A power grid equipment state anomaly monitoring method based on big data

Abstract

The present application relates to the field of power system dispatch automation, in particular to a power grid equipment state abnormality monitoring method based on big data, comprising: obtaining the associated operation state data of each associated power grid equipment of each fault information obtained in each monitoring period, and adjusting the current transmission time interval of the associated operation state data of the associated power grid equipment according to the operation state data associated with other fault information. The present application can transmit the operation state data that has an influence on the fault information at a higher transmission frequency, so as to more accurately know the cause of the fault information.

Description

Technical Field

[0001] The present invention relates to the field of power system dispatching automation, and in particular to a method for monitoring abnormal power grid equipment status based on big data. Background Art

[0002] With the rapid development of big data analysis technology, it has been applied to the field of abnormal status monitoring of power grid equipment. For example, the patent document (CN110032557A) discloses a method and system for monitoring the abnormal status of power grid equipment based on big data. This solution performs structured data cleaning and analysis based on the partial mathematical modeling method of high-dimensional random matrices. It does not require the knowledge of the power system topology and parameter information during analysis, which can lower the professional threshold for data analysis and mining and improve the efficiency of abnormality identification. However, this solution is only used to determine whether the power grid equipment exists, and it cannot accurately know the cause of the abnormality of the power grid equipment. The accurate cause of the abnormality can help reduce the number of abnormalities in the power grid equipment. Therefore, accurately analyzing the cause of the abnormality of the power grid equipment is a topic worth exploring. Summary of the Invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is:

[0004] An embodiment of the present invention provides a method for monitoring abnormal power grid equipment status based on big data, the method comprising the following steps:

[0005] S100, obtaining the fault information set F of the power grid equipment monitored in the current monitoring period = {F i} i＝1……n If n≥n0, execute S200; n0 is the set quantity threshold, F i is the i-th fault information in F, F i =(U i , D i ), n is the number of fault information in F, U i is the fault ID corresponding to the i-th fault information, D i is the operating status dataset of the associated power grid equipment associated with the i-th fault information, D i ={d ij} j＝1……f(i) , d ij F i With D i The target operating status data set associated with the jth associated power grid device in the , f(i) is the number of associated power grid devices of the i-th fault information, d ij ={s ij r} r＝1……g(i，j) , s ij r d ijThe rth target running status data in d, g(i, j) is ij The number of target operating status data in;

[0006] S200, set i=1; execute S300.

[0007] S300, if i≤n, set j=1, execute S400, if i>n, exit the current control program.

[0008] S400, if j≤f(i), for d ij , based on the F in F i The target operating status data of the jth associated power grid equipment associated with the remaining fault information except i The candidate operating status data associated with the jth associated power grid device is obtained as F i For the associated operating status data associated with the j-th associated power grid device, execute S500; if j>f(i), set i=i+1 and execute S300.

[0009] S500, get F i The target weight of the associated operating status data associated with the jth associated power grid device, and the ... i The target weight corresponding to the associated operating status data associated with the j-th associated power grid device and the current transmission time interval are used to obtain a reference transmission time interval of the j-th associated power grid device in the next monitoring cycle; and S600 is executed.

[0010] S600: Based on the reference transmission time interval of the jth associated power grid device in the next monitoring cycle, i The current transmission time interval of the associated operating status data associated with the j-th associated power grid device is adjusted.

[0011] The present invention has at least the following beneficial effects:

[0012] An embodiment of the present invention provides a method for monitoring abnormal power grid equipment status based on big data. In each monitoring cycle, for the associated operating status data of each associated power grid device of each fault information, the current transmission time interval of the associated operating status data of the associated power grid device is adjusted according to the operating status data associated with other fault information. This enables the operating status data that affects the fault information to be transmitted at a higher transmission frequency, thereby enabling the cause of the fault information to be known more accurately.

[0013] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A flowchart of a method for monitoring abnormal power grid equipment status based on big data is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used herein in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0018] It should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of the steps can be performed in parallel, concurrently, or simultaneously. In addition, the order of the steps can be rearranged. A process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. A process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0019] The inventors of this invention recognize that in some practical application scenarios, different power grid devices may upload operating status data at different reporting intervals. This can result in the inability to determine whether fault information is related to the detected operating status data due to some data not being uploaded in a timely manner. Consequently, the cause of the fault information may not be accurately determined. In light of this, the present invention provides a method for monitoring power grid device status anomalies based on big data, aiming to obtain the cause of power grid device fault information as accurately as possible.

