Transformer area voltage active treatment method based on multi-agent self-optimization-approaching regulation and control strategy

Abstract

The invention relates to the technical field of power supply and distribution systems, in particular to a transformer area voltage active governance method based on a multi-agent self-optimization control strategy, and the method comprises the steps: if a current agent meets a regulation and governance starting condition, according to different types of electrical parameters of each access point in an area under administration of the current agent, starting the regulation and governance according to the different types of electrical parameters of each access point in the area under administration of the current agent; determining a cost contribution access point in the access points and the governance cost of the cost contribution access point, and further determining the adjusted governance budget cost of the current agent and the cooperative governance evaluation parameters between the current agent and other agents; and determining a voltage scheduling scheme according to the current voltage of the current agent, the adjusted governance budget cost and the cooperative governance evaluation parameters between the current agent and other agents. According to the method and the device, the treatment cost of the current agent and the cooperative treatment condition between the current agent and other agents are accurately evaluated, so that the accuracy of the determined voltage scheduling scheme is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply and distribution systems, and particularly to an active governance method for substation area voltage based on a multi-agent self-optimizing control strategy. Background Art

[0002] Substation area voltage governance refers to taking various technical means and management measures in the power distribution system to address the problem of unstable voltage at the end of the substation area (the power supply area of the distribution transformer) to ensure that the voltage is within a reasonable range and guarantee the stability and quality of power supply. Since low voltage can cause problems such as abnormal operation of household appliances, affected industrial production, and increased power grid losses, while high voltage may damage electrical equipment. Therefore, substation area voltage governance is of great significance for ensuring power supply safety and improving user satisfaction.

[0003] As an emerging research direction, multi-agent technology is gradually applied to substation area voltage governance by enabling multiple autonomous decision-making units to work together to jointly complete specific tasks. However, in the prior art, during the process of using multi-agents to govern the substation area voltage, there are problems such as a low matching degree between the voltage adjustment of the agents and the surrounding environment, and large adjustments are made to some short-term jitters during the coordination process, resulting in inaccurate adjustment of the substation area voltage and inability to guarantee the power supply stability and quality of the substation area. Summary of the Invention

[0004] In order to solve the above technical problem of inaccurate adjustment of substation area voltage, the purpose of the present invention is to provide an active governance method for substation area voltage based on a multi-agent self-optimizing control strategy, and the specific technical solution adopted is as follows: In the first aspect, the present invention provides an active governance method for substation area voltage based on a multi-agent self-optimizing control strategy, and the method includes: If the current agent meets the condition for starting control and governance, determine the cost contribution access points and the governance costs of the cost contribution access points among the access points according to different types of electrical parameters of each access point within the jurisdiction of the current agent; Determine the governance budget cost of the current agent according to the governance costs of the cost contribution access points, and determine the required optimization cycle of the current agent according to the governance costs and the governance budget cost, and then determine the optimization planning cycle of the layer where the current agent is located according to the required optimization cycles of all agents in the layer where the current agent is located; Determine the collaborative governance evaluation parameters between the current agent and other agents according to the governance budget costs and the optimization planning cycles of the current agent and other agents, and adjust the governance budget cost of the current agent according to the collaborative governance evaluation parameters and the governance budget costs of other agents to obtain the adjusted governance budget cost; Determine the voltage scheduling scheme according to the voltage of the current agent, adjust the governance budget cost and the collaborative governance evaluation parameters.

[0005] Combined with the first aspect above, in some possible implementation manners, determining the cost contribution access points among the access points includes: Construct a system state vector for each access point according to different types of electrical parameters of each access point within the jurisdiction of the current agent; Determine a state transition matrix according to the system state vector, where the dimension of the state transition matrix is determined according to the type of electrical parameter, and each element in the state transition matrix corresponds to two types of electrical parameters; Determine the abnormally fluctuating elements in the state transition matrix according to the distribution of the elements in the state transition matrix; Mark the types of electrical parameters of each access point according to the abnormally fluctuating elements to obtain the sub-marking times of each type of electrical parameter of each access point; Determine the cumulative value of all sub-marking times of each access point as the marking times of each access point, and determine the access points with marking times greater than 0 as cost contribution access points.

[0006] Combined with the first aspect above, in some possible implementation manners, determining the abnormally fluctuating elements in the state transition matrix includes: Obtain the histogram corresponding to all elements in the state transition matrix; Determine the height sequence corresponding to the height values of each peak column in the histogram, and determine the first-order difference sequence of the height sequence; Determine two target peak columns corresponding to the maximum difference value in the first-order difference sequence, determine the average value of all elements included in each target peak column as the element mean value, and determine the maximum element mean value among the two element mean values; Determine all elements included in the peak column corresponding to the maximum element mean value in the histogram and the peak column where the maximum element in the state transition matrix is located as the abnormally fluctuating elements in the state transition matrix.

[0007] Combined with the first aspect above, in some possible implementation manners, determining the governance cost of the cost contribution access points includes: Determine the difference between the real-time voltage and the prior adaptation voltage of the cost contribution access point as the voltage adjustment target; Determine the extreme difference value of the sub-marking times of each type of electrical parameter of the cost contribution access point; Determine the ratio of the marking times of the cost contribution access point to the extreme difference value, and determine the product of the ratio and the voltage adjustment target as the governance cost of the cost contribution access point.

[0008] Combined with the above first aspect, in some possible implementation manners, determining the governance budget cost of the current agent includes: Determining the superposition value of the governance costs of all cost contribution access points as the access point cost loss; Determining the standard deviation of the governance costs of all cost contribution access points as the governance cost standard deviation; Determining the difference between the governance cost of each cost contribution access point and the access point cost loss as the governance cost deviation value of each access point; Determining the governance budget cost of the current agent according to the access point cost loss and the governance cost standard deviation, and in combination with the governance cost deviation values of all cost contribution access points.

