Data-driven dynamic capacity increasing method and system for power transmission line of power system

Abstract

The invention discloses a data-driven dynamic capacity increasing method for a power transmission line of a power system, and the method comprises the steps: obtaining the historical operation data and weather parameters of a transmission line, carrying out the variable selection of the historical operation data and weather parameters of the transmission line, and obtaining different variable groups; using a regression method to obtain a relationship between the different variable groups and the transmission line temperature, based on the relationship between the different variable groups and the transmission line temperature, obtaining a relational expression among the transmission line temperature, the lead load and the weather parameters, and constructing a transmission line regression model according to the relational expression; and calculating transmission line constraint parameters by using the transmission line regression model to obtain a dynamic transmission line constraint, and applying the dynamic transmission line constraint to a dynamic capacity-increasing model to obtain a first dynamic capacity-increasing model, thereby improving the mobility and practicability of the dynamic capacity-increasing model in the power system problem.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic capacity increase of lines, and in particular to a data-driven dynamic capacity increase method and system for power system transmission lines. Background Art

[0002] As the global energy transition accelerates, the large-scale integration of renewable energy generation has put forward higher requirements for the power system, especially in terms of flexibility and stability. To solve the transmission line congestion problem, the current solutions mainly include power flow control, power market participation regulation and other solutions, such as multi-port DC power flow controller based on MMC, continuous power flow model for renewable energy reactive power control, transmission management scheme based on the principle of consistency of responsibility and authority, and DC day-ahead transmission plan optimization model based on master-slave game. Although they have alleviated the congestion problem to a certain extent, they mainly rely on static transmission line capacity setting and fail to effectively utilize the dynamic capacity potential of transmission lines. To solve this problem, dynamic capacity expansion technology has begun to attract attention, such as methods and real-time simulation models for calculating the dynamic capacity of transmission lines based on physical parameters. These methods attempt to dynamically adjust the line capacity according to external conditions, but they have limitations such as relying on too many physical parameters and poor model mobility.

[0003] The data-driven dynamic capacity increase method of lines is worthy of exploration and research, mainly because it has the following significant advantages: the traditional method uses static transmission line capacity, which cannot fully adapt to the volatility of renewable energy generation, resulting in low line utilization. In contrast, the dynamic capacity increase model can adjust the transmission capacity of the transmission line in real time according to environmental conditions and system operation status, thereby improving the efficiency of new energy acceptance. Some dynamic capacity increase methods are highly dependent on the physical parameters of the transmission line, which limits the versatility and scope of application of the model, while the data-driven dynamic capacity increase method can use historical data and regression technology to predict the capacity of the transmission line, reduce direct dependence on physical parameters, and enhance the versatility and portability of the model. In addition, the dynamic capacity increase model based on the heat balance equation is difficult to be directly applied to other power system operation problems, while the data-driven dynamic capacity increase method of transmission lines can form closed constraints and is easy to migrate to the analysis and calculation of power system economic dispatch, optimal power flow and other problems. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the present invention solves the problem of power system transmission line congestion caused by the volatility of renewable energy power generation, especially wind power and solar energy, especially the problem that the traditional static line capacity allocation method cannot fully utilize the transmission line power transmission potential, affecting the efficient consumption of new energy.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a data-driven method for dynamically increasing the capacity of power transmission lines in a power system, comprising:

[0008] Acquire historical operation data and weather parameters of the transmission line, and perform variable selection on the historical operation data and weather parameters of the transmission line to obtain different variable groups;

[0009] Using a regression method to obtain the relationship between the different variable groups and the transmission line temperature, based on the relationship between the different variable groups and the transmission line temperature, obtaining a relationship between the transmission line temperature and the conductor load and the weather parameter, and constructing a transmission line regression model according to the relationship;

[0010] The transmission line constraint parameters are calculated using the transmission line regression model to obtain dynamic transmission line constraints, and the dynamic transmission line constraints are applied to a dynamic capacity increase model to obtain a first dynamic capacity increase model.

