Thermal power generating unit time-phased dynamic adjustment method, system, equipment and medium

Abstract

The invention belongs to the technical field of network source coordination, and discloses a time-phased dynamic adjustment method, system, equipment and medium for a thermal power generating unit, and the method comprises the steps: collecting the power data of a power grid and the thermal power generating unit in an operation state according to a preset sampling interval, and calculating the theoretical output adjustment rate of the thermal power generating unit in an automatic power generation control normal mode; the theoretical output rate of the thermal power generating unit in the automatic power generation control normal mode is clustered, the mean value and the diameter of all categories are calculated, and the minimum clustering loss is calculated according to the diameter of each category and the required clustering number; and obtaining an optimal clustering scheme of the theoretical output regulation rate of the thermal power generating unit in the automatic power generation control normal mode based on recursive solution of an ordered clustering algorithm. The method is beneficial to timely adjusting the starting number of the on-line automatic power generation control normal mode units in different time periods, ensures that the units do not need to be started and stopped frequently, and ensures supply-demand balance and frequency stability of a power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of network source coordination, and in particular to a method, system, equipment and medium for dynamically adjusting time periods of thermal power generation units. Background Art

[0002] With the rapid growth of installed capacity of renewable energy, the power structure of the power grid will gradually change from being dominated by controllable thermal power to being dominated by renewable energy with strong uncertainty and weak controllability, which greatly increases the difficulty of balancing the supply and demand of the power grid. The thermal power units put into automatic generation control (AGC) can adjust the active power according to the needs of the power grid. Among them, the automatic generation control normal mode (AGC-R) units can automatically track the unit output instructions formed by the power deviation of the power grid issued by the dispatcher in real time, and adjust the unit's own output in time, which plays an important role in ensuring the balance of supply and demand of the power grid.

[0003] As traditional thermal power units gradually transform from traditional main power sources to regulating power sources, the rapid change of the output of thermal power units in automatic generation control normal mode has become the norm. For each thermal power unit in automatic generation control normal mode, its power adjustment rate is usually a fixed value and the start and stop of the unit usually takes a long time. Therefore, in the daily operation of the power grid, it is necessary to ensure that there are enough automatic generation control normal mode units as backup to face the possible power deviation of the power grid; in addition, if there are too many backup automatic generation control normal mode units, it will also cause a large waste of fuel. Therefore, it is necessary to study the regulation capacity of the automatic generation control normal mode units required by the power grid in each period.

[0004] Therefore, how to provide a method, system, equipment and medium for dynamic adjustment of thermal power units in time periods is a problem that needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present invention provide a method, system, device and medium for dynamically adjusting time periods of a thermal power unit to solve the above-mentioned technical problems existing in the prior art.

[0006] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended to be a general review, nor is it intended to identify key / important components or to delineate the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0007] According to a first aspect of an embodiment of the present invention, a method for dynamically adjusting time periods of thermal power generation components is provided.

[0008] In one embodiment, the method for dynamically adjusting the time periods of thermal power generation components includes:

[0009] According to the preset sampling interval, collect the power data of the power grid and thermal power units in operation, and calculate the theoretical output regulation rate of the thermal power units in the normal mode of automatic power generation control;

[0010] Cluster the theoretical output rates of thermal power units in normal mode of automatic generation control, calculate the means and diameters of all categories, and calculate the minimum clustering loss based on the diameter of each category and the required number of clusters;

[0011] Based on the recursive solution of the ordered clustering algorithm, the optimal clustering scheme for the theoretical output regulation rate of the thermal power units in normal mode of automatic generation control is obtained.

[0012] In one embodiment, collecting the power data of the power grid and the thermal power unit in operation according to the preset sampling interval and calculating the theoretical output regulation rate of the thermal power unit in the normal mode of automatic power generation control includes:

[0013] Set the sampling interval and total data duration to regularly collect power data of the power grid and thermal power units, including the power load value forecast of the entire network, the output value forecast of all-caliber new energy sources, the output value plan of the tie line, and the output plan data of the direct-controlled public thermal power units in the normal mode of non-automatic power generation control;

[0014] The theoretical output of the thermal power units in the automatic generation control normal mode required by the power grid is obtained by using the forecast of the power load value of the entire network minus the forecast of the output value of the full-caliber new energy, the output value plan of the tie line, and the output plan data of the direct-adjusted public thermal power units in the non-automatic generation control normal mode. The difference between the adjacent output values ​​is divided by the sampling interval to calculate the theoretical output regulation rate of the thermal power units in the automatic generation control normal mode.

[0015] Abnormal values ​​in the theoretical output regulation rate are eliminated, and the absolute value of the theoretical output regulation rate is taken to obtain a set of theoretical output regulation rates arranged in chronological order.

[0016] For the obtained regulation rate set, the maximum value at the same time of each day is used as the theoretical output rate value at that time, and the theoretical output rate of the thermal power unit in normal mode of automatic power generation control with a length of one day is obtained for subsequent clustering.

