Intelligent Control Method and Device for Energy Storage Inverters Based on Multi-Objective Coordination

Abstract

The present invention relates to an intelligent control method and device for an energy storage converter based on multi-objective coordination. In this method, the central communication node conducts the communication of the state evaluation coefficient. The data volume of the state evaluation coefficient is small. According to the state evaluation coefficient, the communication priorities of each coordinated converter are updated in a timely manner. Based on the communication priorities of each coordinated converter, the state request information sent by the target converter is determined, so that the target converter does not need to completely obtain the coordinated state information of all coordinated converters, reducing the communication pressure on the central communication node, enabling multiple energy storage converters to communicate simultaneously, avoiding network congestion, and thus improving the accuracy of the intelligent control of the energy storage converter.

Description

Technical Field

[0001] The present invention is applicable to the field of converter control technology, and particularly relates to an intelligent control method and device for an energy storage converter based on multi-objective coordination. Background Art

[0002] In a distributed energy storage system, there are several energy storage units. The control of the energy storage units usually formulates corresponding control strategies according to the instructions from the power grid dispatching system and the state information of the energy storage system itself, based on the operation requirements and target priorities of the system.

[0003] Existing methods usually adopt centralized control or distributed control methods for intelligent control of energy storage converters. In centralized control, a central controller collects the state information of all energy storage units, calculates the power distribution value of each energy storage unit according to the selected power distribution strategy, and then sends the instructions to each energy storage unit. The advantage of this method is that it can achieve global optimal power distribution, but it has high requirements for the computing power, reliability, and communication of the central controller. In the distributed control method, each energy storage unit has its own controller, and they exchange information through a communication network. Each controller determines the power distribution of its own energy storage unit according to local information and the information exchanged with associated units according to a certain distributed algorithm. The advantage of this method is high reliability and flexibility. Even if the controller of a certain energy storage unit fails, other energy storage units can still continue to work, but it may take a long time to reach the optimal distribution state.

[0004] In order to ensure the reliability of intelligent control of distributed energy storage systems, a distributed control method can be adopted. However, if a ring topology communication method is used for distributed control, when there are faults in nodes or links, it may cause the communication of the entire ring to malfunction, and the reliability is still low. If a mesh topology communication method is used for distributed control, complex communication lines need to be constructed, and the cost is high. Therefore, considering both cost and reliability, a star topology communication method can be selected. Through the central node, the central node can be a virtual coordination node, and the controllers of other energy storage units communicate with this central node. However, different from centralized control, the central node can be only used for communication without determining and issuing control instructions, greatly reducing the situation of central node failure.

[0005] However, the star topology communication method will face communication network congestion caused by insufficient transmission bandwidth of the central node, which will further increase the information transmission delay, making the state information received by the power distribution controller outdated, thereby making inaccurate power distribution decisions and reducing the accuracy of intelligent control of the energy storage converter. Therefore, how to improve the accuracy of intelligent control of the energy storage converter has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, an embodiment of the present invention provides an intelligent control method and device for an energy storage converter based on multi-objective coordination to solve the problem.

[0007] In a first aspect, an intelligent control method for an energy storage converter based on multi-objective coordination is provided. The method includes:

[0008] When the current time point is the i-th first preset time point, obtain the local state information of the target converter, where i is a positive integer;

[0009] According to the local state information corresponding to the target converter from the (i - m)-th first preset time point to the i-th first preset time point and the trained state prediction model, determine the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point, where m is a positive integer and m < i;

[0010] Send the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point to the n cooperative converters corresponding to the target converter through the central communication node, where n is a positive integer;

[0011] Receive the second state evaluation coefficients respectively corresponding to the n cooperative converters at the i-th first preset time point;

[0012] According to the received second state evaluation coefficients of the n cooperative converters at the i-th first preset time point, determine the communication priorities respectively corresponding to the n cooperative converters at the i-th first preset time point;

[0013] According to the communication priorities respectively corresponding to the n cooperative converters at the i-th first preset time point, determine the state request information to be sent to the n cooperative converters respectively at the (i + 1)-th first preset time point;

[0014] When the current time point is the (i + 1)-th first preset time point, send the corresponding state request information to the n cooperative converters through the central communication node;

[0015] Receive the cooperative state information of the n cooperative converters at the (i + 1)-th first preset time point;

[0016] When receiving the control instruction for the target converter at the second preset time point, determine the first preset time point closest to the second preset time point as the reference time point;

[0017] According to the cooperative state information respectively corresponding to the n cooperative converters at the reference time point and the local state information of the target converter at the reference time point, determine the state control quantity of the target converter at the second preset time point.