[0011] As a preferred solution of the data-driven method for dynamic capacity expansion of power system transmission lines of the present invention, the relationship between the different variable groups and the transmission line temperature is obtained by using a regression method, which includes:

[0012] The super quantile regression method is used to obtain the distribution characteristics of random variables in the historical operation data of transmission lines;

[0013] The α-quantile function of the continuous random variable in the historical operation data of the transmission line is defined as: the specific value of the cumulative distribution function in the random variable must be greater than or equal to the value of α, or the value of the inverse function of the cumulative distribution function of the specific value in the random variable at α, where α is the super quantile level of the random variable;

[0014] The tail expectation of the α-quantile function of a random variable is defined as: the expected value when the random variable takes a value greater than or equal to the α-quantile of the random variable;

[0015] The expected value is: integrate the α-quantile function from α to 1, divided by 1-α;

[0016] The α-superquantile used to estimate the random variable is that, under known conditions, the tail expectation of the α-quantile function of the random variable is equal to the product of the known conditions and the corresponding parameter vector.

[0017] As a preferred solution of the data-driven method for dynamic capacity increase of power system transmission lines of the present invention, the parameter vector includes:

[0018] The objective function of ridge regression is defined as adding a regularization term to the least squares loss function to obtain the objective function of ridge regression of the parameter vector;

[0019] Derivative the objective function to obtain the normal equation, and solve the normal equation to obtain the relational expression of the parameter vector containing the regularization parameter;

[0020] Set the search range of the regularization parameter. Within the set range, create a grid of regularization parameters and divide the data set into K parts for K-fold cross validation.

[0021] Use all data except one fold to train the ridge regression model. For each regularization parameter, repeat the process K times, selecting a different fold to train the ridge regression model each time.

[0022] For each regularization parameter, the average of the model performance of K validations is calculated, the optimal regularization parameter is selected from the grid, and the optimal parameter vector is calculated.

[0023] As a preferred solution of the data-driven method for dynamic capacity increase of power system transmission lines of the present invention, the relationship between the transmission line temperature, the conductor load and the weather parameter includes:

[0024] The input vector of the transmission line regression model consists of weather parameters, including wind speed, wind direction angle, ambient temperature, solar radiation, and conductor temperature. The input vector is expressed as:

[0025]

[0026] Among them, W s is the wind speed, W a is the wind direction angle, T a is the ambient temperature, Q s is solar radiation, W s ·W a is the column vector obtained by multiplying wind speed and wind direction angle, W s ·T a is the column vector obtained by multiplying wind speed and ambient temperature, W s Q s is the column vector obtained by multiplying wind speed and solar radiation, W a ·T a is the column vector obtained by multiplying the wind direction angle and the ambient temperature, W a Q s The column vector obtained by multiplying the wind direction angle and the solar radiation, T a Q s is the column vector obtained by multiplying the ambient temperature and the solar radiation, J 2 , J, W s , W a , T a , Q s are all row vectors, J 2 , J is the quadratic term of the conductor current and the conductor current.

[0027] As a preferred solution of the data-driven power system transmission line dynamic capacity increase method described in the present invention, it also includes:

[0028] The conductor current and quadratic terms, wind speed, wind direction angle, ambient temperature and solar radiation in the k periods before the current period are expressed as:

[0029]

[0030] J=[I t-1 , ..., I t-k ]

[0031] W s =[W s，t-1 , ..., W s，t-k ]

[0032] W a =[W a，t-1 , ..., W a，t-k ]

[0033] T a =[T a，t-1 , ..., T a，t-k ]

[0034] Q s =[Q s，t-1 , ..., Q s，t-k ]

[0035] Among them, I t is the wire temperature.

