A data-enhanced state estimation method and system for low-observable distribution network
By introducing power flow embedded projection cone data enhancement optimization model and linearized flow constraints in low-observable distribution network, combined with enhanced optimization branch bounding algorithm, the problems of low-observable distribution network state estimation accuracy and calculation time are solved. , achieving more efficient state estimation.
Patent Information
- Application Number
- CN202410242477.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-04
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-03-04
AI Technical Summary
The traditional weighted least squares state estimator in low-observable distribution network cannot work properly, and the matrix completion state estimation method has a long calculation time and low accuracy, making it difficult to effectively estimate the internal state.
A power flow embedded projection cone data enhancement optimization model is proposed, linearized current constraints are embedded, and a branch delimiting algorithm based on enhancement optimization is adopted to improve state estimation accuracy and computational efficiency.
It significantly improves the accuracy of state estimation, shortens the calculation time, improves the accuracy by about 2 times, and reduces the calculation time to 5% or even less.
Smart Images

Figure CN118336729B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of power system operation and control, and in particular relates to a data enhanced state estimation method and system for a low-observable distribution network. Background Art
[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.
[0003] The data obtained by measuring the input and output of the low-observable distribution network can only reflect the external characteristics of the low-observable distribution network, while the dynamic laws of the low-observable distribution network need to be described by internal (usually not directly measurable) state variables. State estimation can estimate the internal state of the low-observable distribution network based on the available measurement data.
[0004] The lack of sufficient measurements in distribution systems under low observability conditions makes it impossible for traditional weighted least squares state estimators to work properly. Conventional remedies for this problem include installing additional sensors or using pseudo measurements. In addition to these remedies, based on the semi-positive definite programming proposed in the paper Exact MatrixCompletion via Convex Optimization published in the journal Found Comput Math in 2009, the paper Matrix Completion for Low-ObservabilityVoltage Estimation published in the journal IEEE Transactions on Smart Grid in 2020 proposed a matrix completion state estimation method that can estimate bus voltage even under low observability conditions where traditional state estimators may fail. However, this type of matrix completion state estimation method does not always produce satisfactory results, with low estimation accuracy; more importantly, its computational time is prohibitively high. Summary of the invention
[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a data enhanced state estimation method and system for low-observable distribution networks, proposes a new power flow embedded projection cone data enhancement optimization model, which is used for the state estimation problem of low-observable distribution systems, and embeds linearized power flow constraints in the power flow embedded projection cone data enhancement optimization model, thereby improving the accuracy of the state estimator.
[0006] In order to achieve the above object, the present invention adopts the following technical solution:
[0007] A first aspect of the present invention provides a data enhanced state estimation method for a low observable distribution network, comprising:
[0008] Obtaining a low-rank measurement matrix of a distribution network, wherein the low-rank measurement matrix includes measurement variables of a plurality of nodes;
[0009] Based on the low-rank measurement matrix, a data-enhanced measurement matrix is obtained by solving a power flow embedding projection cone data enhancement optimization model;
[0010] Based on the measurement matrix after data enhancement, the state estimation value is obtained;
[0011] Among them, the power flow embedded in the projected cone data enhancement optimization model adopts linearized power flow constraints.
[0012] Furthermore, it is characterized in that the power flow embedding projection cone data enhancement optimization model is:
[0013]
[0014] Where: M is the low-rank measurement matrix; X is the completed measurement matrix of the low-rank measurement matrix M; the subscript ψ is the set of observable elements in the matrix; is the unknown matrix; represents the loss function; Υ is the orthogonal projection matrix; 0 represents the all-zero matrix; I k and I n denote the k-dimensional and n-dimensional identity matrices respectively; λ is a parameter that controls the sensitivity of X to noise; k is a hyperparameter that limits the rank of X; Y 00 and Y 0L is the node admittance matrix; w is the non-relaxed zero-load voltage vector; A and C are constant matrices; v and s collect the non-relaxed voltage and non-relaxed power injection respectively; v0 and s0 collect the relaxed voltage and relaxed power injection respectively; τ Re , τ Im ,γ,α Re and α Im Collect measurement noise; ω ε is the relevant weight of each constraint allowable value ε; n and m represent the number of nodes and the number of measurement variables, respectively; Re(·) and Im(·) represent the real part and imaginary part of a quantity, respectively; and Respectively represent Y 00 , v0, Y 0L and the conjugate of v; ||·|| F Represents the F-norm of a matrix.
