A power system based on big data and control method thereof

By extracting the reactive power overlimit record and active compensation from the power grid big data and calculating the adaptive constraints, the problem of the complexity of reactive power scheduling of power nodes in the power system by traditional mathematical optimization methods is solved, and the reactive power of the power grid is improved Power safety and stability.

CN118676942BActive Publication Date: 2024-11-29COLLEGE OF MOBILE TELECOMM CHONGQING UNIV OF POSTS & TELECOMM
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410784544.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-18
Publication Date
2024-11-29
Estimated Expiration
2044-06-18

AI Technical Summary

Technical Problem

When the reactive power optimization in power systems in the prior art, traditional mathematical optimization methods have high requirements for initial values ​​and complex calculations, making it difficult to effectively constrain and schedule the reactive power of each power node, resulting in voltage stability and operation in large-scale power grids. Efficiency is limited.

Method used

By obtaining the reactive power record of each power node from the power grid big data, using the preset limit threshold value to extract the reactive limit penalty record, calculate the reactive limit penalty entropy and active compensation amount, determine the adaptive constraint amount, and then Constrained scheduling is performed on each power node when the reactive power is in an outlier state.

Benefits of technology

The safety and stability of reactive power in large-scale power grids is improved, and the reactive power is effectively adjusted through quantized adaptive constraints, avoiding the power safety problems caused by mutual restraint relationships.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118676942B_ABST
    Figure CN118676942B_ABST
Patent Text Reader

Abstract

The present application provides a power system based on big data and a control method thereof, which determines the over-limit penalty entropy of reactive power in power transmission through a preset over-limit threshold and reactive over-limit records of historical reactive data; determines the active compensation amount of each power node through historical active data, and then determines the active regulation cost of each power node based on each active compensation amount and over-limit penalty entropy; then determines the reactive safety margin under the over-limit state based on the reactive loss record in the historical reactive data, and determines the adaptive constraint amount of reactive power through all active regulation costs and reactive safety margins; when the reactive power of a large-scale power grid is in an over-limit state, the reactive power of each power node in the large-scale power grid is constrained and dispatched based on the adaptive constraint amount. Based on the above scheme, the constrained dispatch of reactive power in each power node can be realized, thereby improving the safety and stability of reactive power in the large-scale power grid.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of intelligent power dispatching and control, and more specifically, to a power system based on big data and a control method thereof. Background Art

[0002] Intelligent power dispatching and control is an important branch of intelligent operation and management of power systems. Intelligent power dispatching and control covers various technologies and methods for monitoring, predicting, dispatching and controlling the operating status of power systems. The core goal of intelligent power dispatching and control is to ensure that the power system supplies power in a safe, stable, efficient and economical manner while meeting user needs and power market requirements.

[0003] The existing power system is usually a system that manages multiple distributed power sources (such as solar cells, wind turbines, etc.) to optimize energy utilization and grid stability. In the power system, reactive power refers to the virtual power caused by capacitors, inductors or phase differences. Reactive power does not directly do work, but it has an important impact on the voltage stability and operation efficiency of the power grid. The main goal of reactive power optimization is to reasonably manage and adjust the reactive power in the power system to improve the system's operating efficiency, reduce energy loss, ensure grid stability, and meet the actual needs of the power system for reactive power. Reactive power optimization in the existing technology usually adopts traditional mathematical optimization methods. Traditional mathematical optimization methods have high requirements on the initial value of the power system and need to establish a sophisticated mathematical model to reduce errors. The calculation process of traditional mathematical optimization methods is extremely complex, and simple mathematical models will produce large errors. Constraining the reactive power in the power node can effectively reduce the network loss caused by reactive power, thereby improving the voltage stability in the large-scale power grid, and then improving the safety and stability of reactive power in the large-scale power grid. Therefore, how to constrain the reactive power in each power node to improve the safety and stability of reactive power in the large-scale power grid is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a big data-based power system and a control method thereof. Based on the above scheme, constrained scheduling of reactive power in each power node can be achieved, thereby improving the safety and stability of reactive power in large-scale power grids.

[0005] In a first aspect, the present application provides a power control method based on big data, comprising:

[0006] Obtain reactive power records of each power node in a large-scale power grid from power grid big data, and then obtain historical reactive power data;

[0007] Extracting reactive power over-limit records in power transmission from the historical reactive data by using a preset over-limit threshold, and determining over-limit penalty entropy of reactive power in power transmission according to the reactive power over-limit records;

[0008] Obtain active power records in a large-scale power grid, and then obtain historical active power data, determine the active power compensation amount of each power supply node in the large-scale power grid through the historical active power data, and then determine the active power regulation cost of each power supply node in the large-scale power grid according to each active power compensation amount and the over-limit penalty entropy;

[0009] Extracting reactive power loss records of large-scale power grids from the historical reactive power data, and then determining reactive power safety margins of large-scale power grids in over-limit states based on the reactive power loss records, and determining adaptive constraints of reactive power through all active power regulation costs and the reactive power safety margins;

[0010] When the reactive power of the large-scale power grid is in an over-limit state, the reactive power of each power supply node in the large-scale power grid is constrained and dispatched based on the adaptive constraint amount.