[0036] As a preferred solution of the data-driven method for dynamic capacity increase of power system transmission lines of the present invention, wherein: constructing a transmission line regression model according to the relationship includes:

[0037] For a given risk wind turbine, the relationship between past weather parameters and conductor current data is used as the input vector, and the measured actual conductor temperature value is used as the regression target to calculate the transmission line regression model parameters;

[0038] The input vector is constructed by using the future prediction related data and substituted into the model for estimating the α-superquantile of the random variable to obtain the predicted α-superquantile of the transmission line temperature;

[0039] According to the predicted α-superquantile of the transmission line temperature, the transmission line superquantile regression model is obtained as follows: The baseline temperature under a given risk level plus the square of the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding quadratic term coefficient plus the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding linear term coefficient plus the sum of the transmission line in the scenario from tk to t-1 related to the weather parameters, where the transmission line belongs to the transmission line set and all scenarios belong to the scenario set.

[0040] As a preferred solution of the data-driven dynamic capacity increase method for power system transmission lines of the present invention, the first dynamic capacity increase model includes:

[0041] The dynamic transmission line constraint is embedded in the unit combination model, and the first dynamic capacity increase model is obtained as follows: the base temperature under a given risk level plus the square of the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding quadratic term coefficient plus the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding linear term coefficient plus the sum of the transmission line in the scenario from tk to t-1 related to the weather parameters is less than or equal to the temperature threshold set for the conductor;

[0042] in, Transmission lines belong to the Transmission Lines collection, and all scenes belong to the Scenes collection.

[0043] In a second aspect, the present invention provides a data-driven system for dynamic capacity expansion of power system transmission lines, comprising:

[0044] A selection module, used for acquiring historical operation data of the transmission line and weather parameters, and performing variable selection on the historical operation data of the transmission line and weather parameters to obtain different variable groups;

[0045] A model building module, used to obtain the relationship between the different variable groups and the transmission line temperature by using a regression method, obtain a relationship between the transmission line temperature and the conductor load and the weather parameter based on the relationship between the different variable groups and the transmission line temperature, and build a transmission line regression model according to the relationship;

[0046] The calculation module is used to calculate the transmission line constraint parameters by using the transmission line regression model to obtain dynamic transmission line constraints, and apply the dynamic transmission line constraints to the dynamic capacity increase model to obtain a first dynamic capacity increase model.

[0047] In a third aspect, the present invention provides a computing device, comprising:

[0048] Memory and processor;

[0049] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the data-driven power system transmission line dynamic capacity increase method are implemented.

[0050] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the data-driven method for dynamic capacity expansion of power system transmission lines.

[0051] Beneficial effects of the invention: The data-driven dynamic capacity expansion method for power system transmission lines proposed in the invention has good feasibility and reliability, can calculate the real-time capacity of transmission lines in combination with weather parameters, and effectively realize the capacity expansion of transmission lines. At the same time, it also provides a reference theory for power system calculation and analysis problems, and improves the portability and practicality of the dynamic capacity expansion model in power system problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0053] Figure 1 The present invention provides an overall flow chart of a data-driven method for dynamically increasing the capacity of power system transmission lines. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0055] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0056] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0057] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0058] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0059] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0060] Example 1

[0061] Reference Figure 1 , is an embodiment of the present invention, and provides a data-driven method for dynamically increasing the capacity of power system transmission lines, comprising:

[0062] S100: Acquire historical operation data and weather parameters of the transmission line, and perform variable selection on the historical operation data and weather parameters of the transmission line to obtain different variable groups;

[0063] Specifically, the variables selected from the historical operation data of the transmission line and the weather parameters are wind speed, wind direction angle, ambient temperature, solar radiation and conductor temperature, and humidity, air pressure, rainfall, etc. can also be selected;

[0064] It should be noted that the preferred variables have a direct physical connection with the temperature and transmission capacity of the transmission line. Through historical data and regression technology, the statistical relationship between these variables and the temperature of the transmission line can be found, thereby providing input parameters for the dynamic capacity increase model. By considering these variables, the thermal constraints of the transmission line under different environmental conditions can be more accurately predicted, and the transmission capacity of the transmission line can be dynamically adjusted to reduce the risk of line blocking and improve line utilization. If other variables are considered, the impact of other variables on the temperature of the transmission line is small. Introducing more variables will increase the complexity of the model, leading to overfitting, and increase the demand for computing resources.

