Adjustable load interaction capability key parameter confidence interval evaluation method

Abstract

The invention belongs to the technical field of power system automation, and particularly relates to an adjustable load interaction capability key parameter confidence interval evaluation method. Comprising the steps of obtaining a system standby insufficient scene according to historical prediction data, forming a scene set, obtaining the maximum adjustable quantity of an adjustable load in a corresponding time period, and obtaining an adjustable load active response in the corresponding time period of the scene set according to historical operation data; calculating the actual maximum adjustable variable of the adjustable load, carrying out correlation analysis, generating a set taking the actual adjustable load value and the actual maximum adjustable variable of the adjustable load as elements, and grading the set into upper and lower standby difference scene grading sets according to the actual adjustable load value; clustering elements in the grading set to obtain a probability density function set of the actual maximum adjustable quantity of the adjustable load under different load levels; the confidence interval of the actual maximum adjustable quantity of the adjustable load under the given confidence is calculated, the contradiction between supply and demand is solved, peak clipping and valley filling are achieved, and the new energy consumption capacity is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of power system automation, and in particular relates to a confidence interval evaluation method for key parameters of adjustable load interaction capability. Background Art

[0002] The operation and dispatch of power systems plays an important role in the safe, stable and economic operation of power systems. During the dispatch process, the power grid needs to be equipped with a certain amount of spare capacity to ensure the balance of power generation and load under different operation modes such as maintenance, failure, peak shaving and valley filling. With the construction of new power systems, new energy sources are connected to the power grid on a large scale. The randomness, volatility and intermittency of their output can easily lead to insufficient spare capacity of the power system, which also brings new challenges to the safe and stable operation of the power system.

[0003] Adjustable load interaction is an important means to improve the capacity of renewable energy consumption, promote peak shaving and valley filling, and achieve power balance regulation of power systems. In recent years, with the development of big data technology, massive historical operation data has pushed the power grid into the big data era, which provides a new method for evaluating the interactive response capability of adjustable loads.

[0004] However, the existing scenario generation and clustering technology cannot effectively support the grid uncertainty analysis requirements of the interactive characteristics of adjustable loads, and cannot provide the confidence interval of the key parameters of the interactive response capability of adjustable loads, making it difficult to evaluate the reliability of the interactive response of adjustable loads, which makes the grid dispatch decision lack of basis. By mining the key information of the interactive response capability of adjustable loads from the massive historical data of the power grid, constructing the probability distribution model of the key information of the interactive response capability, and providing the interactive response capability evaluation method based on the confidence interval, the new power system resource optimization configuration is realized on this basis, the energy utilization rate is improved, the contradiction between supply and demand is alleviated, and the safe, stable and economic operation of the power grid is ensured. Summary of the invention

[0005] In view of the shortcomings of the above-mentioned prior art, the present invention provides a confidence interval evaluation method for key parameters of adjustable load interaction capability. The purpose is to obtain the probability distribution of key parameters of adjustable load interaction capability by mining the key information of massive power grid historical operation data, realize the evaluation of adjustable load interaction response capability based on confidence interval, and improve the level of lean scheduling.

[0006] The technical solution adopted by the present invention to achieve the above-mentioned purpose is:

[0007] A confidence interval evaluation method for key parameters of adjustable load interaction capability, comprising:

[0008] According to the historical forecast data, the system reserve shortage scenario is obtained to form a scenario set, and the maximum adjustable amount of the adjustable load in the corresponding period is obtained. According to the historical operation data, the active power response of the adjustable load in the corresponding period of the scenario set is obtained;

[0009] Calculate the actual maximum adjustable amount of the adjustable load for each scenario in the scenario set, perform correlation analysis on all scenarios of the upper reserve difference and the lower reserve difference, and generate a correlation set with the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load as elements;

[0010] The correlation sets of the upper reserve difference and the lower reserve difference scenarios are divided into grades according to the actual value of the adjustable load to form an upper reserve difference scenario graded set and a lower reserve difference scenario graded set;

[0011] A Gaussian mixture distribution model is used to cluster each element in the upper reserve difference scenario classification set and the lower reserve difference scenario classification set to obtain a probability density function set of the actual maximum adjustable amount of the adjustable load under different load levels;

[0012] For different adjustable load levels, the confidence interval of the actual maximum adjustable amount of the adjustable load under a given confidence level is calculated respectively.