[0009] Combined with the above first aspect, in some possible implementation manners, determining the period required for the current agent to optimize includes: Determining a number of local governance point pairs according to the governance costs of all cost contribution access points, where a local governance point pair includes two cost contribution access points; Determining the cumulative value of the governance costs of all different cost contribution access points included in all local governance point pairs as the total governance cost, and determining the ceiling result of the ratio of the total governance cost to the absolute value of the governance budget cost of the current agent as the period required for the current agent to optimize.

[0010] Combined with the above first aspect, in some possible implementation manners, determining the optimization planning period of the level where the current agent is located includes: Determining the centralized target interval of the periods required for all agents in the level where the current agent is located to optimize; Determining the target periods required for optimization that are located in the centralized target interval among the periods required for all agents in the level where the current agent is located to optimize, and determining the average value of all target periods required for optimization as the optimization planning period of the level where the current agent is located.

[0011] Combined with the above first aspect, in some possible implementation manners, determining the collaborative governance evaluation parameter between the current agent and other agents includes: Determining the sum of the governance budget costs of the current agent and each other agent as the sum of governance costs; Determining the ratio of the optimization planning periods of the levels where the current agent and each other agent are located as the ratio of planning periods; Determining the collaborative governance evaluation parameter between the current agent and other agents according to the sum of governance costs and the ratio of planning periods.

[0012] Combined with the above first aspect, in some possible implementation manners, adjusting the governance budget cost of the current agent to obtain the adjusted governance budget cost includes: Determine the mean and variance of the collaborative governance evaluation parameters between all agents and other agents in the current level where the current agent is located, and obtain the mean of the evaluation parameters and the variance of the evaluation parameters; Determine the dynamic threshold of the evaluation parameters of the current agent according to the mean of the evaluation parameters and the variance of the evaluation parameters; Determine the target other agents of the current agent, and the collaborative governance evaluation parameter between the current agent and the target other agents is less than the dynamic threshold of the evaluation parameters; Determine the cumulative value of the collaborative governance evaluation parameters between the current agent and all target other agents as the cumulative collaborative governance evaluation parameter; Determine the accumulated value of the governance budget costs of all target other agents of the current agent as the cumulative governance budget cost, and determine the governance budget cost adjustment coefficient according to the ratio of the cumulative collaborative governance evaluation parameter to the cumulative governance budget cost; Determine the product of the governance budget cost of the current agent and the governance budget cost adjustment coefficient as the adjusted governance budget cost of the current agent.

[0013] Combined with the above first aspect, in some possible implementation manners, determining a voltage scheduling scheme includes: Input the current voltage and adjusted governance budget cost of the current agent, and the collaborative governance evaluation parameters between the current agent and all target other agents into a neural network, and the neural network outputs the target other agents that can be scheduled among all target other agents of the current agent and the voltage values that need to be scheduled.

[0014] In a second aspect, the present invention further provides a substation area voltage active governance system based on a multi-agent self-optimizing regulation strategy, including a memory and a processor. The memory is used to store executable computer program code, and the processor is used to call and run the executable computer program code from the memory, so that the system executes a substation area voltage active governance method based on a multi-agent self-optimizing regulation strategy in the above first aspect or any one of the possible implementation manners of the first aspect.

[0015] In a third aspect, the present invention further provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, the computer is enabled to execute the method in the above first aspect or any one of the possible implementation manners of the first aspect.

[0016] In a fourth aspect, the present invention further provides a computer-readable storage medium, which stores computer program code, and when the computer program code runs on a computer, the computer is enabled to execute the method in the above first aspect or any one of the possible implementation manners of the first aspect.

[0017] The present invention has the following beneficial effects: When the current agent starts regulation and governance, by determining the cost contribution access points within the jurisdiction of the previous agent and the governance costs of the cost contribution access points, the governance budget cost of the current agent is further determined to preliminarily budget the governance cost of the current agent; according to the governance costs of the cost contribution access points and the governance budget cost of the current agent, the required period for the current agent to optimize is determined, and according to the required periods for all agents in the current level of the current agent to optimize, the optimization planning period of the current level where the current agent is located is determined, and then the collaborative governance evaluation parameter between the current agent and other agents is determined. Thus, using the collaborative governance evaluation parameter and the governance budget costs of other agents, the governance budget cost of the current agent is adjusted to obtain the adjusted governance budget cost of the current agent; finally, according to the current voltage of the current agent, the adjusted governance budget cost, and the collaborative governance evaluation parameter between the current agent and other agents, a voltage scheduling plan is determined. The present invention accurately evaluates the governance cost of the current agent and the collaborative governance situation between the current agent and other agents, thereby determining a voltage scheduling plan, improving the matching degree between the voltage adjustment of the agent and the surrounding environment, and thus realizing precise voltage adjustment within the jurisdiction of the current agent, effectively ensuring the power supply stability and quality of the jurisdiction of the current agent. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a flowchart of the steps of a method for active governance of substation area voltage based on a multi-agent self-optimizing regulation strategy according to an embodiment of the present invention; Figure 2 It is a distribution diagram of agents at different levels according to an embodiment of the present invention; Figure 3 It is a schematic structural diagram of a system for active governance of substation area voltage based on a multi-agent self-optimizing regulation strategy according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In order to clearly illustrate the technical features of this solution, the present invention will be elaborated in detail below through specific embodiments in combination with the drawings.

[0021] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0022] It should be understood that the various steps recited in the method embodiments of the present invention can be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this regard.

[0023] As used herein, the term "comprising" and its variants are open-ended, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0024] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order of the functions executed by these devices, modules or units or their interdependent relationships.