[0065] S200: using a regression method to obtain the relationship between different variable groups and the transmission line temperature, based on the relationship between the different variable groups and the transmission line temperature, obtaining a relationship between the transmission line temperature and the conductor load and weather parameters, and constructing a transmission line regression model according to the relationship;

[0066] In the embodiment of the present application, the super quantile regression method is used to obtain the distribution characteristics of random variables in the historical operation data of the transmission line;

[0067] The α-quantile function of the continuous random variable in the historical operation data of the transmission line is defined as: the specific value of the cumulative distribution function in the random variable must be greater than or equal to the value of α, or the value of the inverse function of the cumulative distribution function of the specific value in the random variable at α, where α is the super quantile level of the random variable;

[0068] The tail expectation of the α-quantile function of a random variable is defined as: the expected value when the random variable takes a value greater than or equal to the α-quantile of the random variable;

[0069] The expected value is: integrate the α-quantile function from α to 1, divided by 1-α;

[0070] The α-superquantile used to estimate the random variable is that, under known conditions, the tail expectation of the α-quantile function of the random variable is equal to the product of the known conditions and the corresponding parameter vector.

[0071] Specifically, the α-quantile function of the continuous random variable in the historical operation data of the transmission line is defined as: Among them, F y , is the cumulative distribution function and its inverse function, Q α (y) is the α-superquantile of the random variable y, z is a specific value in the random variable, α is a value between 0 and 1, and is the superquantile rank of the random variable;

[0072] The α-superquantile function of a random variable is defined as its tail expectation, expressed as:

[0073]

[0074] The superquantile regression model is used to estimate the α-superquantile of the random variable y, expressed as:

[0075]

[0076] in, is the conditional expected value of the random variable y under the condition that scenario s exceeds its α-superquantile, y α is the estimated α-superquantile, x T is the transpose of the conditional vector, β α is the model parameter vector.

[0077] In the embodiment of the present application, the objective function of the ridge regression is defined as adding a regularization term on the basis of the least squares loss function to obtain the objective function of the ridge regression of the parameter vector;

[0078] Derivative the objective function to obtain the normal equation, and solve the normal equation to obtain the relational expression of the parameter vector containing the regularization parameter;

[0079] Set the search range of the regularization parameter. Within the set range, create a grid of regularization parameters and divide the data set into K parts for K-fold cross validation.

[0080] Use all data except one fold to train the ridge regression model. For each regularization parameter, repeat the process K times, selecting a different fold to train the ridge regression model each time.

[0081] For each regularization parameter, the average of the model performance of K validations is calculated, the optimal regularization parameter is selected from the grid, and the optimal parameter vector is calculated.

[0082] Specifically, the parameter vector is obtained by combining ridge regression with cross validation. The parameter vector can also be obtained by using least squares method, support vector machine regression and particle swarm optimization.

[0083] It should be noted that ridge regression reduces model complexity by adding regularization terms, which helps prevent overfitting and has good robustness to noise and outliers in the data. K-fold cross validation can evaluate model performance on different data subsets and select the optimal regularization parameter, thereby improving the generalization ability of the model on unknown data. If other optimization methods are used, the least squares method does not contain regularization, which is prone to overfitting when the number of features is greater than the number of samples. Support vector machine regression has high computational cost, and particle swarm optimization requires multiple iterations to find a suitable solution, which has high computational cost. The combination of ridge regression and K-fold cross validation is for model parameter estimation, which helps to build a superior and reliable prediction model.

