereof is calculated; the information entropy reflects the uncertainty of the index; the information entropy calculation formula is as follows:

[0197]

[0198] Among them, , is the information entropy.

[0199] Finally, the weight of each index is calculated; the weight is inversely proportional to the size of the entropy value; the calculation formula is:

[0200]

[0201] In the formula: represents the weight of the ith index.

[0202] The subjective weight coefficient and the objective weight coefficient are substituted into the comprehensive weight calculation formula to obtain the comprehensive weight, and the comprehensive weight is used as the final weight coefficient of the power grid information fusion evaluation index; the comprehensive weight calculation formula is specifically:

[0203]

[0204] In the formula: is the comprehensive weight of the ith evaluation index; is the index number of the evaluation index; is the total number of indexes; is the subjective weight coefficient of the ith evaluation index; is the objective weight coefficient of the ith evaluation index.

[0205] ​​​In one embodiment, the real-time data of the power grid information-physical fusion system is compared with the evaluation threshold of the corresponding evaluation index, and a first evaluation result is determined based on the comparison result, specifically including:

[0206] The evaluation thresholds include a first threshold, a second threshold, and a third threshold. When one of the real-time data points is within the first threshold, the real-time data point is determined to be in a normal state, and the first evaluation result is normal state. When one of the real-time data points is within the second threshold, the real-time data point is determined to be in a warning state, and the first evaluation result is warning state. When one of the real-time data points is within the third threshold, the real-time data point is determined to be in a fault state, and the first evaluation result is fault state.

[0207] In one embodiment, the calculation of the comprehensive score specifically includes:

[0208] Based on the analytic hierarchy process, the pre-constructed power grid information-physical fusion system operation status evaluation index system is divided into target layer, criterion layer, sub-criterion layer and scheme layer;

[0209] Based on the final weight of each evaluation indicator, obtain the final weight of each evaluation indicator in the solution layer;

[0210] Based on the real-time data of the power grid information-physical fusion system, the scores of each evaluation indicator in the scheme layer are obtained;

[0211] The comprehensive score is calculated based on the scores of each evaluation indicator in the scheme layer and the final weight of each evaluation indicator in the scheme layer. The specific expression is as follows:

[0212]

[0213] In the formula: For comprehensive scoring, These are the labels for the evaluation indicators in the scheme layer; This represents the total number of evaluation indicators in the scheme layer; For the first layer of the scheme The final weight of each evaluation indicator; For the first layer of the scheme Scores for each evaluation indicator.

[0214] Specifically, the preset thresholds include a first preset threshold, a second preset threshold, and a third preset threshold; when the comprehensive score is within the first preset threshold, the second evaluation result is in a normal state; when the comprehensive score is within the second preset threshold, the second evaluation result is in a warning state; when the comprehensive score is within the third preset threshold, the second evaluation result is in a fault state.

[0215] In one embodiment, the assessment of the operational status of the power grid information-physical fusion system specifically includes:

[0216] The first evaluation result and the second evaluation result each include a normal state, an alert state, and a fault state;

[0217] When the first evaluation result and the second evaluation result are both normal states, the power grid information fusion system is evaluated as a normal state;

[0218] When the first evaluation result and the second evaluation result are both alert states, the power grid information fusion system is evaluated as an alert state;

[0219] When the first evaluation result and the second evaluation result are both fault states, the power grid information fusion system is evaluated as a fault state;

[0220] When the first evaluation result and the second evaluation result are a normal state and an alert state, respectively, the power grid information fusion system is evaluated as an alert state;

[0221] When the first evaluation result and the second evaluation result are a normal state and a fault state, respectively, the power grid information fusion system is evaluated as a fault state;

[0222] When the first evaluation result and the second evaluation result are an alert state and a fault state, respectively, the power grid information fusion system is evaluated as a fault state.

[0223] Specifically, when the power grid information fusion system is in an alert state or a fault state, real-time feedback and early warning are provided.

