Load side demand response mid-term frequency modulation resource configuration method, device, equipment and medium

Abstract

The invention relates to the technical field of demand response, in particular to a load-side demand response medium-term frequency modulation resource allocation method, device and equipment and a medium, and the method comprises the steps: obtaining frequency modulation event generation data, constructing a data set, and extracting frequency modulation event generation features by using a K-means algorithm; analyzing typical scenes faced by the dispatching center when the dispatching center configures frequency modulation resources, and establishing corresponding utility functions for different typical scenes; constructing a typical distribution scene according to the distribution characteristics of the frequency modulation event, calculating the scene probability, and extracting the probability density distribution of the frequency modulation demand from different characteristic dimensions; representing different decision-making behaviors of the dispatching center by utilizing probability density distribution of frequency modulation demand quantity, and establishing a middle-term frequency modulation resource allocation model of the dispatching center under an uncertain condition based on an energy form; and solving the medium-term frequency modulation resource configuration model to obtain the medium-term frequency modulation resource configuration method. According to the invention, the loss caused by uncertain risks is reduced, and the average frequency modulation effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of demand response technology, and in particular to a method, device, equipment and medium for configuring mid-term frequency modulation resources for load-side demand response. Background Art

[0002] Under the "dual carbon" goal, the transformation of energy structure and the low-carbonization of power system have become important ways to achieve sustainable development. Traditional power systems mainly rely on fossil fuel power generation and have strong peak-shaving and frequency-regulating capabilities. However, with the widespread application of renewable energy such as wind power and solar power, the power system has gradually shifted to a diversified structure dominated by renewable energy. Although renewable energy has made a significant contribution to reducing carbon emissions, it is volatile and uncertain and cannot be output as stably as traditional energy. This has led to severe challenges to the peak-shaving capacity of the power system when facing the grid connection of a large number of renewable energy sources.

[0003] In this context, demand response, as a flexible means of load regulation, has gradually gained attention. Demand response uses incentive mechanisms to guide users to actively adjust their electricity consumption during periods of tight power supply or high electricity prices, thereby balancing supply and demand and alleviating grid pressure. In addition, demand response, as a green peak-shaving method, can effectively regulate power loads and achieve supply and demand balance within the system without increasing carbon emissions.

[0004] In view of the sharp increase in peak-shaving demand in new power systems, using the dispatch center to configure demand-response peak-shaving resources can significantly reduce the demand for spare capacity, thereby reducing the operating cost of the power system. The configuration of its peak-shaving resources is affected by the peak-shaving demand. If the amount of configured resources is too large, some resources will be idle, resulting in cost losses; if the amount configured is too small, the peak-shaving demand cannot be met. However, the uncertainty on both the source and load sides makes it impossible to accurately obtain the peak-shaving demand, which brings challenges to the resource configuration of the dispatch center.

[0005] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art already known to those skilled in the art. Summary of the invention

[0006] The present invention provides a method, device, equipment and medium for configuring mid-term frequency modulation resources in response to load-side demand, thereby effectively solving the problems in the background technology.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is: a method for configuring medium-term frequency regulation resources in response to load-side demand, comprising the following steps:

[0008] Obtain FM event occurrence data, construct a data set, and use the K-means algorithm to extract FM event occurrence features;

[0009] Analyze the typical scenarios faced by the dispatch center when configuring frequency modulation resources, and establish corresponding utility functions for different typical scenarios;

[0010] According to the distribution characteristics of the frequency modulation events, a typical distribution scenario is constructed and the scenario probability is calculated, and the probability density distribution of the frequency modulation demand is extracted in different feature dimensions;

[0011] The probability density distribution of the frequency regulation demand is used to represent different decision-making behaviors of the dispatching center, and a medium-term frequency regulation resource allocation model of the dispatching center under uncertainty is established based on the energy form;

[0012] The mid-term frequency modulation resource configuration model is solved to obtain a mid-term frequency modulation resource configuration method.

[0013] Furthermore, the obtaining of frequency modulation event occurrence data includes:

[0014] Selecting the occurrence data of all frequency modulation events in the area, including the occurrence period, duration and amplitude; constructing data sets respectively, wherein each three-dimensional data in the data set is described as a data point;

[0015] The method of using the K-means algorithm to extract the occurrence features of the frequency modulation event includes:

[0016] The K-means algorithm is used to extract typical occurrence scenarios of the three factors combined and the occurrence scenarios of each factor separately, and probability density distributions are generated respectively to analyze the coupling characteristics and independent characteristics of the frequency modulation events in the area.