[0013] Furthermore, the upper reserve difference refers to that the total system load is greater than the maximum active output of the system, and the lower reserve difference refers to that the total system load is less than the minimum active output of the system.

[0014] Furthermore, the actual maximum adjustable amount of the adjustable load is calculated by:

[0015] Step 2-1 If the system has insufficient reserve in scenario i, the actual maximum adjustable amount of the adjustable load As follows:

[0016]

[0017] In the formula, They represent the maximum adjustable amount, actual value and predicted value of the adjustable load of scenario i respectively;

[0018] Step 2-2 If the system has insufficient reserve in scenario i, the actual maximum adjustable amount of the adjustable load As follows:

[0019]

[0020] Furthermore, the correlation sets of the upper standby difference and lower standby difference scenarios are divided into grades according to the actual value of the adjustable load to form a set of upper standby difference scenario grades and a set of lower standby difference scenario grades; including:

[0021] Step 3-1: The vector formed by the actual value of the adjustable load collected on the tth day in all the upper reserve difference scenarios is The vector formed by the actual maximum adjustable amount of the corresponding adjustable load is: And conduct correlation analysis. If the correlation coefficient r t If the absolute value is greater than η1 (>0), Each element in is included in the set S + middle;

[0022] Step 3-2: The vector formed by the actual value of the adjustable load collected on the zth day in all the reserve difference scenarios is The vector formed by the actual maximum adjustable amount of the corresponding adjustable load is: And conduct correlation analysis. If the correlation coefficient r z If the absolute value is greater than η2 (>0), then Each element is included in the set S - middle;

[0023] Among them, the correlation coefficient r t and r z The calculation formula is as follows:

[0024]

[0025]

[0026] In the above formula, k represents the number of collections on the tth day in the upper reserve difference scenario, They represent the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load in the j-th upper reserve insufficient scenario on the t-th day, respectively. They represent the actual value of the adjustable load on the tth day and the average of the actual maximum adjustable amount of the adjustable load; q represents the number of collections on the zth day in the lower reserve difference scenario, They represent the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load in the j-th scenario with insufficient reserve on the z-th day, respectively. They respectively represent the actual value of the adjustable load on the xth day and the average of the actual maximum adjustable amount of the adjustable load.

[0027] Furthermore, the Gaussian mixture distribution model is used to cluster each element in the upper standby difference scenario classification set and the lower standby difference scenario classification set to obtain a probability density function set of the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load, including:

[0028] Step 4-1: The correlation set S of the backup difference scenario + The actual values ​​of the adjustable loads of all elements in are sorted from large to small, and the maximum load is The minimum load is make S + The actual value of the adjustable load is in the range Included in the subset but Where: ΔL + is the step size of the adjustable load actual value in the upper reserve difference scenario, and h is the number of adjustable load actual value steps in the upper reserve difference scenario;

[0029] Step 4-2: The correlation set S of the backup balance scenario - The actual values ​​of the adjustable loads of all elements in are sorted from large to small, and the maximum load is The minimum load is make S - The actual value of the adjustable load is in the range Included in the subset but Where: ΔL - is the step size of the actual value of the load that can be adjusted in the lower reserve difference scenario, and h is the number of the actual value of the load that can be adjusted in the lower reserve difference scenario;

[0030] Step 4-3 uses Gaussian mixture models based on diagonal, spherical, tied, and full covariance to classify the spare difference scenarios into groups. And the next backup difference scenario classification set Each element in is clustered, the number of clusters is N1~N2 respectively, and the one with the smallest Bayesian information criterion score is taken as the clustering model of the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load;

