Connection line branch plan generation method and system, electronic device and storage medium

Abstract

This invention discloses a method, system, electronic device, and storage medium for generating tie-line branching plans, belonging to the technical field of power spot market clearing plans. The method includes: generating a set of typical tie-line branching plans based on historical power system operating data clustering; calculating the distance between the predicted scenario and the centroid of each cluster using the provincial power grid sub-plans given in the clearing plan and the predicted load of each region as feature quantities, and matching the predicted scenario to the cluster with the smallest distance; formulating an initial tie-line branching plan based on the tie-line branching plans of the matched clusters; correcting the initial tie-line branching plan to ensure that the deviation between the power exchange power between the power system and the outside world and the initial tie-line branching plan is less than a set value; and outputting the corrected tie-line branching plan's actual operating scheme. This invention adds a tie-line branching plan correction step to avoid large errors between the operating scheme and actual operating conditions.

Description

Technical Field

[0001] This invention belongs to the technical field of electricity spot market clearing plans, specifically relating to a method, system, electronic device, and storage medium for generating tie-line branching plans. Background Technology

[0002] Most existing electricity spot markets target provincial power grids. To verify the safety and economic viability of clearing plans, it is necessary to simulate and analyze various possible operating modes based on the clearing plan. This requires determining the injected power of the provincial power grid's external interconnection lines, i.e., the interconnection line allocation plan. Interconnection lines are lines that transmit power between power grids. The sum of the interconnection line power is the "port plan," which is formed through electricity market transactions and then allocated to each interconnection line to form the interconnection line allocation plan. Clearing plans generally only provide the total exchange power between the provincial power grid and external power grids based on power balance constraints, i.e., the port plan. However, how to decompose the port plan into interconnection line allocation plans to better reflect the actual operating state of the system is a problem that needs further research. Existing technologies generally do not consider fluctuations in operating scenarios and often allocate the port plan among interconnection lines at a fixed ratio based on the rated transmission capacity of each interconnection line.

[0003] Since the exact values ​​of renewable energy output and load cannot be known when the spot market clears, the transmission power of each tie line can generally only be predicted based on historical operating data or experience. Existing tie line distribution plans are often generated by allocating the plans among the tie lines according to a fixed ratio. However, considering the complexity of the power system and the diversity of operating scenarios, the tie line distribution plans generated based on a fixed ratio using existing technology often deviate significantly from the actual operating conditions. Therefore, how to generate tie line distribution plans quickly and accurately is an important problem facing the electricity spot market. Summary of the Invention

[0004] The purpose of this invention is to address the problems in the prior art by providing a tie-line branching plan generation method, system, electronic device, and storage medium. This invention considers fluctuations in actual operating conditions, adds a tie-line branching plan correction step, avoids large errors between the operating plan and actual operating conditions, and improves the safety and economy of the power system.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] Firstly, a method for generating a tie-line branching plan is provided, including:

[0007] A set of typical tie-line branching plans is generated by clustering historical power system operation data.

[0008] Based on the generated typical tie-line branching plan set, using the provincial power grid sub-plans given by the clearing plan and the predicted load of each region as feature quantities, the distance between the predicted scenario and the centroid of each cluster is calculated, and the predicted scenario is matched to the cluster with the smallest distance. Based on the tie-line branching plan of the matched cluster, the initial tie-line branching plan is formulated.

[0009] Furthermore, the tie-line branching plan generation method of the present invention also includes a step of correcting the initial tie-line branching plan, so that the deviation between the power exchange between the power system and the outside world and the initial tie-line branching plan is less than a set value, and outputting the corrected tie-line branching plan actual operation scheme.

[0010] Furthermore, the tie-line branching plan generation method of the present invention also includes the step of acquiring the power system topology, parameters, and historical operating data. Specifically, the acquired data includes: the composition of the external tie-lines of the provincial power grid under study and the adjustable generators of the external system; and the branching plan P of the provincial power grid under study. tot The proposed branching plan for the provincial power grid interconnection lines (P) needs further study. t,j j = 1, ..., N t N t Number of tie lines; load P in each region L,k k = 1, ..., N L N L The number of regional loads included in the provincial power grid; the power P of each adjustable generator unit. g,i upper limit lower limit P g,i i = 1, ..., N g N g The number of adjustable generators; the maximum permissible power offset for each tie line. The maximum value of the total adjustable power of the adjustable generator