[0224] In an embodiment, the preset threshold values are as shown in Table 2:

[0225]

[0226] In this embodiment, the operating state of the laboratory microgrid is evaluated.

[0227] In view of the scale, structure, and operating environment of the laboratory microgrid, the following indicators are selected to evaluate the operating state:

[0228] Physical side: power quality (such as voltage deviation, voltage fluctuation, frequency deviation); load supply capability (line average load rate, line overload rate, line N-1 passing rate); fault risk rate (transformer fault rate, downtime rate, repeated tripping rate);

[0229] Information side: communication reliability (average communication delay, communication success rate); information side core equipment reliability (device failure rate, device failure interval time); information side core equipment availability (device failure repair time, device repair rate, device online duration).

[0230] The relevant evaluation data is collected through various sensors, fault reports, smart meters, and other devices in the laboratory, as well as manual recording, fault simulation, and other methods, and the evaluation indicator values are calculated.

[0231] Through data processing and in-depth analysis of the calculated index values, a diversified threshold setting method is used to formulate corresponding evaluation standards for each index.

[0232] For example, the evaluation threshold of one of the evaluation indexes is: normal state: voltage deviation ≤ 5%, warning state: 5% ≤ voltage deviation ≤ 10%, fault state: voltage deviation > 10%;

[0233] For example, the voltage deviation is 6.32% in the collected data in the experiment, and the power quality index evaluation is in the warning state, so the first evaluation result is also converted into the warning state; and then the second evaluation result is obtained to evaluate the running state of the power grid signal fusion system.

[0234] In one embodiment, the maximum weight of each evaluation index is as shown in Table 3:

[0235]

[0236] For example, the single index evaluation is within the safe and stable running threshold in the collected data in the experiment, that is, the first evaluation result is in the normal state, and at this time, the overall score of the system is calculated through the comprehensive weight and the score value of the scheme layer:

[0237] = (0.85*0.12) + (0.81*0.12) + (0.82*0.06) + (0.77*0.09) + (0.85*0.054) + (0.71*0.036) + (0.8*0.048) + (0.79*0.048) + (0.72*0.024) + (0.8*0.048) + (0.85*0.8) + (0.73*0.032) + (0.78*0.6) + (0.81*0.06) + (0.7*0.048) + (0.75*0.024) = 0.796;

[0238] At this time, 0.5 ≤ <0.8, so the second evaluation result is in the warning state, there is a certain risk, which needs to be paid attention to and maintained, therefore, the power grid signal fusion system is in the warning state according to the above.

[0239] In order to verify the evaluation accuracy, the evaluation results are compared with the actual historical running state of the power grid, and different power grid running states (for example, simulating voltage deviation, equipment failure, etc.) are simulated through experiments to verify the accuracy of the evaluation system; the present application also uses a confusion matrix to calculate the accuracy rate in the classification task, and the accuracy rate formula is:

[0240]

[0241] In the formula: TP represents true positive, the number of samples correctly predicted by the model as positive class, TN represents true negative, the number of samples correctly predicted by the model as negative class, FP represents false positive, the number of samples incorrectly predicted by the model as positive class, FN represents false negative, the number of samples incorrectly predicted by the model as negative class.

[0242] The evaluation accuracy is shown in Table 4:

[0243]

[0244] According to the above steps, the accuracy is evaluated.

[0245] The present application expands the evaluation of power grid operation state from the limitations of single physical side or information side to the dual dimensions of signal fusion, and constructs a comprehensive evaluation index system; the system can reflect the operation state of the physical system and the operation state of the information system at the same time, and realizes the all-round evaluation of the power grid signal fusion system.

[0246] Based on industry standards, historical data statistics and other diversified methods, the present application customizes threshold setting strategies for different types of evaluation indexes, and monitors data in real time to update the threshold to adapt to environmental condition changes.

