Substation information intelligent automatic acquisition system

Abstract

The invention discloses an intelligent and automatic transformer substation information acquisition system, which relates to the technical field of information acquisition, and is characterized in that an information change coefficient and an information priority coefficient are acquired and substituted into a logistic regression model to obtain an information potential evaluation coefficient, the information potential evaluation coefficient is analyzed with a preset potential threshold to obtain a comparison result, and the transformer substation information is acquired according to the comparison result. Dividing to obtain a real-time acquisition potential information set and a non-real-time acquisition potential information set, substituting into a default score combination mechanism, determining an actual classification acquisition result of each piece of information, obtaining a network state when each piece of information is uploaded, obtaining a network delay degree and a bandwidth utilization rate from the network state, and substituting into fuzzy logic for fuzzy reasoning to obtain a real-time acquisition potential information set and a non-real-time acquisition potential information set; according to the method, the reasonability result of the default score combination mechanism is determined, then the network delay degree and the bandwidth utilization rate when each piece of information is uploaded are substituted into set parameters in the default score combination mechanism, the score combination mechanism is determined and adjusted, and the information redundancy and the system burden are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of information collection, and more specifically, to an intelligent automatic collection system for substation information. Background Art

[0002] With the continuous development of the power system, substations, as an important part of the power system, play a key role in ensuring the safe and stable operation of the power grid through real-time monitoring and data collection of their operating status. Usually, based on the monitoring and data acquisition system, real-time monitoring of equipment status is achieved by deploying intelligent sensors to collect operating parameters in the substation.

[0003] The prior art has the following deficiencies: At present, the limitation of data collection is usually based on real-time collection and irregular collection, which is usually set based on the importance of data and the characteristics of data collection. However, for some extreme collection environments, repeated collection of real-time information, but due to the delay of irregular information collection, the collection of possible key data is delayed, resulting in the overall information collected being too redundant, increasing the risk of subsequent processing and reducing the efficiency of information processing. Therefore, an intelligent automatic collection system for substation information is proposed.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent automatic acquisition system for substation information, which solves the problems raised in the above-mentioned background technology by using different product inspection methods.

[0006] To achieve the above object, the present invention provides the following technical solution: a substation information intelligent automatic acquisition system, comprising a data acquisition module, a potential analysis module, a default scoring module, a reasonable evaluation module and a combination adjustment module; signal connections between the modules; The data acquisition module is used to collect information change characteristic information and information processing characteristic information, obtain information change coefficient and information priority coefficient through data processing, and send them to the potential analysis module; The potential analysis module is used to obtain the information change coefficient and the information priority coefficient, substitute them into the logistic regression model, obtain the information potential evaluation coefficient, and analyze it with the preset potential threshold to obtain the comparison result. According to the comparison result, the real-time collection potential information set and the non-real-time collection potential information set are divided and sent to the default scoring module; The default scoring module is used to obtain the real-time collection potential information set and the non-real-time collection potential information set, substitute them into the default scoring combination mechanism, determine the actual classification collection results of each information, and send them to the reasonable evaluation module; The reasonable evaluation module is used to obtain the actual classification collection results of each information, obtain the network status when each information is uploaded, obtain the network delay degree and bandwidth utilization rate, substitute fuzzy logic for fuzzy reasoning, determine the rationality result of the default scoring combination mechanism, and send it to the combination adjustment module; The combination adjustment module is used to obtain the rationality result of the default scoring combination mechanism, substitute the network delay degree and bandwidth utilization rate when uploading each information into the parameters set in the default scoring combination mechanism, and determine the adjustment of the scoring combination mechanism.

[0007] In a preferred embodiment, the information change characteristic information includes an information change coefficient, and the information processing characteristic information includes an information priority coefficient, wherein the data acquisition module samples continuous data, records the change amplitude and time interval of the information content length, and records the processing time of the information, and performs weighted calculation on the ratio of the amplitude of the information change to the time required for the information change and the ratio of the information processing time to the maximum acceptable processing time of the information, to obtain the information change coefficient. ; For the Substation information; The data acquisition module obtains the safety importance coefficient by setting the ratio of the severity level of the information impact event to the maximum severity level, and then obtains the urgency coefficient by the inverse of the time threshold from the generation of information to the time when it must be processed. Finally, the impact range coefficient is obtained by the ratio of the area affected by the information to the entire station range. The safety importance coefficient, urgency coefficient and impact range coefficient are weighted and calculated to obtain the information priority coefficient. .