[0011] As a preferred embodiment of the tie-line branching plan generation method of the present invention, the step of generating a typical tie-line branching plan set based on historical power system operating data clustering specifically includes:

[0012] The provincial power grid interconnection line branching plan is set as follows: Load in each region The provincial power grid interconnection data is X = (P tot ,P t ,P L ), X is N e dimensional vector, N e =N t +N L +1, the resulting historical data is X. (s) =(P tot(s) ,P t (s) ,P L (s) ), s=1,…,N s N s Let X be the number of samples; normalize the sample data X, where θ is the normalization variable for X, and the m-th element of θ is:

[0013]

[0014] In the formula, m = 1, ..., N e After normalization, the variation of the sample data is limited to the range of [0,1].

[0015] Let the historical data of the samples be respectively The normalized variables are Define the distance between two samples as The K-means clustering method was used to cluster all sample data into N groups. C Clusters, from N s N samples were randomly selected. C N samples, as N C Clusters initial mass center For sample X (s) s=1,…,N s Calculate its relationship with the centroid μ of each cluster. j j = 1, 2, ..., N C Distance between ||X (s) -μ j ||, X (s) Assign it to the cluster of the centroid with the smallest distance, and recalculate the C of each cluster. j j = 1, 2, ..., N C center of mass For cluster C j The number of samples included; the clusters are re-divided based on the calculated centroid vectors, and this process is iterated until the clusters and their centroids no longer change; the output consists of N. C The centroid μ of each cluster j j = 1, 2, ..., N C The typical set of connection line sub-plans represented by this.

[0016] As a preferred embodiment of the tie-line branching plan generation method of the present invention, in the step of correcting the initial tie-line branching plan, a mathematical model of the tie-line branching plan correction problem is constructed based on the actual scenario, and the initial tie-line branching plan is corrected by the mathematical model of the tie-line branching plan correction problem.

[0017] The mathematical model expression for the tie-line branching plan correction problem is as follows:

[0018]

[0019] Where F is the objective function, used to coordinate the generator correction amount and the deviation of the tie line branching plan; ΔP g,i ΔP is the correction amount for the output of the adjustable generator set. t,j Let P be the power deviation of tie line j; M is the penalty factor for tie line power deviation; constraints include the upper limit of tie line power deviation, the upper limit of total generator regulation, and the constraint on generator output power. g,i,0 P t,j,0 Generator set G before correction i and the power of the connecting line j; S ji G represents the adjustable generator set i The sensitivity of the output to the power transmitted through tie line j is calculated using the following formula: P t,j,ref The transmission power of the tie line j as specified in the clearing plan.

[0020] As a preferred embodiment of the tie-line branching plan generation method of the present invention, in the step of correcting the initial tie-line branching plan, the mathematical model of the tie-line branching plan correction problem is solved, and the constraint equations related to tie-line power deviation are approximated as linear equations through sensitivity. In the k-th iteration, let... And recalculate the sensitivity S ji The parameters of the mathematical model for the tie-line branching plan correction problem are updated; this process is iterated until the maximum unit correction value is less than the set threshold ε, expressed as: When the connection converges, the correction scheme and the actual operation scheme of the corrected tie line branching plan are obtained.

[0021] Secondly, a tie-line branching plan generation system is provided, comprising:

[0022] The typical tie-line branch plan generation module is used to generate a typical tie-line branch plan based on the clustering of historical power system operation data;

[0023] The tie-line branch initial plan formulation module is used to calculate the distance between the predicted scenario and the centroid of each cluster based on the generated typical tie-line branch plan set, using the provincial power grid sub-plan given by the clearing plan and the predicted load of each region as feature quantities, and match the predicted scenario to the cluster with the smallest distance. Based on the tie-line branch plan of the matched cluster, the initial tie-line branch plan is formulated.

[0024] Furthermore, the tie-line branching plan generation system of the present invention also includes a tie-line branching initial plan correction module, which is used to correct the tie-line branching initial plan so that the deviation between the power exchange between the power system and the outside world and the tie-line branching initial plan is less than a set value, and outputs the corrected tie-line branching plan actual operation scheme.