[0031] Step 4-4 Group the upper reserve difference scenarios into tiers And the next backup difference scenario classification set Substitute each element of into the following formula to form the probability density function set of the actual maximum adjustable amount of the adjustable load in the upper reserve difference scenario The probability density function set of the actual maximum adjustable amount of the adjustable load in the lower reserve difference scenario

[0032]

[0033] In the above formula, f(x) is the probability density function of the actual maximum adjustable amount of the adjustable load, and K is the optimal number of clusters; w t , μ t ,Σ tare the weight of the t-th category, the mean of the actual maximum adjustable amount of the adjustable load, and the variance of the actual maximum adjustable amount of the adjustable load; N(x|μ t ,Σ t )The probability density function of the t-th Gaussian distribution.

[0034] Furthermore, for different adjustable load levels, respectively calculating the confidence interval of the actual maximum adjustable amount of the adjustable load under a given confidence level includes the following steps:

[0035] Step 5-1 If the current system output exceeds the reserve balance, proceed as follows:

[0036] Step 5-1-1 Find the range to which the adjustable load forecast value belongs Where: The maximum load is The minimum load is ΔL + is the step size of the adjustable load actual value in the upper reserve difference scenario, and H is the number of adjustable load actual value steps in the upper reserve difference scenario;

[0037] Step 5-1-2 From the probability density function set of the actual maximum adjustable amount of the adjustable load in the upper reserve difference scenario Find the corresponding probability density distribution function

[0038] Step 5-1-3 Given a confidence level of α (0<α<1), calculate the confidence interval [M-σ,M+σ] using the following formula:

[0039]

[0040] in, w Hm , μ Hm , KH are The weight, mean, and optimal number of clusters of the mth class;

[0041] Step 5-2 If the current system output is below the reserve balance, execute the following steps:

[0042] Step 5-2-1 Find the range to which the adjustable load forecast value belongs Among them: the minimum load is ΔL - is the step size of the actual value of the load that can be adjusted in the lower reserve difference scenario, and T is the number of the actual value of the load that can be adjusted in the lower reserve difference scenario;

[0043] Step 5-2-2 From the probability density function set of the actual maximum adjustable amount of adjustable load in the lower reserve difference scenario Find the corresponding probability density distribution function

[0044] Step 5-2-3 Given a confidence level of β (0<β<1), calculate the confidence interval [N-β, N+β] using the following formula:

[0045]

[0046] in, w Tn and μ Tn , KT respectively The weight, mean, and optimal number of clusters of the nth class. dx represents the differential of the variable x.

[0047] A device for evaluating confidence intervals of key parameters of adjustable load interaction capability, comprising:

[0048] An acquisition module is used to acquire system reserve shortage scenarios based on historical prediction data, form a scenario set, and acquire the maximum adjustable amount of the adjustable load in the corresponding period, and acquire the active power response of the adjustable load in the corresponding period of the scenario set based on historical operation data;

[0049] A generation module, used for calculating the actual maximum adjustable amount of the adjustable load for each scenario in the scenario set, performing correlation analysis on all scenarios of the upper reserve difference and the lower reserve difference, and generating a set with the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load as elements;

[0050] A set forming module, used for classifying the correlation sets of the upper standby difference and the lower standby difference scenarios according to the actual value of the adjustable load, to form an upper standby difference scenario class set and a lower standby difference scenario class set;

[0051] A clustering module, for clustering each element in the upper standby difference scenario grading set and the lower standby difference scenario grading set using a Gaussian mixture distribution model, to obtain a probability density function set of an actual value of the adjustable load and an actual maximum adjustable amount of the adjustable load;

[0052] The calculation module is used to calculate the confidence interval of the actual maximum adjustable amount of the adjustable load under a given confidence level for different adjustable load levels.

[0053] Furthermore, the evaluation device is used to implement the steps of any one of the methods for evaluating confidence intervals of key parameters of adjustable load interaction capacity.

[0054] A computer device comprises a storage medium, a processor and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the computer program, the steps of any one of the methods for evaluating confidence intervals of key parameters of adjustable load interaction capacity are implemented.