[0018] In a second aspect, there is provided an intelligent control device for an energy storage converter based on multi-objective coordination, and the device includes:

[0019] A state acquisition module, configured to acquire the local state information of a target converter when the current time point is the i-th first preset time point, where i is a positive integer;

[0020] A state evaluation module, configured to determine a first state evaluation coefficient corresponding to the target converter at the i-th first preset time point according to the local state information corresponding to the target converter at the (i - m)-th to the i-th first preset time points respectively and a trained state prediction model, where m is a positive integer and m is less than i;

[0021] A first communication module, configured to send the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point to n coordinated converters corresponding to the target converter respectively through a central communication node, where n is a positive integer;

[0022] A second communication module, configured to receive second state evaluation coefficients respectively corresponding to the n coordinated converters at the i-th first preset time point;

[0023] A priority determination module, configured to determine the communication priorities respectively corresponding to the n coordinated converters at the i-th first preset time point according to the received second state evaluation coefficients at the i-th first preset time point;

[0024] A state request module, configured to determine state request information to be sent to the n coordinated converters respectively at the (i + 1)-th first preset time point according to the communication priorities respectively corresponding to the n coordinated converters at the i-th first preset time point;

[0025] A third communication module, configured to send corresponding state request information to the n coordinated converters through the central communication node when the current time point is the (i + 1)-th first preset time point;

[0026] A fourth communication module, configured to receive the coordinated state information of the n coordinated converters at the (i + 1)-th first preset time point;

[0027] A time point determination module, configured to determine the first preset time point closest to the second preset time point as a reference time point when receiving a control instruction for the target converter at the second preset time point;

[0028] A state control module, configured to determine a state control quantity corresponding to the target converter at the second preset time point according to the coordinated state information respectively corresponding to the n coordinated converters at the reference time point and the local state information of the target converter at the reference time point.

[0029] The beneficial effects of the present invention compared with the prior art are as follows:

[0030] By communicating the state evaluation coefficient through the central communication node, the data volume of the state evaluation coefficient is small. The communication priorities of each coordinated converter are updated in a timely manner according to the state evaluation coefficient. According to the communication priorities of each coordinated converter, the status request information sent by the target converter is determined, so that the target converter does not need to completely obtain the coordinated status information of all coordinated converters, reducing the communication pressure on the central communication node, enabling multiple energy storage converters to communicate simultaneously, avoiding network congestion, and thus improving the accuracy of the intelligent control of the energy storage converter. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 It is a schematic diagram of an application environment of a method for intelligent control of an energy storage converter based on multi-objective coordination provided in Embodiment 1 of the present invention;

[0033] Figure 2 It is a schematic flowchart of a method for intelligent control of an energy storage converter based on multi-objective coordination provided in Embodiment 1 of the present invention;

[0034] Figure 3 It is a schematic structural diagram of an intelligent control device for an energy storage converter based on multi-objective coordination provided in Embodiment 2 of the present invention;

[0035] Figure 4 It is a schematic structural diagram of a computer device for a method for intelligent control of an energy storage converter based on multi-objective coordination provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0037] It should be understood that when used in the specification of the present invention and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0038] It should also be understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0039] As used in the specification of the present invention and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0040] In addition, in the description of the specification of the present invention and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0041] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present invention means that a specific feature, structure or characteristic described in connection with that embodiment is included in one or more embodiments of the present invention. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments" etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0042] It should be understood that the magnitude of the sequence numbers of the steps in the following embodiments does not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0043] In order to illustrate the technical solution of the present invention, the following specific embodiments are used for illustration.

[0044] An intelligent control method for an energy storage converter based on multi-objective coordination provided in the first embodiment of the present invention can be applied in such as Figure 1In the application environment, it is specifically applied to the controller of the target converter. Among them, the target converter communicates with its corresponding controller, and the controllers can communicate through the central communication node. Among them, the controller includes, but is not limited to, terminal devices with computing functions such as palmtop computers, desktop computers, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, cloud terminal devices, and personal digital assistants (PDAs).

[0045] See Figure 2 , which is a schematic flowchart of an intelligent control method for an energy storage converter based on multi-objective coordination provided in the first embodiment of the present invention. The above-mentioned intelligent control of the energy storage converter can be applied to Figure 1 the controller of the target converter in. The controller can communicate with the target converter to obtain local status information. The controller has an operation function, and a trained state prediction model is stored in the controller. As Figure 2 shown, the intelligent control method of the energy storage converter may include the following steps:

[0046] Step S201, when the current time point is the i-th first preset time point, obtain the local status information of the target converter.

[0047] Among them, i is a positive integer. In this embodiment, a star topology communication method is adopted, which includes a central communication node. The central communication node is only used to support the communication between energy storage converters. Under the star topology, there are several energy storage converters. Any energy storage converter can be used as the target converter. Correspondingly, other energy storage converters are used as the cooperative converters of the target converter.