[0020] The embodiment of the present invention provides a method for monitoring abnormal state of power grid equipment based on big data, which may include: Figure 1The following steps are shown:

[0021] S100, obtaining the fault information set F of the power grid equipment monitored in the current monitoring period = {F i} i＝1……n If n≥n0, execute S200; n0 is the set quantity threshold, F i is the i-th fault information in F, F i =(U i , D i ), n is the number of fault information in F, U i is the fault ID corresponding to the i-th fault information, D i is the operating status dataset of the associated power grid equipment associated with the i-th fault information, D i ={d ij} j＝1……f(i) , d ij F i With D i The target operating status data set associated with the jth associated power grid device in the , f(i) is the number of associated power grid devices of the i-th fault information, d ij ={s ij r} r＝1……g(i，j) , s ij r d ij The rth target running status data in d, g(i, j) is ij The number of target operating status data in .

[0022] S200, set i=1; execute S300.

[0023] S300, if i≤n, set j=1, execute S400, if i>n, exit the current control program.

[0024] S400, if j≤f(i), for d ij , based on the F in F i The target operating status data of the jth associated power grid equipment associated with the remaining fault information except i The candidate operating status data associated with the jth associated power grid device is obtained as F i For the associated operating status data associated with the j-th associated power grid device, execute S500; if j>f(i), set i=i+1 and execute S300.

[0025] S500, get F i The target weight of the associated operating status data associated with the jth associated power grid device, and the ... iThe target weight corresponding to the associated operating status data associated with the j-th associated power grid device and the current transmission time interval are used to obtain a reference transmission time interval of the j-th associated power grid device in the next monitoring cycle; and S600 is executed.

[0026] S600: Based on the reference transmission time interval of the jth associated power grid device in the next monitoring cycle, i The current transmission time interval of the associated operating status data associated with the j-th associated power grid device is adjusted.

[0027] An embodiment of the present invention provides a method for monitoring abnormal power grid equipment status based on big data. In each monitoring cycle, for the associated operating status data of each associated power grid device of each fault information, the current transmission time interval of the associated operating status data of the associated power grid device is adjusted according to the operating status data associated with other fault information. This enables the operating status data that affects the fault information to be transmitted at a higher transmission frequency, thereby obtaining the operating status data related to the fault information, and furthermore, more accurately knowing the cause of the fault information.

[0028] Furthermore, in the embodiments of the present invention, power grid equipment primarily includes primary and secondary equipment. Primary equipment directly participates in the generation, transmission, distribution, and use of electrical energy, and includes generators, transformers, circuit breakers, disconnectors, transformers, transmission lines, and power cables. Secondary equipment, including relay protection devices, signaling devices, measurement and control devices, and metering devices, assists in monitoring, measuring, controlling, and protecting primary equipment and systems. The operating status data of power grid equipment includes steady-state data, dynamic data, and transient data. Steady-state data may include switch position changes, total fault signals, and protection action signals. Dynamic data may include synchronized phasor data collected in real time by PMUs. Transient data includes fault recordings. Power grid equipment operating status data can be accessed by data processing centers using ETL tools and stream computing. ETL tools are primarily used to extract, transform, and load data from commercial databases and time-series databases, and then load the data into data warehouses. Stream computing access is primarily used to access data collected in real time from real-time databases into stream computing systems.

[0029] In an embodiment of the present invention, fault information within each monitoring cycle can be obtained using existing methods, such as the technical solution disclosed in patent document CN110032557A. The fault ID can be the name of the fault. The length of the monitoring cycle can be set based on actual needs, for example, one week, one month, or six months.

[0030] In the embodiment of the present invention, the target operating status data associated with the fault information is the already determined operating status data that affects the fault information, and the target operating status data associated with the fault information can be obtained through existing methods.

[0031] In the embodiment of the present invention, n0 can be set based on actual needs. In an exemplary embodiment, n0=2.

[0032] Those skilled in the art know that if n<n0, it means that the monitored fault information is very small and there is little fault information to refer to. It is impossible to adjust the data transmission time interval within the current monitoring cycle based on the monitored fault information, that is, the data transmission time interval within the current monitoring cycle will not be adjusted, and wait for the fault information of the next monitoring cycle.

[0033] Further, in S400, the method based on the F is to remove F from the i The target operating status data of the jth associated power grid equipment associated with the remaining fault information except i The candidate operating status data associated with the j-th associated power grid device can be obtained by the following steps:

[0034] S401, traverse F, get d ij and D h The intersection of , if d ij and D h The intersection of ij , D h , add d ij The corresponding current associated data set; d ij The initial value of the corresponding current associated data set is empty, the value of h ranges from 1 to n-1, and the initial value of h is 1, and h≠i.

[0035] In the embodiment of the present invention, if d ij and D h The intersection of ij , indicating that the jth associated grid device is related to F i The associated running status data is also associated with the fault corresponding to the hth fault information, indicating that d ij It also affects the fault corresponding to the h-th fault information. In this way, we get ij Other related fault information.