[0008] In a preferred embodiment, the potential analysis module substitutes the information change coefficient and the information priority coefficient into the logistic regression calculation formula as follows: ; In the formula, is the result of logistic regression calculation, i.e., the information potential evaluation coefficient, e is the natural base, and y is the linear combination term of the logistic regression model. Specifically, y can be set as: ; In the formula, is the bias term, For the The information variation coefficient of each substation information, For the The information priority coefficient of each substation information, and are the regression coefficients of information change coefficient and information priority coefficient respectively.

[0009] In a preferred embodiment, the potential analysis module is used to obtain the information potential evaluation coefficient and then compare and analyze the information potential evaluation coefficient with the continuously iterated potential threshold; If the information potential evaluation coefficient is greater than or equal to the potential threshold, the current substation information is marked as real-time collection potential information, and a real-time signal is generated; If the information potential evaluation coefficient is less than the potential threshold, the current substation information is marked as non-real-time collection potential information, and a non-real-time signal is generated; According to the marking results, the real-time collection potential information and the non-real-time collection potential information are counted, and a real-time collection potential information set and a non-real-time collection potential information set are established.

[0010] In a preferred embodiment, the default scoring module marks the real-time collection potential information set as L and the non-real-time collection potential information set as G; The parameters set in the default scoring combination mechanism are the number of information calls, the acceleration of information generation, the information burstiness index, and the relevance of information to the remaining information; The number of information calls refers to the number of times the information is called out and used; the acceleration of information generation refers to the variable of the information generation rate; the information burstiness index is calculated by calculating the ratio of the maximum frequency of information generation to the average frequency of information generation; each data in the information is preset with its corresponding weight, and the proportion of each data in other information is counted, and then the proportion of each data in other information is weightedly calculated with the corresponding weight to obtain the correlation between the information and the remaining information; The number of information calls and the acceleration of information generation are marked as a real-time information judgment parameter combination, and the information suddenness index and the correlation between information and remaining information are marked as a non-real-time information judgment parameter combination; The corresponding information call times and information generation acceleration in the real-time potential information set are weighted to obtain the real-time information judgment coefficient; the corresponding information suddenness index and the correlation between the information and the remaining information in the non-real-time potential information set are weighted to obtain the non-real-time information judgment coefficient; The real-time information judgment coefficient and the non-real-time information judgment coefficient are respectively substituted into the preset real-time judgment threshold and the non-real-time judgment threshold to determine the actual classification collection result of each information.

[0011] In a preferred embodiment, the reasonable evaluation module obtains the network status when each piece of information is uploaded based on the actual classification collection result of each piece of information, wherein the information transmission delay time is continuously collected through a network monitoring tool, the average value of the information transmission delay time is calculated, and the difference between the maximum value and the minimum value of the statistical information transmission delay time is added and calculated to obtain the network delay degree; The reasonable evaluation module obtains the current real-time transmission rate in the network through the network performance monitoring tool, and calculates the ratio with the total bandwidth capacity obtained from the device configuration to obtain the bandwidth utilization.

[0012] In a preferred embodiment, the reasonable evaluation module defines the network delay degree and bandwidth utilization as input variables, which are divided into different fuzzy sets respectively; The rationality result of the default scoring combination mechanism is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of network delay and bandwidth utilization on the rationality of the default scoring combination mechanism; Fuzzy reasoning is performed based on fuzzy rules to determine the rationality of the default scoring combination mechanism.

[0013] In a preferred embodiment, the default scoring combination mechanism rationality result obtained by the combination adjustment module includes the default scoring combination mechanism unreasonable result; Substitute the network delay and bandwidth utilization of each piece of information when it is uploaded into the parameters set in the default scoring combination mechanism to determine the process of adjusting the scoring combination mechanism as follows: A1: List the parameters set in the default scoring combination mechanism; A2: Quantify parameters and preset multiple groups of network delay levels and bandwidth utilization; A3: Detect the parameter values ​​of the parameters set in the default scoring combination mechanism under multiple groups of network delay levels and bandwidth utilization; A4: Count and mark the network delay and bandwidth utilization of each piece of information uploaded with the most repetitions; A5: Determine the combination of real-time and non-real-time detection parameters.