[0048] The first preset time point may refer to a preset status information collection time point. In this embodiment, the time interval between adjacent first preset time points is the same.

[0049] The local status information may include information such as voltage and SOC. In this embodiment, the local status information may refer to SOC. It should be noted that this embodiment is described with the controller of the target converter as the object. When the current time point is the i-th first preset time point, the controller of the cooperative converter also obtains the local status information of the cooperative converter at the same time.

[0050] Step S202, according to the local status information corresponding to the target converter from the (i - m)-th first preset time point to the i-th first preset time point and the trained state prediction model, determine the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point.

[0051] Wherein, m is a positive integer and m is less than i. The state prediction model can adopt a recurrent neural network model, a long short-term memory network model, a time-domain convolutional model, etc. The first state evaluation coefficient can be used to characterize the predictability of the local state information of the target converter.

[0052] Optionally, according to the local state information corresponding to the target converter at the (i - m)-th to the i-th first preset time points and the trained state prediction model, determining the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point includes:

[0053] Initialize the identification parameter k = i - m;

[0054] Input the local state information corresponding to the k-th to the (k + q)-th first preset time points into the trained state prediction model to obtain the predicted state information corresponding to the (k + q + 1)-th first preset time point, where q is a preset prediction step.

[0055] Compare the predicted state information and the local state information corresponding to the (k + q + 1)-th first preset time point to obtain the comparison result corresponding to the (k + q + 1)-th first preset time point.

[0056] Update k = k + 1, and return to execute the step of inputting the local state information corresponding to the k-th to the (k + q)-th first preset time points into the trained state prediction model until k + q + 1 = i, to obtain m - q comparison results.

[0057] Determine the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point according to the m - q comparison results.

[0058] Wherein, the identification parameter can be used to identify the first preset time point corresponding to the first local state information input into the trained state prediction model, q is a preset prediction step, and q is less than m.

[0059] The comparison result can characterize the difference between the measured state information and the local state information at the corresponding first preset time point.

[0060] Specifically, in this embodiment, a time-domain convolutional model is used as the state prediction model, and the local state information of the next first preset time point is predicted through q local state information that conforms to the time sequence.

[0061] Comparing the predicted state information and the local state information corresponding to the (k + q + 1)-th first preset time point may refer to calculating the Euclidean distance between the predicted state information and the local state information corresponding to the (k + q + 1)-th first preset time point, and the Euclidean distance calculation result is the corresponding comparison result.

[0062] According to the m - q comparison results, determine the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point, which may refer to calculating the mean value based on the m - q comparison results and determining the mean value calculation result as the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point.

[0063] In this embodiment, the first state evaluation coefficient is quantified by the prediction accuracy of the trained state prediction model, thereby characterizing the predictability of the local state information and providing a basis for determining the subsequent state request information.

[0064] Step S203: Send the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point to the n cooperative converters corresponding to the target converter through the central communication node respectively.

[0065] Wherein, n is a positive integer. Since each energy storage converter can be used as the target converter, correspondingly, the target converter in this embodiment can be used as the cooperative converter of other energy storage converters. Therefore, it is necessary to send the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point to the n cooperative converters corresponding to the target converter through the central communication node respectively.

[0066] Step S204: Receive the second state evaluation coefficients respectively corresponding to the n cooperative converters at the i-th first preset time point.

[0067] Wherein, the second state evaluation coefficient can characterize the predictability of the local state information of the corresponding cooperative converter.

[0068] Specifically, the second state evaluation coefficient can be determined by the controller corresponding to the cooperative converter according to the local state information respectively corresponding to the cooperative converter from the (i - m)-th first preset time point to the i-th first preset time point and the trained state prediction model.

[0069] Step S205: Determine the communication priorities respectively corresponding to the n cooperative converters at the i-th first preset time point according to the received n second state evaluation coefficients at the i-th first preset time point.

[0070] Wherein, the communication priority can be used to determine whether to request state information from the corresponding cooperative converter.

[0071] Optionally, initialize the communication priority of each cooperative converter to a first preset value;

[0072] Determine the upper coefficient value and the lower coefficient value according to the received n second state evaluation coefficients at the i-th first preset time point, and form a coefficient interval from the upper coefficient value and the lower coefficient value;

[0073] Determine a temporary segmentation threshold based on the second state evaluation coefficients at a number of the i-th first preset time points within the coefficient range, and mark the coefficient range as the first execution state;

[0074] Compare the second state evaluation coefficient corresponding to each cooperative converter at the i-th first preset time point with the temporary segmentation threshold. If the second state evaluation coefficient corresponding to any cooperative converter at the i-th first preset time point is greater than the temporary segmentation threshold, keep the communication priority of this cooperative converter unchanged; otherwise, update the communication priority of this cooperative converter by incrementing it by one.