[0084] In the embodiment of the present application, the input vector of the transmission line regression model is composed of weather parameters, including wind speed, wind direction angle, ambient temperature, solar radiation and conductor temperature. The input vector is expressed as:

[0085]

[0086] Among them, W s is the wind speed, W a is the wind direction angle, T a is the ambient temperature, Q s is solar radiation, W s ·W a is the column vector obtained by multiplying wind speed and wind direction angle, W s ·T a is the column vector obtained by multiplying wind speed and ambient temperature, W s Q s is the column vector obtained by multiplying wind speed and solar radiation, W a ·T a is the column vector obtained by multiplying the wind direction angle and the ambient temperature, W a Q s The column vector obtained by multiplying the wind direction angle and the solar radiation, T a Q s is the column vector obtained by multiplying the ambient temperature and the solar radiation, J 2 , J, W s , W a , T a , Q s are all row vectors, J 2 , J is the quadratic term of the conductor current and the conductor current.

[0087] The conductor current and quadratic terms, wind speed, wind direction angle, ambient temperature and solar radiation in the k periods before the current period are expressed as:

[0088]

[0089] J=[I t-1 , ..., I t-k ]

[0090] W s =[W s，t-1 , ..., W s，t-k ]

[0091] W a =[W a，t-1 , ..., W a，t-k ]

[0092] T a =[T a，t-1 , ..., T a，t-k ]

[0093] Q s =[Q s，t-1 , ..., Q s，t-k ]

[0094] Among them, I t is the wire temperature.

[0095] Specifically, in the modeling process, a super quantile regression model is used to quantify the characteristics of conductor temperature changes over time. The super quantile regression model predicts the α-super quantile of the conductor temperature in time period t based on the input environmental parameter vector of the first k time periods.

[0096] It should be noted that the cross product term of the two vectors can better obtain the dependency between the input parameters and analyze the comprehensive impact of environmental parameters on the transmission line temperature;

[0097] In the embodiment of the present application, for a given risk wind turbine, a relational expression constructed based on past weather parameters and conductor current data is used as an input vector, and the measured actual conductor temperature value is used as a regression target to calculate the transmission line regression model parameters;

[0098] The input vector is constructed by using the future prediction related data and substituted into the model for estimating the α-superquantile of the random variable to obtain the predicted α-superquantile of the transmission line temperature;

[0099] According to the predicted α-superquantile of the transmission line temperature, the transmission line superquantile regression model is obtained as follows: The baseline temperature under a given risk level plus the square of the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding quadratic term coefficient plus the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding linear term coefficient plus the sum of the transmission line in the scenario from tk to t-1 related to the weather parameters, where the transmission line belongs to the transmission line set and all scenarios belong to the scenario set.

[0100] Specifically, the estimated α-superquantile of the wire temperature at time t It is expressed as:

[0101]

[0102] Based on a given risk level α, after using the regression model to calculate the model parameters, the super quantile regression model is expressed as:

[0103]

[0104] Among them, I t-j is the transmission line current during the tj period, They are the constant term, linear term and quadratic term coefficients corresponding to time period tj under the α risk level in the model, F t-j is the predicted weather-related parameters for the period tj, Lined is the set of transmission lines considering dynamic capacity increase, s is the scenario, and k is the number of coupling periods.

[0105] It should be noted that the estimated α-superquantile of the wire temperature at time t It can be seen that the transmission temperature is not only related to the current passing through the transmission line in the current period, but also related to the current in the previous periods, reflecting the characteristics of the coupling between the heat capacity of the conductor and time and the environment. The super quantile regression model describes the dynamic functional relationship between the current and temperature of the transmission line in the current and previous periods.