[0247] The prior art mainly evaluates the state based on single data source of operation data, and the present application realizes the fusion and utilization of multi-source data of the physical side and the information side by combining manual recording, real-time data acquisition of the automatic monitoring system, and various ways such as fault simulation, thereby improving the evaluation accuracy.

[0248] From the bottom-up hierarchical evaluation of single index state evaluation to system level state evaluation, the present application can reduce the risk of misjudgment, improve the system robustness, and help managers quickly locate and solve problems.

[0249] The present application independently analyzes the state of each evaluation index, accurately divides it into normal state, alert state and fault state, can quickly identify the abnormal state of a specific index, realizes accurate early warning of single index, and at the same time, the present application generates the evaluation result of the overall operation state of the power grid signal fusion system by weighting the values of each evaluation index, and provides real-time early warning and feedback mechanism.

[0250] The present application not only can intuitively show the running condition of the system, but also can associate the divided normal state, alert state and fault state with the preventive control, emergency control and recovery control in power grid safety control, provide scientific state analysis basis, comprehensive risk early warning ability and accurate recovery guidance strategy for power grid safety control, and greatly improve the safety, stability and intelligent level of power grid operation.

[0251] Example two:

[0252] As Figure 3 shown, a structural schematic diagram of an operation state evaluation device of a power grid information fusion system provided by an embodiment of the present application, comprising:

[0253] The data acquisition module is configured to acquire real-time data of the power grid information fusion system according to a pre-constructed power grid information fusion system operation state evaluation index system, wherein the power grid information fusion system operation state evaluation index system comprises a plurality of evaluation indexes.

[0254] The data processing module is configured to perform data processing and analysis on the real-time data of the power grid information fusion system to determine normalized data, and determine evaluation thresholds of the evaluation indexes based on a diversified threshold setting method according to the normalized data and the pre-constructed power grid information fusion system operation state evaluation index system.

[0255] The index weight calculation module is configured to determine the maximum weights of the evaluation indexes based on an analytic hierarchy process and an entropy weight method according to the power grid information fusion system operation state evaluation index system and the normalized data.

[0256] The state evaluation module is configured to compare the real-time data of the power grid information fusion system with the evaluation thresholds of the corresponding evaluation indexes, determine a first evaluation result according to a comparison result, calculate a comprehensive score according to the real-time data of the power grid information fusion system and the maximum weights of the evaluation indexes, compare the comprehensive score with a preset threshold, and determine a second evaluation result according to a comparison result.

[0257] The feedback module is configured to evaluate the operation state of the power grid information fusion system according to the first evaluation result and the second evaluation result, that is, a feedback and early warning module.

[0258] Specifically, the device further comprises an evaluation index management module configured to define, store and update physical side and information side evaluation indexes and evaluation standards, and a user interface module configured to provide evaluation result display and maintenance suggestions to a user.

[0259] The feedback and early warning module comprises a single index state early warning configured to prompt single index dimensions such as backup capacity margin, power quality and communication reliability, and a comprehensive index state overall early warning configured to prompt information fusion system level fault risk.

[0260] The user interface module displays states, including early warning feedback of single index states and overall evaluation feedback of comprehensive index states, which are all divided into three states: normal state, alert state and fault state.

[0261] The evaluation method supports power grids of different scales and topologies, including but not limited to: urban distribution networks; rural microgrids; industrial park local area networks; and hybrid power grids containing distributed energy.

[0262] Embodiment three:

[0263] The embodiment of the present application further provides a terminal, comprising a processor and a storage medium.

[0264] The storage medium is used for storing instructions.

[0265] The processor is used for operating according to the instructions to perform the steps of the method in the embodiment one.

[0266] Embodiment four:

[0267] The embodiment of the present application further provides a computer readable storage medium, which has a computer program stored thereon, and the program is executed by a processor to realize the steps of the method in the embodiment one.