[0075] When all coefficient ranges are in the first execution state, take all the temporary segmentation thresholds as intermediate values, form a number of coefficient ranges based on the coefficient upper limit value, the coefficient lower limit value, and all the intermediate values, and sequentially return to execute the step of determining the temporary segmentation threshold based on the second state evaluation coefficients at a number of the i-th first preset time points within the coefficient range until the maximum value in the communication priorities of all cooperative converters is the same as the preset priority upper limit, and obtain the communication priority corresponding to each cooperative converter.

[0076] Among them, the coefficient upper limit value is the maximum value among the second state evaluation coefficients at n i-th first preset time points, the coefficient lower limit value is the minimum value among the second state evaluation coefficients at n i-th first preset time points, use the coefficient upper limit value as the right boundary value and the coefficient lower limit value as the left boundary value to determine the coefficient range.

[0077] The coefficient range is initially in the second execution state. After determining the temporary segmentation threshold based on the coefficient range, mark the coefficient range as the first execution state.

[0078] Specifically, forming a number of coefficient ranges based on the coefficient upper limit value, the coefficient lower limit value, and all the intermediate values may mean that for any coefficient upper limit value, coefficient lower limit value, or intermediate value, select the coefficient upper limit value, coefficient lower limit value, or intermediate value closest to it to form a coefficient range. When there is only one coefficient range during the first segmentation and this coefficient range is in the first execution state, take the temporary segmentation threshold as the intermediate value, and two coefficient ranges can be formed based on the coefficient upper limit value, the coefficient lower limit value, and this intermediate value. According to these two coefficient ranges, sequentially return to execute the step of determining the temporary segmentation threshold based on the second state evaluation coefficients at a number of the i-th first preset time points within the coefficient range. At this time, it is necessary to wait until both coefficient ranges are in the first execution state before re-determining the coefficient range.

[0079] The preset priority upper limit may refer to the preset number of priority levels. The preset priority upper limit should be 2 to the power of a, where a is a positive integer. In this embodiment, a is set to 3, and correspondingly, the preset priority is set to 8.

[0080] Optionally, determining a temporary segmentation threshold according to the second state evaluation coefficients at a plurality of the i-th first preset time points within a coefficient range includes:

[0081] Determining a temporary segmentation threshold according to the second state evaluation coefficients at a plurality of the i-th first preset time points within a coefficient range by using the Otsu threshold method.

[0082] Among them, the Otsu threshold method is a method for finding the optimal threshold based on maximizing the between-class variance.

[0083] Step S206, determining the status request information to be sent to the n coordinated converters at the (i + 1)-th first preset time point according to the communication priorities corresponding to the n coordinated converters at the i-th first preset time point respectively.

[0084] Among them, the status request information can represent the content of the status information requested by the target converter from the coordinated converter.

[0085] Optionally, determining the status request information to be sent to the n coordinated converters at the (i + 1)-th first preset time point according to the communication priorities corresponding to the n coordinated converters at the i-th first preset time point respectively includes:

[0086] Determining a priority threshold according to the communication priorities corresponding to the n coordinated converters at the i-th first preset time point respectively;

[0087] For any one of the coordinated converters, if the communication priority of this coordinated converter is greater than the priority threshold, determining the first status request information to be sent to this coordinated converter at the (i + 1)-th first preset time point;

[0088] Otherwise, determining the second status request information to be sent to this coordinated converter at the (i + 1)-th first preset time point.

[0089] Among them, the priority threshold can be used to judge the content of the status request information to be sent to this coordinated converter at the (i + 1)-th first preset time point. The first status request information can indicate that the corresponding coordinated converter does not need to return the coordinated status information at the (i + 1)-th first preset time point, and the second status request information can indicate that the corresponding coordinated converter needs to return the coordinated status information at the (i + 1)-th first preset time point.

[0090] Optionally, for any one of the coordinated converters, when this coordinated converter receives the second status request information corresponding to the (i + 1)-th first preset time point, using the local status information of this coordinated converter at the (i + 1)-th first preset time point as the coordinated status information at the (i + 1)-th first preset time point and sending it to the target converter through the central communication node.

[0091] Specifically, half of the maximum communication priority can be used as the priority threshold. Implementers can choose other methods to determine the priority threshold according to the actual situation, such as quartiles, median, etc.

[0092] Step S207, when the current time point is the (i + 1)-th first preset time point, send corresponding status request information to n cooperative converters through the central communication node.

[0093] Step S208, receive the cooperative status information of n cooperative converters at the (i + 1)-th first preset time point.

[0094] Among them, when no control instruction for the target converter is received, the target converter selectively requests the cooperative status information of the cooperative converters according to the communication priority, thereby reducing the communication data volume, reducing the communication pressure on the central communication node, enabling multiple energy storage converters to communicate simultaneously, avoiding network congestion, and thus improving the accuracy of the intelligent control of the energy storage converter.

