JP2020080630A - Electric power system monitoring system, electric power system monitoring method and program - Google Patents

Abstract

To provide an electric power system monitoring system, an electric power system monitoring method and a program, which can facilitate visualization of a relation between data utilized during preparation of an evaluation model, and input data.SOLUTION: The electric power system monitoring system has an estimation unit, a stability evaluation unit, a generation unit and a display control unit. The estimation unit estimates a second system state which is a system state of power system equipment in a second time point after predetermined time from a first time point. The stability evaluation unit derives stability of the power system equipment which is predicted after an assumed accident, in such a manner that the second system state estimated by the estimation unit and information on an accident assumed in the second system state are input into an evaluation model subjected to learning as input data. The generation unit generates the input data to be input into the evaluation model and an influence degree display image indicating a degree of influence on derivation of stability in each item in the input data. The display control unit displays the influence degree display image generated by the generation unit on a display unit.SELECTED DRAWING: Figure 1

Description

  Embodiments of the present invention relate to a power system monitoring system, a power system monitoring method, and a program.

  It is known that computer simulation is used to evaluate the stability of electric power systems. However, when using the simulation, there is a problem that complicated mathematical analysis processing takes time. Related to this, there is known a technique for evaluating the stability of a power system by using a neural network. In this technique, for example, after performing stability evaluation, machine learning is performed based on input data to create an evaluation model for performing stability evaluation. At this time, for example, the dimension reduction method of the principal component analysis is used to visualize the difference between the input data and the input data used when creating the evaluation model in two dimensions. However, the input data includes various data, and also includes data that makes a small contribution to the stability evaluation. For this reason, due to the influence of data that has a small contribution to the stability evaluation, even if the dimension reduction method of the principal component analysis is used to make the data two-dimensional, it may not be successfully visualized.

JP-A-2-162404

  The problem to be solved by the present invention is to provide a power system monitoring system, a power system monitoring method, and a program that can make it easier to see the relationship between the data used when creating an evaluation model by machine learning and the input data.

  The power system monitoring system according to the embodiment includes an estimation unit, a stability evaluation unit, a generation unit, and a display control unit. The estimating unit, based on a first system state that is a system state of the power system facility at the first time point, a second system state that is a system state of the power system facility at a second time point after a predetermined time from the first time point. To estimate. The stability evaluation unit inputs the second system state estimated by the estimation unit and information on an accident assumed in the second system state into the learned evaluation model as input data, thereby performing the estimation. The stability of the power system equipment predicted after the accident is derived. The generation unit generates an influence degree display image indicating the influence degree on the input data input to the evaluation model and the degree of influence on the derivation of the stability of each item in the input data. The display control unit causes the display unit to display the influence degree display image generated by the generation unit.

The figure which shows an example of a structure of the electric power system monitoring system 10 of embodiment. The figure which shows an example of the content of the assumption accident case information 13A of embodiment. The figure which shows the example of the probability distribution of the renewable energy output prediction of embodiment. The figure which shows an example of the renewable energy output prediction information 13B of embodiment. The figure which shows an example of the content of node data. The figure which shows an example of the content of branch data. The figure which shows an example of a structure of the learning process part 40. The figure which shows an example of several system state data Dt and several stability St. A reference diagram for explaining an example of processing and an evaluation model by learning part 43. The figure which shows an example of the estimated data De and several stability Se. The figure which shows an example of the influence display image IP. The figure which shows an example of selection image CP. The figure which shows an example of the stability display image SP. The figure which shows an example of the stability determination image SJ. The figure which shows an example of a low reliability data image. The figure which shows an example of another low reliability data image. The flowchart which shows an example of the flow of the whole process in the power system monitoring system 10.

  Hereinafter, a power system monitoring system, a power system monitoring method, and a program according to embodiments will be described with reference to the drawings.

  FIG. 1 is a diagram illustrating an example of a configuration of a power system monitoring system 10 of the embodiment. The power system monitoring system 10 is a system that estimates the stability of a future system state of the power system (power system equipment) 21.

  The power system monitoring system 10 estimates a future system state (after a predetermined time, for example, 30 minutes or 60 minutes after the present time) based on the current system state of the power system 21. In addition, the power system monitoring system 10 monitors, for example, the supply and demand state of the power system 21 and estimates the control content for the power system 21 that is executed when an expected accident occurs. The power system monitoring system 10 derives the stability of the power system 21 in the event of a possible accident based on these estimation results. Specific evaluation items for the stability of the power system 21 include, for example, overload, voltage stability, transient stability, and frequency stability. When the values of these items exceed (or fall below) a predetermined management value (threshold value), the power system monitoring system 10 causes a failure or dropout of equipment included in the power system 21 to cause a power failure. Therefore, it is determined that the stability of the power system 21 is low.