[0025] In the embodiments of the present invention, although the operations or steps are described in a specific order in the drawings, it should not be understood as requiring these operations or steps to be executed in the specific order shown or in a serial order, or requiring all the operations or steps shown to obtain the desired result. In the embodiments of the present invention, these operations or steps can be executed serially; they can also be executed in parallel; or a part of these operations or steps can be executed.

[0026] At the same time, it can be understood that the data involved in the technical solution of the present invention (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws, regulations and related provisions. Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs, and all parameters or indicators in the formulas involved in the present invention are numerical values after normalization that eliminate the influence of dimensions.

[0027] Next, a method for active governance of substation area voltage based on a multi-agent self-optimizing regulation strategy provided by the embodiments of the present invention will be introduced in detail with reference to the accompanying drawings.

[0028] Figure 1The figure shows a schematic diagram of the basic process of an active governance method for substation area voltage based on a multi-agent self-optimizing control strategy provided by an embodiment of the present invention. As Figure 1 shown, the method specifically includes the following steps: Step S100: If the current agent meets the conditions for starting regulation and governance, determine the cost contribution access points and the governance costs of the cost contribution access points among the access points according to the different types of electrical parameters of each access point within the jurisdiction of the current agent.

[0029] Specifically, the purpose of the agent for substation area voltage governance is to optimize the inconsistent voltages within its jurisdiction to ensure that the substation area voltage responds in seconds to complete the limitation of voltage fluctuations and ensure the stability and quality of power supply within the jurisdiction.

[0030] Regard the agent as a coupling of a physical node and a computing unit deployed at the grid terminal, and define any one agent ; where S represents the node data unit, and the node voltage, node active power, node reactive power, etc. at the terminal part are collected by deploying power sensors; A represents the node action unit, which is responsible for executing the actions of the node, such as circuit switching, tap adjustment, inverter setpoint adjustment, etc.; R represents the node communication unit, which is responsible for communicating with other agents.

[0031] For the current agent Preset a regulation voltage range (205V - 225V) as the limiting range for triggering regulation. When the real-time monitored voltage of any one entry point within the jurisdiction of the current agent z at the current moment meets the conditions for starting regulation and governance, then it is determined that the current agent meets the conditions for starting regulation and governance, and then starts regulation and governance at the current moment : The current agent

[0032] makes a judgment on the voltage environment within its jurisdiction by sensing the changes in the power data output within its jurisdiction to evaluate the voltage resources required for governance, so as to judge the response ability of the voltage resources that can be utilized within the local range of the jurisdiction to the voltage environment governance during the voltage optimization process. Use the node data unit S of the current agent to obtain the voltages , active powers , and reactive powers of each access point within the jurisdiction of the current agent , so as to obtain different types of electrical parameters of each access point within the jurisdiction of the current agent. Based on the current agent For different types of electrical parameters of each access point within the jurisdiction, screen the cost contribution access points among all access points and determine the governance cost of the cost contribution access points, where the governance cost reflects the current agent The cost of voltage governance for each cost contribution access point within the jurisdiction.

[0033] Step S200: Determine the governance budget cost of the current agent based on the governance cost of the cost contribution access points, and determine the optimal cycle required for the current agent based on the governance cost and the governance budget cost. Furthermore, determine the optimal planning cycle of the layer where the current agent is located based on the optimal cycles required for all agents in the layer where the current agent is located.

[0034] Specifically, by analyzing the governance costs of all cost contribution access points within the jurisdiction of the current agent Perform a preliminary assessment of the governance cost of the current agent . Furthermore, based on the governance costs of all cost contribution access points within the jurisdiction of the current agent And the governance budget cost of the current agent , determine the optimal cycle required for the current agent . Reflect the deviation between the local governance cost and the total governance cost within the jurisdiction of the current agent Through the optimal cycle required.

[0035] In the same way as determining the optimal cycle required for the current agent above, the optimal cycles required for other agents in the layer where the current agent is located can be determined. Figure 2 Give a distribution diagram of agents at different levels. Among Figure 2 , the voltage regulation agent, the temperature control agent, and the distributed power source agent belong to the same level. Furthermore, based on the deviation of the optimal cycles required for all agents in the layer where the current agent is located, obtain the optimal planning cycle of the layer where the current agent is located. Analyze the balance between the optimal planning cycle and the cost of optimization for the layer where the current agent is located. If the optimal planning cycle of the layer where the current agent is located is relatively large, it means that the current agent relies on the local node voltage resource balance and cannot achieve voltage governance within a local area. Therefore, it is necessary to combine the local voltage governance cost with the external to achieve voltage governance within the range and tend to be stable. The additional cost overhead brought by the node scheduling distance generated during the governance process and the power environment stability of the node itself need to be used as the basis for the scheduling process.

[0036] ​Step S300: Determine the collaborative governance evaluation parameters between the current agent and other agents according to the governance budget costs and optimization planning cycles of the current agent and other agents, and adjust the governance budget cost of the current agent according to the collaborative governance evaluation parameters and the governance budget costs of other agents to obtain the adjusted governance budget cost.

[0037] Specifically, according to the governance budget costs and optimization planning cycles of different agents, judge the collaborative governance evaluation between different agents to determine the collaborative governance evaluation parameters between different agents for the collaborative governance scheduling between the same level and different levels. When the collaborative governance evaluation parameters between different agents are small, it indicates that the collaborative efficiency of the two agents is insufficient. Therefore, according to the collaborative governance evaluation parameters between the current agent and other agents, and the governance budget costs of other agents, where other agents refer to an agent at the current agent's level or any other level outside the current agent's level, punitively adjust the governance budget cost of the current agent to obtain the adjusted governance budget cost of the current agent, so as to reallocate the reduced budget to the agents with high collaborative efficiency to accelerate the global optimization process.