[0025] Furthermore, the tie-line branching plan generation system of the present invention also includes a power system information acquisition module, used for acquiring power system topology, parameters and historical operating data;

[0026] The power system information acquisition module specifically acquires the following: the external interconnection lines of the provincial power grid to be studied and the composition of adjustable generators in the external system; and the sub-plan P of the provincial power grid to be studied. tot The proposed branching plan for the provincial power grid interconnection lines (P) needs further study. t,j j = 1, ..., N t N t Number of tie lines; load P in each region L,k k = 1, ..., N L N L The number of regional loads included in the provincial power grid; the power P of each adjustable generator unit. g,i upper limit lower limit P g,i i = 1, ..., N g N g The number of adjustable generators; the maximum permissible power offset for each tie line. The maximum value of the total adjustable power of the adjustable generator

[0027] As a preferred embodiment of the tie-line branching plan generation system of the present invention, the typical tie-line branching plan set generation module sets the provincial power grid tie-line branching plan as follows: Load in each region The provincial power grid interconnection data is X = (P tot ,P t ,P L ), X is N e dimensional vector, N e =N t +N L +1, the resulting historical data is X. (s) =(P tot (s) ,P t (s) ,P L (s) ), s=1,…,N s N sLet X be the number of samples; normalize the sample data X, where θ is the normalization variable for X, and the m-th element of θ is:

[0028]

[0029] In the formula, m = 1, ..., N e After normalization, the variation of the sample data is limited to the range of [0,1].

[0030] Let the historical data of the samples be respectively The normalized variables are Define the distance between two samples as The K-means clustering method was used to cluster all sample data into N groups. C Clusters, from N s N samples were randomly selected. C N samples, as N C Clusters initial mass center For sample X (s) s=1,…,N s Calculate its relationship with the centroid μ of each cluster. j j = 1, 2, ..., N C Distance between ||X (s) -μ j ||, X (s) Assign it to the cluster of the centroid with the smallest distance, and recalculate the C of each cluster. j j = 1, 2, ..., N C center of mass For cluster C j The number of samples included; the clusters are re-divided based on the calculated centroid vectors, and this process is iterated until the clusters and their centroids no longer change; the output consists of N. C The centroid μ of each cluster j j = 1, 2, ..., N C The typical set of connection line sub-plans represented by this.

[0031] As a preferred embodiment of the tie-line branching plan generation system of the present invention, the tie-line branching initial plan correction module constructs a mathematical model of the tie-line branching plan correction problem based on the actual scenario, and corrects the tie-line branching initial plan through the mathematical model of the tie-line branching plan correction problem;

[0032] The mathematical model expression for the tie-line branching plan correction problem is as follows:

[0033]

[0034] Where F is the objective function, used to coordinate the generator correction amount and the deviation of the tie line branching plan; ΔP g,i ΔP is the correction amount for the output of the adjustable generator set. t,j Let P be the power deviation of tie line j; M is the penalty factor for tie line power deviation; constraints include the upper limit of tie line power deviation, the upper limit of total generator regulation, and the constraint on generator output power. g,i,0 P t,j,0 Generator set G before correction i and the power of the connecting line j; S ji G represents the adjustable generator set i The sensitivity of the output to the power transmitted through tie line j is calculated using the following formula: P t,j,ref The transmission power of the tie line j as specified in the clearing plan.

[0035] As a preferred embodiment of the tie-line branching plan generation system of the present invention, the tie-line branching initial plan correction module solves the mathematical model of the tie-line branching plan correction problem, approximates the constraint equations related to tie-line power deviations as linear equations through sensitivity, and in the k-th iteration, lets And recalculate the sensitivity S ji The parameters of the mathematical model for the tie-line branching plan correction problem are updated; this process is iterated until the maximum unit correction value is less than the set threshold ε, expressed as: When the connection converges, the correction scheme and the actual operation scheme of the corrected tie line branching plan are obtained.

[0036] Thirdly, an electronic device is provided, comprising:

[0037] Memory, storing at least one instruction; and

[0038] The processor executes the instructions stored in the memory to implement the tie-line branching plan generation method.

[0039] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the aforementioned tie-line splitting plan generation method.

[0040] Compared with the prior art, the first aspect of the present invention has at least the following beneficial effects:

[0041] A set of typical tie-line distribution plans is generated by clustering historical power system operating data. Based on this set, using provincial grid sub-plans and regional load forecasts as features, the scenario corresponding to the clearing plan is matched, and the typical tie-line distribution plan with the smallest distance from the scenario is selected as the initial scheme. Compared with the method of generating tie-line distribution plans based on a fixed proportion, the method of this invention better considers the load distribution of the studied power system, and the resulting scheme is more consistent with the actual operating state of the system. The tie-line distribution plan generation method under the electricity spot market proposed in this invention overcomes the difficulty of implementing the clearing plan in the existing electricity market clearing process, where the deviation between the predicted and actual scenarios leads to a greater difference between the actual operating state of the system and the clearing plan.