[0017] Furthermore, the use of the K-means algorithm to extract typical occurrence scenarios of the three types of factors combined includes:

[0018] The duration of frequency modulation events is clustered using the K-means algorithm:

[0019] ;

[0020] ;

[0021] Calculate the average duration of FM events:

[0022] ;

[0023] Where, d ij Represents the distance between the current sample and the centroid, D i is the duration of the ith FM event, μ j is the duration centroid of the jth cluster. SSE is the sum of squared errors of the sample distance centroid. jis the proportion of the jth class, and J is the total number of clusters.

[0024] Furthermore, the typical scenarios faced by the analysis dispatch center when configuring frequency modulation resources are established for different typical scenarios, including:

[0025] Assuming that the time period and duration of the frequency modulation event are known, a utility function for the dispatch center to allocate frequency modulation resources for frequency modulation is established under deterministic conditions.

[0026] Considering the unknown nature of frequency modulation events, the actual dispatch center behavior is decomposed into two scenarios and scheduling functions are established under the two scenarios respectively. The two scenarios are: frequency modulation resources can meet the current frequency modulation demand; and frequency modulation resources cannot meet the current frequency modulation demand.

[0027] Furthermore, in the deterministic case, the utility function of the dispatching center configuring the frequency modulation resources for frequency modulation is:

[0028] ;

[0029] In the formula, c FR , P FR and P need are the price of the frequency modulation resources purchased by the dispatch center, the purchased frequency modulation power, and the actual power shortage that caused the frequency drop; A and B are the price coefficients; U is the utility of the dispatch center in this frequency modulation event;

[0030] The scheduling functions in the two scenarios are:

[0031] When the frequency modulation resources can meet the current frequency modulation requirements:

[0032] ;

[0033] When the frequency modulation resources cannot meet the current frequency modulation requirements:

[0034] .

[0035] Furthermore, constructing a typical distribution scenario and calculating the scenario probability according to the distribution characteristics of the frequency modulation event includes:

[0036] Construct [t o , t l , P lose ] dataset and a separate dataset t o ,t l , P lose , and use kernel density estimation to generate probability density functions, generate probability density functions of frequency modulation events occurring in each time period, and express them in the form of probability;

[0037] The method of extracting the probability density distribution of frequency modulation demand in different feature dimensions includes:

[0038] The FM events are divided into very mild, mild, moderate and moderate, and are represented by different weights α;

[0039] Calculate the expectation of mild and above FM events at this point;

[0040] If the frequency modulation event level expected to occur during this period meets the set conditions, it is considered that frequency modulation response resources need to be configured during this period, and the frequency modulation demand R=1; if there is no frequency modulation demand, R=0.

[0041] Further, the generating a probability density function by using kernel density estimation includes:

[0042] ;

[0043] In the formula, represents the estimated probability density function value at point x, M represents the number of sample data; h is the bandwidth, and K(⋅) is the kernel function used to weigh the distance x and each sample point x. i The distance between

[0044] The calculation of the expectation of a mild or above frequency modulation event occurring at this point includes:

[0045] ;

[0046] The setting conditions are:

[0047] ;

[0048] Where E(ρ) is the expectation of the occurrence of frequency modulation events, ρ k is the probability of a mild or above FM event, α k is the weight of the corresponding frequency modulation event, and α2 is the weight of the mild frequency modulation event.

[0049] Furthermore, the probability density distribution of the frequency modulation demand is used to represent different decision-making behaviors of the dispatching center, including:

[0050] The utility function of the dispatch center's mid-term frequency regulation resource configuration considering uncertainty is as follows:

[0051] ;

[0052] The medium-term frequency modulation resource configuration model is:

[0053] ;

[0054] ;

[0055] The frequency modulation event length is 1 hour, that is, the dispatch center provides P FR FM resources;

[0056] The frequency modulation resources actually configured by the dispatch center during period t are shown in the following formula:

[0057] .