[0011] In some embodiments, extracting reactive power exceeding limit records in power transmission from the historical reactive power data by using a preset exceeding limit threshold specifically includes:

[0012] For each reactive power record in the historical reactive power data, obtaining all reactive power values ​​in the reactive power record;

[0013] Taking all reactive power values ​​higher than the preset over-limit threshold as the value range of reactive over-limit values ​​corresponding to the reactive power record, and then obtaining the value range of reactive over-limit values ​​corresponding to each reactive power record in the historical reactive data;

[0014] The reactive power over-limit record in power transmission is determined by the value range of each reactive power over-limit value.

[0015] In some embodiments, determining the reactive power over-limit penalty entropy in power transmission according to the reactive power over-limit record specifically includes:

[0016] Obtaining the over-limit entropy corresponding to each data item in the reactive power over-limit record in power transmission, and then determining the penalty amount of reactive power after over-limit in power transmission;

[0017] Determine the penalty adjustment coefficient of reactive power in power transmission when it exceeds the limit;

[0018] The penalty entropy for reactive power exceeding a limit in power transmission is determined by the penalty adjustment coefficient and the penalty amount.

[0019] In some embodiments, determining the active power compensation amount of each power supply node in the large-scale power grid by using the historical active power data specifically includes:

[0020] For each power supply node, obtaining an active power record corresponding to the power supply node from the historical active power data;

[0021] Determining an active phase difference of active power in the active power record when power is transmitted;

[0022] Determine the compensation factor of active power in power transmission;

[0023] The active power compensation amount of the power supply node is determined according to the active power phase difference and the compensation coefficient, and then the active power compensation amount of each power supply node in the large-scale power grid is obtained.

[0024] In some embodiments, determining the active power regulation cost of each power node in the large-scale power grid according to each active power compensation amount and the over-limit penalty entropy specifically includes:

[0025] For each power node in the large-scale power grid, the active power compensation amount of the power node is obtained;

[0026] Determining an over-limit constraint amount of a power supply node by using the active power compensation amount and the over-limit penalty entropy;

[0027] Obtaining a target regulation amount of active power regulation in a power supply node;

[0028] The active power regulation cost of the power supply node is determined according to the target regulation amount and the over-limit constraint amount, and then the active power regulation cost of each power supply node in the large-scale power grid is obtained.

[0029] In some embodiments, determining the reactive power safety margin of a large-scale power grid in an over-limit state according to the reactive power loss record specifically includes:

[0030] Obtaining all reactive power consumption values ​​when the reactive power reaches an over-limit state in the reactive power loss record;

[0031] Determine the over-limit value corresponding to each reactive power consumption value;

[0032] Determine the reactive power stability under the over-limit state through all reactive power consumption values;

[0033] The reactive power safety margin of a large-scale power grid in an over-limit state is determined by all over-limit values ​​and the reactive power stability.

[0034] In some embodiments, constraining the reactive power of each power node in the large-scale power grid based on the adaptive constraint amount specifically includes:

[0035] Determining the constraint amount of each power source node in the large-scale power grid based on the trained power dispatch model and the adaptive constraint amount;

[0036] The reactive power of each power node is dispatched and allocated through all constraints.

[0037] In a second aspect, the present application provides a power control system based on big data, including a control unit, wherein the control unit includes:

[0038] The acquisition module is used to obtain the reactive power records of each power node in the large-scale power grid from the power grid big data, and then obtain the historical reactive power data;

[0039] A processing module, configured to extract reactive power exceeding limit records in power transmission from the historical reactive power data by using a preset exceeding limit threshold, and determine the exceeding limit penalty entropy of reactive power in power transmission according to the reactive power exceeding limit records;

[0040] The processing module is also used to obtain active power records in the large-scale power grid, and then obtain historical active data, determine the active compensation amount of each power node in the large-scale power grid through the historical active data, and then determine the active regulation cost of each power node in the large-scale power grid according to each active compensation amount and the over-limit penalty entropy;

[0041] The processing module is also used to extract reactive power loss records of the large-scale power grid from the historical reactive power data, and then determine the reactive power safety margin of the large-scale power grid in an over-limit state according to the reactive power loss records, and determine the adaptive constraint amount of reactive power through all active power regulation costs and the reactive power safety margin;

[0042] The execution module is used to constrain the reactive power of each power supply node in the large-scale power grid based on the adaptive constraint when the reactive power of the large-scale power grid is in an over-limit state.

[0043] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned big data-based power control method.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned big data-based power control method when executed.