[0017] In one embodiment, clustering the theoretical output rate of the thermal power unit in the normal mode of automatic power generation control, calculating the mean and diameter of all categories, and calculating the minimum clustering loss according to the diameter of each category and the required number of clusters includes:

[0018] Set the class mean formula and class diameter formula, traverse and calculate the mean and diameter of each class, and use the class diameter to represent the difference of samples in each class;

[0019] Based on the ordered clustering algorithm, combined with the diameter of the class, the loss function is set, the loss value of the clustering result is calculated, and the minimum clustering loss value is found.

[0020] In one embodiment, for a value including a rate {v i ,v i+1 ,...,v j} category V, the class mean formula is:

[0021]

[0022] In the formula, is the mean value of V in this class; v t is the tth theoretical output adjustment rate; i and j are the starting index and ending index of the class;

[0023] The class diameter formula is:

[0024]

[0025] Where D(i,j) is the diameter of this type of V; is the mean of the class; v t is the tth theoretical output adjustment rate.

[0026] In one embodiment, the loss function is calculated as follows:

[0027]

[0028] Where L[b(n,k)] is the clustering loss value; b(n,k) is the value of dividing the theoretical output regulation rate set of length n into k classes V1, V2, ..., V k A clustering method, each of which is abbreviated as V1 = {i1, i1+1, ..., i2-1}, V2 = {i2, i2+1, ..., i3-1}, ..., V k ={i k ,i k +1,...,n}; D(i t ,i t+1 -1) is the diameter of the t-th class.

[0029] In one embodiment, the recursive solution based on the ordered clustering algorithm to obtain the optimal clustering scheme for the theoretical output regulation rate of the thermal power unit in the normal mode of automatic power generation control includes:

[0030] A recursive formula is set based on an ordered clustering algorithm, and an optimal clustering method for dividing a theoretical output regulation rate set of length n into k segments is found through recursive solution of the recursive formula, so as to obtain an optimal clustering scheme for the theoretical output regulation rate.

[0031] In one embodiment, the recursive formula is:

[0032]

[0033] Where L[P(n,k)] is the clustering loss of the optimal clustering scheme; n is the length of the theoretical output rate set; k is the number of subclass segments; L[P(n,2)] is the clustering loss of the optimal clustering method that divides the rate set of length n into two classes; D(j,n) is the diameter of the last class after clustering; j is the index of the starting rate value of the last class after clustering.

[0034] According to a second aspect of an embodiment of the present invention, a system for dynamically adjusting time periods of thermal power plant components is provided.

[0035] In one embodiment, the thermal power generation component time period dynamic adjustment system comprises:

[0036] The data acquisition module is used to collect the power data of the power grid and the thermal power units in operation according to the preset sampling interval, and calculate the theoretical output regulation rate of the thermal power units in the normal mode of automatic power generation control;

[0037] The calculation and storage module clusters the theoretical output rate of the thermal power units in the normal mode of automatic power generation control, calculates the mean and diameter of all categories, and calculates the minimum clustering loss based on the diameter of each category and the required number of clusters;

[0038] The clustering optimization module is used to obtain the optimal clustering solution for the theoretical output regulation rate of the thermal power units in the normal mode of automatic power generation control based on the recursive solution of the ordered clustering algorithm.

[0039] In one embodiment, the data acquisition module includes: a power monitoring module, a rate calculation module and a processing and merging module, wherein:

[0040] The power monitoring module is used to set the sampling interval and the total data duration, and regularly collect power data of the power grid and thermal power units. The power data includes the prediction of the power load value of the whole network, the prediction of the output value of new energy sources with full caliber, the output value plan of the tie line, and the output plan data of the direct-adjusted public thermal power units in the normal mode of non-automatic power generation control;

[0041] The rate calculation module is used to obtain the theoretical output of the thermal power unit in the automatic generation control normal mode required by the power grid by using the power load value forecast of the entire network minus the full-caliber new energy output value forecast, the tie line output value plan, and the output plan data of the direct-adjusted public thermal power unit in the non-automatic generation control normal mode, and calculate the theoretical output adjustment rate of the thermal power unit in the automatic generation control normal mode by dividing the difference between adjacent output values ​​by the sampling interval;

[0042] The processing and merging module is used to eliminate abnormal values ​​in the theoretical output regulation rate and take the absolute value of the theoretical output regulation rate to obtain a set of theoretical output regulation rates arranged in chronological order; for the obtained regulation rate set, the maximum value at the same time of each day is used as the theoretical output rate value at that time, to obtain the theoretical output rate of the thermal power unit in the normal mode of automatic power generation control with a length of one day, and perform subsequent clustering.

[0043] In one embodiment, the calculation and storage module includes: a mean diameter calculation module and a loss calculation module, wherein:

[0044] The mean diameter calculation module is used to set the class mean formula and the class diameter formula, traverse and calculate the mean and class diameter of each class, and use the class diameter to represent the difference of samples in each class after all clustering;

[0045] The loss calculation module is used to set a loss function based on an ordered clustering algorithm in combination with the diameter of a class, calculate the loss value of the clustering result, and find the minimum clustering loss value.

