Electric power communication data processing system based on big data

Abstract

The invention discloses an electric power communication data processing system based on big data, and relates to the technical field of electric power communication. The system comprises a data acquisition module, a data analysis module, a real-time prediction module and an early warning module. According to the invention, a data acquisition module is used to acquire fault log data corresponding to power communication network abnormity based on big data; further processing to obtain a fault association database, sending the fault association database to a data analysis module, and analyzing the fault association database to obtain a fault association probability value; the power communication data is acquired in real time according to the distributed acquisition data network, the power communication data is predicted in real time according to the fault association probability value, an abnormal early warning signal is acquired and sent to the early warning module, and the power communication data is regulated and controlled according to the abnormal early warning signal; and the power communication network prediction capability is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power communication, and specifically to a power communication data processing system based on big data. Background Art

[0002] The power communication network came into being to ensure the safe and stable operation of the power system; it, together with the relay protection and safety and stability control system of the power system and the dispatching automation system, is collectively referred to as the three major pillars for the safe and stable operation of the power system; it is even more the basis for grid dispatching automation, network operation marketization, and management modernization; it is an important means to ensure the safe, stable, and economic operation of the power grid; it is an important infrastructure of the power system; therefore, it is necessary to conduct safety monitoring on power communication; if a fault occurs in power communication, it will cause the inability to monitor key parameters such as voltage and current of substations and transmission and distribution lines in real time, which may lead to misjudgment or missed judgment; it may also cause communication interruption, which may prevent the protection device from receiving correct instructions, resulting in mis-tripping of the circuit breaker or failure to cut off the fault in time, expanding the power outage scope; However, in the prior art, the fault monitoring of power communication usually monitors through a fixed monitoring period, discovers anomalies, transmits the abnormal data through communication equipment, obtains abnormal signals, and then processes them; but due to the diversity of the types of faults corresponding to the faults, it is usually impossible to accurately obtain the fault type, lacking the ability of fault prediction, and thus unable to detect and process faults in time, resulting in adverse effects; therefore, in order to solve the above problems, the present invention provides a power communication data processing system based on big data. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention provides a power communication data processing system based on big data; The object of the present invention can be achieved through the following technical solutions: A power communication data processing system based on big data, the system includes a data acquisition module, a data analysis module, a real-time prediction module, and an early warning module; The data acquisition module is used to collect fault log data corresponding to anomalies in the power communication network based on big data; and process it to obtain a fault association database; The data analysis module is used to analyze the fault association database to obtain a fault association probability value; The real-time prediction module is provided with a distributed data acquisition network, which is used to collect power communication data in real time, and perform real-time prediction on the power communication data according to the fault association probability value to obtain an abnormal early warning signal; The early warning module is used to regulate the power communication data according to the abnormal early warning signal.

[0004] Further, the process by which the data acquisition module collects fault log data corresponding to anomalies in the power communication network based on big data includes: Obtain a number of communication devices corresponding to the power communication network, and collect the basic parameters corresponding to each communication device; Collect historical abnormal communication devices and historical abnormal environment data corresponding to anomalies in the power communication network based on big data; If there are historical abnormal communication devices or historical abnormal environment data, obtain the historical communication device abnormal data corresponding to the basic parameters of each historical abnormal communication device; and then obtain the abnormal type, abnormal time point corresponding to the historical communication device abnormal data and abnormal environment data, and the warning information corresponding to the abnormal type; If not, obtain historical other abnormal data, where the historical other abnormal data includes other abnormal types, the abnormal time points corresponding to other abnormal types, and the warning information corresponding to other abnormal types; Integrate the historical abnormal communication devices, historical abnormal environment data, and historical other abnormal data to generate fault log data.

[0005] Further, the process of obtaining the fault correlation database includes: Schedule and integrate the historical communication device abnormal data, historical abnormal environment data, and historical other data corresponding to the same abnormal time point in the fault log data to generate a historical time point database; and schedule and integrate the historical communication device abnormal data and historical abnormal environment data to generate a historical abnormal type database; then schedule and integrate the historical other abnormal data to generate a historical other abnormal type database; Integrate the historical time point database, historical abnormal type database, and historical other abnormal type database to generate a fault correlation database.