[0014] Technical effects and advantages of the present invention: 1. The present invention collects information variation coefficients and information priority coefficients, substitutes them into a logistic regression model, obtains information potential evaluation coefficients, and analyzes them with preset potential thresholds to obtain comparison results. Based on the comparison results, a real-time collection potential information set and a non-real-time collection potential information set are obtained, which are substituted into a default scoring combination mechanism to determine the actual classification collection results of each information, thereby improving the efficiency of information collection, dynamically adjusting the changing collection requirements, reducing the risk of subsequent processing, and improving the efficiency of information processing.

[0015] 2. The present invention obtains the actual classification and collection results of each information, obtains the network status when each information is uploaded, obtains the network delay degree and bandwidth utilization rate, substitutes them into fuzzy logic for fuzzy reasoning, determines the rationality result of the default scoring combination mechanism, and then substitutes the network delay degree and bandwidth utilization rate when each information is uploaded into the parameters set in the default scoring combination mechanism, determines to adjust the scoring combination mechanism, dynamically optimizes the scoring combination mechanism, improves network resource utilization, and reduces information redundancy and system burden. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a module schematic diagram of the intelligent automatic acquisition system of substation information of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1

[0018] The present invention discloses an intelligent automatic acquisition system for substation information, such as Figure 1 As shown, it includes a data acquisition module, a potential analysis module, a default scoring module, a reasonable evaluation module and a combination adjustment module; and the modules are connected by signals; The data acquisition module is used to collect information change characteristic information and information processing characteristic information, obtain information change coefficient and information priority coefficient through data processing, and send them to the potential analysis module; Specifically, data processing includes data type conversion, which refers to converting the raw data collected by the system into standardized data types; missing value processing, which refers to filling the missing data that may occur during the system collection process through interpolation and mean filling to ensure the continuity and integrity of the data, etc. The purpose of data processing is to make the data clearer and easier to understand, so that the system can calculate faster; Specifically, the above data operation methods are all existing technologies and will not be described in detail here; The information change characteristic information includes the information change coefficient, and the information processing characteristic information includes the information priority coefficient; Specifically, substation information includes transformers in the primary equipment collection information, secondary equipment collection information, environmental monitoring collection information, power operation collection information, etc. Each piece of information includes equipment data such as circuit breakers and protection devices, as well as environmental data such as temperature and humidity as well as voltage and current. The amount of information of a specific substation is not limited and will not be elaborated here. The information change coefficient refers to a parameter used to quantitatively describe the degree of dynamic change of substation information, reflecting the frequency and amplitude of information changes over time. Its acquisition logic is that the data acquisition module samples continuous data, records the amplitude and time interval of information content length changes, and records the processing time of the information. The ratio of the amplitude of information change to the time required for information change and the ratio of information processing time to the maximum acceptable processing time of the information is weighted and calculated to obtain the information change coefficient. ; For the Substation information; Specifically, the calculation formula of the information change coefficient is: ; In the formula, is the information variation coefficient, as well as are the change frequency weight and processing time weight respectively, is the magnitude of information change, The time required for information to change, The time required for information processing, The maximum acceptable processing time for the information; It should be noted that the amplitude of information change refers to the value or field of information that changes during the collection process. The larger the amplitude of change, the smaller the time required for information change, which means that the information change coefficient is larger, and the potential for real-time information collection is greater. At the same time, the time required for information processing refers to the time it takes for the system's built-in algorithm or model to process the information after receiving the information. For the processing time, the experimenter can set a time threshold to limit the division of the time required for information processing. The time required for information processing below the time threshold will not be substituted into the calculation to avoid excessive calculation frequency and excessive system memory. It is not limited here. Among them, the change frequency weight and processing time weight are set by the experimenter based on the changes in historical change frequency and processing time, and will not be elaborated here; The information priority coefficient refers to an indicator used to quantitatively describe the importance of each piece of information in the substation to the safety, stability and decision-making of the system operation. The acquisition logic of this coefficient is based on the importance, urgency and scope of influence of the information. The acquisition logic is that the data acquisition module obtains the safety importance coefficient by setting the ratio of the severity level of the information-affected event to the maximum severity level, and then obtains the urgency coefficient by the inverse of the time threshold from the generation of the information to the time it must be processed. Finally, the impact range coefficient is obtained by the ratio of the information-affected area to the entire station range. The safety importance coefficient, urgency coefficient and impact range coefficient are weighted and calculated to obtain the information priority coefficient. ; Among them, the severity level of the information impact event can be set by the experimenter through the other information of the substation radiated by the information loss. The higher the severity level, the more important the information, which means the greater the potential for real-time information collection. Real-time collection avoids the loss of other information of the substation due to information loss, etc. The setting of the severity level is not elaborated here; Furthermore, the time threshold from when information is generated to when it must be processed refers to the maximum delay time limit for processing information. For example, information such as current and voltage usually needs to be processed immediately after being collected. Therefore, the time threshold from when current and voltage information is generated to when it must be processed is generally very short. The greater the urgency coefficient, the greater the potential for real-time information collection. Furthermore, the information affected area refers to the set of physical ranges of the substation affected by the change of a certain information in the substation, reflecting the coverage and influence of a certain type of information on the operation of the entire substation system. Specifically, the larger the influence range coefficient, the greater the potential for real-time information collection; The potential analysis module is used to obtain the information change coefficient and the information priority coefficient, substitute them into the logistic regression model, obtain the information potential evaluation coefficient, and analyze it with the preset potential threshold to obtain the comparison result. According to the comparison result, the real-time collection potential information set and the non-real-time collection potential information set are divided and sent to the default scoring module; The information change coefficient and the information priority coefficient are normalized, and all input variables are converted to the same range to ensure that the contribution of each input to the model is balanced. Specifically, the normalization method is to normalize the [0,1] interval. The specific formula is: ; In the formula, is the information variation coefficient, is the normalized information change coefficient, is the minimum value of the information variation coefficient, is