[0045] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0046] In a power system based on big data and a control method thereof provided by the present application, the reactive power record of each power supply node in a large-scale power grid is obtained from the power grid big data, and then the historical reactive data is obtained; the reactive over-limit record in power transmission is extracted from the historical reactive data through a preset over-limit threshold, and the over-limit penalty entropy of reactive power in power transmission is determined according to the reactive over-limit record, wherein the over-limit penalty entropy represents the degree of penalty on reactive power after the reactive power reaches the over-limit state; the active power record in the large-scale power grid is obtained, and then the historical active data is obtained, and the active compensation amount of each power supply node in the large-scale power grid is determined through the historical active data, wherein the active compensation amount represents the degree of constraint compensation of active power to reactive power after the reactive power exceeds the limit, Then, the active regulation cost of each power supply node in the large-scale power grid is determined according to each active compensation amount and the above-limit penalty entropy; the reactive loss record of the large-scale power grid is extracted from the above-limit reactive data, and then the reactive safety margin of the large-scale power grid in the above-limit state is determined according to the above-limit reactive loss record, wherein the reactive safety margin refers to the margin or margin between reactive power demand and reactive power supply in the power system, and the adaptive constraint of reactive power is determined through all active regulation costs and the above-limit reactive safety margin, wherein the adaptive constraint refers to the quantitative value of the constraint condition used to describe and control the reactive power regulation capability in the power system; based on the above-limit adaptive constraint, the reactive power of each power supply node in the large-scale power grid is constrained and dispatched.

[0047] It can be seen that in the present application, when the reactive power of a large-scale power grid is in an over-limit state, the reactive power of each power supply node in the large-scale power grid can be constrained and scheduled based on the adaptive constraint amount; wherein, by determining the over-limit penalty entropy through the reactive over-limit record, the quantitative value of the reactive power that needs to be adjusted after reaching the over-limit state can be obtained, which can facilitate the subsequent preliminary adjustment of the reactive power in the power supply nodes of the large-scale power grid; secondly, the active power adjustment cost of each power supply node is determined through historical active power data, wherein, by determining the degree of constraint compensation of active power to reactive power after the over-limit is determined, the mutual constraint relationship between active power and reactive power in power transmission can be accurately obtained, so that in the subsequent When constraining the reactive power of each power node, the mutual constraint relationship is comprehensively considered, which can effectively avoid the power safety problem caused by the mutual constraint relationship, thereby improving the safety of reactive power in large-scale power grids; then, the adaptive constraint amount of reactive power can be determined by all active regulation costs and the reactive safety margin, and then when the reactive power of the large-scale power grid is in an out-of-limit state, the quantified value of the constraint condition of the reactive power regulation capability (i.e., the adaptive constraint amount) can be used to constrain the reactive power of each power node; in summary, based on the above scheme, the constrained scheduling of reactive power in each power node can be realized, thereby improving the safety and stability of reactive power in large-scale power grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0049] Figure 1 is an exemplary flow chart of a power control method based on big data according to some embodiments of the present application;

[0050] Figure 2 is a schematic diagram of a process for determining active power compensation amount according to some embodiments of the present application;

[0051] Figure 3 is a schematic diagram of a process for determining reactive safety margin according to some embodiments of the present application;

[0052] Figure 4 is a schematic diagram of exemplary hardware and / or software of a control unit according to some embodiments of the present application;

[0053] Figure 5 It is a structural diagram of a computer device for implementing a power control method based on big data as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] The embodiment of the present application provides a power system based on big data and a control method thereof, the core of which is to determine the over-limit penalty entropy of reactive power in power transmission through a preset over-limit threshold and reactive over-limit records of historical reactive data; determine the active compensation amount of each power node through historical active data, and then determine the active regulation cost of each power node according to each active compensation amount and over-limit penalty entropy; then determine the reactive safety margin under the over-limit state according to the reactive loss record in the historical reactive data, and determine the adaptive constraint amount of reactive power through all active regulation costs and reactive safety margins; when the reactive power of a large-scale power grid is in an over-limit state, constrain the reactive power of each power node in the large-scale power grid based on the adaptive constraint amount. Based on the above scheme, the constrained scheduling of reactive power in each power node can be realized, thereby improving the safety and stability of reactive power in the large-scale power grid.

[0056] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a power control method based on big data according to some embodiments of the present application, and the power control method based on big data mainly includes the following steps:

[0057] In step 101, the reactive power record of each power source node in the large-scale power grid is obtained from the power grid big data, and then the historical reactive power data is obtained.

[0058] It should be noted that, in the present application, a large-scale power grid refers to an electric power system network that covers a wide area and connects multiple power stations, substations and end users; a power supply node refers to a node or bus that injects electric energy into a large-scale power grid, such as a power station; reactive power refers to the virtual power caused by capacitors, inductors or phase differences, that is, in an AC circuit, energy flows back and forth between the power supply and the load, but is not converted into useful power; the power system usually monitors and records the reactive power level of each power supply node or line. In specific implementation, for each power supply node, the average reactive power of the power supply node within one minute can be used as the reactive power value, and the set of all reactive power values ​​within a month can be used as the reactive power record of the power supply node. The reactive power record of each power supply node can be obtained in the above manner, and the set of all reactive power records can be used as historical reactive data.

[0059] In step 102, reactive power exceeding limit records in power transmission are extracted from the historical reactive power data by using a preset exceeding limit threshold, and the exceeding limit penalty entropy of reactive power in power transmission is determined according to the reactive power exceeding limit records.

[0060] It should be noted that, in the present application, the over-limit threshold indicates that the reactive power reaches the limit value of the reactive power that may affect the safety of the power system. When the reactive power in the power system exceeds the preset over-limit threshold, it is called reactive power over-limit. In specific implementation, the over-limit threshold can be preset based on historical experience to ensure the stability of the power system voltage, thereby further ensuring the safety of the power system. It should be noted that, in the present application, the reactive over-limit record indicates all data records of the reactive power reaching the limit value that may affect the safety of the power system.