[Power system 21]
First, the power system 21 will be described. The power system 21 includes, for example, a plurality of generators 22, a plurality of renewable energy power sources 23 (23-1, 23-2, 23-3, 23-4,...) And a plurality of consumers 24 (24. -1,...) are connected. The generator 22 is, for example, a large-scale generator that performs thermal power generation, hydraulic power generation, nuclear power generation, and the like. The renewable energy power source 23 is, for example, a power generation facility that uses renewable energy such as sunlight and wind power. Renewable energy power supply 23 can be constructed on a variety of scales. The individual renewable energy power sources 23 and the customers 24 may be grouped by region, for example, grouped by regions 31 (31-1, 31-2, 31-3). The pattern of the regional set 31 may be set arbitrarily and can be set in various patterns not limited to the illustration.

  Further, the power system 21 serves as a device for cooperating with the power system monitoring system 10 and includes a plurality of measuring devices 25 (25-1, 25-2,..., 25-m) and a plurality of control terminal devices 26. (26-1, 26-2,..., 26-m). m is an arbitrary natural number.

  The plurality of measuring devices 25 measure the system status at each of the locations (branches and nodes) included in the power system 21, and provide information indicating the measured system status (hereinafter referred to as system status information) to the power system monitoring system. Send to 10. The system state includes, for example, the voltage, phase, power flow, transformer load, generator output, etc. at each branch or each node. The tidal current is an index indicating the magnitude of electricity flow at various places in a state where electricity is flowing, and is represented by magnitudes such as active power and reactive power.

  The control terminal device 26 controls the system control device and the generator 22 (output amount and the like), suppresses the output of the renewable energy power source 23, and the like based on the control command received from the power system monitoring system 10. The system control device includes, for example, a phase advancing capacitor, a shunt reactor, an SVC (Static Var Compensator), and the like.

[Power system monitoring system 10]
Next, the power system monitoring system 10 will be described. The power system monitoring system 10 includes, for example, an input unit 11, a display unit 12, a storage unit 13, a data management unit 14, a system information collection unit 15, a system state estimation unit (estimation unit) 16, and stability. The evaluation unit 17, the control content determination unit 18, the generation unit 19, the display control unit 20, and the learning processing unit 40 are provided. The power system monitoring system 10 includes one or more processors. The power system monitoring system 10 may be a single computer device or may be a computer device distributed in two or more. For example, only the input unit 11 and the display unit 12 are realized by a terminal device such as a PC, and the storage unit 13, the data management unit 14, the system information collection unit 15, the system state estimation unit 16, and the stability evaluation unit 17 are provided. The control content determination unit 18, the generation unit 19, and the display control unit 20 may be realized by a server device or the like connected to a terminal device via a network.

  The input unit 11 includes, for example, some or all of various keys, buttons, dial switches, a mouse, a touch panel integrally formed with the display unit 12, and the like. Further, the input unit 11 may be a connection unit that is electrically connected to an external device. The display unit 12 is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) display device.

  The storage unit 13 is, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory such as an SSD, an HDD, or the like. The storage unit 13 stores information such as expected accident case information 13A, renewable energy output prediction information 13B, demand prediction information 13C, operation plan information 13D, and first system information 13E. The storage unit 13 may be an external storage device such as a NAS (Network Attached Storage) accessible by the power system monitoring system 10 via a network.

  The expected accident case information 13A is information about a presumed expected accident in the power system 21. Typical examples of assumed accidents that have been classified in advance include a transmission line failure, a bus failure, a generator failure (a failure of the generator 22), and a transformer failure. FIG. 2 is a diagram showing an example of the contents of the assumed accident case information 13A of the embodiment. As illustrated in FIG. 2, the assumed accident case information 13A is, for example, information in which an accident target location and an accident aspect are associated with identification information (for example, an accident number) that identifies each accident. .. The accident target location is a location where an accident is expected to occur in the electric power system 21. The accident target location is information indicating the location and is represented by, for example, a track number, a node name, a branch name, or the like. The accident aspect is a type of accident that occurs in the electric power system 21. The information such as "3Φ3LG" in the figure is a code indicating the aspect of the accident. Hereinafter, the combination of the accident number, the target location of the accident, and the appearance of the accident will be referred to as an accident type.

  The renewable energy output prediction information 13B is information on a predicted value predicted as the output of the renewable energy power supply 23 in the future (for example, 30 minutes or 60 minutes after the present time). The renewable energy power supply 23 has an uncertainty that its output changes due to the influence of weather or the like. The renewable energy output prediction information 13B is represented by, for example, a probability distribution in consideration of uncertainty.