[0038] Step S400: Determine the voltage scheduling scheme according to the voltage, adjusted governance budget cost and collaborative governance evaluation parameters of the current agent.

[0039] Specifically, determine the adaptive voltage scheduling scheme according to the current voltage and adjusted governance budget cost of the current agent, and the collaborative governance evaluation parameters between the current agent and other agents, so as to achieve precise voltage adjustment within the jurisdiction of the current agent and ensure the power supply stability and quality of the substation area.

[0040] In the above-mentioned active voltage governance method for the substation area based on the multi-agent self-optimizing regulation strategy, when the current agent meets the conditions for starting the regulation and governance, the governance budget cost of the current agent is determined by the governance costs of all cost contribution access points within the jurisdiction of the current agent, and then the optimal planning period of the current agent's level is determined. According to the governance budget costs and optimal planning periods of the current agent and other agents, the collaborative governance evaluation parameters between the current agent and other agents are determined. Thus, based on the collaborative governance evaluation parameters between the current agent and other agents, as well as the governance budget costs of other agents, the governance budget cost of the current agent is adjusted punitively. Finally, based on the current voltage of the current agent, the adjusted governance budget cost, and the collaborative governance evaluation parameters between the current agent and other agents, the voltage scheduling plan is adaptively determined, thereby achieving precise voltage adjustment within the jurisdiction of the current agent and effectively ensuring the power supply stability and quality of the current agent's jurisdiction.

[0041] Further, in a possible implementation manner, determining the cost contribution access points among the access points in the above step S100 includes: Step S101: Construct a system state vector for each access point according to different types of electrical parameters of each access point within the jurisdiction of the current agent.

[0042] Specifically, according to the current agent of any access point within the jurisdiction at the current moment and its voltages in the past period of time (such as 1 minute), these voltages are arranged in chronological order to obtain a voltage observation vector , representing the nth voltage in the voltage observation vector . Similarly, an active power observation vector and a reactive power observation vector can be obtained. Among them, represents the nth active power in the active power observation vector , represents the nth reactive power in the reactive power observation vector . The voltage observation vector , the active power observation vector and the reactive power observation vector are superimposed to obtain the system state vector of any access point within the jurisdiction of the current agent .

[0043] Step S102: Determine a state transition matrix according to the system state vector. The dimension of the state transition matrix is determined according to the type of electrical parameter, and each element in the state transition matrix corresponds to two types of electrical parameters.

[0044] Specifically, the system state vectors of each access point within the jurisdiction of the current agent are sequentially input into the EKF (Extended Kalman Filter) that has completed running by the current agent itself , and the state transition matrix corresponding to each access point is output by the EKF . Since no predicted value is output, the computational overhead is reduced, and the computational real-time performance is increased to meet the requirement of local agent priority processing and scheduling. It should be understood that the dimension of this state transition matrix is determined according to the type of electrical parameter. Since the types of electrical parameters in this embodiment are voltage, active power, and reactive power, the determined state transition matrix is a 3×3 square matrix, and each element in this state transition matrix corresponds to two of the types among voltage, active power, and reactive power.

[0045] Step S103: Determine the abnormally fluctuating elements in the state transition matrix according to the distribution of the elements in the state transition matrix.

[0046] Specifically, judge the correlation influence of each element in the state transition matrix of each access point within the jurisdiction of the current agent on the power supply state, and determine each abnormally fluctuating element in the state transition matrix .

[0047] More specifically, in a specific implementation manner, determining the abnormally fluctuating elements in the state transition matrix includes: Step S1031: Obtain the histograms corresponding to all elements in the state transition matrix.

[0048] Specifically, count each element r in the state transition matrix of each access point within the jurisdiction of the current agent , take the arithmetic square root of the number nr of element r to obtain the histogram bar spacing , and use the spacing to evenly segment the value range of all elements r in the state transition matrix , and then establish a histogram of all elements r in the state transition matrix according to the number of elements within the segment.

[0049] Step S1032: Determine the height sequence corresponding to the height values of each peak column in the histogram, and determine the first-order difference sequence of the height sequence.

[0050] Specifically, along the direction of increasing element r in the histogram, arrange the height values of each peak column in the histogram to obtain the height sequence, and calculate the difference between each height value in the height sequence and its previous height value. Arrange these differences in the order of the height values in the height sequence to obtain the first-order difference sequence of the height sequence.

[0051] Step S1033: Determine the two target peak columns corresponding to the maximum difference value in the first-order difference sequence, determine the average value of all elements included in each target peak column as the element mean value, and determine the maximum element mean value among the two element mean values.

[0052] Specifically, in the first-order difference sequence of the height sequence corresponding to the state transition matrix of each access point within the jurisdiction of the current agent , determine the maximum difference value, and determine the two height values of this maximum difference value in the height sequence. Then determine the two peak columns in the histogram corresponding to these two height values, and take these two peak columns as the target peak columns. Determine the average value of all elements included in each target peak column, and call it the element mean value. In this way, two element mean values can be obtained, and determine the larger value among the two element mean values as the maximum element mean value.

[0053] Step S1034: Determine all elements included in the peak column corresponding to the maximum element mean value of the histogram and the peak column where the maximum element in the state transition matrix is located as the abnormal fluctuation elements in the state transition matrix.

[0054] Specifically, determine the peak column in the histogram where the maximum value among all elements r in the state transition matrix is located. Take all elements included in this peak column and all elements included in the peak column corresponding to the maximum element mean value of the histogram as the abnormal fluctuation elements in the state transition matrix.

[0055] Thus, the abnormal fluctuation elements in the state transition matrix of any access point within the jurisdiction of the current agent can be accurately obtained.

