Self-adaptive power voltage regulation control system based on artificial intelligence

Abstract

The invention discloses a self-adaptive power voltage regulation control system based on artificial intelligence, and belongs to the technical field of voltage regulation control. The method and the device are used for solving the technical problems of poor reliability and expansibility of multi-dimensional active supervision analysis of self-adaptive power regulation and control in the existing scheme. The method comprises the following steps: performing supervision and data statistics on control implemented by different performance indexes of a control target each time, performing data analysis on implementation effects corresponding to implementation of the control and implementation cooperative influences, and dynamically implementing multi-aspect optimization processing prompts on the different performance indexes according to analysis results. Multi-aspect active supervision and optimization analysis prompting are carried out on single control of different performance indexes, diversified control effect supervision analysis is carried out on the different performance indexes, and alarm prompting of omnibearing local abnormity prevention processing is carried out on self-adaptive control of the different performance indexes according to an analysis result. And active expansion analysis of early-stage different single-time control implementation state supervision data is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of voltage regulation control, and in particular to an adaptive power voltage regulation control system based on artificial intelligence. Background Art

[0002] Adaptive power voltage control is an advanced power system control technology designed to dynamically adjust voltage levels in the power grid to ensure stability and efficiency. This control method automatically adjusts to changes in real-time grid operating conditions, optimizing power transmission and distribution.

[0003] When implementing the existing adaptive power voltage regulation control scheme, it is unable to conduct its own regulatory analysis on the dynamic control of the performance indicators of the control target from different aspects, as well as the regulatory analysis of the control synergy impact, and adaptively perform dynamic processing prompts on the indicator control schemes corresponding to different performance indicators based on the analysis results of different aspects. The reliability and scalability of the multi-dimensional active regulatory analysis of adaptive power regulation and control are poor. Summary of the Invention

[0004] The purpose of the present invention is to provide an adaptive power voltage regulation control system based on artificial intelligence, which is used to solve the technical problems of poor reliability and scalability of multi-dimensional active supervision analysis of adaptive power regulation and control in existing solutions.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] An AI-based adaptive power voltage regulation control system includes a performance indicator single-time control implementation supervision module, which is used to supervise and collect data on each control implementation of different performance indicators of the control target, and perform data analysis on the implementation effect and synergistic impact of the implementation control. Based on the analysis results, the implementation plan, control processing and synergistic impact of different performance indicators are abnormally marked and dynamically optimized.

[0007] The performance indicator control implementation processing module is used to conduct diversified control effect supervision analysis and risk perception expansion analysis on different performance indicators, and independently conduct all-round local abnormality prevention processing and alarm prompts for the adaptive control of different performance indicators based on the analysis results.

[0008] Preferably, when the performance indicator of the control target starts the control, a local supervision instruction is generated, and the total processing time for implementing the control of the corresponding performance indicator, as well as the control state values ​​corresponding to the actuator and several key variables for implementing the control of the performance indicator are obtained according to the local supervision instruction;

[0009] The control state values ​​corresponding to several key variables are traversed and matched with their corresponding output control standard ranges in turn, and the corresponding performance indicators are associated with normal control effect labels or abnormal control effect labels according to the matching results.

[0010] Preferably, the total processing time is compared with the processing time threshold associated with the execution mechanism to which it belongs;

[0011] If the total processing time is less than or equal to the processing time threshold, the control processing is associated with the normal label;

[0012] Otherwise, it is associated with the control processing exception tag.

[0013] Preferably, during the regular supervision period after the execution of the performance indicator control, other performance indicators of the control target are monitored and analyzed to see whether control is initiated;

[0014] If other performance indicators do not start control, the automatic control of the corresponding performance indicators will be associated with the collaborative impact normal label;

[0015] If other performance indicators have startup controls, the automatic controls of the corresponding performance indicators will be associated with the collaborative impact exception label;

[0016] The different tags obtained by the analysis are sorted and combined to obtain the single control multi-dimensional supervision data of the corresponding performance indicators, and the single control multi-dimensional supervision data are traversed and analyzed to determine the single control implementation status of the corresponding performance indicators.

[0017] Preferably, if all tags are normal tags, it is prompted that the single control implementation status of the corresponding performance indicator is normal;

[0018] If there is an abnormal label, it will prompt that the single control implementation status of the corresponding performance indicator is abnormal, and the plan implementation, control processing and / or synergistic impact corresponding to the abnormal label will be marked as abnormal, and the optimization processing prompt will be implemented for the performance indicator marked with the abnormal label.