[0042] Furthermore, the method of the present invention also includes a step of correcting the initial plan for the tie line branching, so that the deviation between the power exchange between the power system and the outside world and the initial plan for the tie line branching is less than a set value, and outputting the actual operation scheme of the corrected tie line branching plan. Based on the correction of the initial plan for the tie line branching, the final operation scheme significantly reduces the power deviation of each tie line, ensuring that the power deviation of each tie line does not exceed the limit after adjustment. The present invention takes into account both the adjustment amount of generator power and the power deviation of tie lines, obtains the correction scheme of adjustable units, and superimposes the correction scheme with the initial scheme to form the final actual operation scheme, thereby improving the feasibility and economy of the clearing plan.

[0043] Furthermore, this invention constructs a mathematical model for the tie-line branching plan correction problem based on actual scenarios. By using the mathematical model for the tie-line branching plan correction problem to correct the initial tie-line branching plan, different optimization results can be obtained by appropriately setting the penalty factor in the objective function and adjusting the weights of the control quantity and power deviation in the objective function.

[0044] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 Flowchart of the method for generating a connection line branching plan according to an embodiment of the present invention;

[0047] Figure 2A structural block diagram of the tie line branching plan generation system according to an embodiment of the present invention. Detailed Implementation

[0048] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0049] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0050] Since the exact output and load of renewable energy in the power system cannot be known when the electricity spot market clears, the transmission power of each tie line can generally only be predicted based on historical operating data or experience. Existing tie line distribution plans often allocate the plan among the tie lines according to a fixed ratio. However, considering the complexity of the power system and the diversity of operating scenarios, the tie line distribution plan generated based on a fixed ratio often deviates significantly from the actual operating conditions. Therefore, how to generate tie line distribution plans quickly and accurately is an important problem facing the electricity spot market.

[0051] This invention addresses the difficulty in determining tie-line splitting plans during existing power market clearing processes, as well as the challenges in implementing clearing plans due to discrepancies between predicted and actual scenarios. It provides a method for generating tie-line splitting plans, which extracts system correction schemes and actual operation schemes that minimize the power deviation of each tie line.

[0052] The basic scheme of the tie line branching plan generation method of the present invention is to generate a tie line branching plan based on the tie line sub-plan and the historical load data of each region. During actual operation, the generator output of the external system is adjusted according to the actual operating conditions so that the tie line branching plan remains basically unchanged, so that the power system can operate according to the clearing plan.

[0053] Example 1

[0054] Please see Figure 1 The tie-line branching plan generation method proposed in this embodiment of the invention includes the following steps:

[0055] (1) Obtain the power system topology, parameters, and historical operating data;

[0056] (2) Generate a typical connection line branching plan set based on historical data clustering;

[0057] (3) Generate the initial plan for the branching of the connecting lines based on the matching of feature quantities;

[0058] (4) Construct a mathematical model for the correction problem of the connecting line branching plan based on actual scenarios;

[0059] (5) Solve the correction scheme for the connecting line branching plan, and determine whether it converges. If it does not converge, update the running scheme and solve it again. If it converges, output the correction scheme and the actual running scheme.

[0060] In one possible implementation, the power system topology, parameters, and historical operating data mentioned in step (1) include: the composition of the external interconnection lines and external system adjustable generators of the provincial power grid to be studied; and the provincial power grid sub-plan P to be studied. tot The proposed branching plan for the provincial power grid interconnection lines (P) needs further study. t,j j = 1, ..., N t N t Number of tie lines; load P in each region L,k k = 1, ..., N L N L The number of regional loads included in the provincial power grid; the power P of each adjustable generator unit. g,i upper limit lower limit P g,i i = 1, ..., N g N g The number of adjustable generators; the maximum permissible power offset for each tie line. The maximum value of the total adjustable power of the adjustable generator

[0061] In one possible implementation, the specific process of generating a typical connection line branching plan set based on historical data clustering in step (2) is as follows:

[0062] The provincial power grid interconnection line branching plan is set as follows: Load in each region The provincial power grid interconnection data is X = (P tot ,P t ,P L If X is N, then X is N. e dimensional vector, N e =N t +N L +1, the resulting historical data is X. (s) =(P tot (s) ,P t (s) ,P L (s)), s=1,…,N s N s Let X be the number of samples; normalize the sample data X, where θ is the normalization variable for X, and the m-th element of θ is:

[0063]

[0064] In the formula, m = 1, ..., N e After normalization, the variation of sample data can be limited to the range of [0,1], so that variables of different dimensions can be compared.