  FIG. 3 is a diagram illustrating an example of a probability distribution of renewable energy output prediction according to the embodiment. In the graph of FIG. 3, the vertical axis represents the probability of occurrence and the horizontal axis represents the renewable energy output. As shown in FIG. 3, the renewable energy output is defined as having some probability distribution because the output varies. Uncertainty in renewable energy output is represented, for example, by defining the range of the output to be within ±σ (σ: standard deviation) of the predicted value (68.27%).

  Note that this range can be arbitrarily determined. For example, the range of the renewable energy output may be defined to be within ±2σ or ±3σ of the predicted value, or an index other than the standard deviation, for example, The capacity ratio of the renewable energy power source 23 may be used to define the inside of ±10% of the predicted value. The renewable energy output prediction information 13B including such uncertainty is stored in the storage unit 13 for each renewable energy power source 23 or each regional set 31.

  FIG. 4 is a diagram showing an example of the renewable energy output prediction information 13B of the embodiment. As shown in FIG. 4, in the renewable energy output prediction information 13B, a renewable energy output predicted value and a value corresponding to ±σ in the probability distribution are given for each area (regional set 31). For example, the predicted value of the output related to the renewable energy power source 23 includes a value larger than the predicted value by a predetermined amount (for example, predicted value +σ) and a value smaller than the predicted value by a predetermined amount (for example, predicted value −σ). By using such renewable energy output prediction information 13B, the power system monitoring system 10 can predict the future power system 21 for any combination pattern of system states including renewable energy output that fluctuates due to uncertainty. It is possible to evaluate whether or not the reliability of can be maintained.

  The demand prediction information 13C is information that predicts the magnitude of demand in each time zone of the day (for example, every 30 minutes), and is highly accurately predicted from the experience rule of the system operator and the like. The operation plan information 13D is information on a predetermined operation plan of the power system 21, such as turning on/off of the phase-modulating equipment, starting/stopping the generator 22, and increasing/decreasing the output of the generator 22.

  Each functional unit of the data management unit 14, the system information collection unit 15, the system state estimation unit 16, the stability evaluation unit 17, the control content determination unit 18, the generation unit 19, and the display control unit 20 is, for example, a CPU (Central Processing). It is realized by a processor such as Unit) executing a program (software). In addition, some or all of these functional units are hardware (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), or other hardware ( It may be realized by a circuit unit (including circuitry), or may be realized by cooperation of software and hardware. The program may be stored in advance in a storage device such as an HDD (Hard Disk Drive) or a flash memory, or may be stored in a removable storage medium such as a DVD or a CD-ROM, and the storage medium may be stored in the drive device. It may be installed by being attached.

  The data management unit 14 stores, in the storage unit 13, information input by the operator of the power system 21 using the input unit 11, for example. Further, the data management unit 14 may store information received from an external device via the network in the storage unit 13.

  The system information collecting unit 15 collects various information regarding the current system state of the power system 21 (hereinafter, referred to as the first system state) based on the system information received from the measuring device 25 installed in the power system 21. . The system information collection unit 15 may output the collected information to the system state estimation unit 16 or may store it in the storage unit 13 as a part of the first system information 13E. The first system state is a state of electric power supplied by the power system 21 at the present time, and includes, for example, at least one of voltage, phase, load, generator output, and power flow at a plurality of locations in the power system 21.

  The first system information 13E includes, for example, node data and branch data. FIG. 5 is a diagram showing an example of the contents of the node data. FIG. 6 is a diagram showing an example of the content of branch data. The node data shown in FIG. 5 includes a voltage, a phase, a generator output (active power output, reactive power output), a load (active power load, reactive power load), and a phase-adjustment facility for the node name. This is information associated with information. The branch data shown in FIG. 6 is information in which the active power flow, the reactive power flow, the active power loss, and the reactive power loss information are associated with the branch name.

  The system state estimation unit 16 estimates a future system state of the power system 21 (hereinafter, referred to as a second system state) based on the current system state (first system state) of the power system 21. The system state estimation unit 16 may acquire the information indicating the first system state from the system information collection unit 15 or may read it from the storage unit 13. When estimating the second system state, the grid state estimation unit 16 further predicts the output value of the renewable energy power source 23 (renewable energy output prediction information 13B), demand forecast related to power demand (demand forecast information 13C), Reference is also made to the operation plan (operation plan information 13D) regarding the power supply in the power system 21. Moreover, the system state estimation unit 16 may estimate the plurality of second system states by changing the predicted value according to the range of the predicted value predicted as the output of the renewable energy power source 23.