[0046] In one embodiment, for a value including a rate {v i ,v i+1 ,...,v j} category V, the class mean formula is:

[0047]

[0048] In the formula, is the mean value of V in this class; v t is the tth theoretical output adjustment rate; i and j are the starting index and ending index of the class;

[0049] The class diameter formula is:

[0050]

[0051] Where D(i,j) is the diameter of this type of V; is the mean of the class; v t is the tth theoretical output adjustment rate.

[0052] In one embodiment, the loss function is calculated as follows:

[0053]

[0054] Where L[b(n,k)] is the clustering loss value; b(n,k) is the value of dividing the theoretical output regulation rate set of length n into k classes V1, V2, ..., V kA clustering method, each of which is abbreviated as V1 = {i1, i1+1, ..., i2-1}, V2 = {i2, i2+1, ..., i3-1}, ..., V k ={i k ,i k +1,...,n}; D(i t ,i t+1 -1) is the diameter of the t-th class.

[0055] In one embodiment, the cluster optimization module includes:

[0056] A recursive formula is set based on an ordered clustering algorithm, and an optimal clustering method for dividing a theoretical output regulation rate set of length n into k segments is found through recursive solution of the recursive formula, so as to obtain an optimal clustering scheme for the theoretical output regulation rate.

[0057] In one embodiment, the recursive formula is:

[0058]

[0059] Where L[P(n,k)] is the clustering loss of the optimal clustering scheme; n is the length of the theoretical output rate set; k is the number of subclass segments; L[P(n,2)] is the clustering loss of the optimal clustering method that divides the rate set of length n into two classes; D(j,n) is the diameter of the last class after clustering; j is the index of the starting rate value of the last class after clustering.

[0060] According to a third aspect of an embodiment of the present invention, a computer device is provided.

[0061] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0062] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.

[0063] In one embodiment, the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0064] The technical solution provided by the embodiment of the present invention may include the following beneficial effects: the present invention obtains the regulation rate that the automatic power generation control normal mode unit should theoretically have during the day by processing the conventional data of the power grid; adopts an ordered clustering method to cluster the obtained regulation rate that the automatic power generation control normal mode unit should theoretically have during the day, and divides the whole day into the required number of time periods, and the required regulation rate of the AGC-R mode unit at each moment in each time period is similar; it is conducive to timely adjusting the number of automatic power generation control normal mode units on the network in different time periods, ensuring that the units do not need to be frequently started and stopped, and ensuring the supply and demand balance and frequency stability of the power grid; in addition, the present invention uses the theoretical output regulation rate of the automatic power generation control normal mode thermal power unit to cluster similar change rate points, so as to realize the effective evaluation of the adjustment capability that the automatic power generation control normal mode unit of the power grid should have on a daily scale, and provide technical support for the dispatching personnel to timely adjust the spare capacity of the AGC-R mode unit at the current moment.

[0065] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0067] Figure 1 is a flow chart showing a method for dynamically adjusting a thermal power plant component time period according to an exemplary embodiment;

[0068] Figure 2 is a structural schematic diagram of a system for dynamically adjusting time periods of a thermal power plant component according to an exemplary embodiment;

[0069] Figure 3 is a schematic diagram of the structure of a computer device according to an exemplary embodiment;

[0070] Figure 4 is a block diagram of an ordered clustering algorithm according to an exemplary embodiment;

[0071] Figure 5 is a real data curve of a power grid shown according to an exemplary embodiment;

[0072] Figure 6 It is a result diagram showing that the adjustment capabilities of the automatic generation control normal mode units required by the power grid are clustered into 6 categories according to an exemplary embodiment. DETAILED DESCRIPTION

[0073] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0074] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0075] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0076] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0077] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0078] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0079] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0080] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0081] Figure 1 An embodiment of a method for dynamically adjusting time periods of a thermal power plant component according to the present invention is shown.

[0082] In this optional embodiment, the method for dynamically adjusting the time periods of the thermal power generation components includes:

[0083] Step S101, collecting power data of the power grid and the thermal power unit in operation according to a preset sampling interval, and calculating the theoretical output regulation rate of the thermal power unit in the normal mode of automatic power generation control;

[0084] Step S103, clustering the theoretical output rates of the thermal power units in the normal mode of automatic power generation control, calculating the means and diameters of all categories, and calculating the minimum clustering loss according to the diameter of each category and the required number of clusters;

[0085] Step S105: Based on the recursive solution of the ordered clustering algorithm, an optimal clustering scheme for the theoretical output regulation rate of the thermal power generating units in the normal mode of automatic power generation control is obtained.