[0019] Preferably, prompts corresponding to all implementation controls of different performance indicators are obtained, and if all prompts indicate that the single control implementation status is normal, the corresponding performance indicator is marked as the first indicator;

[0020] If there is a prompt that the single control implementation state is not normal, the corresponding performance indicator is marked as the second indicator, and the total number of different abnormal marks corresponding to different second indicators is counted in sequence, and the formula is used in sequence. Calculate the abnormal impact value YYk of different abnormal marks of the second indicator; where k is 1, 2, 3, which are abnormal marks of the second indicator corresponding to the implementation of the plan, control processing, and synergistic impact respectively; Pk is the abnormal mark frequency value of the second indicator corresponding to different aspects, through the formula It is calculated that Nk is N1, N2, and N3, which are the total number of abnormal marks in different aspects of the second indicator; T is the time difference between the start of supervision of the second indicator and the current real time; α is the standard value of the abnormal impact.

[0021] Preferably, risk perception is performed on the abnormal impact values ​​of different abnormal marks of the second indicator in sequence to obtain the risk perception states corresponding to the different abnormal marks of the second indicator;

[0022] If the abnormal impact value is less than or equal to 0, the risk perception state of the abnormal mark of the second indicator is determined to be normal, and the corresponding risk perception flag is set to 0;

[0023] Otherwise, it is determined that the risk perception state of the abnormal mark of the second indicator is abnormal, and its corresponding risk perception flag is set to 1, and an alarm prompt for corresponding local abnormality prevention processing is issued.

[0024] Preferably, all risk perception identifiers corresponding to the same abnormal mark are obtained and summed, and the summed value is compared with a preset standard mark threshold for judgment;

[0025] If the summed value is less than or equal to the corresponding standard mark threshold, no local abnormality prevention processing will be performed on the abnormal mark with normal risk perception status;

[0026] On the contrary, the abnormal mark of the normal risk perception status will also be given an alarm prompt for the corresponding local abnormal prevention processing.

[0027] Preferably, the step of obtaining the abnormal impact standard value includes:

[0028] By formula Calculate and obtain the processing frequency values ​​CP corresponding to different first indicators, where M is the total number of times the first indicator implements control;

[0029] The median value of the processing frequency values ​​corresponding to all first indicators is obtained and set as the abnormal impact standard value.

[0030] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0031] The present invention monitors and collects data on each control implemented for different performance indicators of the control target, and performs data analysis on the implementation effect and implementation synergy impact corresponding to the implemented control. According to the analysis results, various optimization processing prompts are dynamically implemented for different performance indicators, thereby realizing various aspects of active supervision and optimization analysis prompts for single control of different performance indicators, and improving the active supervision and analysis effect of single control implementation of different performance indicators.

[0032] The present invention conducts diversified control effect supervision analysis on different performance indicators, and independently provides all-round local abnormality prevention warning prompts for the adaptive control of different performance indicators based on the analysis results, thereby realizing the active expansion analysis of the early stage supervision data of different single control implementation states, and improving the reliability and scalability of the multi-dimensional active supervision analysis of adaptive power regulation and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will be further described below with reference to the accompanying drawings.

[0034] Figure 1 This is a flowchart of the operation of an artificial intelligence-based adaptive power voltage regulation control system of the present invention. DETAILED DESCRIPTION

[0035] 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 ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] like Figure 1 As shown, the present invention is an adaptive power voltage regulation control system based on artificial intelligence, including a performance index single control implementation supervision module and a performance index control implementation processing module;

[0037] The performance indicator single control implementation supervision module is used to supervise and collect data for each control implemented for different performance indicators of the control target, and to analyze the implementation effect and synergistic impact of the corresponding control implementation. Based on the analysis results, the implementation plan, control processing and synergistic impact of different performance indicators are marked as abnormal and dynamic optimization processing prompts are provided; including:

[0038] When the performance indicator of the control target starts the control, a local supervision instruction is generated, and according to the local supervision instruction, the total processing time of the corresponding performance indicator control is obtained in milliseconds, as well as the control state values ​​corresponding to the actuator and several key variables of the performance indicator control;

[0039] It should be noted that the control target can be the bus voltage or the voltage at a specific load point;

[0040] Performance indicators, including but not limited to steady-state accuracy, dynamic response speed, overshoot limit, and robustness requirements;

[0041] Actuators, including but not limited to generator excitation current, on-load tap-changing transformer taps, and static VAR compensator output current / voltage;

[0042] Key variables: Determine the system status that requires real-time measurement, such as bus voltage, key line current, load power, frequency, actuator status, etc. The control state values ​​corresponding to several key variables are implemented based on IoT devices or existing monitoring technologies, and the specific implementation method is not limited;