  The stability evaluation unit 17 is assumed by inputting the second system state estimated by the system state estimation unit 16 and an accident expected in the second system state (supposed accident case information 13A) into the evaluation model. The stability in the power system 21 after the accident is derived. When deriving the stability, the stability evaluation unit 17 determines a number of items of the second system state (voltages and phases of nodes a, b, c... Shown in FIG. 5, active current output of the generator, invalidity). The power output and the like and the active power flow and reactive power flow of each branch A, B, C... Shown in FIG. 6 are input to the evaluation model. The large number of items of the second system state include those having a large degree of influence on the derived stability (influence degree) and those having a small degree of influence.

  The evaluation model is, for example, a learned model generated by the learning processing unit 40. The evaluation model is information generated by an external learning processing device and may be stored in the storage unit 13. The stability is an index indicating the stability of power supply in the power system 21, and includes, for example, at least one of an overload margin, a transient stability margin, a voltage stability margin, and a frequency stability margin. ..

  The control content determination unit 18 determines whether the stability derived by the stability evaluation unit 17 is an unstable level. For example, the control content determination unit 18 determines that the stability is an unstable level when the stability is equal to or lower than a threshold value (for example, 1.05). When it is determined that the stability is the unstable level, the control content determination unit 18 determines, among the devices in the power system 21, a device that can control an input variable having a high correlation with the stability as a predetermined amount or more. To decide. The control content determination unit 18 determines a control content for the determined control target device so that the stability is not at an unstable level, and transmits a control command based on the determined control content to the control terminal device 26. The control terminal device 26 controls the system control device and the generator 22 (output amount and the like) and suppresses the output of the renewable energy power source 23 based on the received control command.

  The generation unit 19 generates output information to be displayed on the display unit 12, and outputs the generated output information to the display control unit 20. The generation unit 19 generates, for example, influence degree information, stability information, and stability determination information as output information. The degree-of-influence information is information regarding the degree-of-impact display image that displays each item of the second system state and the expected accident type. The stability information is information about a stability display image that displays each item of the second system state, the type of assumed accident, and the stability. The stability determination information is information regarding the stability determination image that displays the estimated stability display point on the stability display image. The generation unit 19 stores a distance threshold value for performing stability determination. Information regarding the image generated by the generation unit 19 will be described later.

  The display control unit 20 controls the display unit 12 to display an image. The display control unit 20 causes the display unit 12 to display an image based on the output information generated by the generation unit 19. For example, the display control unit 20 causes the display unit 12 to display the influence degree display image based on the influence degree information output by the generation unit 19. The display control unit 20 also causes the display unit 12 to display the stability display image based on the stability information output by the generation unit 19. The display control unit 20 also causes the display unit 12 to display a stability determination image based on the stability determination information output by the generation unit 19.

[Learning processing unit 40]
The learning processing unit 40 generates an evaluation model. FIG. 7 is a diagram illustrating an example of the configuration of the learning processing unit 40. As illustrated in FIG. 7, the learning processing unit 40 includes, for example, a data acquisition unit 41, a storage unit 42, a learning unit 43, and a derivation unit 44. The learning processing unit 40 may be realized by the power system monitoring system 10 or an external device. Some or all of the functional units of the data acquisition unit 41, the learning unit 43, and the derivation unit 44 are realized by a processor such as a CPU executing a program (software). Further, some or all of these functional units may be realized by hardware such as LSI, ASIC, FPGA, GPU, or may be realized by cooperation of software and hardware. The storage unit 42 is realized by, for example, a RAM, a ROM, a flash memory such as an SSD, an HDD, or the like. The storage unit 42 stores, for example, system state data 42A, stability 42B, evaluation model 42C, and the like.

  The data acquisition unit 41 acquires the system state data Dt and the stability St and stores them in the storage unit 42 as a part of the system state data 42A and a part of the stability 42B, respectively. FIG. 8 is a diagram showing an example of a plurality of system state data Dt and a plurality of stability St. The plurality of system state data Dt includes system state data Dt(1), Dt(2),... Dt(n), for example. n is a natural number. The system status data Dt includes information indicating an assumed system status and the like. With respect to each system state data Dt, a plurality of stability St is derived by simulation for each assumed accident type. For example, the plurality of stability St(1)-1, St(1)-2,..., St(1)-k are k assumed accidents assumed in the system state indicated by the system state data Dt(1). The stability is derived by simulation for each type.