[0058] The present invention also includes a load-side demand response medium-term frequency regulation resource configuration device, using the above method, the device includes:

[0059] Feature extraction unit: the user obtains the FM event occurrence data, constructs a data set, and uses the K-means algorithm to extract the FM event occurrence features;

[0060] A utility unit, used to analyze typical scenarios faced by the dispatch center when configuring frequency modulation resources, and establish corresponding utility functions for different typical scenarios;

[0061] A probability unit, used to construct a typical distribution scenario and calculate the scenario probability according to the distribution characteristics of the frequency modulation event, and extract the probability density distribution of the frequency modulation demand in different feature dimensions;

[0062] A modeling unit, used to use the probability density distribution of the frequency regulation demand to represent different decision-making behaviors of the dispatching center, and to establish a medium-term frequency regulation resource allocation model of the dispatching center under uncertainty based on energy form;

[0063] The calculation unit is used to solve the mid-term frequency modulation resource configuration model to obtain a mid-term frequency modulation resource configuration method.

[0064] The present invention also includes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described above is implemented.

[0065] The present invention also includes a storage medium on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0066] The beneficial effects of the present invention are as follows: the present invention improves the accuracy and reliability of the dispatching center in configuring demand response frequency modulation resources, achieves targeted resource allocation by fully considering the uncertainty of frequency modulation events, greatly reduces the loss caused by configuring resources under uncertainty risks, and improves the average frequency modulation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 is a flow chart of the method in Example 1;

[0069] Figure 2 It is a structural schematic diagram of the device in Example 1;

[0070] Figure 3 is a flow chart of the method in Example 2;

[0071] Figure 4 A schematic diagram of the structure of a computer device. DETAILED DESCRIPTION

[0072] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0073] Embodiment 1:

[0074] like Figure 1 As shown: A method for configuring medium-term frequency regulation resources in response to load-side demand, comprising the following steps:

[0075] Obtain FM event occurrence data, construct a data set, and use the K-means algorithm to extract FM event occurrence features;

[0076] Analyze the typical scenarios faced by the dispatch center when configuring frequency modulation resources, and establish corresponding utility functions for different typical scenarios;

[0077] According to the distribution characteristics of frequency modulation events, typical distribution scenarios are constructed and the scenario probabilities are calculated, and the probability density distribution of frequency modulation demand is extracted in different feature dimensions;

[0078] The probability density distribution of frequency regulation demand is used to represent different decision-making behaviors of the dispatch center. Based on the energy form, a medium-term frequency regulation resource allocation model of the dispatch center under uncertainty is established.

[0079] The medium-term frequency regulation resource allocation model is solved to obtain the medium-term frequency regulation resource allocation method.

[0080] By using the probability density distribution of frequency regulation demand to represent different decision-making behaviors of the dispatching center, a medium-term resource allocation model of the dispatching center under uncertainty is established, which improves the accuracy and reliability of the dispatching center's allocation of demand response frequency regulation resources. By fully considering the uncertainty of frequency regulation events, targeted resource allocation is achieved, which greatly reduces the loss caused by resource allocation under uncertainty risks and improves the average frequency regulation effect.

[0081] In this embodiment, obtaining frequency modulation event occurrence data includes:

[0082] Select the occurrence data of all frequency modulation events in the area, including the occurrence period, duration and amplitude; construct data sets respectively, and each three-dimensional data in the data set is described as a data point;

[0083] Use K-means algorithm to extract the characteristics of frequency modulation events, including:

[0084] The K-means algorithm is used to extract typical occurrence scenarios of the three factors combined and the occurrence scenarios of each factor separately, and probability density distributions are generated respectively to analyze the coupling characteristics and independent characteristics of the frequency modulation events in the area.

[0085] The K-means algorithm is used to extract typical scenarios where three types of factors are combined, including:

[0086] The duration of frequency modulation events is clustered using the K-means algorithm:

[0087] ;

[0088] ;

[0089] Calculate the average duration of FM events:

[0090] ;

[0091] Where, d ij Represents the distance between the current sample and the centroid, D i is the duration of the ith FM event, μ j is the duration centroid of the jth cluster. SSE is the sum of squared errors of the sample distance centroid. j is the proportion of the jth class, and J is the total number of clusters.

[0092] Among them, the typical scenarios faced by the dispatch center when configuring frequency modulation resources are analyzed, and corresponding utility functions are established for different typical scenarios, including:

[0093] Assuming that the time period and duration of the frequency modulation event are known, a utility function for the dispatch center to allocate frequency modulation resources for frequency modulation is established under deterministic conditions.