[0043] The control state values ​​corresponding to several key variables are sequentially matched with their corresponding output control standard ranges; a corresponding output control standard range is pre-set for several key variables, and the specific values ​​are not limited. They can be customized according to actual operating requirements or determined based on the early design data of the corresponding key variables;

[0044] If the control state values ​​corresponding to all key variables fall within the corresponding output control standard range, the corresponding performance indicators are associated with the control effect normal label;

[0045] If the control state value corresponding to a key variable does not fall within the corresponding output control standard range, the corresponding performance indicator will be associated with a control effect abnormality label;

[0046] In the embodiment of the present invention, by performing data analysis from the perspective of output control results and dynamically associating control effect labels with different performance indicators, supervisory data support for control effects can be provided for subsequent data analysis in different aspects.

[0047] Furthermore, the total processing time is compared with the processing time threshold associated with the corresponding execution agency; the value of the processing time threshold is not limited and can be customized according to actual operation requirements or determined based on the preliminary design data of the corresponding key variables;

[0048] If the total processing time is less than or equal to the processing time threshold, the control processing is associated with the normal label;

[0049] Otherwise, it will be associated with the control processing exception tag;

[0050] In the embodiment of the present invention, by performing data analysis from the control processing aspect and dynamically associating control processing tags with different performance indicators, supervisory data support for control processing effects can be provided for subsequent data analysis in different aspects.

[0051] Furthermore, during the regular supervision period after the performance indicator control is completed, monitoring and analyzing whether other performance indicators of the control target are activated; wherein the regular supervision period refers to a period of Q milliseconds after the performance indicator control is completed, and the specific value of Q can be half of the corresponding total processing time value;

[0052] If other performance indicators do not start control, the automatic control of the corresponding performance indicators will be associated with the collaborative impact normal label;

[0053] If other performance indicators have startup controls, the automatic control of the corresponding performance indicator will be associated with a collaborative impact exception label. This can be understood as the execution of the performance indicator control affecting the normal operation of other performance indicators.

[0054] In the embodiment of the present invention, by performing supervision and data analysis from the perspective of collaborative impact and dynamically associating collaborative impact labels with different performance indicators, it is possible to provide supervisory data support for collaborative impact for subsequent data analysis in different aspects.

[0055] Sort and combine the different tags obtained by analysis to obtain the single control multi-dimensional supervision data of the corresponding performance indicators, and perform traversal analysis on the single control multi-dimensional supervision data to determine the single control implementation status of the corresponding performance indicators;

[0056] If all tags are normal, it indicates that the single control implementation status of the corresponding performance indicators is normal;

[0057] If there is an abnormal label, it will prompt that the single control implementation status of the corresponding performance indicator is abnormal, and the plan implementation, control processing and / or synergistic impact corresponding to the abnormal label will be marked as abnormal, and the optimization processing prompt will be implemented for the performance indicator marked with the abnormal label.

[0058] In an embodiment of the present invention, by supervising and collecting data on each implementation of the control of different performance indicators of the control target, and performing data analysis on the implementation effect and implementation synergy impact corresponding to the implementation of the control, various optimization processing prompts are dynamically implemented for different performance indicators based on the analysis results, thereby realizing various aspects of active supervision and optimization analysis prompts for single control of different performance indicators, and improving the active supervision and analysis effect of single control implementation of different performance indicators.

[0059] The performance indicator control implementation processing module is used to conduct diversified control effect supervision analysis and risk perception expansion analysis on different performance indicators, and independently conduct all-round local abnormality prevention and warning prompts for adaptive control of different performance indicators based on the analysis results; including:

[0060] Obtain prompts corresponding to all implementation controls of different performance indicators. If all prompts indicate that the single control implementation status is normal, mark the corresponding performance indicator as the first indicator;

[0061] If there is a prompt that the single control implementation state is not normal, the corresponding performance indicator is marked as the second indicator, and the total number of different abnormal marks corresponding to different second indicators is counted in sequence, and the formula is used in sequence. Calculate the abnormal impact value YYk of different abnormal marks of the second indicator; where k is 1, 2, 3, which are abnormal marks of the second indicator corresponding to the implementation of the plan, control processing, and synergistic impact respectively; Pk is the abnormal mark frequency value of the second indicator corresponding to different aspects, through the formula Calculated, Nk is N1, N2, and N3, which are the total number of abnormal flags for different aspects of the second indicator; T is the time difference between the start of monitoring of the second indicator and the current real-time time, in days; α is the abnormal impact standard value, the specific value is not limited and can be determined based on the application requirements of the actual application scenario or based on the preliminary design test data of the power operation;