  The learning unit 43 generates an evaluation model that is a learned model by learning the relationship between the system state data Dt acquired by the data acquisition unit 41 and the stability St for each accident. For example, the learning unit 43 optimizes the discriminator so that when the system information included in each system state data Dt is input as a vector element to a discriminator such as a neural network, a result reaching a simulation result is obtained. An evaluation model is generated by obtaining various parameters and is stored in the storage unit 42 as an evaluation model 42C.

  Here, an example of the processing by the learning unit 43 and the evaluation model will be described with reference to FIG. 9. FIG. 9 is a reference diagram for explaining an example of the processing by the learning unit 43 and the evaluation model. The learning unit 43 generates the evaluation model Em by executing machine learning for each accident based on the plurality of system state data Dt and the plurality of stability St. The evaluation model Em derives stability by inputting input data (explanatory variables). For example, when the input data is the estimated data De, the evaluation model Em derives the stability Se. When the input data is the system state data Dt, the evaluation model Em derives the stability Stm.

  The estimation data De includes information indicating the second system state estimated by the system state estimating unit 16 and information indicating the expected accident type used when estimating the second system state. FIG. 10 is a diagram showing an example of the estimated data De and the plurality of stability levels Se. The plurality of estimated data De includes, for example, estimated data De(1), De(2)... De(j). j is a natural number. Each estimated data De includes information indicating the second system state, information indicating the expected accident type assumed in the second system state, and the like. For each estimated data De, a plurality of stability levels Se are derived for each type of expected accident using an evaluation model. For example, the plurality of stability levels Se(1)-1, Se(1)-2,..., Se(1)-k are k assumed accident types assumed in the system state indicated by the estimated data De(1). It is the stability derived using the evaluation model for each.

[Generation of impact display image]
When generating the impact degree display image, the generation unit 19 outputs a plurality of second system states and expected accident case information which are a plurality of input data input to the evaluation model when the stability evaluation unit 17 derives the stability. Calculate the slope of each input data for 13A. The gradient here indicates the rate of change in stability with respect to changes in the respective values of the plurality of input data, and for example, the partial derivative of each of the plurality of input data (for example, all input data) input to the evaluation model It is obtained by collecting them as a vector. The slope is an index value indicating how much the stability changes when the input data changes. The generation unit 19 calculates the absolute value of the calculated gradient, and calculates the gradient information in which the data is standardized for each pattern in which the plurality of second system states and the assumed accident case information 13A are combined.

  Based on the calculated gradient information, the generation unit 19 selects, from the input data, large influence input data that has a large influence on the calculation of the stability of the system state data by the evaluation model used by the stability evaluation unit 17. The generation unit 19 stores a threshold value when selecting the large influence input data. The generation unit 19 compares the gradient of the input data with the threshold value, and selects the input data that is greater than or equal to the threshold value as the large influence input data. The generation unit 19 omits input data other than the large influence input data and generates the following image from the remaining input data.

[Regarding Image Generated by Generating Unit 19]
An image generated by the generation unit 19 and displayed by the display control unit 20 on the display unit 12 will be described. The image generated by the generation unit 19 and displayed by the display control unit 20 on the display unit 12 includes information on the influence display image, the stability display image, and the stability determination image. FIG. 11 is a diagram showing an example of the influence degree display image IP. The display control unit 20 (see FIG. 1) displays the influence degree display image IP shown in FIG. 11 on the display unit 12. As shown in FIG. 11, the influence degree display image IP is an image in which display sections having the same area are arranged in a matrix. The influence degree display image IP indicates the derived influence degree by the shade of the display of each display section. A large number of input data (input 1, input 2, input 3,..., Input n) of models such as nodes, branches and contingencies in the second system state are arranged on the horizontal axis of the impact degree display image IP. . On the vertical axis of the influence degree display image IP, pattern numbers of patterns in which a plurality of second system states and the assumed accident case information 13A are combined are arranged. Each display section shows each item in the plurality of second system states and the derived impact degree of the supposed accident type assumed in the second system state. Further, as the input data here, for example, system state data shown in FIG. 8 is used.

  In each display section in the influence display image IP, the derived influence degree is indicated by the density of the display section. In each display section, a color having a higher density (lighter color) is displayed in the display section as the influence degree is larger, and a color having a lower density (dark color) is displayed in the display section as the influence degree is smaller. On the right side of the influence display image, a sample bar SB indicating the relationship between the display shade and the derived influence is displayed. The derived influence degree for each input data may be displayed by characters or images other than the influence degree display image IP shown in FIG. 11.