[0086] In this optional embodiment, when collecting the power data of the power grid and the thermal power units in operation according to the preset sampling interval and calculating the theoretical output regulation rate of the thermal power units in the normal mode of automatic power generation control, the sampling interval and the total data duration can be set to regularly collect the power data of the power grid and the thermal power units, and the power data includes the power load value forecast of the whole network, the output value forecast of the full-caliber new energy, the output value plan of the interconnection line, and the output plan data of the direct-adjusted public thermal power units in the normal mode of non-automatic power generation control; the power load value forecast of the whole network minus the output value forecast of the full-caliber new energy, the output value plan of the interconnection line, and the output plan data of the direct-adjusted public thermal power units in the normal mode of non-automatic power generation control is used. The output plan data of public thermal power units are adjusted to obtain the theoretical output of the thermal power units in normal mode of automatic power generation control required by the power grid, and the difference between adjacent output values ​​is divided by the sampling interval to calculate the theoretical output regulation rate of the thermal power units in normal mode of automatic power generation control; the abnormal values ​​in the theoretical output regulation rate are eliminated, and the absolute value of the theoretical output regulation rate is taken to obtain a set of theoretical output regulation rates arranged in chronological order; for the obtained regulation rate set, the maximum value at the same time of each day is used as the theoretical output rate value at that time, to obtain the theoretical output rate of the thermal power units in normal mode of automatic power generation control for one day, and perform subsequent clustering.

[0087] In this optional embodiment, the theoretical output rate of the thermal power unit in normal mode of automatic power generation control is clustered, the means and diameters of all categories are calculated, and the minimum clustering loss is calculated based on the diameter of each category and the required number of clusters; when calculating the minimum clustering loss, the class mean formula and the class diameter formula can be set, the mean of each category and the diameter of the category are traversed and calculated, and the diameter of the category is used to represent the difference of samples in each category; based on the ordered clustering algorithm, the theoretical output rate of the thermal power unit in normal mode of automatic power generation control is clustered, based on the ordered clustering algorithm, combined with the diameter of the category, the loss function is set, the loss value of the clustering result is calculated, and the minimum clustering loss value is found.

[0088] In this alternative embodiment, for the inclusion of rate values ​​{v i ,v i+1 ,...,v j} category V, the class mean formula is:

[0089]

[0090] In the formula, is the mean value of V in this class; v t is the tth theoretical output adjustment rate; i and j are the starting index and ending index of the class;

[0091] The class diameter formula is:

[0092]

[0093] Where D(i,j) is the diameter of this type of V; is the mean of the class; v t is the tth theoretical output adjustment rate.

[0094] In this optional embodiment, the calculation formula of the loss function is:

[0095]

[0096] Where L[b(n,k)] is the clustering loss value; b(n,k) is the value of dividing the theoretical output regulation rate set of length n into k classes V1, V2, ..., V k A clustering method, each of which is abbreviated as V1 = {i1, i1+1, ..., i2-1}, V2 = {i2, i2+1, ..., i3-1}, ..., V k ={i k ,i k +1,...,n}; D(i t ,i t+1 -1) is the diameter of the tth class.

[0097] In this optional embodiment, when the recursive solution based on the ordered clustering algorithm is used to obtain the optimal clustering scheme for the theoretical output regulation rate of the normal mode thermal power unit with automatic power generation control, a recursive formula can be set based on the ordered clustering algorithm, and the optimal clustering method for dividing the theoretical output regulation rate set of length n into k segments is found through the recursive solution of the recursive formula to obtain the optimal clustering scheme for the theoretical output regulation rate.

[0098] In this optional embodiment, the recursive formula is:

[0099]

[0100] Where L[P(n,k)] is the clustering loss of the optimal clustering scheme; n is the length of the theoretical output rate set; k is the number of subclass segments; L[P(n,2)] is the clustering loss of the optimal clustering method that divides the rate set of length n into two classes; D(j,n) is the diameter of the last class after clustering; j is the index of the starting rate value of the last class after clustering.

[0101] Figure 2 An embodiment of a system for dynamically adjusting time periods of thermal power plant components according to the present invention is shown.

[0102] In this optional embodiment, the thermal power generation component time period dynamic adjustment system includes:

[0103] The data acquisition module 201 is used to collect the power data of the power grid and the thermal power unit in operation according to the preset sampling interval, and calculate the theoretical output regulation rate of the thermal power unit in the normal mode of automatic power generation control;

[0104] The calculation and storage module 203 clusters the theoretical output rate of the thermal power unit in the normal mode of automatic power generation control, calculates the mean and diameter of all categories, and calculates the minimum clustering loss according to the diameter of each category and the required number of clusters;

[0105] The clustering optimization module 205 is used to obtain the optimal clustering solution of the theoretical output regulation rate of the thermal power unit in the normal mode of automatic power generation control based on the recursive solution of the ordered clustering algorithm.

[0106] In this optional embodiment, the data acquisition module 201 includes: a power monitoring module (not shown in the figure), a rate calculation module (not shown in the figure) and a processing and merging module (not shown in the figure), wherein the power monitoring module is used to set the sampling interval and the total data duration, and regularly collect power data of the power grid and thermal power units, wherein the power data includes the power load value forecast of the entire network, the full-caliber new energy output value forecast, the interconnection line output value plan, and the output plan data of the direct-adjusted public thermal power units in the normal mode of non-automatic power generation control; the rate calculation module is used to use the power load value forecast of the entire network minus the full-caliber new energy output value forecast, the interconnection line output value plan, and the non-automatic power generation control normal mode. The output plan data of the direct-controlled public thermal power units in normal mode are used to obtain the theoretical output of the thermal power units in normal mode under automatic power generation control required by the power grid, and the difference between adjacent output values ​​is divided by the sampling interval to calculate the theoretical output regulation rate of the thermal power units in normal mode under automatic power generation control; the processing and merging module is used to eliminate abnormal values ​​in the theoretical output regulation rate, and take the absolute value of the theoretical output regulation rate to obtain a set of theoretical output regulation rates arranged in chronological order; for the obtained regulation rate set, the maximum value at the same time of each day is used as the theoretical output rate value at that time, to obtain the theoretical output rate of the thermal power units in normal mode under automatic power generation control for one day, and perform subsequent clustering.