[0106] S300: Calculate transmission line constraint parameters using a transmission line regression model to obtain dynamic transmission line constraints, and apply the dynamic transmission line constraints to a dynamic capacity increase model to obtain a first dynamic capacity increase model;

[0107] In the embodiment of the present application, the dynamic transmission line constraint is embedded in the unit combination model, and the first dynamic capacity increase model is obtained as follows: the base temperature under a given risk level plus the square of the current of the transmission line in the scenario from tk to t-1 period multiplied by the corresponding quadratic term coefficient plus the current of the transmission line in the scenario from tk to t-1 period multiplied by the corresponding linear term coefficient plus the sum of the transmission line in the scenario from tk to t-1 period related to the weather parameter is less than or equal to the temperature threshold set for the conductor;

[0108] in, Transmission lines belong to the Transmission Lines collection, and all scenes belong to the Scenes collection.

[0109] Specifically, based on the dynamic capacity increase model that has been obtained, it is modified into a dynamic transmission line constraint and embedded into the unit commitment model. The dynamic capacity increase model is modified to be expressed as:

[0110]

[0111] in, Set the temperature threshold for wire l.

[0112] It should be noted that the temperature threshold of conductor l is set. By analyzing the historical operation data, the actual temperature performance of the conductor under different conditions can be understood, which provides a basis for setting the temperature threshold. The inequality is a quadratic convex constraint and can be easily embedded in other power system optimization problems.

[0113] The above is a schematic scheme of a data-driven method for dynamic capacity expansion of power system transmission lines in this embodiment. It should be noted that the technical scheme of the data-driven device for dynamic capacity expansion of power system transmission lines and the technical scheme of the data-driven method for dynamic capacity expansion of power system transmission lines belong to the same concept, and the details of the technical scheme of the data-driven device for dynamic capacity expansion of power system transmission lines in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the data-driven method for dynamic capacity expansion of power system transmission lines.

[0114] The data-driven device for dynamically increasing the capacity of power transmission lines in the power system in this embodiment includes:

[0115] A selection module, used for acquiring historical operation data of the transmission line and weather parameters, and performing variable selection on the historical operation data of the transmission line and weather parameters to obtain different variable groups;

[0116] A model building module, used to obtain the relationship between the different variable groups and the transmission line temperature by using a regression method, obtain a relationship between the transmission line temperature and the conductor load and the weather parameter based on the relationship between the different variable groups and the transmission line temperature, and build a transmission line regression model according to the relationship;

[0117] The calculation module is used to calculate the transmission line constraint parameters by using the transmission line regression model to obtain dynamic transmission line constraints, and apply the dynamic transmission line constraints to the dynamic capacity increase model to obtain a first dynamic capacity increase model.

[0118] This embodiment further provides a computing device, which is applicable to data-driven dynamic capacity increase of power system transmission lines, including:

[0119] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the data-driven dynamic capacity increase method for power system transmission lines proposed in the above embodiment.

[0120] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing data-driven dynamic capacity increase of power system transmission lines as proposed in the above embodiment is implemented.

[0121] The storage medium proposed in this embodiment and the method for realizing data-driven dynamic capacity expansion of power system transmission lines proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0122] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0123] Example 2

[0124] Referring to Table 1, which is an embodiment of the present invention, a data-driven method for dynamic capacity increase of power system transmission lines is provided to verify and illustrate the technical effects adopted in the method.

[0125] Verify the capacity increase effect of the dynamic capacity increase model on the transmission line, use the first dynamic capacity increase model to build a dynamic transmission line constraint, and embed it into the power system unit combination model, modify the temperature upper limit of the first dynamic capacity increase model, and obtain the results shown in Table 1;

[0126] Table 1 Calculation results of unit combination at different temperatures

[0127]

[0128] Among them, T max 、f val ,∑P line , n represent the maximum transmission line temperature setting value, the calculated operating cost, the total power of the transmission line in each period and the total number of periods when the transmission line load exceeds the static constraint capacity respectively;