[0006] Further, the process by which the data analysis module analyzes the fault correlation database to obtain the abnormal probability value includes: Obtain the total quantity corresponding to all abnormal types in each historical time point database, and obtain the historical total quantity of abnormal types in all historical time point databases, and then obtain the ratio of the total quantity in each historical time point database to the historical total quantity, denoted as the abnormal time probability value; Obtain the total quantity corresponding to the coexistence of historical abnormal communication devices and historical abnormal environment data in the historical abnormal type database, marked as the double-layer abnormal quantity, and obtain the total quantity corresponding to only historical abnormal communication devices, marked as the abnormal device quantity, and similarly obtain the total quantity corresponding to only historical abnormal environment data, marked as the abnormal environment quantity; According to the total number of anomaly types in the historical anomaly database, which is marked as the total number of anomalies, calculate the ratios of the double-layer anomaly quantity, the anomaly device quantity, and the anomaly environment quantity to the total number of anomalies respectively, and mark them as the double-layer anomaly probability value, the anomaly device probability value, and the anomaly environment probability value respectively.

[0007] Further, the process of obtaining the fault association library according to the anomaly probability value includes: Integrate the same historical other anomaly types in the historical other anomaly type database and obtain the corresponding total quantity, which is marked as the other anomaly type quantity, and obtain the total quantity corresponding to the other anomaly types in the historical other anomaly type database, which is marked as the historical other total quantity. Then calculate the ratios of each other anomaly type quantity to the historical other total quantity, and mark them as the other fault type probability values, and connect the other fault key sets with the corresponding historical other fault types; Connect the anomaly time probability value with the historical time point database to generate a time - fault key set; Connect the double-layer anomaly probability value, the anomaly device probability value, and the anomaly environment probability value with the historical anomaly type database to generate an environment - device fault key set; Merge the time - fault key set, the environment - device fault key set, and the other fault key sets to generate a fault association library.

[0008] Further, the real-time prediction module is provided with a distributed data acquisition network. The process of real-time collecting power communication data includes: Obtain a number of monitoring devices corresponding to the power communication network and number them, denoted as i, where i takes positive integer values; connect the monitoring nodes generated by each monitoring device to form a distributed data acquisition network.

[0009] Further, the process of real-time predicting power communication data according to the fault association probability value and obtaining an anomaly warning signal includes: Set the anomaly threshold range and anomaly difference range corresponding to the monitoring node, obtain the normal power communication data according to the anomaly threshold range; and send the normal power communication data to the fault association library in real time to obtain the historical anomaly types corresponding to the difference from the normal power communication data in the fault association database within the anomaly difference range, and mark the possible anomaly types; Obtain the corresponding fault association library according to the possible anomaly types, and perform mapping to obtain the corresponding anomaly probability value. Obtain the corresponding fault association library according to the possible anomaly types, and perform mapping to obtain the corresponding anomaly probability value. Calculate the weights of several possible anomaly types within the anomaly difference range to obtain the corresponding possible anomaly probability value; Obtain several warning messages corresponding to the possible anomaly types, and send them to the communication terminals connected to the monitoring devices with the corresponding numbers to generate an anomaly warning signal; Set the prediction time points corresponding to the possible abnormal types of the monitoring nodes, send them to the corresponding time-fault key set, obtain the corresponding abnormal time probability values and warning information, and send the warning information to the communication terminal connected to the monitoring device with the corresponding number to generate an abnormal warning signal.

[0010] Furthermore, the process of the warning module regulating the power communication data according to the abnormal warning signal includes: Obtain the abnormal warning signal, and according to the abnormal warning signal, obtain the possible abnormal types, the possible abnormal probability values corresponding to the possible abnormal types, the prediction time points, and the abnormal time probabilities corresponding to the prediction time points; Obtain the corresponding number, obtain the corresponding monitoring device according to the number, and then regulate the power communication data according to the possible abnormal types, the possible abnormal probability values corresponding to the possible abnormal types, the prediction time points, and the abnormal time probabilities corresponding to the prediction time points.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention uses the data acquisition module and collects the fault log data corresponding to the anomalies of the power communication network based on big data; then processes it to obtain the fault association database and sends it to the data analysis module, analyzes the fault association database to obtain the fault association probability value; collects the power communication data in real time according to the distributed data acquisition network, and makes a real-time prediction of the power communication data according to the fault association probability value, obtains the abnormal warning signal and sends it to the warning module, and regulates the power communication data according to the abnormal warning signal; improves the prediction ability of the power communication network. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0013] Figure 1 It is the schematic diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0015] Such as Figure 1As shown in the figure, a power communication data processing system based on big data, the system includes a data acquisition module, a data analysis module, a real-time prediction module, and an early warning module; The data acquisition module is used to collect fault log data corresponding to the anomalies of the power communication network based on big data; and perform preprocessing to obtain a fault association database; The data analysis module is used to analyze the fault association database to obtain a fault association probability value; The real-time prediction module is provided with a distributed data acquisition network, which is used to collect power communication data in real time, and perform real-time prediction on the power communication data according to the fault association probability value to obtain an anomaly warning signal; The early warning module is used to regulate the power communication data according to the anomaly warning signal.