[0061] In some embodiments, extracting reactive power exceeding limit records in power transmission from the historical reactive power data by using a preset exceeding limit threshold may be achieved by the following steps:

[0062] For each reactive power record in the historical reactive power data, obtaining all reactive power values ​​in the reactive power record;

[0063] Taking all reactive power values ​​higher than the preset over-limit threshold as the value range of reactive over-limit values ​​corresponding to the reactive power record, and then obtaining the value range of reactive over-limit values ​​corresponding to each reactive power record in the historical reactive data;

[0064] The reactive power over-limit record in power transmission is determined by the value range of each reactive power over-limit value.

[0065] Preferably, in the above embodiment, determining the reactive over-limit record in power transmission through the value range of each reactive over-limit value can be implemented in the following manner, namely: for each reactive over-limit value, each value in the reactive over-limit value, the power supply node of the reactive over-limit value, and the recording time of the reactive over-limit value in the reactive power record are used as data items corresponding to the values ​​in the reactive over-limit value. The data items corresponding to the values ​​in each reactive over-limit value can be obtained in the above manner, and the set of all data items can be used as a reactive over-limit record.

[0066] In some embodiments, determining the reactive power over-limit penalty entropy in power transmission according to the reactive power over-limit record can be implemented by the following steps:

[0067] Obtaining the over-limit entropy corresponding to each data item in the reactive power over-limit record in power transmission, and then determining the penalty amount of reactive power after over-limit in power transmission;

[0068] Determine the penalty adjustment coefficient of reactive power in power transmission when it exceeds the limit;

[0069] The penalty entropy for reactive power exceeding a limit in power transmission is determined by the penalty adjustment coefficient and the penalty amount.

[0070] It should be noted that in the present application, the over-limit penalty entropy represents the degree of penalty for reactive power after the reactive power reaches the over-limit state, wherein the degree of penalty refers to the amount of power required for reactive power transfer; the penalty amount is the theoretical quantitative value of the degree of penalty for reactive power after the reactive power reaches the over-limit state; and the penalty adjustment coefficient is a parameter used to adjust the penalty amount.

[0071] In the specific implementation, preferably, in some embodiments, the following method can be adopted, namely: first, the maximum and minimum values ​​of the reactive over-limit values ​​of all data items in the reactive over-limit record are obtained, and then the difference between the maximum and the minimum value is used as the over-limit fluctuation value. For each data item in the reactive over-limit record, the difference between the reactive over-limit value in the data item and the over-limit threshold can be used as the over-limit value of the data item, and the ratio of the over-limit value to the over-limit fluctuation value can be used as the over-limit entropy of the data item. The over-limit entropy of each data item can be obtained by the above method, and the sum of the squares of all over-limit entropies can be used as the penalty amount of reactive power after over-limit in power transmission; then, the penalty adjustment coefficient can be preset through historical experience in combination with different external environments, and the penalty adjustment coefficient can be used to adjust the penalty amount to comprehensively consider the impact of different external environments on reactive power, thereby improving the feasibility and safety of the final reactive power scheduling; finally, the product of the penalty adjustment coefficient and the penalty amount can be used as the over-limit penalty entropy of reactive power in power transmission. In other embodiments, other methods can also be adopted for implementation, which are not limited in this application.

[0072] It should be noted that in the present application, the over-limit fluctuation value is an indicator used to measure the stability of the reactive power after it exceeds the limit. The smaller the over-limit fluctuation value, the more stable the reactive power after it exceeds the limit. When the over-limit fluctuation value is 0, it means that the reactive power no longer changes after it exceeds the limit. This situation is an ideal state. The situation where the over-limit fluctuation value is 0 is not considered in this application; the over-limit entropy is used to measure the stability of the reactive over-limit value in the data item relative to the reactive over-limit values ​​in other data items.

[0073] In step 103, the active power record in the large-scale power grid is obtained, and then the historical active power data is obtained. The active power compensation amount of each power supply node in the large-scale power grid is determined by the historical active power data, and then the active power regulation cost of each power supply node in the large-scale power grid is determined according to each active power compensation amount and the over-limit penalty entropy.

[0074] In specific implementation, for each power supply node, the average of the active power of the power supply node within one minute can be used as the active power value, and the set of all active power values ​​within a month can be used as the active power record of the power supply node. The active power record of each power supply node can be obtained in the above manner, and the set of all active power records can be used as historical reactive data.

[0075] In some embodiments, the active power compensation amount of each power supply node in the large-scale power grid is determined by the historical active power data, referring to Figure 2 As described above, the figure is a schematic diagram of a process for determining the active power compensation amount in some embodiments of the present application. In this embodiment, determining the active power compensation amount can be implemented by the following steps:

[0076] In step 1031, for each power supply node, an active power record corresponding to the power supply node is obtained from the historical active power data;

[0077] In step 1032, determining an active phase difference of the active power in the active power record when the active power is transmitted;

[0078] In step 1033, a compensation coefficient of active power in power transmission is determined;

[0079] In step 1034, the active power compensation amount of the power supply node is determined according to the active power phase difference and the compensation coefficient, thereby obtaining the active power compensation amount of each power supply node in the large-scale power grid.