[0129] As can be seen from the table above, as the maximum transmission line temperature setting increases from 75°C to 100°C, the system operating cost gradually decreases from $2,142,780.7 to $2,132,563.4, indicating that a lower-cost operating method can be found when a higher transmission line temperature is allowed;

[0130] As the maximum transmission line temperature setting increases, the total load of the transmission line also increases successively, from 173515.9MW to 176603.7MW, indicating that at higher temperature settings, the transmission line can carry more power, thereby improving the power transmission capacity of the power system;

[0131] At the same time, as the maximum transmission line temperature setting value increases from 75℃ to 85℃, the number of blocking periods increases from 3 to 44, indicating that the increase in temperature setting significantly reduces the blocking of the transmission line. Then, when the maximum transmission line temperature setting value continues to increase from 85℃ to 100℃, the number of blocking periods remains unchanged, indicating that the capacity increase potential of the transmission line is close to saturation above 85℃.

[0132] The system operating cost obtained by the unit combination model using static transmission line constraints is $2,139,302, and the total power of the transmission line in each period is 175,411.41 MW. It can be seen that the system operating cost of the unit combination model using dynamic capacity expansion is lower and the transmission line capacity is larger. The dynamic capacity expansion model can significantly increase the line capacity and reduce line congestion.

[0133] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A data-driven method for dynamic capacity expansion of power system transmission lines, characterized in that: include: Acquire historical operation data and weather parameters of the transmission line, and perform variable selection on the historical operation data and weather parameters of the transmission line to obtain different variable groups; Using a regression method to obtain the relationship between the different variable groups and the transmission line temperature, based on the relationship between the different variable groups and the transmission line temperature, obtaining a relationship between the transmission line temperature and the conductor load and the weather parameter, and constructing a transmission line regression model according to the relationship; The transmission line constraint parameters are calculated using the transmission line regression model to obtain dynamic transmission line constraints, and the dynamic transmission line constraints are applied to a dynamic capacity increase model to obtain a first dynamic capacity increase model.

2. The data-driven method for dynamic capacity expansion of power system transmission lines according to claim 1, characterized in that: The relationship between the different variable groups and the transmission line temperature obtained by using the regression method includes: The super quantile regression method is used to obtain the distribution characteristics of random variables in the historical operation data of transmission lines; The α-quantile function of the continuous random variable in the historical operation data of the transmission line is defined as: the specific value of the cumulative distribution function in the random variable must be greater than or equal to the value of α, or the value of the inverse function of the cumulative distribution function of the specific value in the random variable at α, where α is the super quantile level of the random variable; The tail expectation of the α-quantile function of a random variable is defined as: the expected value when the random variable takes a value greater than or equal to the α-quantile of the random variable; The expected value is: integrate the α-quantile function from α to 1, divided by 1-α; The α-superquantile used to estimate the random variable is that, under known conditions, the tail expectation of the α-quantile function of the random variable is equal to the product of the known conditions and the corresponding parameter vector.

3. The data-driven method for dynamic capacity expansion of power system transmission lines according to claim 2, characterized in that: The parameter vector includes: The objective function of ridge regression is defined as adding a regularization term to the least squares loss function to obtain the objective function of ridge regression of the parameter vector; Derivative the objective function to obtain the normal equation, and solve the normal equation to obtain the relational expression of the parameter vector containing the regularization parameter; Set the search range of the regularization parameter. Within the set range, create a grid of regularization parameters and divide the data set into K parts for K-fold cross validation. Use all data except one fold to train the ridge regression model. For each regularization parameter, repeat the process K times, selecting a different fold to train the ridge regression model each time. For each regularization parameter, the average of the model performance of K validations is calculated, the optimal regularization parameter is selected from the grid, and the optimal parameter vector is calculated.