[0016] It should be further noted that the process of the data acquisition module collecting fault log data corresponding to the anomalies of the power communication network based on big data includes: Obtain a number of communication devices corresponding to the power communication network, and collect the device information corresponding to each communication device; the device information includes device coding and device location; obtain the corresponding basic parameters according to the device information; Collect historical abnormal communication devices and historical abnormal environment data corresponding to the anomalies of the power communication network based on big data; If there are historical abnormal communication devices or historical abnormal environment data, then obtain the historical communication device abnormal data of the basic parameters corresponding to each historical abnormal communication device; furthermore, obtain the abnormal type, abnormal time point, recovery time point, influence range corresponding to the historical communication device abnormal data and abnormal environment data, and the warning information corresponding to the abnormal type; If not, obtain historical other abnormal data, the historical other abnormal data includes other abnormal types and the abnormal time point, recovery time point, influence range corresponding to other abnormal types, and the warning information corresponding to other abnormal types; Integrate the historical abnormal communication devices, historical abnormal environment data, and historical other abnormal data to generate fault log data; In the above embodiment, it should be further noted that the basic parameters include but are not limited to electrical parameters such as voltage, current, power, etc., device temperature, vibration frequency, etc.; the environment data includes natural environment and computer room environment, the natural environment includes but is not limited to temperature, humidity, wind speed, rainfall, etc.; the computer room environment includes but is not limited to temperature and humidity, dust concentration, air quality, etc.; the warning information includes but is not limited to device abnormal states (such as overload, overheat), network attacks, intrusions, etc.; It should be further noted that perform preprocessing to obtain a fault association database; including: Schedule the integration of historical communication device exception data, historical exception environment data, and historical other data corresponding to the same abnormal time points in the scheduling fault log data to generate a historical time point database; schedule the integration of historical communication device exception data and historical exception environment data to generate a historical exception type database; and then schedule the integration of historical other exception data to generate a historical other exception type database; Integrate the historical time point database, the historical exception type database, and the historical other exception type database to generate a fault association database; In the above embodiments, it should be further noted that several historical fault types are integrated and preprocessed to obtain databases of different types; different types of data are associated with the fault types to generate a fault association database, which can better improve the prediction ability.

[0017] It should be further noted that the data analysis module analyzes the fault association database to obtain an abnormal probability value, and obtains a fault association library according to the abnormal probability value; including: Obtain the total number corresponding to all abnormal types in each historical time point database, and obtain the historical total number of abnormal types in all historical time point databases, and then obtain the ratio of the total number in each historical time point database to the historical total number, which is denoted as the abnormal time probability value; Connect the abnormal time probability value with the historical time point database to generate a time - fault key set; Obtain the total number corresponding to the co - existence of historical abnormal communication devices and historical abnormal environment data in the historical exception type database, which is marked as the double - layer abnormal quantity; and obtain the total number corresponding to only historical abnormal communication devices, which is marked as the abnormal device quantity; similarly, obtain the total number corresponding to only historical abnormal environment data, which is marked as the abnormal environment quantity; According to the total number of abnormal types in the historical exception database, which is marked as the abnormal total quantity, calculate the ratios of the double - layer abnormal quantity, the abnormal device quantity, and the abnormal environment quantity to the abnormal total quantity, and mark them as the double - layer abnormal probability value, the abnormal device probability value, and the abnormal environment probability value respectively; Connect the double - layer abnormal probability value, the abnormal device probability value, and the abnormal environment probability value with the historical exception type database to generate an environment - device fault key set; Integrate the same historical other abnormal types in the historical other abnormal type database and obtain the corresponding total number, which is marked as the other abnormal type quantity, and obtain the total number corresponding to other abnormal types in the historical other abnormal type database, which is marked as the historical other total quantity, and then calculate the ratio of each other abnormal type quantity to the historical other total quantity, which is marked as the other fault type probability value, and connect it with the corresponding historical other fault type to form an other fault key set; Merge the time-fault key set, environment-equipment fault key set, and other fault key sets to generate a fault association library.