[0080] It should be noted that the active power compensation amount represents the degree of constraint compensation of active power after the reactive power exceeds the limit; in specific implementation, first, for each power supply node, the active power record corresponding to the power supply node is obtained in the historical active power data; secondly, all active power values ​​in the active power record are obtained, an active power value is selected, and the reactive power record of the power supply node in the historical reactive power data is obtained. The reactive power value at the same minute as the active power value is obtained in the reactive power record, and the square root of the sum of the square of the active power value and the square of the reactive power value can be used as the apparent power. The apparent power is used to evaluate the electrical The active power transmission and the total capacity of the power equipment are indicators. The ratio of the active power value to the apparent power can be used as the active phase difference. Then, the compensation coefficient can be preset through historical experience in combination with different external environments. The compensation coefficient is a parameter used to compensate for the active phase difference. The use of the compensation coefficient to compensate for the active phase difference can comprehensively consider the impact of different external environments on reactive power, thereby further improving the feasibility and safety of the final reactive power dispatch. Finally, the product of the active phase difference and the compensation coefficient can be used as the active compensation amount. The active compensation amount of each power node in the large-scale power grid can be obtained in the above manner.

[0081] In some embodiments, determining the active power regulation cost of each power node in the large-scale power grid according to each active power compensation amount and the over-limit penalty entropy can be implemented by the following steps:

[0082] For each power node in the large-scale power grid, the active power compensation amount of the power node is obtained;

[0083] Determining an over-limit constraint amount of a power supply node by using the active power compensation amount and the over-limit penalty entropy;

[0084] Obtaining a target regulation amount of active power regulation in a power supply node;

[0085] The active power regulation cost of the power supply node is determined according to the target regulation amount and the over-limit constraint amount, and then the active power regulation cost of each power supply node in the large-scale power grid is obtained.

[0086] It should be noted that the active power regulation cost refers to the degree of influence of the energy loss of the active power of the power system during the transmission process on the safe and stable regulation of the power system. The active power regulation cost is manifested as the loss of active power. The active power regulation cost will cause the electric energy on the transmission line to be converted into heat energy, thereby affecting the safety of the power system. In specific implementation, first, for each power node in the large-scale power grid, the active power compensation amount of the power node is obtained; secondly, an over-limit constraint model is initialized, and the active power compensation amount can be used as the constraint condition of the active power in the over-limit constraint model, and the over-limit penalty entropy can be used as the constraint condition of the reactive power in the over-limit constraint model, and then the over-limit constraint amount of the power node can be obtained through the over-limit constraint model. It should be noted that other existing The model obtains the over-limit constraint of the power node, which is not limited here. It only needs to ensure that the determination process of the over-limit constraint needs to comprehensively consider the mutual constraint relationship between the active power compensation of active power and the over-limit penalty of reactive power on reactive power. The over-limit constraint represents the common constraint degree of the active power compensation of active power and the over-limit penalty of reactive power on the reactive power after reaching the over-limit state, among which the active power compensation of active power refers to the active power compensation of the power node; then, the target adjustment amount can be preset according to historical experience, and the target adjustment amount represents the quantitative value of the active network loss after the power node is over-limited; finally, the difference between the target adjustment amount and the over-limit constraint amount can be used as the active adjustment cost of the power node. The active adjustment cost of each power node in the large-scale power grid can be obtained in the above manner.

[0087] In step 104, the reactive loss records of the large-scale power grid are extracted from the historical reactive data, and then the reactive safety margin of the large-scale power grid in an over-limit state is determined based on the reactive loss records, and the adaptive constraint of reactive power is determined through all active regulation costs and the reactive safety margin.

[0088] It should be noted that reactive loss refers to the energy loss caused by the inductance and capacitance of power system components (such as transformers, cables, etc.) during the transmission and distribution process; in specific implementation, for each reactive power record in the historical reactive data, the difference between the reactive power value in the reactive power record and the reactive power value of the previous minute is cyclically used as the reactive loss value of the corresponding reactive power value, and all reactive loss values ​​can be used as the value range of the reactive loss corresponding to the reactive power record. The value range of the reactive loss corresponding to each reactive power record in the historical reactive data can be obtained in the above manner, and the set of all values ​​of all reactive losses is used as the reactive loss record.

[0089] In some embodiments, the reactive power safety margin of a large-scale power grid under an over-limit state is determined based on the reactive power loss record, referring to Figure 3 As described above, the figure is a schematic diagram of a process for determining a reactive power safety margin in some embodiments of the present application. In this embodiment, determining the reactive power safety margin can be achieved by using the following steps:

[0090] In step 1041, all reactive power consumption values ​​when the reactive power reaches an over-limit state are obtained in the reactive power loss record;

[0091] In step 1042, determining an over-limit value corresponding to each reactive power consumption value;

[0092] In step 1043, the reactive power stability in the over-limit state is determined by all reactive power consumption values;

[0093] In step 1044, the reactive power safety margin of the large-scale power grid in the over-limit state is determined by all over-limit values ​​and the reactive power stability.