[0107] In this optional embodiment, the calculation and storage module 203 includes: a mean diameter calculation module (not shown in the figure) and a loss calculation module (not shown in the figure), wherein the mean diameter calculation module is used to set the class mean formula and the class diameter formula, traverse and calculate the mean and class diameter of each class, and use the class diameter to represent the difference between samples in each class; the loss calculation module is used to set the loss function based on the ordered clustering algorithm, combined with the class diameter, calculate the loss value of the clustering result, and find the minimum clustering loss value.

[0108] In this alternative embodiment, for the inclusion of rate values ​​{v i ,vi+1 ,...,v j} category V, the class mean formula is:

[0109]

[0110] In the formula, is the mean value of V in this class; v t is the tth theoretical output adjustment rate; i and j are the starting index and ending index of the class;

[0111] The class diameter formula is:

[0112]

[0113] Where D(i,j) is the diameter of this type of V; is the mean of the class; v t is the tth theoretical output adjustment rate.

[0114] In this optional embodiment, the calculation formula of the loss function is:

[0115]

[0116] Where L[b(n,k)] is the clustering loss value; b(n,k) is the value of dividing the theoretical output regulation rate set of length n into k classes V1, V2, ..., V k A clustering method, each of which is abbreviated as V1 = {i1, i1+1, ..., i2-1}, V2 = {i2, i2+1, ..., i3-1}, ..., V k ={i k ,i k +1,...,n}; D(i t ,i t+1 -1) is the diameter of the tth class.

[0117] In this optional embodiment, the clustering optimization module 205 includes: setting a recursive formula based on an ordered clustering algorithm, and finding the optimal clustering method for dividing the theoretical output regulation rate set of length n into k segments through recursive solution of the recursive formula, so as to obtain the optimal clustering scheme for the theoretical output regulation rate.

[0118] In this optional embodiment, the recursive formula is:

[0119]

[0120] Where L[P(n,k)] is the clustering loss of the optimal clustering scheme; n is the length of the theoretical output rate set; k is the number of subclass segments; L[P(n,2)] is the clustering loss of the optimal clustering method that divides the rate set of length n into two classes; D(j,n) is the diameter of the last class after clustering; j is the index of the starting rate value of the last class after clustering.

[0121] A method for dynamically adjusting the time periods of a thermal power plant component constructed by the present invention is described in detail below in conjunction with specific embodiments and drawings.

[0122] Taking the actual data of a province as an example, the data of AGC-R mode thermal power units (automatic generation control normal mode thermal power units) are clustered in an orderly manner, such as Figure 4 The specific process is as follows.

[0123] 1. According to the data measurement points included in the dispatching system, the forecast of the power load value of the whole network, the forecast of the output value of new energy sources with full caliber, the output value plan of the interconnection line and the output plan data of the direct-controlled public thermal power units in non-AGC-R mode are obtained. The sampling interval of the data is 15 minutes, and the total data duration is m days.

[0124] The data is preprocessed, and the whole province's electricity load value is used to deduct the full-caliber new energy output value, the actual output value of the interconnection line, and the actual output value data of the non-AGC-R mode direct-adjusted public thermal power units to calculate the theoretical output that the AGC-R mode thermal power units required by the power grid should have. The difference between adjacent output values ​​is divided by the time interval to calculate the theoretical output regulation rate of the AGC-R mode thermal power units, and the regulation rate unit is MW / min. The regulation rate value has positive and negative values, and the active power of the AGC-R mode units has increases and decreases. Considering that the rate setting of the AGC-R mode units when increasing or decreasing power is the same, in order to intuitively measure the level of unit rate change, the calculated theoretical output change rate is taken as the absolute value, and the maximum value at the same time of m days is used as the theoretical output rate value at that time, and the theoretical output rate of the thermal power unit in the normal mode of automatic power generation control with a length of one day is obtained. The final output change rate data is recorded as {v1,v2,...,v 96}.

[0125] The objective of the present invention is to find a suitable clustering method so that the change rate data in each cluster are as similar as possible, and the number of units started in AGC-R mode can be effectively adjusted while avoiding frequent start and stop of the units.

[0126] 2. For the point containing the change rate {v i ,v i+1 ,...,v j},j>i category V, denoted as V={i,i+1,...,j}, the mean of this category is use Calculate the diameter of the class.

[0127] Calculate the diameters of all possible clusters and store them in Table 1.