[0055] A computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods for evaluating confidence intervals of key parameters of adjustable load interaction capacity are implemented.

[0056] The present invention has the following beneficial effects and advantages:

[0057] The present invention can obtain the probability distribution of key parameters of adjustable load interaction capability by mining key information of massive power grid operation data, realize the evaluation of adjustable load interaction response capability based on confidence interval, provide technical support for dispatching and operating personnel to take power balance adjustment measures to solve the contradiction between supply and demand and reduce peaks and fill valleys, and ensure the safe, stable and economical operation of the power grid, and fill the technical gap in obtaining confidence intervals of key parameters of adjustable load interaction response capability.

[0058] The present invention determines the adjustable loads participating in interactive control in each scenario through correlation analysis between the maximum load regulation capacity and the load active response curve. For the scenarios where the upper and lower regulation capacity of the adjustable load is insufficient, Gaussian mixture distribution model clustering is used to obtain the probability distribution of the maximum adjustable amount of the adjustable load under different load levels. On this basis, for different adjustable load levels, the confidence interval of the maximum adjustable amount of the adjustable load under a given confidence level is calculated. Compared with the existing dispatching strategies, the present invention effectively supports the grid uncertainty analysis of the interactive characteristics of the adjustable load, can evaluate the reliability of the interactive response of the adjustable load, improve the new energy consumption capacity, and provide a basis for grid dispatching decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0060] Figure 1 It is a flow chart of the evaluation method of the present invention. DETAILED DESCRIPTION

[0061] In order to more clearly understand the above-mentioned objectives, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0062] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0063] Refer to the following Figure 1 The technical solutions of some embodiments of the present invention are described.

[0064] Example 1

[0065] The present invention provides an embodiment, which is a confidence interval evaluation method for key parameters of adjustable load interaction capacity. Figure 1 As shown, Figure 1 It is a flow chart of the evaluation method of the present invention.

[0066] The present invention provides a method for evaluating confidence intervals of key parameters of adjustable load interaction capability, comprising the following steps:

[0067] Step 1. Obtain the system reserve shortage scenario according to historical prediction data to form scenario set S0, and obtain the maximum adjustable amount of the adjustable load in the corresponding period, and obtain the active power response of the adjustable load in the corresponding period of scenario set S0 according to historical operation data;

[0068] Step 2. For the scene set S 0 For each scenario i, the actual maximum adjustable amount of the adjustable load is calculated, and all scenarios of the upper reserve difference and the lower reserve difference are respectively subjected to correlation analysis to generate a correlation set S with the actual value of the adjustable load in the upper reserve difference scenario and the actual maximum adjustable amount of the adjustable load as elements. + The correlation set S with the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load in the following reserve difference scenario as elements - .

[0069] In the present invention, the upper reserve difference refers to that the total system load is greater than the maximum value of the system active output, and the lower reserve difference refers to that the total system load is less than the minimum value of the system active output.

[0070] The actual maximum adjustable amount of the adjustable load is calculated as follows:

[0071] Step 2-1 If the system has insufficient reserve in scenario i, the actual maximum adjustable amount of the adjustable load Calculate as follows:

[0072]

[0073] In the formula, They represent the maximum adjustable amount, actual value and predicted value of the adjustable load of scenario i respectively;

[0074] Step 2-2 If the system has insufficient reserve in scenario i, the actual maximum adjustable amount of the adjustable load Calculate as follows:

[0075]

[0076] Step 3. The correlation set S of the upper reserve difference scenario+ and the correlation set S of the next reserve difference scenario - The upper reserve difference scenario classification set is formed after being classified according to the actual value of the adjustable load And the next backup difference scenario classification set The specific steps include:

[0077] Step 3-1: The vector formed by the actual value of the adjustable load collected on the tth day in all the upper reserve difference scenarios is The vector formed by the actual maximum adjustable amount of the corresponding adjustable load is: And conduct correlation analysis. If the correlation coefficient r t If the absolute value is greater than η1 (>0), Each element in is included in the set S + middle.