  The generation unit (selection unit) 19 selects the large influence input data from the data (input data) shown in each display section of the influence degree display image IP. For example, the input data whose density shown in each display section is equal to or higher than a predetermined density is selected as the large influence input data. The selection of the large influence input data may be performed by the generation unit 19 or may be selected by the user who views the influence degree display image IP. The selection unit may be provided as a configuration different from that of the generation unit 19.

  FIG. 12 is a diagram showing an example of the selected image CP. As shown in FIG. 12, the selected image CP includes an image of a button for allowing the user to select the large influence input data. As shown in FIG. 12, the generation unit 19 generates information about the images of the check box BT10, the all-selection button BT11, and the all-selection cancel button BT12 as selection buttons that the user can select, together with the influence degree display image IP. You may do it. In this case, the display control unit 20 causes the display unit 12 to display the check box BT10, the all selection button BT11, and the all selection release button BT12 shown in FIG. In this example, the large influence input data is selected for each input number. For example, the input data included in the “input 1” is selected as the large influence input data by performing the operation of checking the check box under the “input 1”. Further, by unchecking the check box, the selection as the large influence input data is canceled. By operating the all-select button BT11, all the check boxes are checked, and by operating the all-select cancel button BT12, all the check boxes are unchecked. The input data may be selected not for each input number but for each input data. Further, the sample bar SB may be displayed in FIG. Further, in the selected image, not the selection button but the contents of selectable large influence input data may be displayed, and the user may select the large influence input data by another input means such as a keyboard.

  FIG. 13 is a diagram showing an example of the stability display image SP. The display control unit 20 causes the display unit 12 to display the stability display image SP shown in FIG. As shown in FIG. 13, the stability display image SP is a diagram in which stability display points ST on the XYZ space which is a vectorized space are plotted. The stability display point ST is an n-dimensionalized input data (n=natural number, here 2) obtained by two-dimensionalizing (n-dimensionalizing) the input data by a principal component analysis. Is the value of the X coordinate and the value of the Y coordinate, and the value indicating the stability derived from this input data is the value of the Z coordinate. The display unit 12 displays a stability display image SP including a large number of stability display points ST corresponding to a large number of input data.

  In the example shown in FIG. 13, in a region where the first principal component is small, that is, 0.00 to 0.02, the second principal component has stability in a relatively wide range of 0.6 to −0.4. The display point ST is plotted. Further, in the range of 0.6 to -0.4 where the second principal component is large, the stability becomes higher as the second principal component becomes smaller, and in the range where the second principal component is smaller than -0.4, the second principal component becomes smaller. There is a tendency for the stability to decrease as the value increases. In these regions, the plotted stability display points ST rise to a large number and are displayed as if they were rod-shaped.

  In the area where the second principal component is large, the stability display points ST are grouped in many areas where the first principal component is small. The stability display point ST is displayed over a wide area of the first principal component. In particular, in a small area where the second principal component is less than −0.4, stability display points ST are scattered in a wide area of 0.02 to 0.08, and further exceeding 0.08.

  FIG. 14 is a diagram showing an example of the stability determination image SJ. The display control unit 20 causes the display unit 12 to display the stability determination image shown in FIG. As shown in FIG. 14, the stability determination image SJ is an image in which the estimated stability display point PST is displayed on the stability display image SP shown in FIG. 13. The estimated stability display point PST uses the values of the first and second principal components obtained by two-dimensionally analyzing the input data by the principal component analysis as the X coordinate value and the Y coordinate value. This is the point where the value indicating the derived stability is taken as the value of the Z coordinate. The estimated data shown in FIG. 10 is used as the input data here.

  The stability determination image SJ displays the stability display point ST obtained from the system state data and the estimated stability display point PST obtained from the estimation data. Various data are included in the input data when the estimated stability display point PST is generated, and it is conceivable that the input data that is significantly different from the input data used in generating the evaluation model is included. The generation unit 19 obtains the shortest distance between the stability display point ST and the estimated stability display point PST (the distance between the estimated stability display point PST and the closest stability display point ST). When the shortest distance between the stability display point ST and the estimated stability display point PST is greater than or equal to a predetermined distance threshold, the generation unit 19 uses the evaluation model when generating the estimated stability display point PST. The input data (estimated data) that has been input is determined to be low reliability data. As described above, the determination of low reliability data may be performed by the generation unit 19, or may be performed by an operator visually checking the stability determination image SJ displayed on the display unit 12.