[0128] Table 1. Various diameters D(i,j)

[0129]

[0130] Among them, D(i,j) measures the difference between samples in the class. If i=j, then D(i,j)=0; if i>j, then D(i,j)=+∞. The smaller D(i,j), the smaller the difference between samples {v i ,v i+1 ,...,v j If D(i,j)=0, it means that all samples are the same.

[0131] In practical applications, since the start and stop of thermal power units takes a long time, the clustered classes with too short length will cause the thermal power units before and after this time period to quickly adjust the start and stop status of the units, which increases the difficulty of practical applications. Therefore, in the calculation process of {D(i,j)}, the constant l can be selected as the threshold. If ji < l, then define {D(i,j)} = +∞, which can effectively prevent the shorter class from being selected. For example, l = 8 is selected, that is, the length of each class is at least 2h. At this time, the diameter table D(i,j) of each class is shown in Table 2:

[0132] Table 2. Various diameters D(i,j)

[0133]

[0134] In addition, to simplify the application, other restrictions can be added, such as requiring that the start time and end time of each segment after clustering must not appear in the 15th minute or the 45th minute. Different restrictions only require that the corresponding diameter D(i,j) value in Table 2 be set to +∞.

[0135] 3. According to the calculated diameters of each category {D(i,j)}, calculate the minimum clustering loss L[P(l,k)] and store the results in Table 3.

[0136] The theoretical output adjustment rate {v1,v2,...,v n} is divided into k categories V1, V2, …, V k , where V1 = {i1, i1+1, ..., i2-1}, V2 = {i2, i2+1, ..., i3-1}, ..., Vk ={i k ,i k +1,...,n}(1=i1≤i2≤i3≤...≤i k ≤n=i k+1 +1), and this division method is recorded as b(n,k).

[0137] Define the loss function of the clustering method The smaller L[b(n,k)] is, the closer the rate values ​​in each class are after the division, and the more reasonable the clustering is. Therefore, the goal of the present invention is to find an optimal division method P(n,k) whose clustering loss L[P(n,k)] is the smallest among all the loss values ​​L[b(n,k)].

[0138] When looking for the optimal clustering method to divide the theoretical output regulation rate of length n into k segments, we should first clarify the optimal division method to divide the regulation rate value of length j-1 into k-1 categories. By recursively solving the recursive formula, we can obtain the optimal clustering P(n,k).

[0139] First, the value of L[P(l,k)] when k=2 is calculated based on {D(i,j)}. For example, when l=3:

[0140]

[0141] By comparing the small values ​​of D(1,1)+D(2,3) and D(1,2)+D(3,3), we can determine the minimum classification loss L[P(3,2)] for clustering the rate values ​​of length l=3 into k=2 classes, and construct an index table Table 4. The j value at this time is defined as j 3,2 And record it in the relevant position. Using the same method, after determining the values ​​of L[P(4,2)], L[P(5,2)], ..., L[P(n,2)], the corresponding index value j 4,2 、j 5,2 ,……,j n,2 Record in the corresponding position of Table 4.

[0142] After obtaining L[P(l,2)], the value of L[P(l,3)] is calculated based on the obtained L[P(l,2)]. For example, when l=4:

[0143]

[0144] By comparing the smaller values ​​of L[P(2,2)]+D(3,4) and L[P(3,2)]+D(4,4), we can determine the minimum classification loss L[P(4,3)] for clustering the rate values ​​of length l=4 into k=3 classes. Similarly, we can calculate the values ​​of L[P(5,3)], L[P(6,3)], ..., L[P(n,3)] and their corresponding index values ​​j 5,3 、j 6,3 ,……,j n,3 Recorded in Table 4.

[0145] According to the calculated L[P(l,3)] value, the values ​​of L[P(l,4)], ..., L[P(l,l-1)] can be calculated in sequence. When l = k, L[P(l,k)] = 0. The calculated minimum clustering loss L[P(l,k)] and its corresponding j lk The values ​​are stored separately in the table.

[0146] The minimum clustering loss L[P(l,k)] is shown in Table 3.

[0147] Table 3. Minimum clustering loss L[P(l,k)]

[0148]

[0149] Get the index j of the minimum clustering loss L[P(l,k)] lk As shown in Table 4.

[0150] Table 4. Index j that achieves the minimum clustering loss L[P(l,k)] lk

[0151]

[0152] After constructing the above table, the optimal partitioning method can be found through recursion. Specifically, if the required number of clusters is k, the partition point j should be found according to the index table. 96,k , j 96,k That is to obtain the minimum clustering loss L[P(n,k)]=L[P(j k -1,k-1)]+D(j k ,n) in the value j k , i.e. j k =j 96,k , thus determining the kth class G k ={j k ,j k +1,...,n}.

[0153] Next, find the point j k-1 , according to the point j determined in the previous step k , because k-1Requirements:

[0154] L[P(j k-1 ,k-1)]=L[P(j k-1 -1,k-2)]+D(j k-1 ,j k -1)

[0155] Get the k-1th class G k-1 ={j k-1 ,j k-1 +1,...,j k -1}. Through this method, the optimal clusters G1, G2, ..., G k .