[0078] Step 3-2: The vector formed by the actual value of the adjustable load collected on the zth day in all the reserve difference scenarios is The vector formed by the actual maximum adjustable amount of the corresponding adjustable load is: And conduct correlation analysis. If the correlation coefficient r z If the absolute value is greater than η2 (>0), then Each element is included in the set S - middle.

[0079] Among them, the correlation coefficient r t and r z The calculation formula is as follows:

[0080]

[0081]

[0082] In the above formula, k represents the number of collections on the tth day in the upper reserve difference scenario, They represent the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load in the j-th upper reserve insufficient scenario on the t-th day, respectively. They represent the actual value of the adjustable load on the tth day and the average of the actual maximum adjustable amount of the adjustable load; q represents the number of collections on the zth day in the lower reserve difference scenario, They represent the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load in the j-th scenario with insufficient reserve on the z-th day, respectively. They represent the actual value of the adjustable load on day z and the average of the actual maximum adjustable amount of the adjustable load respectively;

[0083] Step 4. Use the Gaussian mixture distribution model to classify the backup difference scenario into a set of tiers And the next backup difference scenario classification set Cluster each element in to obtain the probability density function set of the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load and The details are as follows:

[0084] Step 4-1: The correlation set S of the backup difference scenario + The actual values ​​of the adjustable loads of all elements in are sorted from large to small, and the maximum load is The minimum load is make S + The actual value of the adjustable load is in the range Included in the subset but Where: ΔL + is the step size of the adjustable load actual value in the upper reserve difference scenario, and h is the number of adjustable load actual value steps in the upper reserve difference scenario;

[0085] The correlation set S of the backup difference scenario in step 4-2 - The actual values ​​of the adjustable loads of all elements in are sorted from large to small, and the maximum load is The minimum load is make S - The actual value of the adjustable load is in the range Included in the subset but Where: ΔL - is the step size of the actual value of the load that can be adjusted in the lower reserve difference scenario, and h is the number of the actual value of the load that can be adjusted in the lower reserve difference scenario;

[0086] Step 4-3 uses Gaussian mixture models based on diagonal, spherical, tied, and full covariance to classify the spare difference scenarios into groups. And the next backup difference scenario classification set Each element in is clustered, the number of clusters is N1~N2 respectively, and the one with the smallest Bayesian information criterion score is taken as the clustering model of the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load.

[0087] Step 4-4 Group the upper reserve difference scenarios into tiers And the next backup difference scenario classification set Substitute each element of into the following formula to form the probability density function set of the actual maximum adjustable amount of the adjustable load in the upper reserve difference scenario The probability density function set of the actual maximum adjustable amount of the adjustable load in the lower reserve difference scenario

[0088]

[0089] In the above formula, f(x) is the probability density function of the actual maximum adjustable amount of the adjustable load, and K is the optimal number of clusters; w t , μ t ,Σ t are the weight of the t-th category, the mean of the actual maximum adjustable amount of the adjustable load, and the variance of the actual maximum adjustable amount of the adjustable load; N(x|μ t ,Σ t )The probability density function of the t-th Gaussian distribution.

[0090] Step 5. For different adjustable load levels, the confidence interval of the actual maximum adjustable amount of the adjustable load under a given confidence level is calculated respectively, and finally the confidence interval of the maximum adjustable amount of the adjustable load under different confidence levels is obtained, which is as follows:

[0091] Step 5-1 If the current system output exceeds the reserve balance, proceed as follows:

[0092] Step 5-1-1 Find the range to which the adjustable load forecast value belongs Where: The maximum load is The minimum load is ΔL + is the step size of the adjustable load actual value in the upper reserve difference scenario, and H is the number of adjustable load actual value steps in the upper reserve difference scenario;

[0093] Step 5-1-2 From the probability density function set of the actual maximum adjustable amount of the adjustable load in the upper reserve difference scenario Find the corresponding probability density distribution function