[0094] It should be noted that the reactive safety margin refers to the margin or allowance between reactive power demand and reactive power supply in the power system. The reactive safety margin is used to ensure the stability and safe operation of the power system. The reactive stability is used to measure the stability of reactive power consumption in the out-of-limit state.

[0095] In the specific implementation, first, a reactive loss value in the reactive loss record is selected, and the reactive power value corresponding to the reactive loss value is obtained, and the relationship between the reactive power value and the preset over-limit threshold is determined. If the reactive power value is greater than the preset over-limit threshold, it is determined that the reactive loss value has reached the over-limit state. If the reactive loss value is less than or equal to the preset over-limit threshold, it is determined that the reactive loss value is in a normal state. Repeat the above steps to judge the state of each reactive loss value in the reactive loss record, and the state of each reactive loss value can be obtained. Each reactive loss value that reaches the over-limit state can be used as the reactive power consumption value, and all reactive power consumption values ​​when the reactive power reaches the over-limit state can be obtained; secondly, for each reactive power consumption value, obtain the reactive power value corresponding to the reactive loss value, and use the difference between the reactive power value and the preset over-limit threshold as the over-limit value corresponding to the reactive power consumption value. The over-limit value corresponding to each reactive power consumption value can be obtained in the above manner; then, the standard deviation of all reactive power consumption values ​​can be used as the reactive stability in the over-limit state; finally, initialize a safety assessment model, all the over-limit values ​​can be used as training parameters of the safety assessment model, and the reactive stability can be used as the initialization parameter. The reactive safety margin of a large-scale power grid in the over-limit state can be obtained through the safety assessment model. It should be noted that in other embodiments, other existing assessment models can also be used to obtain the reactive safety margin of a large-scale power grid in the over-limit state, which is not limited here.

[0096] In some embodiments, determining the adaptive constraint amount of reactive power by all active power regulation costs and the reactive power safety margin may be implemented by the following steps:

[0097] For each power node in the large-scale power grid, the active power regulation cost of the power node is obtained;

[0098] Performing power flow iteration on the reactive power of the power supply node by using the active power regulation cost to obtain the power adaptability of the power supply node;

[0099] Determining an adaptation constraint value of a power source node based on the power adaptability and the reactive power safety margin, and then obtaining an adaptation constraint value of each power source node in a large-scale power grid;

[0100] The adaptive constraint amount of reactive power is determined according to all adaptive constraint values.

[0101] It should be noted that the adaptive constraint refers to the quantitative value of the constraint condition used to describe the reactive power regulation capability in the power system. The adaptive constraint can ensure that the power system has sufficient reactive power regulation capability to maintain the voltage stability and safe operation of the system. In the specific implementation, first, for each power node in the large-scale power grid, the active power regulation cost of the power node is obtained. Secondly, an electric power flow model is initialized, and the active power regulation cost is used as the initial solution of the power flow iteration. The reactive power of the power node is calculated through the power flow model. After n iterations, n power fitness can be obtained. The maximum value of all power fitness is taken as the power fitness of the power node. The power fitness is expressed as n is the power flow iteration. The setting of times, n needs to comprehensively consider factors such as the complexity of the power system, the calculation accuracy requirements, and the convergence speed. It can be preset through historical experience summary and the actual situation of the power system to ensure the accuracy and efficiency of the power flow iteration calculation. Power flow iteration calculation is a commonly used method in power systems. The power flow iteration calculation method can effectively estimate the fitness parameters of the power supply nodes in the system by iteratively calculating the current and voltage relationship between nodes; then, the product of the power fitness and the reactive safety margin can be used as the adaptation constraint value of the power supply node. The adaptation constraint value of each power supply node in the large-scale power grid can be obtained in the above manner; finally, all the adaptation constraint values ​​can be used as the value range of the adaptive constraint of reactive power.

[0102] In step 105, when the reactive power of the large-scale power grid is in an over-limit state, the reactive power of each power source node in the large-scale power grid is constrained and scheduled based on the adaptive constraint amount.

[0103] In some embodiments, constraining the reactive power of each power source node in the large-scale power grid based on the adaptive constraint amount can be implemented by the following steps:

[0104] Determining the constraint amount of each power source node in the large-scale power grid based on the trained power dispatch model and the adaptive constraint amount;

[0105] The reactive power of each power node is dispatched and allocated through all constraints.

[0106] In the specific implementation, first, a trained power dispatching model is initialized, and the adaptive constraint amount is used as the dispatching parameter of the power dispatching model. For each power node in the large-scale power grid, the output result of the power dispatching model on the reactive power of the power node can be used as the constraint amount of the reactive power of the power node. The constraint amount represents the reactive power that needs to be constrained and allocated in the power node. A positive constraint amount indicates that the reactive power in the power node is too high. At this time, the reactive power in the power node needs to be allocated to other power nodes, otherwise the voltage in the power node may increase; a negative constraint amount indicates that the reactive power of the power node is too low. At this time, reactive power needs to be dispatched from other power nodes, otherwise the voltage in the power node may decrease; both voltage increases and decreases may cause overload of power generation equipment, thereby causing instability in the large-scale power grid; then, the balancing algorithm in the prior art can be used to dispatch the reactive power in the power nodes corresponding to each positive constraint amount to each negative constraint amount to ensure that the constraint amount of each power node tends to 0. The above steps can complete the constrained dispatch of the reactive power of each power node in the large-scale power grid.