[0056] Step S104: Mark the types of the electrical parameters of each access point according to the abnormal fluctuation elements to obtain the sub-mark counts of each type of the electrical parameters of each access point.

[0057] Specifically, according to the state transition matrix The abnormal fluctuation elements in The identification in the rows and columns of the state transition matrix is used to label the types of electrical parameters, and thus the marking times of various types of electrical parameters of the corresponding access points can be obtained. The marking times are recorded as sub-marking times.

[0058] Step S105: Determine the cumulative value of all sub-marking times of each access point as the marking time of each access point, and determine the access points with marking times greater than 0 as cost contribution access points.

[0059] Specifically, determine the state transition matrix The cumulative value of the sub-marking times of each corresponding type is determined, and this cumulative value is used as the marking time of the access point corresponding to the state transition matrix From this, the marking times of each access point within the jurisdiction of the current agent can be determined. The access points with markings, that is, the marking times greater than 0, are determined as the cost contribution access points of the current agent .

[0060] By establishing the system state vectors of each access point and determining the state transition matrix, and then identifying the abnormal fluctuation elements in the state transition matrix, the accurate identification of the cost contribution access points within the jurisdiction of the current agent can be finally realized.

[0061] Furthermore, in a possible implementation manner, the governance cost of determining the cost contribution access points in the above step S100 includes: Step S106: Determine the difference between the real-time voltage and the prior adaptation voltage of the cost contribution access point as the voltage adjustment target.

[0062] Specifically, determine the real-time voltage of the current cost contribution access point and the difference from the prior adaptation voltage ( ) as the voltage adjustment target. Among them, the prior adaptation voltage refers to the rated voltage of the current cost contribution access point .

[0063] Step S107: Determine the extreme difference of the sub-marking times of various types of electrical parameters of the cost contribution access point.

[0064] Specifically, count the sub-marking times of various types of electrical parameters corresponding to the current cost contribution access point to distinguish the types of abnormal power supply parameters of the current cost contribution access point , that is, determine the maximum value and the minimum value , obtain the range value of the sub - tag times , and use this range value as the evaluation of the specificity of the abnormal power supply parameter.

[0065] Step S108: Determine the ratio of the tag times of the cost - contribution access point to the range value, and determine the product of the ratio and the voltage - adjustment target as the governance cost of the cost - contribution access point.

[0066] Specifically, determine the current cost - contribution access point 's tag times and the range value as the abnormal contribution of the current cost - contribution access point , and combine it with the voltage - adjustment target of the current cost - contribution access point ( ), so as to evaluate the cost of voltage governance for the current cost - contribution access point through the following formula: ; In the formula: represents the governance cost of the current cost - contribution access point within the jurisdiction of the current agent ; and respectively represent the real - time voltage and the prior - adaptation voltage of the current cost - contribution access point ; represents the tag times of the current cost - contribution access point ; and respectively represent the maximum and minimum values among the sub - tag times of each type of the current cost - contribution access point .

[0067] By combining the voltage - adjustment target of the cost - contribution access point, and the ratio of the tag times of the cost - contribution access point to the range value of the sub - tag times of each type of electrical parameter, the cost of voltage governance for the cost - contribution access point can be accurately evaluated finally.

[0068] Furthermore, in a possible implementation manner, determining the governance budget cost of the current agent in the above - mentioned step S200 includes: Step S201: Determine the superposition value of the governance costs of all cost - contribution access points as the access - point cost loss.

[0069] Specifically, superimpose all the governance costs of all cost - contribution access points within the jurisdiction of the current agent to obtain the access - point cost loss of the current agent 。Current agent The access point cost loss The larger the value of the higher the governance budget cost of the current agent.

[0070] Step S202: Determine the standard deviation of the governance costs of all cost - contributing access points as the governance cost standard deviation.

[0071] Step S203: Determine the difference between the governance cost of each cost - contributing access point and the access point cost loss as the governance cost deviation value of each access point.

[0072] Specifically, since the access point cost loss of the current agent represents the abnormal voltage governance expense within the jurisdiction of the current agent therefore, the deviation of the governance cost of the access point cost loss compared with the governance costs of each cost - contributing access point can reflect the abnormal contribution situation of the cost - contributing access points within the jurisdiction of the current agent . Thus, determine the difference between the governance cost of each cost - contributing access point and the access point cost loss as the governance cost deviation value of each access point.

[0073] Step S204: Determine the governance budget cost of the current agent according to the access point cost loss and the governance cost standard deviation, and in combination with the governance cost deviation values of all cost - contributing access points.

[0074] Specifically, according to the ratio of the governance costs of all cost - contributing access points within the jurisdiction of the current agent to the access point cost loss of the current agent , and in combination with the access point cost loss corresponding to the current agent , determine the governance budget cost of the current agent through the following formula: ; In the formula: represents the governance budget cost of the current agent ; represents the access point cost loss corresponding to the current agent ; represents the total number of all cost - contributing access points within the jurisdiction of the current agent ; represents the governance cost of the cost - contributing access point within the jurisdiction of the current agent ; Represents the current agent The standard deviation of the corresponding governance cost.

[0075] By calculating the access point cost loss, the standard deviation of the governance cost, and the governance cost deviation values of all cost contribution access points as described above, the governance budget cost of the current agent can be accurately determined finally.

[0076] Furthermore, in a possible implementation manner, determining the optimal cycle required for the current agent in step S200 above includes: Step S205: Determine a number of local governance point pairs according to the governance costs of all cost contribution access points, where a local governance point pair includes two cost contribution access points.