[0094] Step 5-1-3 Given a confidence level of α (0<α<1), calculate the confidence interval [M-σ,M+σ] using the following formula:

[0095]

[0096] in, w Hm , μ Hm , KH are The weight, mean, and optimal number of clusters of the mth class;

[0097] Step 5-2 If the current system output is below the reserve balance, execute the following steps:

[0098] Step 5-2-1 Find the range to which the adjustable load forecast value belongs Among them: the minimum load is ΔL - is the step size of the actual value of the load that can be adjusted in the lower reserve difference scenario, and T is the number of the actual value of the load that can be adjusted in the lower reserve difference scenario;

[0099] Step 5-2-2 From the probability density function set of the actual maximum adjustable amount of adjustable load in the lower reserve difference scenario Find the corresponding probability density distribution function

[0100] Step 5-2-3 Given a confidence level of β (0<β<1), calculate the confidence interval [N-β, N+β] using the following formula:

[0101]

[0102] in, w Tn and μ Tn , KT respectively The weight, mean, and optimal number of clusters of the nth class. dx represents the differential of the variable x.

[0103] Example 2

[0104] The present invention further provides an embodiment, which is a device for evaluating confidence intervals of key parameters of adjustable load interaction capability, comprising:

[0105] An acquisition module is used to acquire system reserve shortage scenarios based on historical prediction data, form a scenario set, and acquire the maximum adjustable amount of the adjustable load in the corresponding period, and acquire the active power response of the adjustable load in the corresponding period of the scenario set based on historical operation data;

[0106] A generation module, used for calculating the actual maximum adjustable amount of the adjustable load for each scenario in the scenario set, performing correlation analysis on all scenarios of the upper reserve difference and the lower reserve difference, and generating a set with the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load as elements;

[0107] A set forming module, used for dividing the set with the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load as elements into grades according to the actual value of the adjustable load, to form an upper standby difference scenario graded set and a lower standby difference scenario graded set;

[0108] A clustering module, for clustering each element in the upper standby difference scenario grading set and the lower standby difference scenario grading set using a Gaussian mixture distribution model, to obtain a probability density function set of an actual value of the adjustable load and an actual maximum adjustable amount of the adjustable load;

[0109] The calculation module is used to calculate the confidence interval of the actual maximum adjustable amount of the adjustable load under a given confidence level for different adjustable load levels, and finally obtain the confidence interval of the maximum adjustable amount of the adjustable load under different confidence levels.

[0110] Example 3

[0111] Based on the same inventive concept, an embodiment of the present invention further provides a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, the steps of the method for evaluating the confidence interval of key parameters of the interactive capacity of adjustable loads described in Example 1 are implemented.

[0112] Example 4

[0113] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of a confidence interval evaluation method for key parameters of adjustable load interaction capacity described in Example 1 are implemented.

[0114] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A confidence interval evaluation method for key parameters of adjustable load interaction capacity, characterized by: include: According to the historical forecast data, the system reserve shortage scenario is obtained to form a scenario set, and the maximum adjustable amount of the adjustable load in the corresponding period is obtained. According to the historical operation data, the active power response of the adjustable load in the corresponding period of the scenario set is obtained; Calculate the actual maximum adjustable amount of the adjustable load for each scenario in the scenario set, perform correlation analysis on all scenarios of the upper reserve difference and the lower reserve difference, and generate a correlation set with the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load as elements; The correlation sets of the upper reserve difference and the lower reserve difference scenarios are divided into grades according to the actual value of the adjustable load to form an upper reserve difference scenario graded set and a lower reserve difference scenario graded set; A Gaussian mixture distribution model is used to cluster each element in the upper reserve difference scenario classification set and the lower reserve difference scenario classification set to obtain a probability density function set of the actual maximum adjustable amount of the adjustable load under different load levels; For different adjustable load levels, the confidence interval of the actual maximum adjustable amount of the adjustable load under a given confidence level is calculated respectively.