[0018] In the above embodiments, it should be further noted that the time-fault key set, environment-equipment fault key set, and other fault key sets are related to the corresponding probability values, and the probability values are related to the quantities in the corresponding historical time point database, historical abnormal type database, and historical other abnormal type database of the fault association database; among them, when the fault association database changes, the corresponding probability value changes; improve the comprehensiveness of the fault types in the fault association database and the accuracy of the probability values.

[0019] It should be further noted that the real-time prediction module is provided with a distributed data acquisition network for real-time collecting power communication data and performing real-time prediction on the power communication data according to the fault association probability value to obtain an abnormal warning signal; including: Obtain a number of monitoring devices corresponding to the power communication network and number them, denoted as i, where i takes positive integer values; connect the monitoring nodes generated by each monitoring device to form a distributed data acquisition network; Set the abnormal threshold range and abnormal difference range corresponding to the monitoring node, obtain the normal power communication data according to the abnormal threshold range; and send the normal power communication data to the fault association library in real time to obtain the historical abnormal types corresponding to the difference between the normal power communication data and the fault association database within the abnormal difference range, and mark the possible abnormal types; Obtain the corresponding fault association library according to the possible abnormal types, perform mapping to obtain the corresponding abnormal probability value, and calculate the weights of several possible abnormal types within the abnormal difference range to obtain the corresponding possible abnormal probability value; Obtain several warning messages corresponding to the possible abnormal types, and send them to the communication terminal connected to the monitoring device with the corresponding number to generate an abnormal warning signal; Set the prediction time point corresponding to the possible abnormal type of the monitoring node, send it to the corresponding time-fault key set, obtain the corresponding abnormal time probability value and warning message, and send the warning message to the communication terminal connected to the monitoring device with the corresponding number to generate an abnormal warning signal; In the above embodiments, it should be further noted that performing abnormal prediction on the normal power communication data can better predict and process in advance to ensure the integrity of the power communication network.

[0020] Obtain the abnormal warning signal, and obtain the possible abnormal type, the possible abnormal probability value corresponding to the possible abnormal type, the prediction time point, and the abnormal time probability corresponding to the prediction time point according to the abnormal warning signal; Obtain the corresponding number, obtain the corresponding monitoring device according to the number, and then regulate the power communication data according to the possible abnormal types, the possible abnormal probability values corresponding to the possible abnormal types, the prediction time points, and the abnormal time probabilities corresponding to the prediction time points.

[0021] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in combination with the accompanying drawings and specific embodiments; it should be understood that the specific embodiments described herein are only intended to explain the present application, rather than limiting the present application; for those skilled in the art, the present application can be implemented without some of these specific details; the above description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.

[0022] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A power communication data processing system based on big data, characterized in that A power communication data processing system based on big data, the system includes a data acquisition module, a data analysis module, a real-time prediction module, and an early warning module; The data acquisition module is used to collect fault log data corresponding to the abnormality of the power communication network based on big data; and process it to obtain a fault association database; The data analysis module is used to analyze the fault association database to obtain a fault association probability value; The real-time prediction module is provided with a distributed data acquisition network, which is used to collect power communication data in real time, and perform real-time prediction on the power communication data according to the fault association probability value to obtain an abnormal early warning signal; The early warning module is used to regulate the power communication data according to the abnormal early warning signal.

2. The power communication data processing system based on big data according to claim 1, characterized in that, The process of the data acquisition module collecting fault log data corresponding to the abnormality of the power communication network based on big data includes: Obtain several communication devices corresponding to the power communication network, and collect the basic parameters corresponding to each communication device; Collect historical abnormal communication devices and historical abnormal environment data corresponding to the abnormality of the power communication network based on big data; If there are historical abnormal communication devices or historical abnormal environment data, obtain the historical communication device abnormal data corresponding to the basic parameters of each historical abnormal communication device; and then obtain the abnormal type, abnormal time point corresponding to the historical communication device abnormal data and abnormal environment data, and the early warning information corresponding to the abnormal type; If not, obtain historical other abnormal data, where the historical other abnormal data includes other abnormal types, the abnormal time points corresponding to other abnormal types, and the early warning information corresponding to other abnormal types; Integrate the historical abnormal communication devices, historical abnormal environment data, and historical other abnormal data to generate fault log data.