[0095] Specifically, for the cooperative converter that sends the first status request information at the (i + 1)-th first preset time point, the controller of the target converter predicts the cooperative status information at the (i + 1)-th first preset time point through several cooperative status information before the (i + 1)-th first preset time point, and uses the prediction result as the cooperative status information of the cooperative converter at the (i + 1)-th first preset time point.

[0096] Step S209, at the second preset time point when a control instruction for the target converter is received, determine the first preset time point closest to the second preset time point as the reference time point.

[0097] Among them, the control instruction can be used to instruct the target converter to make adjustments.

[0098] Step S210, determine the status control amount of the target converter at the second preset time point according to the cooperative status information corresponding to n cooperative converters at the reference time point and the local status information of the target converter at the reference time point.

[0099] Among them, the status control amount can refer to the adjustment amount of the target converter.

[0100] Optionally, determining the status control amount of the target converter at the second preset time point according to the cooperative status information corresponding to n cooperative converters at the reference time point and the local status information of the target converter at the reference time point includes:

[0101] According to the collaborative status information corresponding to n collaborative converters at the reference time point and the local status information of the target converter at the reference time point, a consistency algorithm is used to determine the status control quantity corresponding to the target converter at the second preset time point.

[0102] Among them, the consistency algorithm may refer to the target converter updating its own local status based on the difference between the collaborative status information of the collaborative converters and its own local status information. The greater the difference, the greater the update amplitude.

[0103] In this embodiment, the communication of the status evaluation coefficient is carried out through the central communication node. The data volume of the status evaluation coefficient is small. The communication priorities of each collaborative converter are updated in a timely manner according to the status evaluation coefficient. According to the communication priorities of each collaborative converter, the status request information sent by the target converter is determined, so that the target converter does not need to completely obtain the collaborative status information of all collaborative converters, reducing the communication pressure on the central communication node, enabling multiple energy storage converters to communicate simultaneously, avoiding network congestion, and thus improving the accuracy of the intelligent control of the energy storage converter.

[0104] Corresponding to the method in the above embodiment, Figure 3 FIG. shows a schematic structural diagram of an intelligent control device for an energy storage converter based on multi-objective coordination provided in the second embodiment of the present invention. The above intelligent control device for an energy storage converter is applied to the controller of the target converter. The controller can communicate with the target converter to obtain local status information. The controller has an operation function, and a trained status prediction model is stored in the controller. For the sake of convenience of description, only the parts related to the embodiments of the present invention are shown.

[0105] See Figure 3 , the intelligent control device for an energy storage converter includes:

[0106] A status acquisition module 301, configured to acquire the local status information of the target converter when the current time point is the i-th first preset time point, where i is a positive integer;

[0107] A status evaluation module 302, configured to determine the first status evaluation coefficient corresponding to the target converter at the i-th first preset time point according to the local status information corresponding to the target converter from the (i - m)-th first preset time point to the i-th first preset time point and the trained status prediction model, where m is a positive integer and m is less than i;

[0108] A first communication module 303, configured to send the first status evaluation coefficient corresponding to the target converter at the i-th first preset time point to the n collaborative converters corresponding to the target converter through the central communication node, where n is a positive integer;

[0109] The second communication module 304 is configured to receive the second state evaluation coefficients respectively corresponding to n cooperative converters at the i-th first preset time point;

[0110] The priority determination module 305 is configured to determine the communication priorities respectively corresponding to n cooperative converters at the i-th first preset time point according to the received n second state evaluation coefficients at the i-th first preset time point;

[0111] The state request module 306 is configured to determine the state request information to be sent to n cooperative converters respectively at the (i + 1)-th first preset time point according to the communication priorities respectively corresponding to n cooperative converters at the i-th first preset time point;

[0112] The third communication module 307 is configured to send the corresponding state request information to n cooperative converters through the central communication node when the current time point is the (i + 1)-th first preset time point;

[0113] The fourth communication module 308 is configured to receive the cooperative state information of n cooperative converters at the (i + 1)-th first preset time point;

[0114] The time point determination module 309 is configured to determine the first preset time point closest to the second preset time point as the reference time point when receiving the second preset time point of the control instruction for the target converter;

[0115] The state control module 310 is configured to determine the state control quantity corresponding to the target converter at the second preset time point according to the cooperative state information respectively corresponding to n cooperative converters at the reference time point and the local state information of the target converter at the reference time point.