[0268] Since the storage medium provided by the embodiment of the present application can execute the method provided by the embodiment one of the present application, it has the corresponding function modules and beneficial effects of the method.

[0269] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product in the form of one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0270] The present application is described with reference to flowcharts and / or block diagrams according to the method, device (system), and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks

[0271] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow or flows and / or blocks Figure 1 The flow or flows and / or blocks

[0272] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 The flow or flows and / or blocks Figure 1 The flow or flows and / or blocks

[0273] The above description is only preferred embodiments of the present application, it should be pointed out that for those skilled in the art, without departing from the technical principles of the present application, a number of improvements and modifications can be made, these improvements and modifications should also be considered as the protection scope of the present application.

Claims

1. A method for assessing the state of a cyber-physical power grid system, characterized by, The method comprises the following steps: According to the pre-constructed power grid and information fusion system operation state evaluation index system, the real-time data of the power grid and information fusion system is collected; wherein the power grid and information fusion system operation state evaluation index system comprises a plurality of evaluation indexes; The real-time data of the power grid and information fusion system is processed and analyzed to determine normalized data; According to the normalized data and the pre-constructed power grid and information fusion system operation state evaluation index system, the evaluation threshold of each evaluation index is determined based on a diversified threshold setting method; According to the power grid and information fusion system operation state evaluation index system and the normalized data, the maximum weight of each evaluation index is determined based on the analytic hierarchy process and the entropy weight method; The real-time data of the power grid and information fusion system is compared with the evaluation threshold of the corresponding evaluation index, and the first evaluation result is determined according to the comparison result; According to the real-time data of the power grid and information fusion system and the maximum weight of each evaluation index, the comprehensive score is calculated, the comprehensive score is compared with the preset threshold, and the second evaluation result is determined according to the comparison result; According to the first evaluation result and the second evaluation result, the operation state of the power grid and information fusion system is evaluated; The pre-constructed power grid and information fusion system operation state evaluation index system comprises physical side evaluation indexes and information side evaluation indexes; The physical side evaluation indexes include backup capacity margin, independent power supply capability, power quality, load supply capability and fault risk rate; the backup capacity margin includes probability area backup, transformer power margin, generator backup capacity and power structure backup capacity, the independent power supply capability includes partition load balancing degree and partition autonomous power supply rate, the power quality includes voltage deviation, voltage fluctuation, frequency deviation, three-phase voltage imbalance and total harmonic distortion, the load supply capability includes line average load rate, line overload rate and line N-1 passing rate, and the fault risk rate includes line fault rate, distribution transformer fault rate and downtime rate; N is the total number of related lines or elements in the power grid and information fusion system; The information side evaluation indexes include communication reliability, information side core device reliability and information side core device availability; the communication reliability includes average communication delay and communication success rate, the information side core device reliability includes device failure rate and device failure interval time, and the information side core device availability includes device failure repair time, device repair rate and device online time length; The real-time data of the power grid and information fusion system is collected by the following methods: The real-time data of the power grid and information fusion system is collected by manual recording, automatic monitoring system and fault simulation; The diversified threshold setting method specifically comprises: Based on the set industry standard and historical data statistics, a customized evaluation threshold setting strategy is set for different types of evaluation indexes, and the data is monitored in real time to update the evaluation threshold to adapt to the change of environmental conditions; The maximum weight of each evaluation index is determined by the following steps: According to the pre-constructed power grid and information fusion system operation state evaluation index system, the subjective weight coefficient of each evaluation index is calculated based on the analytic hierarchy process; According to the normalized data and a pre-constructed power grid signal fusion system operation state evaluation index system, objective weight coefficients of each evaluation index are calculated based on an entropy weight method; According to the subjective weight coefficients of each evaluation index and the objective weight coefficients of each evaluation index, a comprehensive weight of each evaluation index is calculated, and a specific expression is as follows: ； In the formula: is the comprehensive weight of the evaluation index; is the comprehensive weight of the evaluation index; is the label of the evaluation index; is the total number of evaluation indexes; is the subjective weight coefficient of the evaluation index; is the subjective weight coefficient of the evaluation index; is the objective weight coefficient of the evaluation index; and is the objective weight coefficient of the evaluation index.