  The generation unit 19 also generates a low-reliability data image regarding the input data determined to be low-reliability data. The generation unit 19 may express the information related to the input data determined as the low reliability data in another form such as a tabular format instead of the reliability data image. The generation unit 19 outputs information regarding the low reliability data image to the display control unit 20, and the display control unit 20 causes the display unit 12 to display the low reliability data image based on the information output by the generation unit 19. FIG. 15 is a diagram showing an example of a low reliability data image. As shown in FIG. 15, in the low reliability data image, the contents of the input data with the input numbers are listed. For example, the low-reliability data image when the input data of the input number 1 is low-reliability data is, as shown in FIG. 15, “aV:1.01 θ:15 GEO:1.00 GIO:0.20... Numerical values of the node name, voltage, phase, active power output of the generator,... Shown in FIG. 5 are listed. By displaying the low reliability data, the operator is notified of the contents of the low reliability data.

  The low-reliability data image is displayed on the display unit 12 by the display control unit 20 when a click operation is performed with the pointer placed on the estimated stability display point PST determined to be low-reliability data, for example. It The low reliability data image may be displayed on the display unit 12 by another operation.

  FIG. 16 is a diagram showing an example of another stability determination image SJ1. While one estimated stability display point PST is displayed on the stability determination image SJ shown in FIG. 13, a plurality of estimated stability display points are displayed on the stability determination image SJ1 as shown in FIG. The point PST is displayed. In this way, by displaying the plurality of estimated stability display points PST, it is possible to determine whether or not the plurality of input data are low reliability data. Further, by displaying the estimated stability display point PST for a plurality of input data, it is possible to confirm the similarity of the input data regarding the patterns of the plurality of input data. Also in the stability determination image SJ1 shown in FIG. 16, when the click operation is performed with the pointer placed on the estimated stability display point PST, the low reliability data image is displayed on the display unit 12 by the display control unit 20. It may be done.

  FIG. 17 is a flowchart showing an example of the overall processing flow in the power system monitoring system 10. Note that in the following description, processing for displaying an image such as an influence degree display image will be mainly described.

  First, the system information collecting unit 15 collects system information indicating the first system state, which is the current system state of the power system 21 (step S101). The system state estimation unit 16 estimates a second system state, which is a future system state of the power system 21, based on the system information indicating the first system state (step S102). The stability evaluation unit 17 inputs the second system state estimated by the system state estimation unit 16 and an accident expected in the second system state (supposed accident case information 13A) to the evaluation model Em, and thereby the assumption is made. The stability Se in the power system 21 after the accident is derived (step S103).

  Next, the generation unit 19 generates output information for causing the display control unit 20 to display the influence degree display image and the like on the display unit 12 (step S104). Then, the generation unit 19 outputs the output information for displaying the influence degree display image to the display control unit 20. Thereby, the display control unit 20 causes the display unit 12 to display the influence degree display image (step S105). Next, the generation unit 19 determines whether or not a display instruction of the stability display image has been received using the input unit 11 (step S106). The generation unit 19 outputs the output information for displaying the specified stability display image to the display control unit 20 according to the instruction received using the input unit 11. Thereby, the display control unit 20 causes the display unit 12 to display the stability display image (step S107). When the generation unit 19 has not received the instruction to display the stability display image, the generation unit 19 skips step S107 and proceeds to step S108.

  Next, the generation unit 19 determines whether or not a display instruction of the stability determination image is received using the input unit 11 (step S108). The generation unit 19 outputs the output information for displaying the specified stability determination image to the display control unit 20 according to the instruction received using the input unit 11. Thereby, the display control unit 20 displays the stability determination image on the display unit 12 (step S109). Thus, the process shown in FIG. 16 is completed. When the generation unit 19 has not received the instruction to display the stability display image, the generation unit 19 skips step S109 and ends the processing illustrated in FIG.

  According to at least one embodiment described above, based on the first system state which is the system state of the power system facility at the first time point, the system state of the power system facility at the second time point after a predetermined time from the first time point. Inputting the estimation unit that estimates the second system state that is the above, the second system state estimated by the estimation unit, and the information of the accident assumed in the second system state into the learned evaluation model as input data. The stability evaluation unit that derives the predicted stability of the power system equipment after an expected accident, and the degree of influence on the input of the evaluation model and the stability of each item in the input data By having a generation unit that generates an influence degree display image that represents, and a display control unit that displays the image generated by the generation unit on the display unit, input data that contributes little to the stability evaluation is excluded, and the like. Input data can be appropriately selected. Therefore, the relationship between the data used when creating the evaluation model and the input data can be easily seen.

  Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the invention described in the claims and the equivalents thereof as well as included in the scope and the gist of the invention.