2. The method for evaluating the confidence interval of key parameters of adjustable load interaction capacity according to claim 1 is characterized by: The upper reserve difference refers to that the total system load is greater than the maximum active output of the system, and the lower reserve difference refers to that the total system load is less than the minimum active output of the system.

3. The method for evaluating the confidence interval of key parameters of adjustable load interaction capacity according to claim 1 is characterized by: The actual maximum adjustable amount of the adjustable load is calculated by: Step 2-1 If the system has insufficient reserve in scenario i, the actual maximum adjustable amount of the adjustable load As follows: In the formula, They represent the maximum adjustable amount, actual value and predicted value of the adjustable load of scenario i respectively; Step 2-2 If the system has insufficient reserve in scenario i, the actual maximum adjustable amount of the adjustable load As follows:

4. The method for evaluating the confidence interval of key parameters of adjustable load interaction capacity according to claim 1 is characterized by: The correlation sets of the upper standby difference and lower standby difference scenarios are divided into grades according to the actual value of the adjustable load to form a set of upper standby difference scenarios and a set of lower standby difference scenarios; include: Step 3-1: The vector formed by the actual value of the adjustable load collected on the tth day in all the upper reserve difference scenarios is The vector formed by the actual maximum adjustable amount of the corresponding adjustable load is: And conduct correlation analysis. If the correlation coefficient r t If the absolute value is greater than η1 (>0), Each element in is included in the set S + middle; Step 3-2: The vector formed by the actual value of the adjustable load collected on the zth day in all the reserve difference scenarios is The vector formed by the actual maximum adjustable amount of the corresponding adjustable load is: And conduct correlation analysis. If the correlation coefficient r z If the absolute value is greater than η2 (>0), then Each element is included in the set S - middle; Among them, the correlation coefficient r t and r z The calculation formula is as follows: In the above formula, k represents the number of collections on the tth day in the upper reserve difference scenario, They represent the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load in the j-th upper reserve insufficient scenario on the t-th day, respectively. They represent the actual value of the adjustable load on the tth day and the average of the actual maximum adjustable amount of the adjustable load; q represents the number of collections on the zth day in the lower reserve difference scenario, They represent the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load in the j-th scenario with insufficient reserve on the z-th day, respectively. They represent the actual value of the adjustable load on the zth day and the average of the actual maximum adjustable amount of the adjustable load respectively.

5. The method for evaluating the confidence interval of key parameters of adjustable load interaction capacity according to claim 1 is characterized by: The Gaussian mixture distribution model is used to cluster each element in the upper standby difference scenario classification set and the lower standby difference scenario classification set to obtain a probability density function set of the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load, including: Step 4-1: The correlation set S of the backup difference scenario + The actual values ​​of the adjustable loads of all elements in are sorted from large to small, and the maximum load is The minimum load is make S + The actual value of the adjustable load is in the range Included in the subset but h=1,2,…,20; where: ΔL + is the step size of the adjustable load actual value in the upper reserve difference scenario, and h is the number of adjustable load actual value steps in the upper reserve difference scenario; Step 4-2: The correlation set S of the backup difference scenario - The actual values ​​of the adjustable loads of all elements in are sorted from large to small, and the maximum load is The minimum load is make S - The actual value of the adjustable load is in the range Included in the subset but h=1,2,…,20; where: ΔL - is the step size of the actual value of the load that can be adjusted in the lower reserve difference scenario, and h is the number of the actual value of the load that can be adjusted in the lower reserve difference scenario; Step 4-3 uses Gaussian mixture models based on diagonal, spherical, tied, and full covariance to classify the backup difference scenario into groups. And the next backup difference scenario classification set Each element in is clustered, the number of clusters is N1~N2 respectively, and the one with the smallest Bayesian information criterion score is taken as the clustering model of the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load; Step 4-4: Group the upper reserve difference scenarios into tiers And the next backup difference scenario classification set Substitute each element of into the following formula to form the probability density function set of the actual maximum adjustable amount of the adjustable load in the upper reserve difference scenario The probability density function set of the actual maximum adjustable amount of the adjustable load in the lower reserve difference scenario In the above formula, f(x) is the probability density function of the actual maximum adjustable amount of the adjustable load, and K is the optimal number of clusters; w t , μ t ,Σ t are the weight of the t-th category, the mean of the actual maximum adjustable amount of the adjustable load, and the variance of the actual maximum adjustable amount of the adjustable load; N(x|μ t ,Σ t )The probability density function of the t-th Gaussian distribution.