[0062] The steps for obtaining the abnormal impact standard value include:

[0063] By formula Calculate and obtain the processing frequency values ​​CP corresponding to different first indicators, where M is the total number of times the first indicator implements control;

[0064] Obtaining the median of the processing frequency values ​​corresponding to all first indicators, and setting it as the abnormal impact standard value;

[0065] It should be noted that the abnormal impact value is used to integrate and calculate all the regulatory processing data corresponding to different abnormal marks of the second indicator to digitally represent the risk perception status of different abnormal marks of the second indicator;

[0066] In addition, the formula calculations involved in the embodiments of the present invention are all normalized before the calculations. The normalization includes but is not limited to dimensionalization of the calculated data and extraction of numerical values ​​of the calculated data.

[0067] Meanwhile, the formula calculation in the embodiment of the present invention is only a technical means, and the form and logic of the formula can also be adjusted according to the actual application scenario, or it can be implemented according to other existing technical means;

[0068] and, sequentially performing risk perception on the abnormal impact values ​​of different abnormal marks of the second indicator to obtain risk perception states corresponding to the different abnormal marks of the second indicator;

[0069] If the abnormal impact value is less than or equal to 0, the risk perception state of the abnormal mark of the second indicator is determined to be normal, and the corresponding risk perception flag is set to 0;

[0070] Otherwise, the risk perception state of the abnormal flag of the second indicator is determined to be abnormal, and the corresponding risk perception flag is set to 1, and an alarm prompt is issued for the corresponding local abnormality prevention processing; wherein, the alarm prompt does not include the specific processing content of the corresponding local abnormality prevention processing, and the specific processing content can be determined by professional and technical personnel in this field according to actual work content and work requirements;

[0071] It is worth noting that in the embodiment of the present invention, by performing data analysis on the abnormal impact values ​​of different second indicators and different abnormal markers, it is possible to obtain the risk perception status corresponding to different second indicators and different abnormal markers, and implement targeted local abnormal prevention and processing prompts therefor, and provide reliable local risk perception data support for subsequent extended analysis of the same abnormal marker dimension, thereby improving the diversity of risk perception data analysis and extended utilization of different second indicators and different abnormal markers.

[0072] Obtain all risk perception identifiers corresponding to the same anomaly mark and sum them, and compare the summed value with the preset standard mark threshold for judgment. The specific value of the standard mark threshold is not limited and can be determined based on the application requirements of the actual application scenario or based on the preliminary design test data of the power operation;

[0073] If the summed value is less than or equal to the corresponding standard mark threshold, no local abnormality prevention processing will be performed on the abnormal mark with normal risk perception status;

[0074] On the contrary, the abnormal mark of the normal risk perception state will also be given an alarm prompt corresponding to the local abnormal prevention process;

[0075] It should be noted that by expanding the processing and analysis of risk perception data with different second indicators and different abnormal markers, further risk perception analysis and alarm prompts can be achieved from the same abnormal marker dimension, thereby improving the diversity and comprehensiveness of risk perception regulatory analysis corresponding to different second indicators and different abnormal markers.

[0076] In the embodiment of the present invention, by performing diversified control effect supervision analysis on different performance indicators and autonomously performing all-round local abnormality prevention processing alarm prompts on the adaptive control of different performance indicators based on the analysis results, active expansion analysis of the early stage supervision data of different single control implementation states is achieved, thereby improving the reliability and scalability of the multi-dimensional active supervision analysis of adaptive power regulation and control.

[0077] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the embodiments of the invention described above are merely illustrative. For example, the division of modules is only a logical function division, and other division methods may be used in actual implementation.

[0078] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected to achieve the objectives of this embodiment based on actual needs.

[0079] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing module, each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or hardware plus software functional modules.

[0080] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, but that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An adaptive power voltage regulation control system based on artificial intelligence, characterized in that: It includes a performance indicator single control implementation supervision module, which is used to supervise and collect data statistics on each control implemented for different performance indicators of the control target, and conduct data analysis on the implementation effect and synergistic impact of the implementation control. Based on the analysis results, it can mark abnormalities in the implementation of different performance indicators, control processing and synergistic impact, and provide dynamic optimization processing prompts. The performance indicator control implementation processing module is used to conduct diversified control effect supervision analysis and risk perception expansion analysis on different performance indicators, and independently conduct all-round local abnormality prevention processing and alarm prompts for the adaptive control of different performance indicators based on the analysis results.