[0065] Let the historical data of the samples be respectively The normalized variables are Define the distance between two samples Apply the K-means clustering method to cluster all sample data into N groups. C Clusters, from N s N samples were randomly selected. C N samples, as N C Clusters initial mass center N C The larger the value, the higher the accuracy of the generated typical scene, but the greater the computational cost; for sample X (s) s=1,…,N s Calculate its relationship with the centroid μ of each cluster. j j = 1, 2, ..., N C Distance between ||X (s) -μ j ||, X (s) Assign it to the cluster of the centroid with the smallest distance, and recalculate the C of each cluster. j j = 1, 2, ..., N C center of mass For cluster C j The number of samples included; the clusters are re-divided based on the calculated centroid vectors, and this process is iterated until the clusters and their centroids no longer change; the output consists of N. C The centroid μ of each cluster j j = 1, 2, ..., N C The typical set of connection line sub-plans represented by this.

[0066] In one possible implementation, the process of generating the initial plan for the tie-line branching based on feature quantity matching in step (3) is as follows:

[0067] Based on the obtained typical tie-line sub-plan set, the provincial power grid sub-plan P given by the clearing plan is... totand the predicted load P in each region L Using the feature quantity, calculate the distance between the predicted scene and the centroid of each cluster, match the predicted scene to the corresponding cluster with the minimum distance, and divide the cluster according to the connection line plan P of the matched cluster. t Develop an initial plan for the branching of the connecting lines.

[0068] In one possible implementation, the process of constructing a mathematical model for the tie-line branching plan correction problem based on the actual scenario in step (4) is as follows:

[0069] The predicted values ​​of wind power, photovoltaic power and load power in the power system inevitably have certain errors. At the same time, considering factors such as unplanned unit shutdowns, there is often a certain deviation between the system's operating scenario and the predicted scenario. In order to make the system operate as close as possible to the existing clearing plan, it is necessary to correct the initial tie line splitting plan and make appropriate adjustments to the adjustable generator output of the external system, so that the deviation between the power exchanged between the system and the outside world and the initial tie line splitting plan is controlled within the allowable range.

[0070] The mathematical model for the tie-line branching plan correction problem is as follows:

[0071]

[0072] Where F is the objective function, which reconciles the generator correction amount and the deviation of the tie-line branching plan; ΔP g,i ΔP is the correction amount for the output of the adjustable generator set. t,j Let P be the power deviation of tie line j; M is the penalty factor for tie line power deviation; constraints include the upper limit of tie line power deviation, the upper limit of total generator regulation, and the constraint on generator output power. g,i,0 P t,j,0 Generator set G before correction i and the power of the connecting line j; S ji G represents the adjustable generator set i The sensitivity of the output power to the power transmitted through tie line j can be calculated numerically using the following formula: P t,j,ref The transmission power of the tie line j as specified in the clearing plan.

[0073] In one possible implementation, step (5) of solving the tie-line branching plan correction scheme is as follows:

[0074] The objective function of the mathematical model for the tie-line splitting plan correction problem contains quadratic terms and can be solved using the IPOPT solver in the optimization software GAMS. The constraint equations related to tie-line power deviation are nonlinear equations, which are approximated as linear equations using sensitivity analysis; therefore, the solution process generally requires multiple iterations. In the k-th iteration, let... And recalculate the sensitivity S ji The parameters for the correction problem are updated; this process is iterated until the maximum value of the unit's correction is less than the set threshold ε, i.e. When the algorithm converges, the final solution yields the correction scheme and the actual operating scheme.

[0075] The tie-line branching plan generation method of this invention generates a typical tie-line branching plan set based on historical data clustering, generates an initial operating scheme through feature quantity matching, and takes into account the fluctuations of actual operating conditions. It also adds a tie-line branching plan correction step, avoiding the problem of large differences between the operating scheme and the actual operating conditions, and improving the system's safety and economy.