the maximum value of the information variation coefficient; The information priority coefficient is also normalized using the above formula, which will not be described in detail here. After normalization, the values ​​of the information change coefficient and the information priority coefficient are both in the range of [0, 1]. The system can make comparisons and decisions on a unified scale, thereby improving the accuracy and efficiency of the logistic regression model. The potential analysis module substitutes the information change coefficient and the information priority coefficient into the logistic regression calculation formula as follows: ; In the formula, is the result of logistic regression calculation, i.e., the information potential evaluation coefficient, e is the natural base, and y is the linear combination term of the logistic regression model. Specifically, y can be set as: ; In the formula, is the bias term, For the The information variation coefficient of each substation information, For the The information priority coefficient of each substation information, and are the regression coefficients of information change coefficient and information priority coefficient respectively; The logic of obtaining the potential threshold is to collect a set of substation information samples obtained by the experimenters in the laboratory, divide the data set into a training set and a test set, set the evaluation index and clustering algorithm, and in each round of cross-validation, train the model on the training set and evaluate the model performance on the test set. Then, adjust the potential threshold according to the performance of the validation set. Therefore, the potential threshold is constantly updated. In the present invention, clustering algorithm is a kind of unsupervised learning algorithm, which is used to divide the real-time substation information samples in the data set into groups or clusters with similarity; the common one is K-means clustering, which divides the real-time substation information samples in the data set into K clusters, so that the distance between each real-time substation information sample and the center point (center of mass) of its cluster is minimized, and finally the similarity between the real-time substation information samples is measured by the Euclidean distance, so as to set the potential threshold; The potential analysis module is used to obtain the information potential evaluation coefficient and then compare and analyze the information potential evaluation coefficient with the continuously iterated potential threshold; If the information potential evaluation coefficient is greater than or equal to the potential threshold, the current substation information is marked as real-time collection potential information, and a real-time signal is generated; If the information potential evaluation coefficient is less than the potential threshold, the current substation information is marked as non-real-time collection potential information, and a non-real-time signal is generated; Specifically, according to the marking results, the real-time collection potential information and the non-real-time collection potential information are counted, and a real-time collection potential information set and a non-real-time collection potential information set are established; Among them, non-real-time collection refers to irregular collection. The specific irregular time interval and interval frequency are not limited, but are set by the experimenters according to the actual implementation of the substation status, which will not be elaborated here; The default scoring module is used to obtain the real-time collection potential information set and the non-real-time collection potential information set, substitute them into the default scoring combination mechanism, determine the actual classification collection results of each information, and send them to the reasonable evaluation module; The default scoring module marks the real-time collection potential information set as L, and the specific set is expressed as ,in Collect potential information for the nth in real time; The non-real-time potential information collection set is marked as G, and the specific set is expressed as ,in Collect potential information for the mth non-real-time; Specifically, the default scoring combination mechanism refers to determining the actual classification collection results of the real-time collection potential information and the non-real-time collection potential information in the real-time collection potential information set and the non-real-time collection potential information set by substituting the set parameter combination; Among them, the parameters set in the default scoring combination mechanism are the number of information calls, the acceleration of information generation, the information burstiness index, and the relevance of information to the remaining information; Specifically, the number of information calls refers to the number of times the information is called out and used, for example, the number of times the information is clicked, etc. The information generation acceleration refers to the variable of the rate at which information is generated; The information burst index is calculated by the ratio of the maximum frequency of information generation to the average frequency of information generation. The maximum frequency of information generation is the maximum amount of data generated per unit time, and the average frequency of information generation is the average amount of data generated per unit time. Specifically, the unit time is determined by the experimenter based on the specific amount of substation information and the upload frequency, which will not be elaborated here; The correlation between information and remaining information is to preset the corresponding weight of each data in the information, and count the proportion of each data in other information, and then perform weighted calculation on the proportion of each data in other information and the corresponding weight to obtain the correlation between information and remaining information, which can reflect the strength of the correlation between information and remaining information; The number of information calls and the acceleration of information generation are marked as a real-time information judgment parameter combination, and the information suddenness index and the correlation between information and remaining information are marked as a non-real-time information judgment parameter combination; It should be noted that the default scoring combination mechanism determines the real-time information judgment parameter combination and the non-real-time information judgment parameter combination contained therein through the past big data model and data analysis results, that is, in any case, the real-time or non-real-time collection means of the analysis information in the default scoring combination mechanism is given priority, and the specific parameter combination division is not limited and will not be elaborated here; The corresponding information call times and information generation acceleration in the real-time potential information set are weighted to obtain the real-time information judgment coefficient; the corresponding information suddenness index and the correlation between the information and the remaining information in the non-real-time potential information set are weighted to obtain the non-real-time information judgment coefficient; Substitute the real-time information judgment coefficient and the non-real-time information judgment coefficient into the preset real-time judgment threshold and the non-real-time judgment threshold respectively. When the real-time information judgment coefficient is greater than or equal to the real-time judgment threshold, the real-time collection potential information is real-time collection; otherwise, the real-time collection potential information is non-real-time collection. When the non-real-time information judgment coefficient is greater than or equal to the non-real-time judgment threshold, the non-real-time collection potential information is non-real-time collection; otherwise, the non-real-time collection potential information is real-time collection. It should be noted that the preset real-time judgment threshold and the non-real-time judgment threshold are obtained by the experimenter through the real-time collection status and the non-real-time collection status of the historical substation information, respectively, and will not be elaborated here; The present invention collects information variation coefficients and information priority coefficients, substitutes them into a logistic regression model, obtains an information potential evaluation coefficient, and analyzes it with a preset potential threshold to obtain a comparison result. According to the comparison result, a real-time collection potential information set and a non-real-time collection potential information set are obtained, which are substituted into a default scoring combination mechanism to determine the actual classification collection result of each information, thereby improving the efficiency of information collection, dynamically adjusting the changing collection requirements, reducing the risk of subsequent processing, and improving the efficiency of information processing. Example 2