[0156] Figure 5 This is the real data curve of the power grid. The curve is obtained by deducting the full-caliber new energy output forecast, the interconnection line output plan and the output plan data of the direct-controlled public thermal power units in non-AGC-R mode from the power load forecast of the entire network for several days, and then selecting the maximum value at each moment and taking the absolute value.

[0157] Figure 6 The figure shows the result of clustering the AGC-R mode unit adjustment capacity required by the power grid into 6 categories using the method proposed in the present invention. The duration of each category is at least 2 hours, and the unit adjustment capacity required at each moment in each category is relatively similar. In practical applications, the maximum value in each category can be selected as the adjustment rate that the AGC-R mode unit started in the time period should have according to the clustering results. This ensures that the AGC-R mode unit has sufficient spare capacity, and facilitates scheduling to adjust the number of AGC-R mode units in a timely manner, thereby ensuring the supply and demand balance and frequency stability of the power grid.

[0158] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0159] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present invention, and does not constitute a limitation on the computer device to which the scheme of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or some components of the method, or have a different arrangement of components.

[0160] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0161] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0162] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0163] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for dynamically adjusting the time periods of thermal power generation components, characterized in that: include: According to the preset sampling interval, collect the power data of the power grid and thermal power units in operation, and calculate the theoretical output regulation rate of the thermal power units in the normal mode of automatic power generation control; Cluster the theoretical output rates of thermal power units in normal mode of automatic generation control, calculate the means and diameters of all categories, and calculate the minimum clustering loss based on the diameter of each category and the required number of clusters; Based on the recursive solution of the ordered clustering algorithm, the optimal clustering scheme for the theoretical output regulation rate of the thermal power units in normal mode of automatic generation control is obtained.

2. The method for dynamically adjusting the time periods of thermal power generation components according to claim 1 is characterized in that: The method of collecting power data of the power grid and the thermal power generation unit in operation according to the preset sampling interval and calculating the theoretical output regulation rate of the thermal power generation unit in the normal mode of automatic power generation control includes: Set the sampling interval and total data duration to regularly collect power data of the power grid and thermal power units, including the power load value forecast of the entire network, the output value forecast of all-caliber new energy sources, the output value plan of the tie line, and the output plan data of the direct-controlled public thermal power units in the normal mode of non-automatic power generation control; The theoretical output of the thermal power units in the automatic generation control normal mode required by the power grid is obtained by using the forecast of the power load value of the entire network minus the forecast of the output value of the full-caliber new energy, the output value plan of the tie line, and the output plan data of the direct-adjusted public thermal power units in the non-automatic generation control normal mode. The difference between the adjacent output values ​​is divided by the sampling interval to calculate the theoretical output regulation rate of the thermal power units in the automatic generation control normal mode. Eliminate abnormal values ​​in the theoretical output regulation rate, and take the absolute value of the theoretical output regulation rate to obtain a set of theoretical output regulation rates arranged in chronological order; For the obtained regulation rate set, the maximum value at the same time of each day is used as the theoretical output rate value at that time, and the theoretical output rate of the thermal power unit in normal mode of automatic power generation control with a length of one day is obtained for subsequent clustering.

3. The method for dynamically adjusting the time periods of thermal power generation components according to claim 1, characterized in that: The theoretical output rate of thermal power units in normal mode of automatic generation control is clustered, the mean and diameter of all categories are calculated, and the minimum clustering loss is calculated based on the diameter of each category and the required number of clusters, including: Set the class mean formula and class diameter formula, traverse and calculate the mean and diameter of each class, and use the class diameter to represent the difference of samples in each class after all clustering; Based on the ordered clustering algorithm, combined with the diameter of the class, the loss function is set, the loss value of the clustering result is calculated, and the minimum clustering loss value is found.

4. The method for dynamically adjusting the time periods of thermal power generation components according to claim 3 is characterized in that: For the value containing the rate {v i ,v i+1 ,...,v j } category V (abbreviated as V = {i, i + 1, ..., j}), the class mean formula is: In the formula, is the mean value of V in this class; v t is the tth theoretical output adjustment rate; i and j are the starting index and ending index of the class; The class diameter formula is: Where D(i,j) is the diameter of this type of V; is the mean of the class; v t is the tth theoretical output adjustment rate.

5. The method for dynamically adjusting the time periods of thermal power generation components according to claim 3 is characterized in that: The calculation formula of the loss function is: Where L[b(n,k)] is the clustering loss value; b(n,k) is the value of dividing the theoretical output regulation rate set of length n into k classes V1, V2, ..., V k A clustering method, each of which is abbreviated as V1 = {i1, i1+1, ..., i2-1}, V2 = {i2, i2+1, ..., i3-1}, ..., V k ={i k ,i k +1,...,n}; D(i t ,i t+1 -1) is the diameter of the tth class.

6. The method for dynamically adjusting the time periods of thermal power generation components according to claim 1, characterized in that: The recursive solution based on the ordered clustering algorithm to obtain the optimal clustering scheme for the theoretical output regulation rate of the thermal power unit in the normal mode of automatic power generation control includes: A recursive formula is set based on an ordered clustering algorithm, and an optimal clustering method for dividing a theoretical output regulation rate set of length n into k segments is found through recursive solution of the recursive formula, so as to obtain an optimal clustering scheme for the theoretical output regulation rate.