2. The adaptive power voltage regulation control system based on artificial intelligence according to claim 1, characterized in that: When the performance indicator of the control target starts the control, a local supervision instruction is generated, and the total processing time of the corresponding performance indicator implementation control, as well as the execution mechanism of the performance indicator implementation control and the control state values ​​corresponding to several key variables are obtained according to the local supervision instruction; The control state values ​​corresponding to several key variables are traversed and matched with their corresponding output control standard ranges in turn, and the corresponding performance indicators are associated with normal control effect labels or abnormal control effect labels according to the matching results.

3. The adaptive power voltage regulation control system based on artificial intelligence according to claim 2, characterized in that: Compare the total processing time with the processing time threshold associated with the execution agency to which it belongs; If the total processing time is less than or equal to the processing time threshold, the control processing is associated with the normal label; Otherwise, it is associated with the control processing exception tag.

4. The adaptive power voltage regulation control system based on artificial intelligence according to claim 3, characterized in that: During the regular supervision period after the execution of performance indicator control, monitor and analyze whether other performance indicators of the control target have been activated; If other performance indicators do not start control, the automatic control of the corresponding performance indicators will be associated with the collaborative impact normal label; If other performance indicators have startup controls, the automatic controls of the corresponding performance indicators will be associated with the collaborative impact exception label; The different tags obtained by the analysis are sorted and combined to obtain the single control multi-dimensional supervision data of the corresponding performance indicators, and the single control multi-dimensional supervision data are traversed and analyzed to determine the single control implementation status of the corresponding performance indicators.

5. The adaptive power voltage regulation control system based on artificial intelligence according to claim 4, characterized in that: If all tags are normal, it indicates that the single control implementation status of the corresponding performance indicators is normal; If there is an abnormal label, it will prompt that the single control implementation status of the corresponding performance indicator is abnormal, and the plan implementation, control processing and / or synergistic impact corresponding to the abnormal label will be marked as abnormal, and the optimization processing prompt will be implemented for the performance indicator marked with the abnormal label.

6. The artificial intelligence-based adaptive power voltage regulation control system according to claim 5, characterized in that: Obtain prompts corresponding to all implementation controls of different performance indicators. If all prompts indicate that the single control implementation status is normal, mark the corresponding performance indicator as the first indicator; If there is a prompt that the single control implementation state is not normal, the corresponding performance indicator is marked as the second indicator, and the total number of different abnormal marks corresponding to different second indicators is counted in sequence, and the formula is used in sequence. Calculate the abnormal impact value YYk of different abnormal marks of the second indicator; where k is 1, 2, 3, which are abnormal marks of the second indicator corresponding to the implementation of the plan, control processing, and synergistic impact respectively; Pk is the abnormal mark frequency value of the second indicator corresponding to different aspects, through the formula It is calculated that Nk is N1, N2, and N3, which are the total number of abnormal marks in different aspects of the second indicator; T is the time difference between the start of supervision of the second indicator and the current real time; α is the standard value of the abnormal impact.

7. The artificial intelligence-based adaptive power voltage regulation control system according to claim 6, characterized in that: Perform risk perception on the abnormal impact values ​​of different abnormal marks of the second indicator in sequence to obtain the risk perception states corresponding to the different abnormal marks of the second indicator; If the abnormal impact value is less than or equal to 0, the risk perception state of the abnormal mark of the second indicator is determined to be normal, and the corresponding risk perception flag is set to 0; Otherwise, it is determined that the risk perception state of the abnormal mark of the second indicator is abnormal, and its corresponding risk perception flag is set to 1, and an alarm prompt for corresponding local abnormality prevention processing is issued.

8. The artificial intelligence-based adaptive power voltage regulation control system according to claim 7, characterized in that: Obtain all risk perception indicators corresponding to the same anomaly mark and sum them up, and compare the summed value with the preset standard mark threshold for judgment; If the summed value is less than or equal to the corresponding standard mark threshold, no local abnormality prevention processing will be performed on the abnormal mark with normal risk perception status; On the contrary, the abnormal mark of the normal risk perception status will also be given an alarm prompt for the corresponding local abnormal prevention processing.

9. The artificial intelligence-based adaptive power voltage regulation control system according to claim 6, characterized in that: The steps for obtaining the abnormal impact standard value include: By formula Calculate and obtain the processing frequency values ​​CP corresponding to different first indicators, where M is the total number of times the first indicator implements control; The median value of the processing frequency values ​​corresponding to all first indicators is obtained and set as the abnormal impact standard value.

Images