[0036] S402, obtain d ij The intersection of all data in the corresponding current associated data set. If the intersection of all data is not empty, the running status data corresponding to the intersection is used as F i Candidate operating status data associated with the j-th associated power grid device.

[0037] In the embodiment of the present invention, due to d ij The corresponding faults of the current associated data set include i The corresponding faults have the same target operating status data. Therefore, the common target operating status data corresponding to the faults in these associated data sets may also affect F i Corresponding fault.

[0038] It is known to those skilled in the art that if d ij The intersection of all data in the corresponding current associated data set is empty, then F i The candidate operating status data associated with the j-th associated power grid device is empty, that is, there is no candidate operating status data.

[0039] Furthermore, in S500, F i The target weight Wt of the rth target operating status data associated with the jth associated power grid device ij The following conditions must be met:

[0040] Wt ij r =W1 ij r / ((∑ g(i，j) r＝1 W1 ij r )+(∑ z(i，j) k＝1 W2 ij k ).

[0041] Among them, W1 ij r F i The initial weight of the rth target operating status data associated with the jth associated power grid device, W2 ij k F i The initial weight of the kth candidate operating status data associated with the jth associated power grid device, k ranges from 1 to z(i, j), z(i, j) is F i The number of candidate operating status data associated with the jth associated power grid device, W2 ij k Based on d ij The number of power grid devices corresponding to the corresponding current associated data set is determined.

[0042] Furthermore, in S500, F i The target weight Wc of the kth candidate operating status data associated with the jth associated power grid device ij k The following conditions must be met:

[0043] Wc ij k =W2 ij k / ((∑ g(i，j) r＝1 W1 ij r )+(∑ z(i，j) k＝1 W2 ij k ).

[0044] In an exemplary embodiment of the present invention, W1 ij 1 =……=W1 ij r =……=W1 ij g(i，j) ;W2 ij 1 =……=W2 ij k =……=W2 ij z(i，j) , that is, the initial weights of all target operating state data are the same, and the initial weights of all candidate operating state data are the same. In a specific embodiment, W1 ij r =1,W2 ij k =m / f(i), where m is d ij The number of faults corresponding to the current associated data set, for example, if f(i) = 10, d ij The number of faults corresponding to the corresponding current associated data set is 5, and the initial weight of the candidate operating status data is 5 / 10=0.5.

[0045] Furthermore, in S500, the jth associated grid device has a reference transmission time interval Δt in the next monitoring cycle. j next The following conditions must be met:

[0046] △t j next =∑ p(i，j) x＝1 W ij x ×△t ij x ;

[0047] Among them, W ij x F i The target weight of the xth associated operating status data associated with the jth associated power grid device, x ranges from 1 to p(i, j), p(i, j) is Fi The number of associated operating status data associated with the jth associated power grid device, △t ij x F i The current transmission time interval corresponding to the x-th associated operating status data associated with the j-th associated power grid device is, that is, the current reporting period of the operating status data.

[0048] Furthermore, S600 specifically includes:

[0049] If △t ij x ≤△t j next , indicating that the reporting cycle of the operating status data is reasonable and does not need to be adjusted, that is, △t is not adjusted. ij x Otherwise, it means that the reporting cycle of the running status data is unreasonable and the data is not reported in time, which needs to be adjusted, that is, set △t ij x =△t j next .

[0050] Furthermore, the method for monitoring abnormal power grid equipment status based on big data provided by an embodiment of the present invention may further include the following steps:

[0051] If at least one candidate operating status data of a certain associated power grid device corresponding to a certain fault information monitored in the current monitoring cycle does not exist in the target operating status data of the associated power grid device associated with the fault information monitored in the current monitoring cycle, the current transmission time interval of the at least one candidate operating status data is adjusted to the transmission time interval corresponding to the previous monitoring cycle.

[0052] If at least one candidate operating status data of a certain associated power grid device corresponding to a certain fault information monitored in the current monitoring cycle does not exist in the target operating status data of the associated power grid device associated with the fault information monitored in the current monitoring cycle, it means that the fault information may not be associated with the at least one candidate operating status data, and its current transmission time interval can be adjusted to the transmission time interval of the previous monitoring cycle.

[0053] Those skilled in the art know that if at least one candidate operating status data of a certain associated power grid device corresponding to a certain fault information monitored in the current monitoring cycle does not exist in the target operating status data of the certain associated power grid device associated with the fault information monitored in the current monitoring cycle, its current transmission time interval may not be adjusted.

[0054] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed herein are achieved, which is not limited herein.