3. A power communication data processing system based on big data according to claim 2, characterized in that, The process of obtaining the fault association database includes: Schedule the historical communication device abnormal data, historical abnormal environment data, and historical other data corresponding to the same abnormal time point in the fault log data to be integrated to generate a historical time point database; and schedule the historical communication device abnormal data and historical abnormal environment data to be integrated to generate a historical abnormal type database; and then schedule the historical other abnormal data to be integrated to generate a historical other abnormal type database; Integrate the historical time point database, historical abnormal type database, and historical other abnormal type database to generate a fault association database.

4. A power communication data processing system based on big data according to claim 3, characterized in that, The process of the data analysis module analyzing the fault association database to obtain an abnormal probability value includes: Obtain the total number corresponding to all abnormal types in each historical time point database, and obtain the historical total number of abnormal types in all historical time point databases, and then obtain the ratio of the total number in each historical time point database to the historical total number, denoted as the abnormal time probability value; Obtain the total number corresponding to the coexistence of historical abnormal communication devices and historical abnormal environment data in the historical abnormal type database, marked as the double-layer abnormal number, and obtain the total number corresponding to only historical abnormal communication devices, marked as the abnormal device number, and similarly obtain the total number corresponding to only historical abnormal environment data, marked as the abnormal environment number; Based on the total number of anomaly types in the historical anomaly database, which is marked as the total number of anomalies, calculate the ratios of the double-layer anomaly quantity, the anomaly device quantity, and the anomaly environment quantity to the total number of anomalies respectively, and mark them as the double-layer anomaly probability value, the anomaly device probability value, and the anomaly environment probability value respectively.

5. A power communication data processing system based on big data according to claim 4, characterized in that, The process of obtaining the fault association library according to the anomaly probability value includes: Integrate the same historical other anomaly types in the historical other anomaly type database and obtain the corresponding total quantity, which is marked as the other anomaly type quantity, and obtain the total quantity corresponding to the other anomaly types in the historical other anomaly type database, which is marked as the historical other total quantity. Then calculate the ratio of each other anomaly type quantity to the historical other total quantity, and mark it as the other fault type probability value, and connect the other fault key sets with the corresponding historical other fault types; Connect the anomaly time probability value with the historical time point database to generate a time - fault key set; Connect the double-layer anomaly probability value, the anomaly device probability value, and the anomaly environment probability value with the historical anomaly type database to generate an environment - device fault key set; Merge the time - fault key set, the environment - device fault key set, and the other fault key sets to generate a fault association library.

6. A power communication data processing system based on big data according to claim 5, characterized in that, The real-time prediction module is provided with a distributed data acquisition network. The process of real-time collecting power communication data includes: Obtain a number of monitoring devices corresponding to the power communication network and number them, denoted as i, where i takes positive integer values; connect the monitoring nodes generated by each monitoring device to form a distributed data acquisition network.

7. A power communication data processing system based on big data according to claim 6, characterized in that, The process of real-time predicting power communication data according to the fault association probability value and obtaining an anomaly warning signal includes: Set the anomaly threshold range and anomaly difference range corresponding to the monitoring node, and obtain the normal power communication data according to the anomaly threshold range; and send the normal power communication data to the fault association library in real time to obtain the historical anomaly types corresponding to the difference from the normal power communication data in the fault association database within the anomaly difference range, and mark the possible anomaly types; Obtain the corresponding fault association library according to the possible anomaly types and perform mapping to obtain the corresponding anomaly probability value. Obtain the corresponding fault association library according to the possible anomaly types and perform mapping to obtain the corresponding anomaly probability value. Calculate the weights of several possible anomaly types within the anomaly difference range to obtain the corresponding possible anomaly probability value; Obtain several warning messages corresponding to the possible anomaly types and send them to the communication terminal connected to the monitoring device with the corresponding number to generate an anomaly warning signal; Set the prediction time point corresponding to the possible anomaly type of the monitoring node, send it to the corresponding time - fault key set, obtain the corresponding anomaly time probability value and warning message, and send the warning message to the communication terminal connected to the monitoring device with the corresponding number to generate an anomaly warning signal.

8. A power communication data processing system based on big data according to claim 7, characterized in that, The process of the warning module regulating the power communication data according to the anomaly warning signal includes: Obtain the anomaly warning signal, and obtain the possible anomaly type, the possible anomaly probability value corresponding to the possible anomaly type, the prediction time point, and the anomaly time probability corresponding to the prediction time point according to the anomaly warning signal; Obtain the corresponding number, obtain the corresponding monitoring device according to the number, and then regulate the power communication data based on the possible abnormal types, the possible abnormal probability values corresponding to the possible abnormal types, the prediction time points, and the abnormal time probabilities corresponding to the prediction time points.

Images