[0019] In Example 1 of the present invention, an example is given to illustrate that by collecting information variation coefficient and information priority coefficient, substituting them into a logistic regression model, obtaining information potential evaluation coefficient, and analyzing them with a preset potential threshold to obtain a comparison result, and according to the comparison result, dividing the real-time collection potential information set and the non-real-time collection potential information set, substituting them into the default scoring combination mechanism, and determining the operation strategy of the actual classification collection result of each information; however, in Example 1, only the default scoring mechanism combination is used to evaluate the actual classification collection result of each information. For information, it is usually unpredictable, and the collection and upload network is closely related. If the rationality of the default scoring mechanism combination is not determined first, it is impossible to improve the deep mining and understanding of the information, thereby causing redundant information collection, further extending the upload time, and delaying the subsequent process of processing and analysis; in view of the above problems, Example 2 of the present invention is further refined; The reasonable evaluation module is used to obtain the actual classification collection results of each information, obtain the network status when each information is uploaded, obtain the network delay degree and bandwidth utilization rate, substitute fuzzy logic for fuzzy reasoning, determine the rationality result of the default scoring combination mechanism, and send it to the combination adjustment module; Specifically, the actual classification collection result of each information includes the collection means of each information, including real-time collection and non-real-time collection. After the collection of each information is completed, the network status when each information is uploaded is monitored and combined into the actual classification collection result of each information; The logic for obtaining the degree of network delay is that the reasonable assessment module continuously collects the information transmission delay time through the network monitoring tool, calculates the average value of the information transmission delay time, and adds the difference between the maximum and minimum values ​​of the statistical information transmission delay time to obtain the degree of network delay; It should be noted that network monitoring tools include a series of monitoring tools such as ping. The selection of specific monitoring tools is obtained by the experimenters based on the actual network status, so they will not be described here. The logic of obtaining bandwidth utilization is to obtain the current real-time transmission rate in the network through the network performance monitoring tool, and calculate the ratio with the total bandwidth capacity obtained from the device configuration to obtain the bandwidth utilization; It should be noted that network performance monitoring tools include a series of network performance monitoring tools such as SNMP or NMS. The selection of specific network performance monitoring tools is obtained by the experimenters based on the actual network status, and will not be described here; For example, "High", "Low", and "Medium" for network latency and bandwidth utilization; Formulate a set of fuzzy rules to describe the impact of different input variables on output variables. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example: The network delay degree is marked as X, the bandwidth utilization is marked as U, and the default scoring combination mechanism rationality result is marked as C_results; Then we can define: Rule 1: IF (X is High) AND (U is Low) THEN (C_results is Low) Rule 2: IF (U is Low) AND (U is High) THEN (C_results is High) ... It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this embodiment takes three fuzzy sets as examples, the network delay degree and bandwidth utilization can actually be divided into more than three sets to facilitate better precise adjustment according to different adjustment heights.