[0076] Example 2

[0077] Please see Figure 2 An embodiment of the present invention proposes a tie-line branching plan generation system, comprising:

[0078] Typical tie-line branch plan generation module 2 is used to generate typical tie-line branch plan sets based on the clustering of historical power system operation data;

[0079] The tie-line branch initial plan formulation module 3 is used to calculate the distance between the predicted scenario and the centroid of each cluster based on the generated typical tie-line branch plan set, using the provincial power grid sub-plan given by the clearing plan and the predicted load of each region as feature quantities, and match the predicted scenario to the cluster with the smallest distance, and formulate the tie-line branch initial plan based on the tie-line branch plan of the matched cluster.

[0080] In one possible implementation, the tie-line branching plan generation system of this embodiment of the invention further includes a tie-line branching initial plan correction module 4, which is used to correct the tie-line branching initial plan so that the deviation between the power exchange power between the power system and the outside world and the tie-line branching initial plan is less than a set value, and outputs the corrected tie-line branching plan actual operation scheme.

[0081] In one possible implementation, the tie-line branching plan generation system of this embodiment of the invention further includes a power system information acquisition module 1, which is used to acquire the power system topology, parameters and historical operating data.

[0082] Furthermore, the specific content acquired by the power system information acquisition module 1 includes: the external interconnection lines of the provincial power grid to be studied and the composition of adjustable generators in the external system; and the sub-plan P of the provincial power grid to be studied. tot The proposed branching plan for the provincial power grid interconnection lines (P) needs further study. t,j j = 1, ..., N t N t Number of tie lines; load P in each region L,kk = 1, ..., N L N L The number of regional loads included in the provincial power grid; the power P of each adjustable generator unit. g,i upper limit lower limit P g,i i = 1, ..., N g N g The number of adjustable generators; the maximum permissible power offset for each tie line. The maximum value of the total adjustable power of the adjustable generator

[0083] In one possible implementation, the typical tie-line branching plan generation module 2 sets the provincial power grid tie-line branching plan as follows: Load in each region The provincial power grid interconnection data is X = (P tot ,P t ,P L ), X is N e dimensional vector, N e =N t +N L +1, the resulting historical data is N s Let X be the number of samples; normalize the sample data X, where θ is the normalization variable for X, and the m-th element of θ is:

[0084]

[0085] In the formula, m = 1, ..., N e After normalization, the variation of the sample data is limited to the range of [0,1].

[0086] Let the historical data of the samples be respectively The normalized variables are Define the distance between two samples as The K-means clustering method was used to cluster all sample data into N groups. C Clusters, from N s N samples were randomly selected. C N samples, as N C Clusters initial mass center For sample X (s) s=1,…,N s Calculate its relationship with the centroid μ of each cluster. j j = 1, 2, ..., N C Distance between ||X (s) -μ j ||, X (s)Assign it to the cluster of the centroid with the smallest distance, and recalculate the C of each cluster. j j = 1, 2, ..., N C center of mass For cluster C j The number of samples included; the clusters are re-divided based on the calculated centroid vectors, and this process is iterated until the clusters and their centroids no longer change; the output consists of N. C The centroid μ of each cluster j j = 1, 2, ..., N C The typical set of connection line sub-plans represented by this.

[0087] In one possible implementation, the tie line branch initial plan correction module 4 constructs a mathematical model of the tie line branch plan correction problem based on the actual scenario, and corrects the tie line branch initial plan through the mathematical model of the tie line branch plan correction problem;

[0088] The mathematical model expression for the tie-line branching plan correction problem is as follows:

[0089]

[0090] Where F is the objective function, used to coordinate the generator correction amount and the deviation of the tie line branching plan; ΔP g,i ΔP is the correction amount for the output of the adjustable generator set. t,j Let P be the power deviation of tie line j; M is the penalty factor for tie line power deviation; constraints include the upper limit of tie line power deviation, the upper limit of total generator regulation, and the constraint on generator output power. g,i,0 P t,j,0 Generator set G before correction i and the power of the connecting line j; S ji G represents the adjustable generator set i The sensitivity of the output to the power transmitted through tie line j is calculated using the following formula: P t,j,ref The transmission power of the tie line j as specified in the clearing plan.

[0091] In one possible implementation, the tie-line branching initial planning correction module 4 uses the IPOPT solver of the optimization software GAMS to solve the mathematical model of the tie-line branching planning correction problem. By using sensitivity, the constraint equations related to tie-line power deviation are approximated as linear equations. In the k-th iteration, let... And recalculate the sensitivity S ji The parameters of the mathematical model for the tie-line branching plan correction problem are updated; this process is iterated until the maximum unit correction value is less than the set threshold ε, expressed as: When the connection converges, the correction scheme and the actual operation scheme of the corrected tie line branching plan are obtained.