[0077] Specifically, when performing voltage adjustment within a local area, first, the voltage rise and voltage drop between access points within this local area are utilized for complementarity to achieve active voltage environment governance at the local position without relying on external power resources. Therefore, for any cost contribution access point within the jurisdiction of the current agent , if the absolute value of the governance cost of this cost contribution access point is less than the average value of the governance costs of all cost contribution access points within the jurisdiction of the current agent , then this cost contribution access point is not governed. Among the remaining cost contribution access points, arbitrarily select one cost contribution access point with the same governance cost sign and ascending cost absolute value, and record its governance cost as . Then, from the governance costs with different governance cost signs and not forming local governance access point pairs, select the governance cost closest to the absolute value| |of the governance cost . Record the two cost contribution access points corresponding to the governance costs , as a group of local governance access point pairs. In another possible implementation manner, the governance costs of two groups with the same governance cost sign among the remaining cost contribution access points can also be used as the left endpoint and the right endpoint respectively, and the negative correlation mapping result of the absolute value of the difference between the governance costs of each left endpoint and each right endpoint (such as using the opposite number of the absolute value of the difference as the exponent of the exponential function to achieve negative correlation mapping) is used as the matching value. Based on this matching value, use a matching algorithm such as the KM (Kuhn - Munkres) matching algorithm to perform one - to - one matching on the left endpoint and the right endpoint, and record the two cost contribution access points corresponding to the left endpoint and the right endpoint in each obtained one - to - one matching pair as a group of local governance access point pairs.

[0078] Step S206: Determine the sum of the governance costs of all different cost - contributing access points included in all local governance point pairs as the total governance cost, and determine the ceiling result of the ratio of the total governance cost to the absolute value of the governance budget cost of the current agent as the optimal - seeking required period of the current agent.

[0079] Specifically, for the current agent in the jurisdiction, the sum of the governance costs of all cost - contributing access points selected as local governance point pairs is used as the numerator, and the absolute value of the governance budget cost of the current agent is used as the denominator. The ceiling value of the ratio is denoted as the optimal - seeking required period of the current agent . .

[0080] By determining several local governance point pairs and calculating the ratio of the sum of the governance costs of all different cost - contributing access points included in all local governance point pairs to the absolute value of the governance budget cost of the current agent, the optimal - seeking required period of the current agent can be accurately determined.

[0081] Further, in a possible implementation, determining the optimal - seeking planning period of the level where the current agent is located in step S200 includes: Step S207: Determine the centralized target interval of the optimal - seeking required periods of all agents in the level where the current agent is located.

[0082] Specifically, considering that the process of optimal - seeking requires multiple agents to complete optimal - seeking in a close time duration, and the too - slow optimal - seeking of a single agent will affect the stability of the power environment. Therefore, based on the optimal - seeking required periods of all agents in the level where the current agent is located, a high - heat range is statistically obtained to get the optimal - seeking planning period of the current agent in the current level. In a specific implementation, determine the 3 - sigma interval of the optimal - seeking required periods of all agents in the level where the current agent is located, and use this 3 - sigma interval as the centralized target interval.

[0083] Step S208: Determine the target optimal - seeking required periods within the centralized target interval among the optimal - seeking required periods of all agents in the level where the current agent is located, and determine the average value of all target optimal - seeking required periods as the optimal - seeking planning period of the level where the current agent is located.

[0084] Specifically, determine all the optimal - seeking required periods within the centralized target interval among the optimal - seeking required periods of all agents in the level where the current agent is located, and call these optimal - seeking required periods the target optimal - seeking required periods. Calculate the average value of these target optimal - seeking required periods as the optimal - seeking required period of the previous agent The optimization planning period of the current level where it is located .

[0085] By determining the centralized target interval of the periods required for optimization of all agents in the current level where the current agent is located, and by calculating the average value of the target periods required for optimization within this centralized target interval, the optimization planning period of the current level where the current agent is located can be accurately determined.

[0086] Furthermore, in a possible implementation, determining the collaborative governance evaluation parameters between the current agent and other agents in step S300 above includes:[[]] Step S301: Determine the sum of the governance budget costs of the current agent and each other agent as the total governance cost.

[0087] Step S302: Determine the ratio of the optimization planning periods of the current level where the current agent and each other agent are located as the ratio of the planning periods.

[0088] Step S303: Determine the collaborative governance evaluation parameters between the current agent and other agents based on the total governance cost and the ratio of the planning periods.

[0089] Specifically, in order to judge the collaborative governance evaluation between agents at the same level and between different levels, so as to facilitate the collaborative governance scheduling between the same level and different levels, based on the current agent and the sum of the governance costs and the ratio of the planning periods of each other agent, calculate the current agent and the collaborative governance evaluation parameters between each other agent through the following formula:[[]] ; In the formula:[[]] represents the collaborative governance evaluation parameters between the current agent and other agents ; represents the governance budget cost of the current agent ; represents the governance budget cost of other agents ; represents the optimization planning period of the current level where the current agent is located; represents the optimization planning period of the level where other agents are located.

[0090] By determining the sum of the governance costs between the current agent and each other agent and the ratio of the planning period, the collaborative governance evaluation parameter between the current agent and each other agent is determined, so as to achieve an accurate evaluation of the collaborative governance between the current agent and each other agent.

[0091] Further, in a possible implementation manner, adjusting the governance budget cost of the current agent in step S300 to obtain an adjusted governance budget cost includes: Step S304: Determine the mean and variance of the collaborative governance evaluation parameters between all agents in the layer where the current agent is located and other agents, and obtain the evaluation parameter mean and the evaluation parameter variance.

[0092] Step S305: Determine the dynamic threshold of the evaluation parameter of the current agent according to the evaluation parameter mean and the evaluation parameter variance.