[0116] Optionally, the above state evaluation module 302 includes:

[0117] The first initialization unit is configured to initialize the identification parameter k = i - m;

[0118] The state prediction unit is configured to input the local state information respectively corresponding to the k-th first preset time point to the (k + q)-th first preset time point into the trained state prediction model to obtain the predicted state information corresponding to the (k + q + 1)-th first preset time point, where q is the preset prediction step length;

[0119] The state comparison unit is configured to compare the predicted state information and the local state information respectively corresponding to the (k + q + 1)-th first preset time point to obtain the comparison result corresponding to the (k + q + 1)-th first preset time point;

[0120] The first iteration unit is used to update k = k + 1, and return to execute the step of inputting the local state information corresponding to the k-th to (k + q)-th first preset time points into the trained state prediction model until k + q + 1 = i, obtaining m - q comparison results;

[0121] The coefficient determination unit is used to determine the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point according to the m - q comparison results.

[0122] Optionally, the above-mentioned priority determination module 305 includes:

[0123] The second initialization unit is used to initialize the communication priority of each cooperating converter to a first preset value;

[0124] The interval determination unit is used to determine the coefficient upper limit value and the coefficient lower limit value according to the n second state evaluation coefficients at the i-th first preset time point received, and form a coefficient interval from the coefficient upper limit value and the coefficient lower limit value;

[0125] The splitting unit is used to determine a temporary splitting threshold according to several second state evaluation coefficients at the i-th first preset time point within the coefficient interval, and mark the coefficient interval as the first execution state;

[0126] The priority update unit is used to compare the second state evaluation coefficient corresponding to each cooperating converter at the i-th first preset time point with the temporary splitting threshold. If the second state evaluation coefficient corresponding to any cooperating converter at the i-th first preset time point is greater than the temporary splitting threshold, the communication priority of this cooperating converter remains unchanged; otherwise, the communication priority of this cooperating converter is updated to increase by one.

[0127] The second iteration unit is used to, when all coefficient intervals are in the first execution state, take all the temporary splitting thresholds as intermediate values, form several coefficient intervals according to the coefficient upper limit value, the coefficient lower limit value and all the intermediate values, and sequentially return to execute the step of determining the temporary splitting threshold according to several second state evaluation coefficients at the i-th first preset time point within the coefficient interval until the maximum value among the communication priorities of all cooperating converters is the same as the preset priority upper limit, obtaining the communication priority corresponding to each cooperating converter.

[0128] Optionally, the above-mentioned splitting unit includes:

[0129] The threshold splitting sub-unit is used to determine the temporary splitting threshold using the Otsu threshold method according to several second state evaluation coefficients at the i-th first preset time point within the coefficient interval.

[0130] Optionally, the above-mentioned state request module 306 includes:

[0131] A threshold determination unit, configured to determine a priority threshold according to the communication priorities respectively corresponding to n cooperative converters at the i-th first preset time point;

[0132] A first request unit, configured to, for any one of the cooperative converters, if the communication priority of the cooperative converter is greater than the priority threshold, determine first status request information to be sent to the cooperative converter at the (i + 1)-th first preset time point;

[0133] A second request unit, configured to, otherwise, send second status request information to the cooperative converter at the (i + 1)-th first preset time point.

[0134] Optionally, the above status request module 306 further includes:

[0135] For any one of the cooperative converters, when the cooperative converter receives the second status request information corresponding to the (i + 1)-th first preset time point, use the local status information of the cooperative converter at the (i + 1)-th first preset time point as the cooperative status information at the (i + 1)-th first preset time point and send it to the target converter through the central communication node.

[0136] Optionally, the above status control module 310 includes:

[0137] A control quantity determination unit, configured to determine a status control quantity corresponding to the target converter at the second preset time point by using a consensus algorithm according to the cooperative status information respectively corresponding to n cooperative converters at the reference time point and the local status information of the target converter at the reference time point.

[0138] It should be noted that for the information interaction, execution process, etc. among the above modules, units, and subunits, since they are based on the same concept as the method embodiment of the present invention, for their specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not described herein again.

[0139] Figure 4 This is a schematic structural diagram of a computer device for an intelligent control method of an energy storage converter based on multi-objective coordination provided in Embodiment III of the present invention. As Figure 4 shown, the computer device of this embodiment includes: a processor, a memory, a network interface, and a database connected through a system bus, where the processor is at least one ( Figure 4 only one is shown in the figure), and further includes a computer program stored in the memory and executable on at least one processor. When the processor executes the computer program, it implements the steps in any of the above embodiments of the intelligent control method of the energy storage converter based on multi-objective coordination.

[0140] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand,Figure 4 The examples of computer devices are merely illustrative and do not limit computer devices. A computer device may include more or fewer components than shown in the figure, or combine certain components, or have different components. For example, it may also include a network interface, a display screen, an input device, etc.

[0141] The so-called processor may be a CPU. This processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0142] The memory includes a readable storage medium, an internal memory, etc. Among them, the internal memory may be the memory of the computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be the hard disk of the computer device, or in other embodiments, it may also be an external storage device of the computer device. For example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may also include both the internal storage unit of the computer device and the external storage device. The memory is used to store the operating system, application programs, a boot loader, data, and other programs, such as the program code of a computer program. The memory may also be used to temporarily store data that has been output or will be output.