4. The data-driven method for dynamic capacity expansion of power system transmission lines as claimed in claim 2 or 3, characterized in that: The relationship between the transmission line temperature and the conductor load and the weather parameters includes: The input vector of the transmission line regression model consists of weather parameters, including wind speed, wind direction angle, ambient temperature, solar radiation, and conductor temperature. The input vector is expressed as: Among them, W s is the wind speed, W a is the wind direction angle, T a is the ambient temperature, Q s is solar radiation, W s ·W a is the column vector obtained by multiplying wind speed and wind direction angle, W s ·T a is the column vector obtained by multiplying wind speed and ambient temperature, W s Q s is the column vector obtained by multiplying wind speed and solar radiation, W a ·T a is the column vector obtained by multiplying the wind direction angle and the ambient temperature, W a Q s The column vector obtained by multiplying the wind direction angle and the solar radiation, T a Q s is the column vector obtained by multiplying the ambient temperature and the solar radiation, J 2 ,J,W s ,W a ,T a ,Q s are all row vectors, J 2 , J is the quadratic term of the conductor current and the conductor current.

5. The data-driven method for dynamic capacity expansion of power system transmission lines according to claim 4, characterized in that: Also includes: The conductor current and quadratic terms, wind speed, wind direction angle, ambient temperature and solar radiation in the k periods before the current period are expressed as: J=[I t-1 ,...,I t-k ] IN s =[W s,t-1 ,...,IN s,t-k ] IN a =[W a,t-1 ,...,IN a,t-k ] T a =[T a,t-1 ,...,T a,t-k ] Q s =[Q s,t-1 ,...,Q s,t-k ] Among them, I t is the wire temperature.

6. The data-driven method for dynamic capacity expansion of power system transmission lines as claimed in claim 5, characterized in that: Constructing a transmission line regression model according to the relationship includes: For a given risk wind turbine, the relationship between past weather parameters and conductor current data is used as the input vector, and the measured actual conductor temperature value is used as the regression target to calculate the transmission line regression model parameters; The input vector is constructed by using the future prediction related data and substituted into the model for estimating the α-superquantile of the random variable to obtain the predicted α-superquantile of the transmission line temperature; According to the predicted α-superquantile of the transmission line temperature, the transmission line superquantile regression model is obtained as follows: The baseline temperature under a given risk level plus the square of the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding quadratic term coefficient plus the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding linear term coefficient plus the sum of the transmission line in the scenario from tk to t-1 related to the weather parameters, where the transmission line belongs to the transmission line set and all scenarios belong to the scenario set.

7. The data-driven method for dynamic capacity expansion of power system transmission lines according to claim 6, characterized in that: The first dynamic capacity expansion model includes: The dynamic transmission line constraint is embedded in the unit combination model, and the first dynamic capacity increase model is obtained as follows: the base temperature under a given risk level plus the square of the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding quadratic term coefficient plus the current of the transmission line in the scenario from tk to t-1 multiplied by the corresponding linear term coefficient plus the sum of the transmission line in the scenario from tk to t-1 related to the weather parameters is less than or equal to the temperature threshold set for the conductor; in, Transmission lines belong to the Transmission Lines collection, and all scenes belong to the Scenes collection.

8. A data-driven system for a method for dynamically increasing the capacity of power transmission lines in a power system, characterized in that: include: A selection module, used for obtaining historical operation data of the transmission line and weather parameters, and performing variable selection on the historical operation data of the transmission line and weather parameters to obtain different variable groups; A model building module, used to obtain the relationship between the different variable groups and the transmission line temperature by using a regression method, obtain a relationship between the transmission line temperature and the conductor load and the weather parameter based on the relationship between the different variable groups and the transmission line temperature, and build a transmission line regression model according to the relationship; The calculation module is used to calculate the transmission line constraint parameters by using the transmission line regression model to obtain dynamic transmission line constraints, and apply the dynamic transmission line constraints to the dynamic capacity increase model to obtain a first dynamic capacity increase model.

9. An electronic device, characterized in that: The device comprises: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 7.

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

Images