[0094] Considering the unknown nature of frequency modulation events, the actual dispatch center behavior is decomposed into two scenarios and scheduling functions are established under the two scenarios respectively. The two scenarios are: frequency modulation resources can meet the current frequency modulation demand; and frequency modulation resources cannot meet the current frequency modulation demand.

[0095] As a preferred embodiment of the above, in a deterministic situation, the utility function of the dispatching center configuring the frequency modulation resources for frequency modulation is:

[0096] ;

[0097] In the formula, c FR , P FR and P need are the price of the frequency modulation resources purchased by the dispatch center, the purchased frequency modulation power, and the actual power shortage that caused the frequency drop; A and B are price coefficients; U is the utility of the dispatch center in this frequency modulation event;

[0098] The scheduling functions in the two scenarios are:

[0099] When the frequency modulation resources can meet the current frequency modulation requirements:

[0100] ;

[0101] When the frequency modulation resources cannot meet the current frequency modulation requirements:

[0102] .

[0103] In this embodiment, constructing a typical distribution scenario and calculating the scenario probability according to the distribution characteristics of the frequency modulation event includes:

[0104] Construct [t o , t l , P lose ] dataset and a separate dataset t o ,t l , P lose , and use kernel density estimation to generate probability density functions, generate probability density functions of frequency modulation events occurring in each time period, and express them in the form of probability;

[0105] The probability density distribution of frequency modulation demand extracted in different feature dimensions includes:

[0106] The FM events are divided into very mild, mild, moderate and moderate, and are represented by different weights α;

[0107] Calculate the expectation of mild and above FM events at this point;

[0108] If the frequency modulation event level expected to occur during this period meets the set conditions, it is considered that frequency modulation response resources need to be configured during this period, and the frequency modulation demand R=1; if there is no frequency modulation demand, R=0.

[0109] Among them, the probability density function is generated using kernel density estimation, including:

[0110] ;

[0111] In the formula, represents the estimated probability density function value at point x, M represents the number of sample data; h is the bandwidth, and K(⋅) is the kernel function used to weigh the distance x and each sample point x. i The distance between

[0112] Calculate the expectation of a mild or above FM event at this point, including:

[0113] ;

[0114] The setting conditions are:

[0115] ;

[0116] Where E(ρ) is the expectation of the occurrence of frequency modulation events, ρ k is the probability of a mild or above FM event, α k is the weight of the corresponding frequency modulation event, and α2 is the weight of the mild frequency modulation event.

[0117] As a preferred embodiment of the above, the probability density distribution of the frequency modulation demand is used to represent different decision-making behaviors of the dispatching center, including:

[0118] The utility function of the dispatch center's mid-term frequency regulation resource configuration considering uncertainty is as follows:

[0119] ;

[0120] The medium-term frequency regulation resource allocation model is:

[0121] ;

[0122] ;

[0123] The frequency modulation event length is 1 hour, that is, the dispatch center provides P FR FM resources;

[0124] The frequency modulation resources actually configured by the dispatch center during period t are shown in the following formula:

[0125] .

[0126] like Figure 2 As shown, this embodiment also includes a load-side demand response mid-term frequency regulation resource configuration device, using the above method, the device includes:

[0127] Feature extraction unit: the user obtains the FM event occurrence data, constructs a data set, and uses the K-means algorithm to extract the FM event occurrence features;

[0128] The utility unit is used to analyze the typical scenarios faced by the dispatch center when configuring frequency modulation resources, and to establish corresponding utility functions for different typical scenarios;

[0129] The probability unit is used to construct a typical distribution scenario and calculate the scenario probability according to the distribution characteristics of the frequency modulation event, and to extract the probability density distribution of the frequency modulation demand in different feature dimensions;

[0130] A modeling unit is used to use the probability density distribution of frequency regulation demand to represent different decision-making behaviors of the dispatching center, and to establish a medium-term frequency regulation resource allocation model of the dispatching center under uncertainty based on energy form;

[0131] The calculation unit is used to solve the medium-term frequency regulation resource configuration model to obtain the medium-term frequency regulation resource configuration method.