[0143] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction and do not limit the protection scope of the present invention. The specific working processes of the units and modules in the above-mentioned device can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned method embodiments of the present invention, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0144] To implement all or part of the processes in the above-mentioned method embodiments of the present invention, it can also be completed by a computer program product. When the computer program product runs on a computer device, it enables the computer device to execute and implement the steps in the above-mentioned method embodiments.

[0145] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0146] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0147] In the embodiments provided by the present invention, it should be understood that the disclosed device / computer equipment and method can be implemented in other ways. For example, the device / computer equipment embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0148] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0149] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; 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 make the essence of the corresponding technical solutions deviate from the spirit and 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. An intelligent control method for energy storage converters based on multi-objective coordination, characterized in that The method includes: When the current time point is the i-th first preset time point, obtaining the local status information of the target converter, where i is a positive integer; According to the local status information corresponding to the target converter from the (i - m)-th first preset time point to the i-th first preset time point respectively and the trained status prediction model, determining the first status evaluation coefficient corresponding to the target converter at the i-th first preset time point, where m is a positive integer and m < i; Sending the first status evaluation coefficient corresponding to the target converter at the i-th first preset time point to the n cooperative converters corresponding to the target converter respectively through the central communication node, where n is a positive integer; Receiving the second status evaluation coefficients corresponding to the n cooperative converters at the i-th first preset time point respectively; According to the received second status evaluation coefficients of the n cooperative converters at the i-th first preset time point, determining the communication priorities corresponding to the n cooperative converters at the i-th first preset time point respectively; According to the communication priorities corresponding to the n cooperative converters at the i-th first preset time point respectively, determining the status request information to be sent to the n cooperative converters respectively at the (i + 1)-th first preset time point; Wherein, the determining the status request information to be sent to the n cooperative converters respectively at the (i + 1)-th first preset time point according to the communication priorities corresponding to the n cooperative converters at the i-th first preset time point respectively includes: Determining a priority threshold according to the communication priorities corresponding to the n cooperative converters at the i-th first preset time point respectively; For any one of the cooperative converters, if the communication priority of this cooperative converter is greater than the priority threshold, determining the first status request information to be sent to this cooperative converter at the (i + 1)-th first preset time point; Otherwise, sending the second status request information to this cooperative converter at the (i + 1)-th first preset time point, where the first status request information indicates that the corresponding cooperative converter does not need to return the cooperative status information at the (i + 1)-th first preset time point, and the second status request information indicates that the corresponding cooperative converter needs to return the cooperative status information at the (i + 1)-th first preset time point; When the current time point is the (i + 1)-th first preset time point, sending the corresponding status request information to the n cooperative converters through the central communication node; For any one of the cooperative converters, if this cooperative converter receives the second status request information corresponding to the (i + 1)-th first preset time point, sending the local status information of this cooperative converter at the (i + 1)-th first preset time point to the target converter as the cooperative status information at the (i + 1)-th first preset time point through the central communication node; Receiving the cooperative status information of the n cooperative converters at the (i + 1)-th first preset time point; When the second preset time point for receiving the control instruction for the target converter is reached, determining the first preset time point closest to the second preset time point as the reference time point; Determine the state control quantity corresponding to the target converter at the second preset time point according to the collaborative state information corresponding to n collaborative converters at the reference time point and the local state information of the target converter at the reference time point.

2. The intelligent control method of the energy storage converter according to claim 1, wherein The determining of the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point according to the local state information corresponding to the target converter at the (i - m)-th to i-th first preset time points and the trained state prediction model includes: Initialize the identification parameter k = i - m; Input the local state information corresponding to the k-th to (k + q)-th first preset time points into the trained state prediction model to obtain the predicted state information corresponding to the (k + q + 1)-th first preset time point, where q is the preset prediction step; Compare the predicted state information and the local state information corresponding to the (k + q + 1)-th first preset time point to obtain the comparison result corresponding to the (k + q + 1)-th first preset time point; Update k = k + 1, and return to execute the step of inputting the local state information corresponding to the k-th to (k + q)-th first preset time points into the trained state prediction model until k + q + 1 = i, to obtain m - q comparison results; Determine the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point according to the m - q comparison results.