[0107] In the present application, when the reactive power of a large-scale power grid is in an over-limit state, the reactive power of each power supply node in the large-scale power grid can be constrained and scheduled based on the adaptive constraint amount; wherein, the over-limit penalty entropy is determined by the reactive over-limit record, and the quantitative value of the reactive power that needs to be adjusted after reaching the over-limit state can be obtained, which can facilitate the subsequent preliminary adjustment of the reactive power in the power supply nodes of the large-scale power grid; secondly, the active power adjustment cost of each power supply node is determined by historical active power data, wherein, by determining the degree of constraint compensation of active power to reactive power after the over-limit is determined, the mutual constraint relationship between active power and reactive power in power transmission can be accurately obtained, so that each power supply node can be adjusted in the subsequent When the reactive power of the node is constrained and dispatched, the mutual constraint relationship is comprehensively considered, which can effectively avoid the power safety problem caused by the mutual constraint relationship, thereby improving the safety of reactive power in large-scale power grids; then, the adaptive constraint amount of reactive power can be determined by all active regulation costs and the reactive safety margin, and then when the reactive power of the large-scale power grid is in an out-of-limit state, the quantified value of the constraint condition of the reactive power regulation capability (i.e., the adaptive constraint amount) can be used to constrain the reactive power of each power node; in summary, based on the above scheme, the constrained dispatch of reactive power in each power node can be realized, thereby improving the safety and stability of reactive power in large-scale power grids.

[0108] In addition, in another aspect of the present application, in some embodiments, the present application provides a power control system based on big data, and the power control system based on big data also includes a control unit, referring to Figure 4, which is a schematic diagram of exemplary hardware and / or software of a control unit according to some embodiments of the present application, the control unit includes: an acquisition module 201, a processing module 202 and an execution module 203, which are described as follows:

[0109] Acquisition module 201, in this application, acquisition module 201 is mainly used to acquire reactive power records of each power node in a large-scale power grid from power grid big data, and then obtain historical reactive power data;

[0110] Processing module 202, in the present application, the processing module 202 is used to extract reactive power over-limit records in power transmission from the historical reactive data through a preset over-limit threshold, and determine the over-limit penalty entropy of reactive power in power transmission according to the reactive power over-limit records;

[0111] It should be noted that the processing module 202 is also used to obtain active power records in the large-scale power grid, and then obtain historical active data, determine the active compensation amount of each power node in the large-scale power grid through the historical active data, and then determine the active regulation cost of each power node in the large-scale power grid according to each active compensation amount and the over-limit penalty entropy;

[0112] In addition, the processing module 202 is also used to extract the reactive power loss record of the large-scale power grid from the historical reactive power data, and then determine the reactive power safety margin of the large-scale power grid in the over-limit state according to the reactive power loss record, and determine the adaptive constraint amount of reactive power through all active power regulation costs and the reactive power safety margin;

[0113] Execution module 203, in the present application, the execution module 203 is mainly used to constrain the reactive power of each power supply node in the large-scale power grid based on the adaptive constraint when the reactive power of the large-scale power grid is in an out-of-limit state.

[0114] The above describes in detail the examples of the power system based on big data and the control method thereof provided by the embodiments of the present application. It can be understood that in order to realize the above functions, the corresponding device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0115] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned big data-based power control method.

[0116] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or the module is optional, and the figure is a schematic diagram of the structure of a computer device for implementing a power control method based on big data according to an embodiment of the present application. The power control method based on big data described in the above embodiment can be Figure 5 The computer device shown in the figure is implemented, and the computer device includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device can be a terminal device, a server or a chip.

[0117] The processor 301 may be a general-purpose processor or a special-purpose processor. For example, the processor 301 may be a central processing unit (CPU), which may be used to control the computer device, execute software programs, and process data of the software programs. The computer device may also include a communication unit 305 to implement signal input (reception) and output (transmission).

[0118] For example, the computer device may be a chip, the communication unit 305 may be an input and / or output circuit of the chip, or the communication unit 305 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

[0119] For another example, the computer device may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0120] The computer device may include one or more memories 302, on which a program 304 is stored. The program 304 can be executed by the processor 301 to generate instructions 303, so that the processor 301 performs the method described in the above method embodiment according to the instructions 303. Optionally, data (such as a target audit model) can also be stored in the memory 302. Optionally, the processor 301 can also read the data stored in the memory 302, and the data can be stored at the same storage address as the program 304, or the data can be stored at a different storage address from the program 304.

[0121] The processor 301 and the memory 302 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0122] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0123] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0124] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned big data-based power control method when executed.