[0132] Embodiment 2:

[0133] like Figure 3 As shown, in this embodiment, a method for configuring medium-term frequency regulation resources for load-side demand response taking into account strong uncertainty is proposed to improve the effectiveness and economy of peak-shaving resource configuration, thereby maximizing the system peak-shaving effect and reducing the procurement cost of demand response peak-shaving resources. Perform the following steps:

[0134] Step 1: Analyze massive FM event data, construct a data set, and use the K-means algorithm to extract FM event occurrence features;

[0135] Step 2: Analyze the typical scenarios faced by the dispatch center when configuring frequency modulation resources, and establish different utility functions accordingly;

[0136] Step 3: Construct a typical distribution scenario based on the distribution characteristics of frequency modulation events and calculate the scenario probability, and extract the probability density distribution of frequency modulation demand in different feature dimensions;

[0137] Step 4: Use the probability density distribution of frequency regulation demand to represent different decision-making behaviors of the dispatching center, and establish a frequency regulation resource allocation model of the dispatching center under uncertainty based on the energy form.

[0138] In step 1, the following data are extracted from the historical data of frequency modulation events to construct a frequency modulation event data set. The data set is preprocessed, and the data preprocessing process includes but is not limited to data cleaning, missing value filling, outlier removal, and data standardization. The data types that need to be extracted are the occurrence period, duration, and amplitude of the frequency modulation event. The unit of the amplitude is Hz. By establishing a single-machine infinite system for simulation, the missing power corresponding to the amplitude is reversed.

[0139] The above four types of data sets are clustered by K-means algorithm to extract the characteristics of the duration of FM events, as shown in the formula - . formula - Cluster the duration of frequency modulation events, formula The average duration of FM events was calculated.

[0140]

[0141]

[0142]

[0143] Where, d ij Represents the distance between the current sample and the centroid, D i is the duration of the ith FM event, μ j is the duration centroid of the jth cluster. SSE is the sum of squared errors of the sample distance centroid. j is the proportion of the jth class, and J is the total number of clusters.

[0144] In step 2, the typical scenarios faced by the dispatch center when configuring frequency modulation resources are analyzed, and different utility functions are established in a targeted manner. When the dispatch center configures frequency modulation resources, it focuses on the effect of frequency modulation on the one hand, and the cost of frequency modulation resource configuration on the other hand. First, it is assumed that the time period and duration of the frequency modulation event are known, and only the decision of the dispatch center on the frequency modulation event at the current moment is used as the basis for modeling. In the deterministic case, the utility function of the dispatch center configuring frequency modulation resources for frequency modulation is as follows: , including the cost of purchasing demand response frequency regulation resources and the cost of purchasing system frequency regulation resources. Since frequency regulation events will affect system stability, the dispatch center will not receive additional benefits by making up for work income. In addition, the more system frequency regulation resources the dispatch center purchases temporarily, the higher the unit price it pays. This is because this behavior occupies the system spinning reserve and reduces the stability of system operation.

[0145]

[0146] In the formula, c FR , P FR and P need are the price of the frequency modulation resources purchased by the dispatch center, the purchased frequency modulation power, and the actual power shortage that caused the frequency drop. A and B are the price coefficients. U is the income of the dispatch center in this frequency modulation event.

[0147] The establishment of the above utility function only considers the decision-making behavior of the dispatch center when all information is completely known. Obviously, the optimal amount of configured resources can be directly calculated. However, the frequency modulation event is unknown, and the specific power shortage and the actual frequency modulation resources configured by the dispatch center may not match. Therefore, the actual economic behavior of the dispatch center can be decomposed into the following two scenarios: the frequency modulation resources can meet the current frequency modulation needs. and frequency modulation resources cannot meet the current frequency modulation needs .

[0148]

[0149]

[0150] At this point, the decision utility function of the dispatch center under different circumstances can be obtained.

[0151] In step 3, a typical distribution scenario is constructed based on the distribution characteristics of the frequency modulation event and the scenario probability is calculated, and the probability density distribution of the frequency modulation demand is extracted in different feature dimensions. o , t l , P lose ] dataset and a separate dataset t o ,t l , P lose , and use kernel density estimation to generate a probability density function, such as the formula Generate the probability density function of frequency modulation events in each time period and express it in the form of probability. Frequency modulation events are divided into very light, light, moderate and moderate, and are represented by different weights α. Calculate the expectation of light and above frequency modulation events at this point according to the formula, as shown in the formula If the frequency modulation event degree during this period is expected to satisfy the formula , it is considered that frequency modulation response resources need to be configured during this period, and the frequency modulation demand R=1; if there is no frequency modulation demand, R=0.