[0015] Furthermore, the solution of the power flow embedded projection cone data enhancement optimization model adopts a branch and bound algorithm based on enhanced optimization.
[0016] Furthermore, the measured variables include real and imaginary parts of voltage, voltage amplitude, active power injection and reactive power injection.
[0017] Furthermore, the power flow embedded projection cone data enhancement optimization model satisfies the constraints during the solution process:
[0018]
[0019] Where x is a unit vector; U i is the i-th column of U; for The i-th column of b i and is the constraint limit of the branch; U represents an n×k unknown matrix; Represents the current relaxed solution.
[0020] A second aspect of the present invention provides a data enhanced state estimation system for a low observable power distribution network, comprising:
[0021] A data acquisition module is configured to: acquire a low-rank measurement matrix of a distribution network, wherein the low-rank measurement matrix includes measurement variables of a plurality of nodes;
[0022] A data enhancement module is configured to: based on the low-rank measurement matrix, obtain a data-enhanced measurement matrix by solving a power flow embedded projection cone data enhancement optimization model;
[0023] A state estimation module is configured to: obtain a state estimation value based on the measurement matrix after data enhancement;
[0024] Among them, the power flow embedded in the projected cone data enhancement optimization model adopts linearized power flow constraints.
[0025] Furthermore, the solution of the power flow embedded projection cone data enhancement optimization model adopts a branch and bound algorithm based on enhanced optimization.
[0026] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the data-enhanced state estimation method for a low-observable distribution network as described above.
[0027] A fourth aspect of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the data enhanced state estimation method for a low-observable distribution network as described above are implemented.
[0028] A fifth aspect of the present invention provides a computer program product, which is a computer program product containing a computer program. When a processor executes the computer program, the steps in the data enhanced state estimation method for a low-observable distribution network as described above are implemented.
[0029] Compared with the prior art, the present invention has the following beneficial effects:
[0030] In terms of accuracy, the present invention proposes a new power flow embedded projection cone data enhancement optimization model for the state estimation problem of low observable distribution systems. Linearized power flow constraints are embedded in the power flow embedded projection cone data enhancement optimization model, which further improves the accuracy of the state estimator.
[0031] In terms of computing time, the present invention proposes an accelerated solution strategy based on an enhanced optimized branch and bound algorithm, thereby solving a power flow embedded projection cone data enhanced optimization model in a shorter time. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
[0033] Figure 1 This is a flow chart of a data enhanced state estimation method for a low observable distribution network according to a first embodiment of the present invention. DETAILED DESCRIPTION
[0034] In order to enable those skilled in the art to better understand the technical solutions in this application, the following will further illustrate the technical solutions for achieving the invention purpose of this application through several specific embodiments. It should be noted that the technical solutions claimed for protection in this application include but are not limited to the following embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.
[0035] Embodiment 1
[0036] This embodiment provides a data enhanced state estimation method for a low-observable distribution network.
[0037] This embodiment provides a data enhanced state estimation method for a low-observable distribution network. In terms of accuracy, a new power flow embedded projection cone data enhancement optimization model is proposed for the state estimation problem of a low-observable distribution system. Linearized power flow constraints are embedded in the power flow embedded projection cone data enhancement optimization model, which can be regarded as a kind of "domain knowledge", further improving the accuracy of the state estimator.
[0038] This embodiment provides a data-enhanced state estimation method for a low-observable distribution network. In terms of computing time, an accelerated solution strategy of a branch-and-bound algorithm based on enhanced optimization is proposed, so as to solve the power flow embedded projection cone data enhancement optimization model in a shorter time.
[0039] This embodiment provides a data enhancement state estimation method for a low observable distribution network, such as Figure 1 As shown, the following steps are included:
[0040] Step 1: Obtain a low-rank measurement matrix of a distribution network, where the low-rank measurement matrix includes measurement variables of several nodes; wherein the distribution network may be a three-phase unbalanced distribution network;
[0041] Step 2: Assume that there is a completed measurement matrix generated based on the low-rank measurement matrix, and use the power flow embedding projection cone data enhancement optimization formula to express the data enhancement problem of recovering the unknown items in the low-rank measurement matrix;
[0042] Step 3: A pruning branch and bound algorithm based on enhanced optimization is used to iteratively solve the power flow embedding projection cone data enhancement optimization model, and the measurement matrix is enhanced to obtain the enhanced measurement matrix X opt , the corresponding values of the state quantities obtained in the measurement matrix after data enhancement can also be regarded as state estimation values.