[0020] Furthermore, for the judgment of the network delay degree and the bandwidth utilization rate, the threshold can be set according to the actual situation for judgment. For example, when the network delay degree value exceeds 65%, it is marked as "High", and when the bandwidth utilization value is lower than 34% of the overall coefficient, it is marked as "Low", etc., which will not be elaborated here; Specifically, the judgment of the rationality of the default scoring combination mechanism can be based on the quantitative value of the result or the number of the results. For example, the number of the rationality results of the default scoring combination mechanism marked as "Low" and "High" is counted. If the number of the rationality results of the default scoring combination mechanism marked as "Low" is greater than the number of the rationality results of the default scoring combination mechanism marked as "High", then the default scoring combination mechanism is unreasonable. Otherwise, the default scoring combination mechanism is reasonable, etc., which will not be elaborated here. The combination adjustment module is used to obtain the rationality result of the default scoring combination mechanism, substitute the network delay degree and bandwidth utilization rate when uploading each piece of information into the parameters set in the default scoring combination mechanism, and determine the adjustment of the scoring combination mechanism; The default score combination mechanism rationality results obtained by the combination adjustment module include the default score combination mechanism unreasonable results; Substitute the network delay and bandwidth utilization of each piece of information when it is uploaded into the parameters set in the default scoring combination mechanism to determine the process of adjusting the scoring combination mechanism as follows: A1: List the parameters set in the default scoring combination mechanism; Specifically, the parameters that have been set in the default scoring combination mechanism are listed, including the number of information calls, the acceleration of information generation, the information burstiness index, and the relevance of information to the remaining information; A2: Quantify parameters and preset multiple groups of network delay levels and bandwidth utilization; Specifically, the number of information calls, the acceleration of information generation, the information burst index, and the correlation between information and remaining information are quantified, and the network delay degree and bandwidth utilization rate when uploading multiple groups of information are preset; A3: Detect the parameter values ​​of the parameters set in the default scoring combination mechanism under multiple groups of network delay levels and bandwidth utilization; Specifically, the network delay degree and bandwidth utilization rate of each different information upload are substituted into the detection information call times, information generation acceleration, information burst index and the correlation between information and remaining information, and multiple groups of information call times, information generation acceleration, information burst index and the correlation between information and remaining information are obtained; A4: Count and mark the network delay and bandwidth utilization of each piece of information uploaded with the most repetitions; Specifically, four groups of network delays and bandwidth utilizations when uploading each piece of information are obtained, and the number of repetitions of the network delays and bandwidth utilizations when uploading each piece of information is counted respectively, and the network delays and bandwidth utilizations when uploading each piece of information with the most repetitions are selected for marking; A5: Determine the combination of real-time and non-real-time detection parameters; Specifically, the number of information calls, information generation acceleration, information burst index, and the correlation between information and remaining information are detected under the conditions of marked network delay degree and marked bandwidth utilization. The two largest values ​​are selected as the parameter combination for real-time detection, and the remaining two values ​​are selected as the parameter combination for non-real-time detection to determine the adjustment score combination mechanism; It should be noted that the network delay and bandwidth utilization when uploading multiple sets of information are set by the experimenter based on the historical substation information collection mode and historical network transmission status, and will not be elaborated here; What the experimenters can understand is that if the statistical repetition times in the values ​​of the four groups of network delay and bandwidth utilization are the same, a secondary screening processing method based on comprehensive priority is given, by introducing priority weights, calculating comprehensive scores and then comparing or setting the average method as a bottom-up mechanism, etc. The specific processing method is an existing technology and will not be described in detail here; The present invention obtains the actual classification collection results of each information, obtains the network status when each information is uploaded, obtains the network delay degree and bandwidth utilization rate, substitutes them into fuzzy logic for fuzzy reasoning, determines the rationality result of the default scoring combination mechanism, and then substitutes the network delay degree and bandwidth utilization rate when each information is uploaded into the parameters set in the default scoring combination mechanism, determines to adjust the scoring combination mechanism, dynamically optimizes the scoring combination mechanism, improves network resource utilization, and reduces information redundancy and system burden.