[0152] The probability density distribution function of the frequency modulation demand can also be calculated according to the formula Derived.

[0153]

[0154]

[0155]

[0156] In the formula, represents the estimated probability density function value at point x, M represents the number of sample data. h is the bandwidth, and K(⋅) is the kernel function used to weigh the distance x and each sample point x. i The distance between.

[0157] Step 4: Use the probability density distribution of frequency regulation demand to represent different decision-making behaviors of the dispatch center. Based on the energy form, establish a frequency regulation resource configuration model for the dispatch center under uncertainty. In step 2, the utility function of the dispatch center for configuring medium-term frequency regulation resources was discussed by category, but it was not unified and could not be compatible with the model for calculation. Therefore, the utility function of the dispatch center under different circumstances is unified through the probability density of frequency regulation demand. The utility function of the dispatch center for configuring medium-term frequency regulation resources under uncertainty is as follows: shown.

[0158]

[0159] The load-side demand response resource configuration model that ultimately takes into account the source-load correlation is listed below.

[0160]

[0161]

[0162] The above calculations assume that the frequency modulation event length is 1 hour, that is, the dispatch center provides P FR Considering that the duration of frequency modulation events is relatively short, the frequency modulation resources configured by the dispatch center in the actual period t should be the formula .

[0163]

[0164] The demand response medium-term frequency regulation resource configuration model proposed in this embodiment effectively solves the problem of the dispatching center configuring demand response medium-term frequency regulation resources. Configuring resources in the form of energy improves the utilization rate of frequency regulation resources and reduces configuration costs. Based on the frequency regulation demand faced by the dispatching center under strong uncertainty in the medium-term time scale, it can effectively improve the reliability and applicability of the planning results.

[0165] See also Figure 4 A computer device 400 provided in an embodiment of the present application includes: a processor 410 and a memory 420, wherein the memory 420 stores a computer program executable by the processor 410, and when the computer program is executed by the processor 410, the above method is executed.

[0166] The embodiment of the present application further provides a storage medium 430 on which a computer program is stored. When the computer program is run by the processor 410, the above method is executed.

[0167] Among them, the storage medium 430 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, disk or optical disk.

[0168] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0169] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0170] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0171] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0172] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0173] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0174] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0175] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for configuring medium-term frequency regulation resources for load-side demand response, characterized in that: The steps include: Obtain FM event occurrence data, construct a data set, and use the K-means algorithm to extract FM event occurrence features; Analyze the typical scenarios faced by the dispatch center when configuring frequency modulation resources, and establish corresponding utility functions for different typical scenarios; According to the distribution characteristics of the frequency modulation events, a typical distribution scenario is constructed and the scenario probability is calculated, and the probability density distribution of the frequency modulation demand is extracted in different feature dimensions; The probability density distribution of the frequency regulation demand is used to represent different decision-making behaviors of the dispatching center, and a medium-term frequency regulation resource allocation model of the dispatching center under uncertainty is established based on the energy form; The mid-term frequency modulation resource configuration model is solved to obtain a mid-term frequency modulation resource configuration method.

2. The method for configuring medium-term frequency regulation resources for load-side demand response according to claim 1, characterized in that: The step of obtaining frequency modulation event occurrence data includes: Selecting the occurrence data of all frequency modulation events in the area, including the occurrence period, duration and amplitude; constructing data sets respectively, wherein each three-dimensional data in the data set is described as a data point; The method of using the K-means algorithm to extract the occurrence features of the frequency modulation event includes: The K-means algorithm is used to extract typical occurrence scenarios of the three factors combined and the occurrence scenarios of each factor separately, and probability density distributions are generated respectively to analyze the coupling characteristics and independent characteristics of the frequency modulation events in the area.

3. The method for configuring medium-term frequency regulation resources for load-side demand response according to claim 2, characterized in that: The typical occurrence scenarios of the three types of factors combined by using the K-means algorithm include: The duration of frequency modulation events is clustered using the K-means algorithm: ； ； Calculate the average duration of FM events: ； Where, d ij Represents the distance between the current sample and the centroid, D i is the duration of the ith FM event, μ j is the duration centroid of the jth cluster, SSE is the sum of squared errors of the sample distance centroid, ρ j is the proportion of the jth class, and J is the total number of clusters.