3. The intelligent control method of the energy storage converter according to claim 1, characterized in that The determining of the communication priorities corresponding to n collaborative converters at the i-th first preset time point according to the received second state evaluation coefficients at the i-th first preset time point includes: Initialize the communication priority of each collaborative converter to the first preset value; Determine the coefficient upper limit value and the coefficient lower limit value according to the received second state evaluation coefficients at the i-th first preset time point, and form a coefficient interval from the coefficient upper limit value and the coefficient lower limit value; Determine a temporary segmentation threshold according to several second state evaluation coefficients at the i-th first preset time point within the coefficient interval, and mark the coefficient interval as the first execution state; Compare the second state evaluation coefficient corresponding to each collaborative converter at the i-th first preset time point with the temporary segmentation threshold. If the second state evaluation coefficient corresponding to any collaborative converter at the i-th first preset time point is greater than the temporary segmentation threshold, keep the communication priority of this collaborative converter unchanged. Otherwise, update the communication priority of this collaborative converter to increase by one; When all coefficient intervals are in the first execution state, take all the temporary segmentation thresholds as intermediate values, form several coefficient intervals according to the coefficient upper limit value, the coefficient lower limit value and all the intermediate values, and sequentially return to execute the step of determining the temporary segmentation threshold according to several second state evaluation coefficients at the i-th first preset time point within the coefficient interval until the maximum value among the communication priorities of all collaborative converters is the same as the preset priority upper limit, to obtain the communication priority corresponding to each collaborative converter.

4. The intelligent control method of the energy storage converter according to claim 3, wherein Determining a temporary segmentation threshold according to a plurality of second state evaluation coefficients at the i-th first preset time point within the coefficient interval includes: Using the Otsu threshold method to determine a temporary segmentation threshold according to a plurality of second state evaluation coefficients at the i-th first preset time point within the coefficient interval.

5. The intelligent control method of the energy storage converter according to claim 1, characterized in that Determining a state control quantity corresponding to the target converter at the second preset time point according to the collaborative state information respectively corresponding to n collaborative converters at the reference time point and the local state information of the target converter at the reference time point includes: Using a consensus algorithm to determine a state control quantity corresponding to the target converter at the second preset time point according to the collaborative state information respectively corresponding to n collaborative converters at the reference time point and the local state information of the target converter at the reference time point.

6. An intelligent control device for an energy storage converter based on multi-objective coordination, characterized in that, The device includes: A state acquisition module, configured to acquire local state information of a target converter when the current time point is the i-th first preset time point, where i is a positive integer; A state evaluation module, configured to determine a first state evaluation coefficient corresponding to the target converter at the i-th first preset time point according to the local state information respectively corresponding to the target converter from the (i - m)-th first preset time point to the i-th first preset time point and a trained state prediction model, where m is a positive integer and m is less than i; A first communication module, configured to send the first state evaluation coefficient corresponding to the target converter at the i-th first preset time point to n collaborative converters corresponding to the target converter respectively through a central communication node, where n is a positive integer; A second communication module, configured to receive second state evaluation coefficients respectively corresponding to n collaborative converters at the i-th first preset time point; A priority determination module, configured to determine communication priorities respectively corresponding to n collaborative converters at the i-th first preset time point according to the received second state evaluation coefficients at the i-th first preset time point; A state request module, configured to determine state request information to be sent to n collaborative converters respectively at the (i + 1)-th first preset time point according to the communication priorities respectively corresponding to n collaborative converters at the i-th first preset time point; Among them, determining state request information to be sent to n collaborative converters respectively at the (i + 1)-th first preset time point according to the communication priorities respectively corresponding to n collaborative converters at the i-th first preset time point includes: Determining a priority threshold according to the communication priorities respectively corresponding to n collaborative converters at the i-th first preset time point; For any collaborative converter, if the communication priority of this collaborative converter is greater than the priority threshold, then determine first state request information to be sent to this collaborative converter at the (i + 1)-th first preset time point; Otherwise, the second status request information sent to the cooperative converter at the (i + 1)-th first preset time point, the first status request information indicates that the corresponding cooperative converter does not need to return the cooperative status information at the (i + 1)-th first preset time point, and the second status request information indicates that the corresponding cooperative converter needs to return the cooperative status information at the (i + 1)-th first preset time point; The third communication module is configured to, when the current time point is the (i + 1)-th first preset time point, send corresponding status request information to n cooperative converters through the central communication node; For any cooperative converter, if the cooperative converter receives the second status request information corresponding to the (i + 1)-th first preset time point, the local status information of the cooperative converter at the (i + 1)-th first preset time point is used as the cooperative status information at the (i + 1)-th first preset time point and sent to the target converter through the central communication node; The fourth communication module is configured to receive the cooperative status information of n cooperative converters at the (i + 1)-th first preset time point; The time point determination module is configured to, when receiving the second preset time point of the control instruction for the target converter, determine the first preset time point closest to the second preset time point as the reference time point; The status control module is configured to determine the status control amount of the target converter corresponding to the second preset time point according to the cooperative status information corresponding to n cooperative converters at the reference time point and the local status information of the target converter at the reference time point.

Images