[0021] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0022] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0023] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0024] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0025] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0026] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0027] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0028] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0029] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0030] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Intelligent automatic acquisition system for substation information, characterized by: It includes data collection module, potential analysis module, default scoring module, reasonable evaluation module and combination adjustment module; signal connection between each module; The data acquisition module is used to collect information change characteristic information and information processing characteristic information, obtain information change coefficient and information priority coefficient through data processing, and send them to the potential analysis module; The potential analysis module is used to obtain the information change coefficient and the information priority coefficient, substitute them into the logistic regression model, obtain the information potential evaluation coefficient, and analyze it with the preset potential threshold to obtain the comparison result. According to the comparison result, the real-time collection potential information set and the non-real-time collection potential information set are divided and sent to the default scoring module; The default scoring module is used to obtain the real-time collection potential information set and the non-real-time collection potential information set, substitute them into the default scoring combination mechanism, determine the actual classification collection results of each information, and send them to the reasonable evaluation module; The reasonable evaluation module is used to obtain the actual classification collection results of each information, obtain the network status when each information is uploaded, obtain the network delay degree and bandwidth utilization rate, substitute fuzzy logic for fuzzy reasoning, determine the rationality result of the default scoring combination mechanism, and send it to the combination adjustment module; The combination adjustment module is used to obtain the rationality result of the default scoring combination mechanism, substitute the network delay degree and bandwidth utilization rate when uploading each information into the parameters set in the default scoring combination mechanism, and determine the adjustment of the scoring combination mechanism.

2. The intelligent automatic acquisition system for substation information according to claim 1 is characterized in that: The information change characteristic information includes the information change coefficient, and the information processing characteristic information includes the information priority coefficient. The data acquisition module samples continuous data, records the change amplitude and time interval of the information content length, and records the processing time of the information. The ratio of the amplitude of the information change to the time required for the information change and the ratio of the information processing time to the maximum acceptable processing time of the information are weighted and calculated to obtain the information change coefficient. ; For the Substation information; The data acquisition module obtains the safety importance coefficient by setting the ratio of the severity level of the information impact event to the maximum severity level, and then obtains the urgency coefficient by the inverse of the time threshold from the generation of information to the time when it must be processed. Finally, the impact range coefficient is obtained by the ratio of the area affected by the information to the entire station range. The safety importance coefficient, urgency coefficient and impact range coefficient are weighted and calculated to obtain the information priority coefficient. .