[0043] Among them, the state quantity can be regarded as: some values in the low-rank measurement matrix M contain the state quantity, for example, Re(v i ),Im(v i ),|v i | is related to the state quantity. In step 1, let is the low-rank measurement matrix, M ij is an unknown quantity, n and m represent the number of rows (number of nodes) and columns (number of measurement variables) of the low-rank measurement matrix M, respectively, and the subscript ψ is the set of observable elements in the low-rank measurement matrix M, then:
[0044]
[0045] In the low-rank measurement matrix, each row integrates the information of a node and each column represents a measurement variable; these columns (measurement variables) include the real and imaginary parts of the node voltage, the voltage amplitude, and the active and reactive power injection parts.
[0046] For each node i, its corresponding row in the low-rank measurement matrix is defined as:
[0047] [Re(v i ),Im(v i ),|v i |,Re(s i), Im(s i )], (1≤i≤n)
[0048] Where: v i represents the complex voltage of node i; s i represents the complex power of node i; the symbols Re(·), Im(·) and |·| represent the real part, imaginary part and absolute value of a quantity, respectively.
[0049] In step 2, the completed measurement matrix X is used as the "recovered version" of the low-rank measurement matrix M. According to the projection quadratic curve model for the general matrix, the power flow embedded projection cone data enhancement optimization model is used to perform data enhancement optimization on the unknown items in the low-rank measurement matrix. The power flow embedded projection cone data enhancement optimization model is:
[0050]
[0051] Where: M is the low-rank measurement matrix; X is the completed measurement matrix of the low-rank measurement matrix M; the subscript ψ is the set of observable elements in the matrix; is the unknown matrix; Represents the loss function; the orthogonal projection matrix Υ satisfies the condition Υ 2 = Υ and tr(Υ)≤k; 0 represents a matrix of all zeros, I k and I n denote the k-dimensional and n-dimensional identity matrices respectively; λ>0 is a parameter that regularizes X to control its sensitivity to noise; k is a hyperparameter that limits the rank of X; Y 00 and Y 0L is the node admittance matrix, w is the non-relaxed zero-load voltage vector; A and C are constant matrices; v and s collect the non-relaxed voltage and non-relaxed power injection respectively; v0 and s0 collect the relaxed voltage and relaxed power injection respectively; the vector τ Re , τ Im ,γ,α Re and α Im The measurement noise is collected into the set E = {τ Re ,τ Im ,γ,α Re ,α Im}, τ Re , τ Im ,γ,α Re and α Im Represents the noise (or error) caused by different measurements; ω ε is the relevant weight of each constraint admissible value ε∈E; n and m represent the number of nodes and the number of measurement variables, respectively; Re(·) and Im(·) represent the real part and imaginary part of a quantity, respectively; and Respectively represent Y 00 , v0, Y0L and the conjugate of v; ||·|| F Represents the F-norm of a matrix.
[0052] In step 3, a branch and bound algorithm based on enhanced optimization is used. The idea is to gradually branch the original feasible region into smaller regions, gradually narrowing the scope of the solution until a feasible solution is found. Continuous branching reduces the scope of the replacement problem, thereby accelerating the solution of the problem. When the solution of the proposed power flow embedded projection cone data enhancement optimization model meets the branching condition, the current node is branched. At this time, there exists a unit vector x such that Therefore, imposing the inequality constraint U i (1≤i≤k) is the i-th column of matrix U, is a scalar. For any You can use the function The boundary of is approximated by two segments, where
[0053]
[0054] Where: for The i-th column of The eigenvector of b and is the constraint limit vector; b i and Separate vector b and The i-th column of ; U represents an n×k unknown matrix; Represents the current relaxed solution.