DESCRIPTION OF SYMBOLS 10... Electric power system monitoring system, 11... Input part, 12... Display part, 13... Storage part, 14... Data management part, 15... System information collection part, 16... System state estimation part (estimation part), 17... Stability Evaluation unit, 18... Control content determination unit, 19... Generation unit (selection unit), 20... Display control unit, 21... Power system, 22... Generator, 23... Renewable energy power supply, 24... Consumer, 25... Measurement Device, 26... Control terminal device, 31... Regional set, 40... Learning processing unit, 41... Data acquisition unit, 42... Storage unit, 43... Learning unit, 44... Derivation unit, IP... Impact degree display image, SP... Stable Display image, SJ... Stability determination image, CP... Selected image

Claims (13)

Estimating a second system state that is a system state of the power system facility at a second time point after a predetermined time from the first time point, based on a first system state that is a system state of the power system facility at the first time point Department,
Prediction after the assumed accident by inputting the second system state estimated by the estimation unit and the information about the accident assumed in the second system state as input data into the learned evaluation model A stability evaluation unit for deriving the stability of the power system equipment,
A generation unit that generates an influence degree display image that represents an influence degree that influences the stability of each item in the input data and the input data that is input to the evaluation model.
A display control unit for displaying the influence degree display image generated by the generation unit on a display unit;
An electric power system monitoring system. The generation unit calculates the absolute value of the gradient indicating the rate of change of the stability with respect to the change for each value of the plurality of input data input to the evaluation model, for the absolute value of the gradient of each input data, The influence degree is determined based on the gradient information obtained by standardizing the data for each pattern in which a plurality of the second system states and the expected accident case information are combined, and the influence degree display image representing the determined influence degree is generated. To do
The power system monitoring system according to claim 1. A learning processing unit that generates the evaluation model,
A selection unit that selects input data whose gradient is equal to or more than a threshold value as large influence input data that has a large influence on the stability evaluation by the evaluation model, and the learning processing unit is selected by the selection unit. Generate the evaluation model using the large impact input data,
The power system monitoring system according to claim 1. The generation unit generates the influence degree display image showing the influence degree represented in the influence degree display image by the shade of the display of the display section,
The power system monitoring system according to claim 1. The display sections in the influence display image are arranged in a matrix,
The power system monitoring system according to claim 4. A learning processing unit for generating the evaluation model,
The generation unit generates a selection image that allows a user to select large-impact input data that has a large influence on stability evaluation by the evaluation model,
The display control unit causes the display unit to display the selection image generated by the generation unit,
The learning processing unit generates the evaluation model using the large influence input data selected by the user according to the display of the selected image,
The power system monitoring system according to claim 4 or 5. The generation unit uses n-dimensionalized input data obtained by converting the input data into n (n: natural number) dimensions, and the stability obtained by inputting the input data into the evaluation model as stability display points. Generate a stability display image represented on a vectorized space,
The power system monitoring system according to any one of claims 1 to 6. The generator stabilizes the n-dimensionalized input data obtained by converting the input data into n (n: natural number) dimensions and the stability obtained by inputting the selected large influence input data into the evaluation model. As a degree display point, a stability display image represented in a vectorized space is generated,
The power system monitoring system according to claim 6. The generation unit, the second stability state estimated by the estimation unit and the estimated stability display point generated by inputting the stability obtained by inputting the second system state into the evaluation model, Generating a stability determination image displayed on the stability display image,
The power system monitoring system according to claim 7. When the shortest distance between the stability display point and the estimated stability display point is a distance threshold or more, the generation unit inputs the estimated stability display point to the evaluation model when generating the estimated stability display point. The input data that is input is determined as low reliability data,
The power system monitoring system according to claim 9. The generation unit generates a low reliability data image showing each item of the low reliability data,
The power system monitoring system according to claim 10. Computer
Estimating a second system state which is a system state of the power system equipment at a second time point after a predetermined time from the first time point, based on a first system state which is a system state of the power system equipment at a first time point,
By inputting the estimated second system state and information on an accident assumed in the second system state as input data to a learned evaluation model, the power predicted after the assumed accident. Derive the stability of system equipment,
Generating an influence degree display image showing an influence degree on the derivation of the stability for each item in the input data and the input data input to the evaluation model,
Displaying the generated influence degree display image on a display unit,
Power system monitoring method. On the computer,
A second system state, which is a system state of the power system equipment at a second time point after a predetermined time from the first time point, is estimated based on a first system state that is a system state of the power system equipment at a first time point,
By inputting the estimated second system state and information on an accident assumed in the second system state as input data into a learned evaluation model, the power system predicted after the assumed accident. Derive the stability of the equipment,
Generating an influence degree display image representing the degree of influence on the derivation of the stability for each item in the input data and the input data input to the evaluation model,
Displaying the generated influence degree display image on a display unit,
program.