6. The method for evaluating the confidence interval of key parameters of adjustable load interaction capability according to claim 1 is characterized by: The method of calculating the confidence interval of the actual maximum adjustable amount of the adjustable load under a given confidence level for different adjustable load levels comprises the following steps: Step 5-1 If the current system output exceeds the reserve balance, proceed as follows: Step 5-1-1 Find the range to which the adjustable load forecast value belongs Where: The maximum load is The minimum load is ΔL + is the step size of the adjustable load actual value in the upper reserve difference scenario, and H is the number of adjustable load actual value steps in the upper reserve difference scenario; Step 5-1-2 From the probability density function set of the actual maximum adjustable amount of the adjustable load in the upper reserve difference scenario Find the corresponding probability density distribution function Step 5-1-3 Given a confidence level of α (0<α<1), calculate the confidence interval [M-σ,M+σ] using the following formula: in, w Hm , μ Hm , KH are The weight, mean, and optimal number of clusters of the mth class; Step 5-2 If the current system output is below the reserve balance, execute the following steps: Step 5-2-1 Find the range to which the adjustable load forecast value belongs Among them: the minimum load is ΔL - is the step size of the actual value of the load that can be adjusted in the lower reserve difference scenario, and T is the number of the actual value of the load that can be adjusted in the lower reserve difference scenario; Step 5-2-2 From the probability density function set of the actual maximum adjustable amount of adjustable load in the lower reserve difference scenario Find the corresponding probability density distribution function Step 5-2-3 Given a confidence level of β (0<β<1), calculate the confidence interval [N-β, N+β] using the following formula: in, w Tn and μ Tn , KT respectively The weight, mean, and optimal number of clusters of the nth class. dx represents the differential of the variable x.

7. A device for evaluating confidence intervals of key parameters of adjustable load interaction capability, characterized by: include: An acquisition module is used to acquire system reserve shortage scenarios based on historical prediction data, form a scenario set, and acquire the maximum adjustable amount of the adjustable load in the corresponding period, and acquire the active power response of the adjustable load in the corresponding period of the scenario set based on historical operation data; A generation module, used for calculating the actual maximum adjustable amount of the adjustable load for each scenario in the scenario set, performing correlation analysis on all scenarios of the upper reserve difference and the lower reserve difference, and generating a set with the actual value of the adjustable load and the actual maximum adjustable amount of the adjustable load as elements; A set forming module, used for classifying the correlation sets of the upper standby difference and the lower standby difference scenarios according to the actual value of the adjustable load, to form an upper standby difference scenario class set and a lower standby difference scenario class set; A clustering module, for clustering each element in the upper standby difference scenario grading set and the lower standby difference scenario grading set using a Gaussian mixture distribution model, to obtain a probability density function set of an actual value of the adjustable load and an actual maximum adjustable amount of the adjustable load; The calculation module is used to calculate the confidence interval of the actual maximum adjustable amount of the adjustable load under a given confidence level for different adjustable load levels.

8. The device for evaluating confidence intervals of key parameters of adjustable load interaction capability according to claim 7, characterized in that: The evaluation device is used to implement the steps of a confidence interval evaluation method for key parameters of adjustable load interaction capacity as described in any one of claims 1-6.

9. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the processor implements the steps of a method for evaluating confidence intervals of key parameters of adjustable load interaction capacity as described in any one of claims 1-6.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of a confidence interval evaluation method for key parameters of adjustable load interaction capacity as described in any one of claims 1 to 6.

Images