2. The power grid cyber-physical system state estimation method of claim 1, wherein, The comprehensive score is calculated, specifically including: Based on an analytic hierarchy process, the pre-constructed power grid signal fusion system operation state evaluation index system is divided into a target layer, a criterion layer, a sub-criterion layer and a scheme layer; According to the maximum weights of each evaluation index, the maximum weights of each evaluation index in the scheme layer are obtained; According to the real-time data of the power grid signal fusion system, scores of each evaluation index in the scheme layer are obtained; According to the scores of each evaluation index in the scheme layer and the maximum weights of each evaluation index in the scheme layer, a comprehensive score is calculated, and a specific expression is as follows: ； In the formula: is the comprehensive score, is the label of the evaluation index in the scheme layer; is the total number of evaluation indexes in the scheme layer; is the maximum weight of the evaluation index in the scheme layer; is the score of the evaluation index in the scheme layer. is the score of the evaluation index in the scheme layer. is the score of the evaluation index in the scheme layer.

3. The power grid cyber-physical system state estimation method of claim 1, wherein, The operation state of the power grid signal fusion system is evaluated, specifically including: The first evaluation result and the second evaluation result both include a normal state, an alert state and a fault state; When the first evaluation result and the second evaluation result are both normal states, the power grid signal fusion system is evaluated as a normal state; When the first evaluation result and the second evaluation result are both alert states, the power grid signal fusion system is evaluated as an alert state; When the first evaluation result and the second evaluation result are both fault states, the power grid signal fusion system is evaluated as a fault state; When the first evaluation result and the second evaluation result are a normal state and an alert state respectively, the power grid signal fusion system is evaluated as an alert state; When the first evaluation result and the second evaluation result are a normal state and a fault state respectively, the power grid signal fusion system is evaluated as a fault state; When the first evaluation result and the second evaluation result are an alert state and a fault state respectively, the power grid signal fusion system is evaluated as a fault state.

4. An operating state evaluation device of a power grid information fusion system, based on the power grid information fusion system state evaluation method according to any one of claims 1 to 3, characterized in that, Including: A data acquisition module is configured to acquire real-time data of a power grid signal fusion system according to a pre-constructed power grid signal fusion system operation state evaluation index system; the power grid signal fusion system operation state evaluation index system includes a plurality of evaluation indexes; A data processing module is configured to perform data processing and analysis on the real-time data of the power grid signal fusion system to determine normalized data; and according to the normalized data and the pre-constructed power grid signal fusion system operation state evaluation index system, evaluation threshold values of each evaluation index are determined based on a diversified threshold value setting method; An index weight calculation module is configured to determine maximum weights of each evaluation index based on an analytic hierarchy process and an entropy weight method according to the power grid signal fusion system operation state evaluation index system and the normalized data; A state evaluation module is configured to compare the real-time data of the power grid signal fusion system with evaluation threshold values of corresponding evaluation indexes, and determine a first evaluation result according to a comparison result; a comprehensive score is calculated according to the real-time data of the power grid signal fusion system and the maximum weights of each evaluation index, and the comprehensive score is compared with a preset threshold value to determine a second evaluation result according to a comparison result. The feedback module is configured to evaluate the operation state of the power grid information fusion system according to the first evaluation result and the second evaluation result.

5. A terminal, characterized by comprising: The system comprises a processor and a storage medium; The storage medium is configured to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1 to 3.

6. A computer readable storage medium having stored thereon a computer program, characterized in that, The program, when executed by the processor, implements the steps of the method according to any one of claims 1 to 3.

Images