[0125] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0126] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A power control method based on big data, characterized in that: The steps include: Obtain reactive power records of each power node in a large-scale power grid from power grid big data, and then obtain historical reactive power data; Extracting reactive power over-limit records in power transmission from the historical reactive data by using a preset over-limit threshold, and determining over-limit penalty entropy of reactive power in power transmission according to the reactive power over-limit records; Obtain active power records in a large-scale power grid, and then obtain historical active power data, determine the active power compensation amount of each power supply node in the large-scale power grid through the historical active power data, and then determine the active power regulation cost of each power supply node in the large-scale power grid according to each active power compensation amount and the over-limit penalty entropy; Extracting reactive power loss records of large-scale power grids from the historical reactive power data, and then determining reactive power safety margins of large-scale power grids in over-limit states based on the reactive power loss records, and determining adaptive constraints of reactive power through all active power regulation costs and the reactive power safety margins; When the reactive power of the large-scale power grid is in an over-limit state, constraining the reactive power of each power source node in the large-scale power grid is dispatched based on the adaptive constraint amount; Wherein, determining the reactive power over-limit penalty entropy in power transmission according to the reactive power over-limit record specifically includes: Obtaining the over-limit entropy corresponding to each data item in the reactive power over-limit record in power transmission, and then determining the penalty amount of reactive power after over-limit in power transmission; Determine the penalty adjustment coefficient of reactive power in power transmission when it exceeds the limit; Determine the over-limit penalty entropy of reactive power in power transmission by using the penalty adjustment coefficient and the penalty amount; Wherein, determining the active power compensation amount of each power supply node in the large-scale power grid through the historical active power data specifically includes: For each power supply node, obtaining an active power record corresponding to the power supply node from the historical active power data; Determining an active phase difference of active power in the active power record when power is transmitted; Determine the compensation factor of active power in power transmission; Determine the active compensation amount of the power supply node according to the active phase difference and the compensation coefficient, and then obtain the active compensation amount of each power supply node in the large-scale power grid; Among them, determining the active power regulation cost of each power node in the large-scale power grid according to each active power compensation amount and the over-limit penalty entropy specifically includes: For each power node in the large-scale power grid, the active power compensation amount of the power node is obtained; Determining an over-limit constraint amount of a power supply node by using the active power compensation amount and the over-limit penalty entropy; Obtaining a target regulation amount of active power regulation in a power supply node; Determine the active power regulation cost of the power supply node according to the target regulation amount and the over-limit constraint amount, and then obtain the active power regulation cost of each power supply node in the large-scale power grid; Wherein, determining the reactive power safety margin of a large-scale power grid in an over-limit state according to the reactive power loss record specifically includes: Obtaining all reactive power consumption values ​​when the reactive power reaches an over-limit state in the reactive power loss record; Determine the over-limit value corresponding to each reactive power consumption value; Determine the reactive power stability under the over-limit state through all reactive power consumption values; Determine the reactive power safety margin of the large-scale power grid in the over-limit state through all over-limit values ​​and the reactive power stability; The method of constraining the reactive power of each power source node in the large-scale power grid based on the adaptive constraint quantity specifically includes: Determining the constraint amount of each power source node in the large-scale power grid based on the trained power dispatch model and the adaptive constraint amount; The reactive power of each power node is dispatched and allocated through all constraints.

2. The method according to claim 1, characterized in that Extracting reactive power exceeding limit records in power transmission from the historical reactive power data by using a preset exceeding limit threshold specifically includes: For each reactive power record in the historical reactive power data, obtaining all reactive power values ​​in the reactive power record; Taking all reactive power values ​​higher than the preset over-limit threshold as the value range of reactive over-limit values ​​corresponding to the reactive power record, and then obtaining the value range of reactive over-limit values ​​corresponding to each reactive power record in the historical reactive data; The reactive power over-limit record in power transmission is determined by the value range of each reactive power over-limit value.

3. A power control system based on big data, which uses the method described in any one of claims 1 or 2 to perform power control, and the power control system based on big data includes a control unit, characterized in that: The control unit comprises: The acquisition module is used to obtain the reactive power records of each power node in the large-scale power grid from the power grid big data, and then obtain the historical reactive power data; A processing module, configured to extract reactive power exceeding limit records in power transmission from the historical reactive power data by using a preset exceeding limit threshold, and determine the exceeding limit penalty entropy of reactive power in power transmission according to the reactive power exceeding limit records; The processing module is also used to obtain active power records in the large-scale power grid, and then obtain historical active data, determine the active compensation amount of each power node in the large-scale power grid through the historical active data, and then determine the active regulation cost of each power node in the large-scale power grid according to each active compensation amount and the over-limit penalty entropy; The processing module is also used to extract reactive power loss records of the large-scale power grid from the historical reactive power data, and then determine the reactive power safety margin of the large-scale power grid in an over-limit state according to the reactive power loss records, and determine the adaptive constraint amount of reactive power through all active power regulation costs and the reactive power safety margin; The execution module is used to constrain the reactive power of each power supply node in the large-scale power grid based on the adaptive constraint when the reactive power of the large-scale power grid is in an over-limit state.

4. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the big data-based power control method described in any one of claims 1 or 2.

5. A computer-readable storage medium, wherein instructions or codes are stored in the computer-readable storage medium. When the instructions or codes are executed on a computer, the computer implements the big data-based power control method as described in any one of claims 1 or 2.

Citation Information

Patent Citations

  • Rapid coordination control method for reactive voltage of power system adapting to multi-energy access

    CN105098801A

  • Power grid operation management system based on big data

    CN111461519A