4. The method for configuring medium-term frequency regulation resources for load-side demand response according to claim 1, characterized in that: The typical scenarios faced by the analysis scheduling center when configuring frequency modulation resources, and establishing corresponding utility functions for different typical scenarios, include: Assuming that the time period and duration of the frequency modulation event are known, a utility function for the dispatch center to allocate frequency modulation resources for frequency modulation is established under deterministic conditions. Considering the unknown nature of frequency modulation events, the actual dispatch center behavior is decomposed into two scenarios and scheduling functions are established under the two scenarios respectively. The two scenarios are: frequency modulation resources can meet the current frequency modulation demand; and frequency modulation resources cannot meet the current frequency modulation demand.

5. The method for configuring medium-term frequency regulation resources for load-side demand response according to claim 4 is characterized in that: In the deterministic case, the utility function of the dispatch center to configure frequency modulation resources for frequency modulation is: ； In the formula, c FR , P FR and P need are the price of the frequency modulation resources purchased by the dispatch center, the purchased frequency modulation power, and the actual power shortage that caused the frequency drop; A and B are price coefficients; U is the utility of the dispatch center in this frequency modulation event; The scheduling functions in the two scenarios are: When the frequency modulation resources can meet the current frequency modulation requirements: ； When the frequency modulation resources cannot meet the current frequency modulation requirements: 。 6. The method for configuring medium-term frequency regulation resources for load-side demand response according to claim 1, characterized in that: The constructing a typical distribution scenario and calculating the scenario probability according to the distribution characteristics of the frequency modulation event includes: Construct [t o , t l , P lose ] dataset and a separate dataset t o ,t l , P lose , and use kernel density estimation to generate probability density functions, generate probability density functions of frequency modulation events occurring in each time period, and express them in the form of probability; The method of extracting the probability density distribution of frequency modulation demand in different feature dimensions includes: The FM events are divided into very mild, mild, moderate and moderate, and are represented by different weights α; Calculate the expectation of mild and above FM events at this point; If the frequency modulation event level expected to occur during this period meets the set conditions, it is considered that frequency modulation response resources need to be configured during this period, and the frequency modulation demand R=1; if there is no frequency modulation demand, R=0.

7. The method for configuring medium-term frequency regulation resources for load-side demand response according to claim 6, characterized in that: The method of generating a probability density function by using kernel density estimation includes: ； In the formula, represents the estimated probability density function value at point x, M represents the number of sample data; h is the bandwidth, and K(⋅) is the kernel function used to weigh the distance x and each sample point x. i The distance between The calculation of the expectation of a mild or above frequency modulation event occurring at this point includes: ； The setting conditions are: ； Where E(ρ) is the expectation of the occurrence of frequency modulation events, ρ k is the probability of a mild or above FM event, α k is the weight of the corresponding frequency modulation event, and α2 is the weight of the mild frequency modulation event.

8. The method for configuring medium-term frequency regulation resources for load-side demand response according to claim 5, characterized in that: The method of using the probability density distribution of the frequency modulation demand to represent different decision-making behaviors of the dispatching center includes: The utility function of the dispatch center's mid-term frequency regulation resource configuration considering uncertainty is as follows: ； The medium-term frequency modulation resource configuration model is: ； ； The frequency modulation event length is 1 hour, that is, the dispatch center provides P FR FM resources; The frequency modulation resources actually configured by the dispatch center during period t are shown in the following formula: 。 9. A load-side demand response mid-term frequency regulation resource configuration device, characterized in that: Using the method according to any one of claims 1 to 8, the device comprises: Feature extraction unit: the user obtains the FM event occurrence data, constructs a data set, and uses the K-means algorithm to extract the FM event occurrence features; A utility unit, used to analyze typical scenarios faced by the dispatch center when configuring frequency modulation resources, and establish corresponding utility functions for different typical scenarios; A probability unit, used to construct a typical distribution scenario and calculate the scenario probability according to the distribution characteristics of the frequency modulation event, and extract the probability density distribution of the frequency modulation demand in different feature dimensions; A modeling unit, used to use the probability density distribution of the frequency regulation demand to represent different decision-making behaviors of the dispatching center, and to establish a medium-term frequency regulation resource allocation model of the dispatching center under uncertainty based on energy form; The calculation unit is used to solve the mid-term frequency modulation resource configuration model to obtain a mid-term frequency modulation resource configuration method.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

11. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images