[0092] Example 3

[0093] An electronic device according to an embodiment of the present invention includes:

[0094] Memory, storing at least one instruction; and

[0095] The processor executes the instructions stored in the memory to implement the tie-line branching plan generation method of the present invention.

[0096] Example 4

[0097] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the tie-line branching plan generation method of the present invention.

[0098] The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals. For ease of explanation, the above content only shows the parts related to the embodiments of the present invention; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. This computer-readable storage medium is non-transitory and can be stored in storage devices formed by various electronic devices, enabling the execution process described in the method of the embodiments of the present invention.

[0099] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0100] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0101] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0102] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do 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 tie-line sectionalizing plan generation method characterized by comprising: include: A set of typical tie-line branching plans is generated by clustering historical power system operation data. Based on the generated typical tie-line branching plan set, using the provincial power grid sub-plans given by the clearing plan and the predicted load of each region as feature quantities, the distance between the prediction scenario and the centroid of each cluster is calculated, and the prediction scenario is matched to the cluster with the smallest distance. The initial tie-line branching plan is formulated based on the tie-line branching plan of the matched cluster. It also includes a step of correcting the initial plan for the tie line branching, so that the deviation between the power exchange between the power system and the outside world and the initial plan for the tie line branching is less than a set value, and outputs the actual operation plan of the corrected tie line branching plan. It also includes steps for acquiring power system topology, parameters, and historical operating data. Specifically, this acquisition includes: the external interconnection lines of the provincial power grid to be studied and the composition of adjustable generators in the external system; and the provincial power grid sub-projects to be studied. The branching plan for the provincial power grid interconnection lines needs to be studied. , , Number of connecting lines; load in each area , , The number of regional loads included in the provincial power grid; the power of each adjustable generator unit. upper limit Lower limit , , The number of adjustable generators; the maximum permissible power offset for each tie line. The maximum value of the total adjustable power of the adjustable generator. ; In the step of correcting the initial plan for the tie line branching, a mathematical model of the tie line branching plan correction problem is constructed based on the actual scenario, and the initial plan for the tie line branching is corrected by the mathematical model of the tie line branching plan correction problem. The mathematical model expression for the tie-line branching plan correction problem is as follows: in, F The objective function is used to coordinate the deviations in generator correction and tie line branching plans; This is a correction amount for the output of the adjustable generator set; For connecting lines j Power deviation; M It is the penalty factor for tie-line power deviation; the constraints include the upper limit of tie-line power deviation, the upper limit of total generator regulation, and the constraint of generator output power. , Generator set G before correction i and connecting lines j power; G represents the adjustable generator set i Output to the connecting line j The sensitivity of transmission power is calculated using the following formula: ; To clear the communication lines stipulated in the plan j The transmission power.

2. The method for generating a tie-line branching plan according to claim 1, characterized in that, The steps for generating a typical tie-line branching plan set based on historical power system operation data clustering specifically include: The provincial power grid interconnection line branching plan is set as follows: Load in each region is The data for provincial power grid interconnection lines is as follows: , for dimensional vector, The obtained historical data is , , The number of samples; for the sample data Normalization is performed. for Normalized variables, The m The dimension element is: In the formula, After normalization, the variation of the sample data is limited to the range of [0,1]. Let the historical data of the samples be respectively , The normalized variables are , The distance between two samples is defined as Use the K-means clustering method to cluster all sample data into Each cluster class, from Randomly selected from the samples One sample, as Clusters initial mass center For the sample , Calculate its centroid with respect to each cluster. , Distance between ,Will Assign it to the cluster of the centroid with the smallest distance, and recalculate each cluster. , center of mass , For clusters The number of samples included; the clusters are re-divided based on the calculated centroid vectors, and this process is iterated until the clusters and their centroids no longer change; the output is... Centroid of each cluster , The typical set of connection line sub-plans represented by this.