7. The method for dynamically adjusting the time periods of thermal power generation components according to claim 6, characterized in that: The recursive formula is: Where L[P(n,k)] is the clustering loss of the optimal clustering scheme; n is the length of the theoretical output rate set; k is the number of segments; L[P(n,2)] is the clustering loss of the optimal clustering method that divides the rate set of length n into two categories; D(j,n) is the diameter of the last class after clustering; j is the index of the starting rate value of the last class after clustering.

8. A system for dynamically adjusting the time periods of thermal power generation components, characterized in that: include: The data acquisition module is used to collect the power data of the power grid and the thermal power units in operation according to the preset sampling interval, and calculate the theoretical output regulation rate of the thermal power units in the normal mode of automatic power generation control; The calculation and storage module clusters the theoretical output rate of the thermal power units in the normal mode of automatic power generation control, calculates the mean and diameter of all categories, and calculates the minimum clustering loss based on the diameter of each category and the required number of clusters; The clustering optimization module is used to obtain the optimal clustering solution for the theoretical output regulation rate of the thermal power units in the normal mode of automatic power generation control based on the recursive solution of the ordered clustering algorithm.

9. The system for dynamically adjusting the time periods of thermal power generation components according to claim 8, characterized in that: The data acquisition module includes: a power monitoring module, a rate calculation module and a processing and merging module, wherein: The power monitoring module is used to set the sampling interval and the total data duration, and regularly collect power data of the power grid and thermal power units. The power data includes the prediction of the power load value of the whole network, the prediction of the output value of new energy sources with full caliber, the output value plan of the tie line, and the output plan data of the direct-adjusted public thermal power units in the normal mode of non-automatic power generation control; The rate calculation module is used to obtain the theoretical output of the thermal power unit in the automatic generation control normal mode required by the power grid by using the power load value forecast of the entire network minus the full-caliber new energy output value forecast, the tie line output value plan, and the output plan data of the direct-adjusted public thermal power unit in the non-automatic generation control normal mode, and calculate the theoretical output adjustment rate of the thermal power unit in the automatic generation control normal mode by dividing the difference between adjacent output values ​​by the sampling interval; The processing and merging module is used to eliminate abnormal values ​​in the theoretical output regulation rate and take the absolute value of the theoretical output regulation rate to obtain a set of theoretical output regulation rates arranged in chronological order; for the obtained regulation rate set, the maximum value at the same time of each day is used as the theoretical output rate value at that time, to obtain the theoretical output rate of the thermal power unit in the normal mode of automatic power generation control with a length of one day, and perform subsequent clustering.

10. The system for dynamically adjusting the time periods of thermal power generation components according to claim 8, characterized in that: The calculation and storage module includes: a mean diameter calculation module and a loss calculation module, wherein: The mean diameter calculation module is used to set the class mean formula and the class diameter formula, traverse and calculate the mean and class diameter of each class, and use the class diameter to represent the difference of samples in each class; The loss calculation module sets a loss function based on an ordered clustering algorithm and the diameter of a class, calculates the loss value of the clustering result, and searches for the minimum clustering loss value.

11. The system for dynamically adjusting the time periods of thermal power generation components according to claim 10, characterized in that: For the value containing the rate {v i ,v i+1 ,...,v j } category V, the class mean formula is: In the formula, is the mean value of V in this class; v t is the tth theoretical output adjustment rate; i and j are the starting index and ending index of the class; The class diameter formula is: Where D(i,j) is the diameter of this type of V; is the mean of the class; v t is the tth theoretical output adjustment rate.

12. The system for dynamically adjusting the time periods of thermal power generation components according to claim 10, characterized in that: The calculation formula of the loss function is: Where L[b(n,k)] is the clustering loss value; b(n,k) is the value of dividing the theoretical output regulation rate set of length n into k classes V1, V2, ..., V k A clustering method, each of which is abbreviated as V1 = {i1, i1+1, ..., i2-1}, V2 = {i2, i2+1, ..., i3-1}, ..., V k ={i k ,i k +1,...,n}; D(i t ,i t+1 -1) is the diameter of the tth class.

13. The system for dynamically adjusting the time periods of thermal power generation components according to claim 8, characterized in that: The clustering optimization module includes: A recursive formula is set based on an ordered clustering algorithm, and an optimal clustering method for dividing a theoretical output regulation rate set of length n into k segments is found through recursive solution of the recursive formula, so as to obtain an optimal clustering scheme for the theoretical output regulation rate.

14. The system for dynamically adjusting the time periods of thermal power generation components according to claim 13, characterized in that: The recursive formula is: Where L[P(n,k)] is the clustering loss of the optimal clustering scheme; n is the length of the theoretical output rate set; k is the number of segments; L[P(n,2)] is the clustering loss of the optimal clustering method that divides the rate set of length n into two categories; D(j,n) is the diameter of the last class after clustering; j is the index of the starting rate value of the last class after clustering.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images