3. The intelligent automatic acquisition system for substation information according to claim 2 is characterized in that: The potential analysis module substitutes the information change coefficient and the information priority coefficient into the logistic regression calculation. The specific calculation formula is expressed as follows: ； In the formula, is the result of logistic regression calculation, i.e., the information potential evaluation coefficient, e is the natural base, and y is the linear combination term of the logistic regression model. Specifically, y can be set as: ； In the formula, is the bias term, For the The information variation coefficient of each substation information, For the The information priority coefficient of each substation information, and are the regression coefficients of information change coefficient and information priority coefficient respectively.

4. The intelligent automatic acquisition system for substation information according to claim 3 is characterized in that: The potential analysis module is used to obtain the information potential evaluation coefficient and then compare and analyze the information potential evaluation coefficient with the continuously iterated potential threshold; If the information potential evaluation coefficient is greater than or equal to the potential threshold, the current substation information is marked as real-time collection potential information, and a real-time signal is generated; If the information potential evaluation coefficient is less than the potential threshold, the current substation information is marked as non-real-time collection potential information, and a non-real-time signal is generated; According to the marking results, the real-time collection potential information and the non-real-time collection potential information are counted, and a real-time collection potential information set and a non-real-time collection potential information set are established.

5. The intelligent automatic acquisition system for substation information according to claim 4 is characterized in that: The default scoring module marks the real-time collection potential information set as L and the non-real-time collection potential information set as G; The parameters set in the default scoring combination mechanism are the number of information calls, the acceleration of information generation, the information burstiness index, and the relevance of information to the remaining information; The number of information calls refers to the number of times the information is called out and used; the acceleration of information generation refers to the variable of the information generation rate; the information burstiness index is calculated by calculating the ratio of the maximum frequency of information generation to the average frequency of information generation; each data in the information is preset with its corresponding weight, and the proportion of each data in other information is counted, and then the proportion of each data in other information is weightedly calculated with the corresponding weight to obtain the correlation between the information and the remaining information; The number of information calls and the acceleration of information generation are marked as a real-time information judgment parameter combination, and the information suddenness index and the correlation between information and remaining information are marked as a non-real-time information judgment parameter combination; The corresponding information call times and information generation acceleration in the real-time potential information set are weighted to obtain the real-time information judgment coefficient; the corresponding information suddenness index and the correlation between the information and the remaining information in the non-real-time potential information set are weighted to obtain the non-real-time information judgment coefficient; The real-time information judgment coefficient and the non-real-time information judgment coefficient are respectively substituted into the preset real-time judgment threshold and the non-real-time judgment threshold to determine the actual classification collection result of each information.

6. The intelligent automatic acquisition system for substation information according to claim 5 is characterized in that: The reasonable evaluation module obtains the network status of each information when it is uploaded based on the actual classification collection results of each information. Among them, through the network monitoring tool, the information transmission delay time is continuously collected, the average value of the information transmission delay time is calculated, and the difference between the maximum and minimum values ​​of the statistical information transmission delay time is added and calculated to obtain the network delay degree; The reasonable evaluation module obtains the current real-time transmission rate in the network through the network performance monitoring tool, and calculates the ratio with the total bandwidth capacity obtained from the device configuration to obtain the bandwidth utilization.

7. The intelligent automatic acquisition system for substation information according to claim 6 is characterized in that: The reasonable evaluation module defines the network delay degree and bandwidth utilization as input variables, which are divided into different fuzzy sets respectively; The rationality result of the default scoring combination mechanism is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of network delay and bandwidth utilization on the rationality of the default scoring combination mechanism; Fuzzy reasoning is performed based on fuzzy rules to determine the rationality of the default scoring combination mechanism.

8. The intelligent automatic acquisition system for substation information according to claim 7 is characterized in that: The default score combination mechanism rationality results obtained by the combination adjustment module include the default score combination mechanism unreasonable results; Substitute the network delay and bandwidth utilization of each piece of information when it is uploaded into the parameters set in the default scoring combination mechanism to determine the process of adjusting the scoring combination mechanism as follows: A1: List the parameters set in the default scoring combination mechanism; A2: Quantify parameters and preset multiple groups of network delay levels and bandwidth utilization; A3: Detect the parameter values ​​of the parameters set in the default scoring combination mechanism under multiple groups of network delay levels and bandwidth utilization; A4: Count and mark the network delay and bandwidth utilization of each piece of information uploaded with the most repetitions; A5: Determine the combination of real-time and non-real-time detection parameters.

Images