[0093] Specifically, according to the current agent The mean and variance of the collaborative governance evaluation parameters between all agents in the layer where it is located and other agents are used to simultaneously determine the Dynamic threshold of the evaluation parameter of the current agent: ; In the formula: Represents the dynamic threshold of the evaluation parameter of the current agent ; Represents the evaluation parameter mean, that is, the average value of the collaborative governance evaluation parameters between all agents in the layer where the current agent Is located and other agents ; Represents the evaluation parameter variance, that is, the variance of the collaborative governance evaluation parameters between all agents in the layer where the current agent Is located and other agents ; Represents the adaptive coefficient. In a specific implementation manner, Is set.

[0094] Step S306: Determine the target other agent of the current agent, and the collaborative governance evaluation parameter between the current agent and the target other agent is less than the dynamic threshold of the evaluation parameter.

[0095] Specifically, judge the collaborative governance evaluation parameter between the current agent And other agents When the collaborative governance evaluation parameter is less than the dynamic threshold of the evaluation parameter , that is, when there is , then it is judged that the current agent When With other agents The collaboration efficiency is insufficient. At this time, the corresponding other agents are determined as the target other agents of the current agent . Thus, several target other agents of the current agent can be determined.

[0096] Step S307: Determine the cumulative value of the collaborative governance evaluation parameters between the current agent and all target other agents as the cumulative collaborative governance evaluation parameter.

[0097] Step S308: Determine the accumulated value of the governance budget costs of all target other agents of the current agent as the cumulative governance budget cost, and determine the governance budget cost adjustment coefficient according to the ratio of the cumulative collaborative governance evaluation parameter to the cumulative governance budget cost.

[0098] Step S309: Determine the product of the governance budget cost of the current agent and the governance budget cost adjustment coefficient as the adjusted governance budget cost of the current agent.

[0099] According to the collaborative governance evaluation parameters between the current agent and all target other agents, and the governance budget costs of all target other agents of the current agent , calculate the adjusted governance budget cost of the current agent through the following formula: ; In the formula: represents the adjusted governance budget cost of the current agent ; represents the governance budget cost of the current agent ; represents the collaborative governance evaluation parameter between the current agent and the target other agent ; represents the governance budget cost of the target other agent of the current agent ; represents the total number of target other agents of the current agent .

[0100] By determining the dynamic threshold of the evaluation parameters of the current agent as described above, the screening of other agents corresponding to the current agent is realized. Thus, based on the collaborative governance evaluation parameters between the current agent and all target other agents and the governance budget costs of all target other agents of the current agent, the punitive adjustment of the governance budget cost of the current agent is realized, and finally the accurate budget of the governance expenses of the current agent is achieved.

[0101] Further, in a possible implementation, determining the voltage scheduling scheme in the above step S400 includes: Input the current voltage and adjusted governance budget cost of the current agent, as well as the collaborative governance evaluation parameters between the current agent and all target other agents into the neural network, and the neural network outputs the target other agents that can be scheduled among all target other agents of the current agent and the voltage values that need to be scheduled.

[0102] Specifically, by pre-training the neural network, the neural network can specifically be a Recurrent Neural Network (RNN), and the current voltage and adjusted governance budget cost of the current agent are input into the pre-trained neural network, as well as the collaborative governance evaluation parameters between the current agent and each target other agent . The neural network outputs the target other agents that can be scheduled among all target other agents of the current agent and the voltage values that need to be scheduled.

[0103] Among them, during the training process of the neural network, a large amount of historical data on voltage regulation in the distribution area can be used to obtain the real-time voltage of different agents when performing voltage regulation on different agents. At the same time, in the same way as obtaining the adjusted governance budget cost of the current agent and the collaborative governance evaluation parameters between the current agent and each target other agent as described above, the adjusted governance budget cost of different agents and the collaborative governance evaluation parameters between different agents and all target other agents can be determined, and the target other agents that can be scheduled among all target other agents of different agents and the voltage values that need to be scheduled are obtained as the label values when performing voltage regulation on different agents, so as to obtain a training data set. The neural network is trained using this training data set to obtain a trained neural network. Since the specific training process of the neural network belongs to the prior art, it will not be elaborated here.

[0104] By pre-training the neural network as described above, learning the characteristics of voltage regulation of the current agent through the neural network, and inputting the current voltage and adjusted governance budget cost of the current agent, as well as the collaborative governance evaluation parameters between the current agent and all target other agents into the neural network, an accurate voltage scheduling scheme can be finally obtained.

[0105] ​​Based on the same inventive concept, an embodiment of the present invention further provides a substation area voltage active governance system based on a multi-agent self-optimizing regulation strategy, as Figure 3 shown. The system includes: a memory 301, a processor 302, and computer program code 303 stored in the memory 301 and running on the processor 302. When the processor 302 executes the computer program code 303, the system can execute any one of the substation area voltage active governance methods based on the multi-agent self-optimizing regulation strategy introduced above.

[0106] An embodiment of the present invention can divide the functions of the system according to the above method examples. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0107] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, the computer is enabled to execute any one of the substation area voltage active governance methods based on the multi-agent self-optimizing regulation strategy introduced above.

[0108] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer is enabled to execute any one of the substation area voltage active governance methods based on the multi-agent self-optimizing regulation strategy introduced above.

[0109] It should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for active voltage management in a transformer substation based on a multi-agent self-optimization control strategy, characterized in that: The method comprises: If the current intelligent body meets the conditions for starting regulation and control, the cost contribution access point and the governance cost of the cost contribution access point among the access points are determined according to the different types of electrical parameters of the access points within the jurisdiction of the current intelligent body; According to the governance cost of the cost contribution access point, the governance budget cost of the current intelligent body is determined, and according to the governance cost and the governance budget cost, the optimization cycle required for the current intelligent body is determined, and then according to the optimization cycle required for all intelligent bodies in the level where the current intelligent body is located, the optimization planning cycle of the level where the current intelligent body is located is determined; According to the governance budget costs and optimal planning cycles of the current intelligent agent and other intelligent agents, the collaborative governance evaluation parameters between the current intelligent agent and other intelligent agents are determined, and according to the collaborative governance evaluation parameters and the governance budget costs of other intelligent agents, the governance budget cost of the current intelligent agent is adjusted to obtain the adjusted governance budget cost; Determine the voltage dispatching plan based on the current intelligent body voltage, adjustment of governance budget cost and collaborative governance evaluation parameters.

2. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 1 is characterized in that: Determine the cost contribution of each access point, including: According to the different types of electrical parameters of each access point within the current intelligent agent's jurisdiction, the system state vector of each access point is constructed; Determine a state transfer matrix according to the system state vector, wherein the dimension of the state transfer matrix is ​​determined according to the type of the electrical parameter, and each element in the state transfer matrix corresponds to two types of the electrical parameter; Determining abnormal fluctuation elements in the state transfer matrix according to the distribution of elements in the state transfer matrix; Marking the type of the electrical parameter of each access point according to the abnormal fluctuation element to obtain the number of sub-marks of each type of the electrical parameter of each access point; An accumulated value of all sub-marking times of each access point is determined as the marking time of each access point, and an access point with a marking time greater than 0 is determined as a cost contribution access point.

3. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 2 is characterized in that: Determining the abnormal fluctuation elements in the state transfer matrix includes: Obtaining a histogram corresponding to all elements in the state transfer matrix; Determine the height sequence corresponding to the height values ​​of each peak column in the histogram, and determine the first-order difference sequence of the height sequence; Determine two target peak cylinders corresponding to the maximum difference value in the first-order difference sequence, determine the average value of all elements contained in each target peak cylinder as the element mean, and determine the maximum element mean of the two element means; The peak column corresponding to the maximum element mean in the histogram and all elements included in the peak column where the maximum element in the state transfer matrix is ​​located are determined as abnormal fluctuation elements in the state transfer matrix.

4. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 2 is characterized in that: Determine governance costs at the cost contribution access point, including: Determine the difference between the real-time voltage of the cost contribution access point and the a priori adaptation voltage as a voltage adjustment target; Determine the range value of the number of sub-marks of each type of electrical parameters of the cost contribution access point; The ratio of the number of times the cost contribution access point is marked to the extreme value is determined, and the product of the ratio and the voltage adjustment target is determined as the governance cost of the cost contribution access point.

5. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 1 is characterized in that: Determine the governance budget cost of the current agent, including: Determine the superposition value of the governance costs of all cost contributing access points as the access point cost loss; Determine the standard deviation of the governance costs of all cost contribution access points as the governance cost standard deviation; Determine the difference between the governance cost of each cost contribution access point and the cost loss of the access point as the governance cost deviation value of each access point; The governance budget cost of the current intelligent entity is determined based on the access point cost loss and the standard deviation of the governance cost, combined with the governance cost deviation values ​​of all cost-contributing access points.

6. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 1 is characterized in that: Determine the period required for the current agent to reach optimality, including: According to the governance costs of all cost contribution access points, a number of local governance point pairs are determined, where the local governance point pairs include two cost contribution access points; Determine the cumulative value of the governance costs of all local governance points for all access points with different cost contributions as the sum of the governance costs, and determine the rounded-up result of the ratio of the sum of the governance costs to the absolute value of the governance budget cost of the current intelligent body as the period required for the current intelligent body to optimize.

7. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 1 is characterized in that: Determine the optimal planning cycle for the current agent level, including: Determine the central target interval of the optimization cycle required for all agents in the current agent's level; Determine the target optimization period in the concentrated target interval among the optimization periods of all agents in the level where the current agent is located, and determine the average value of all target optimization periods as the optimization planning period of the level where the current agent is located.

8. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 1 is characterized in that: Determine the collaborative governance evaluation parameters between the current agent and other agents, including: Determine the sum of the governance costs as the sum of the governance budget costs of the current agent and each other agent; Determine the ratio of the optimal planning period of the current agent and each other agent in the same level as the planning period ratio; According to the sum of the governance costs and the ratio of the planning cycles, the collaborative governance evaluation parameters between the current intelligent agent and other intelligent agents are determined.

9. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 1 is characterized in that: Adjust the governance budget cost of the current intelligent entity to obtain the adjusted governance budget cost, including: Determine the average value and variance of the collaborative governance evaluation parameters between all agents in the level where the current agent is located and other agents, and obtain the evaluation parameter mean and evaluation parameter variance; Determine the dynamic threshold of the evaluation parameter of the current agent according to the mean value and variance of the evaluation parameter; Determine the target other intelligent agents of the current intelligent agent, and the collaborative governance evaluation parameter between the current intelligent agent and the target other intelligent agents is less than the dynamic threshold of the evaluation parameter; Determine the cumulative value of the collaborative governance evaluation parameter between the current intelligent agent and all other target intelligent agents as the cumulative collaborative governance evaluation parameter; Determine the cumulative value of the governance budget costs of all other target agents of the current agent as the cumulative governance budget cost, and determine the governance budget cost adjustment coefficient based on the ratio of the cumulative collaborative governance evaluation parameter to the cumulative governance budget cost; Determine the product of the current agent's governance budget cost and the governance budget cost adjustment coefficient as the current agent's adjusted governance budget cost.

10. The method for active voltage management in a substation based on a multi-agent self-optimization control strategy according to claim 9, characterized in that: Determine the voltage dispatch plan, including: The current voltage and adjustment governance budget cost of the current intelligent agent, as well as the collaborative governance evaluation parameters between the current intelligent agent and all other target intelligent agents are input into the neural network, and the neural network outputs the target other intelligent agents that can be scheduled among all other target intelligent agents of the current intelligent agent and the voltage values ​​that need to be scheduled.

Images