3. The method for generating a tie-line branching plan according to claim 1, characterized in that, In the step of correcting the initial tie-line splitting plan, the mathematical model of the tie-line splitting plan correction problem is solved. The constraint equations related to tie-line power deviation are approximated as linear equations using sensitivity analysis. k During step iteration, let And recalculate the sensitivity. The parameters of the mathematical model for the tie-line branching plan correction problem are updated; this process is iterated until the maximum unit correction value is less than the set threshold. The expression is When the connection converges, the correction scheme and the actual operation scheme of the corrected tie line branching plan are obtained.

4. A tie-line branching plan generation system, characterized in that, include: The typical tie-line branch plan generation module is used to generate a typical tie-line branch plan based on the clustering of historical power system operation data; The tie-line branch initial plan formulation module is used to calculate the distance between the predicted scenario and the centroid of each cluster based on the generated typical tie-line branch plan set, using the provincial power grid sub-plan given by the clearing plan and the predicted load of each region as feature quantities, and match the predicted scenario to the cluster with the smallest distance, and formulate the tie-line branch initial plan based on the tie-line branch plan of the matched cluster. It also includes a tie-line branch initial plan correction module, which is used to correct the tie-line branch initial plan so that the deviation between the power exchange between the power system and the outside world and the tie-line branch initial plan is less than a set value, and outputs the corrected tie-line branch plan actual operation scheme. It also includes a power system information acquisition module, which is used to acquire power system topology, parameters and historical operating data; The power system information acquisition module specifically acquires the following: the external interconnection lines of the provincial power grid to be studied and the composition of adjustable generators in the external system; and the sub-plans of the provincial power grid to be studied. The branching plan for the provincial power grid interconnection lines needs to be studied. , , Number of connecting lines; load in each area , , The number of regional loads included in the provincial power grid; the power of each adjustable generator unit. upper limit Lower limit , , The number of adjustable generators; the maximum permissible power offset for each tie line. The maximum value of the total adjustable power of the adjustable generator. ; The tie-line branch initial plan correction module constructs a mathematical model of the tie-line branch plan correction problem based on the actual scenario, and corrects the tie-line branch initial plan through the mathematical model of the tie-line branch plan correction problem; The mathematical model expression for the tie-line branching plan correction problem is as follows: in, F The objective function is used to coordinate the deviations in generator correction and tie line branching plans; This is a correction amount for the output of the adjustable generator set; For connecting lines j Power deviation; M It is the penalty factor for tie-line power deviation; the constraints include the upper limit of tie-line power deviation, the upper limit of total generator regulation, and the constraint of generator output power. , Generator set G before correction i and connecting lines j power; G represents the adjustable generator set i Output to the connecting line j The sensitivity of transmission power is calculated using the following formula: ; To clear the communication lines stipulated in the plan j The transmission power.

5. The tie-line branching plan generation system according to claim 4, characterized in that, The typical tie-line branching plan generation module sets the provincial power grid tie-line branching plan as follows: Load in each region is The data for provincial power grid interconnection lines is as follows: , for dimensional vector, The obtained historical data is , , The number of samples; for the sample data Normalization is performed. for Normalized variables, The m The dimension element is: In the formula, After normalization, the variation of the sample data is limited to the range of [0,1]. Let the historical data of the samples be respectively , The normalized variables are , The distance between two samples is defined as Use the K-means clustering method to cluster all sample data into Each cluster class, from Randomly selected from the samples One sample, as Clusters initial mass center For the sample , Calculate its centroid with respect to each cluster. , Distance between ,Will Assign it to the cluster of the centroid with the smallest distance, and recalculate each cluster. , center of mass , For clusters The number of samples included; the clusters are re-divided according to the calculated centroid vectors, and this process is repeated iteratively until the clusters and their centroids no longer change; Output by Centroid of each cluster , The typical set of connection line sub-plans represented by this.

6. The tie-line branching plan generation system according to claim 4, characterized in that, The tie-line branching initial planning correction module solves the mathematical model of the tie-line branching planning correction problem, and approximates the constraint equations related to tie-line power deviations into linear equations through sensitivity analysis. k During step iteration, let And recalculate the sensitivity. The parameters of the mathematical model for the tie-line branching plan correction problem are updated; this process is iterated until the maximum unit correction value is less than the set threshold. The expression is When the connection converges, the correction scheme and the actual operation scheme of the corrected tie line branching plan are obtained.

7. An electronic device, characterized in that, include: Memory, storing at least one instruction; and The processor executes instructions stored in the memory to implement the tie-line branching plan generation method as described in any one of claims 1 to 3.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the tie-line branching plan generation method as described in any one of claims 1 to 3.

Images