[0055] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for monitoring abnormal status of power grid equipment based on big data, characterized in that: The method comprises the following steps: S100, obtain the fault information set F of the power grid equipment monitored in the current monitoring period = {F i } i=1……n If n≥n0, execute S200; n0 is the set quantity threshold, F i is the i-th fault information in F, F i =(U i , D i ), n is the number of fault information in F, U i is the fault ID corresponding to the i-th fault information, D i is the operating status dataset of the associated power grid equipment associated with the i-th fault information, D i ={d ij } j=1……f（i） , d ij F i With D i The target operating status data set associated with the jth associated power grid device in the , f (i) is the number of associated power grid devices of the i-th fault information, d ij ={s ij r } r=1……g（i，j） , s ij r d ij The rth target running status data in d, g(i, j) is ij The number of target operating status data in; S200, set i=1; execute S300; S300, if i≤n, set j=1, execute S400, if i>n, exit the current control program; S400, if j≤f(i), for d ij , based on the F in F i The target operating status data of the jth associated power grid equipment associated with the remaining fault information except i The candidate operating status data associated with the jth associated power grid device is obtained as F i For the associated operating status data associated with the j-th associated power grid device, execute S500; if j>f(i), set i=i+1 and execute S300; S500, get F i The target weight of the associated operating status data associated with the jth associated power grid device, and the ... i The target weight corresponding to the associated operating status data associated with the j-th associated power grid device and the current transmission time interval are used to obtain a reference transmission time interval of the j-th associated power grid device in the next monitoring cycle; executing S600; S600: Based on the reference transmission time interval of the jth associated power grid device in the next monitoring cycle, i The current transmission time interval of the associated operating status data associated with the j-th associated power grid device is adjusted.

2. The method according to claim 1, characterized in that In S400, the method based on the F is to divide F i The target operating status data of the jth associated power grid equipment associated with the remaining fault information except i The candidate operating status data associated with the j-th associated power grid device is obtained by the following steps: S401, traverse F, get d ij and D h The intersection of , if d ij and D h The intersection of ij , D h Join d ij The corresponding current associated data set; d ij The initial value of the corresponding current associated data set is empty, the value of h ranges from 1 to n-1, and the initial value of h is 1, and h≠i; S402, obtain d ij The intersection of all data in the corresponding current associated data set. If the intersection of all data is not empty, the running status data corresponding to the intersection is used as F i Candidate operating status data associated with the j-th associated power grid device.

3. The method according to claim 2, characterized in that In S500, F i The target weight Wt of the rth target operating status data associated with the jth associated power grid device ij r The following conditions are met: Wt ij r =W1 ij r / ((∑ g（i，j） r=1 W1 ij r )+(∑ z（i，j） k=1 W2 ij k ); W1 ij r F i The initial weight of the rth target operating status data associated with the jth associated power grid device, W2 ij k F i The initial weight of the kth candidate operating status data associated with the jth associated power grid device, where k ranges from 1 to z(i, j), and z(i, j) is F i The number of candidate operating status data associated with the jth associated power grid device, W2 ij k Based on d ij The number of power grid devices corresponding to the corresponding current associated data set is determined.

4. The method according to claim 3, characterized in that In S500, F i The target weight Wc of the kth candidate operating status data associated with the jth associated power grid device ij k The following conditions are met: Toilet ij k =W2 ij k / ((∑ g（i，j） r=1 W1 ij r )+(∑ z（i，j） k=1 W2 ij k ).

5. The method according to claim 3, characterized in that In S500, the reference transmission time interval Δt of the jth associated grid device in the next monitoring cycle j next The following conditions are met: △t j next =∑ p（i，j） x=1 IN ij x ×△t ij x ; Among them, W ij x F i The target weight of the xth associated operating status data associated with the jth associated power grid device, x ranges from 1 to p(i, j), p(i, j) is F i The number of associated operating status data associated with the jth associated power grid device, △t ij x F i The current transmission time interval corresponding to the x-th associated operating status data associated with the j-th associated power grid device.

6. The method according to claim 5, characterized in that W1 ij 1 =……=W1 ij r =……=W1 ij g（i，j） ; W2 ij 1 =……=W2 ij k =……=W2 ij z（i，j） 。 7. The method according to claim 6, characterized in that W1 ij r =1,W2 ij k =m / f(i), m is d ij The number of faults corresponding to the current associated data set.

8. The method according to claim 5, characterized in that S600 specifically includes: If △t ij x ≤△t j next , without adjusting △t ij x Otherwise, set △t ij x =△t j next .

9. The method according to claim 1, characterized in that The following steps are also included: If at least one candidate operating status data of a certain associated power grid device corresponding to a certain fault information monitored in the current monitoring cycle does not exist in the target operating status data of the associated power grid device associated with the fault information monitored in the current monitoring cycle, the current transmission time interval of the at least one candidate operating status data is adjusted to the transmission time interval corresponding to the previous monitoring cycle.

10. The method according to claim 1, characterized in that The operating status data includes steady-state data, dynamic data and transient data.

Images