[0055] For unsolvable subproblems, the branch is pruned. For solvable but unsatisfactory solutions, further branching is performed and the lower bound Z of the objective function is updated. lower , a "compromise" is made on the minimum value to meet the conditions. For solutions that are both solvable and meet the conditions, no further branching is performed, but the upper bound Z of the objective function is simply updated upper When Z upper -Z lower When it is small enough, the optimal solution is returned. This strategy reduces the size of the original problem by branching, significantly reducing the time to solve each subproblem; by setting boundaries, the optimal solution that meets the conditions is sought. Obviously, for a segmented delimitation with q segments, each disjunction will produce q k Definition: Q is the problem queue; Z is the problem queue. upper and Z lower are the current upper and lower bounds respectively; ε is the maximum allowable error; the overall idea of the branch and bound algorithm based on enhanced optimization is as follows:
[0056] Step (1), initialization: set the superscript t to the current problem index, initial t = 0, upper bound Z lower = -∞, lower bound Z upper =+∞, maximum allowable error ε, given initial value b 0 , x 0 ;
[0057] Step (2), initialize a question queue Q;
[0058] Step (3), if Q is a non-empty set and Z upper -Z lower >ε, then go to step (4);
[0059] Step (4), retrieve a question Q(t) from the question queue Q;
[0060] Step (5), solve the following problem (the power flow after branching is embedded in the projection cone data enhancement optimization problem), and get the solution And the objective function in represents the obtained Θ t ,Υ t ,X t ,U t Solution:
[0061]
[0062] Step (6), if Then execute step (7); otherwise, execute step (8);
[0063] Step (7), if Z < Z upper , then Z upper =Z, Go to step (9);
[0064] Step (8), if Z < Z upper , then seek a satisfying x t+1 , according to the branch constraint limit b and Generate q k subproblem, and let t = t + 1, and (q k sub-problems) are added to the problem queue Q, and Z is updated lower is the minimum value of the lower bound of all unexplored nodes, and returns to step (3);
[0065] Among them, q k The specific steps of adding a sub-problem to the problem queue are: For each sub-problem, the objective function parameter Z is defined as Execution: Q:=Q∪{Z};
[0066] Step (9), return (θ opt ,Υ opt ,X opt ,U opt ).
[0067] Case studies show that compared with the existing matrix completion state estimation method, the data enhancement state estimation method for a low-observable distribution network provided in this embodiment has an accuracy improved by about 2 times and the calculation time can be shortened to 5% or even less.
[0068] Embodiment 2
[0069] This embodiment provides a data enhanced state estimation system for a low observable distribution network, which specifically includes:
[0070] A data acquisition module is configured to: acquire a low-rank measurement matrix of a distribution network, wherein the low-rank measurement matrix includes measurement variables of a plurality of nodes;
[0071] A data enhancement module is configured to: based on the low-rank measurement matrix, obtain a data-enhanced measurement matrix by solving a power flow embedded projection cone data enhancement optimization model;
[0072] A state estimation module is configured to: obtain a state estimation value based on the measurement matrix after data enhancement;
[0073] Among them, the power flow embedded in the projected cone data enhancement optimization model adopts linearized power flow constraints.
[0074] Among them, the power flow embedding projection cone data enhancement optimization model is:
[0075]
[0076] Where: M is the low-rank measurement matrix; X is the completed measurement matrix of the low-rank measurement matrix M; the subscript ψ is the set of observable elements in the matrix; is the unknown matrix; represents the loss function; Υ is the orthogonal projection matrix; 0 represents the all-zero matrix; I k and I n denote the k-dimensional and n-dimensional identity matrices respectively; λ is a parameter that controls the sensitivity of X to noise; k is a hyperparameter that limits the rank of X; Y 00 and Y 0L is the node admittance matrix; w is the non-relaxed zero-load voltage vector; A and C are constant matrices; v and s collect the non-relaxed voltage and non-relaxed power injection respectively; v0 and s0 collect the relaxed voltage and relaxed power injection respectively; τ Re , τ Im,γ,α Re and α Im Collect measurement noise; ω ε is the relevant weight of each constraint allowable value ε; n and m represent the number of nodes and the number of measurement variables, respectively; Re(·) and Im(·) represent the real part and imaginary part of a quantity, respectively; and Respectively represent Y 00 , v0, Y 0L and the conjugate of v; ||·|| F Represents the F-norm of a matrix.
[0077] Among them, the solution of the power flow embedded projection cone data enhancement optimization model adopts the branch and bound algorithm based on enhanced optimization.
[0078] The measured variables include the real and imaginary parts of voltage, voltage amplitude, active power injection, reactive power injection, active power injection of current, and reactive power injection of current.
[0079] Among them, the power flow embedded projection cone data enhancement optimization model satisfies the constraints in the solution process:
[0080]
[0081] Where x is a unit vector; U i is the i-th column of U; for The i-th column of b i and is the constraint limit of the branch; U represents an n×k unknown matrix; Represents the current relaxed solution.
[0082] This embodiment provides a data-enhanced state estimation system for a low-observable distribution network. In terms of accuracy, a new power flow embedded projection cone data enhancement optimization model is proposed for the state estimation problem of a low-observable distribution system. Linearized power flow constraints are embedded in the power flow embedded projection cone data enhancement optimization model, which can be regarded as a kind of "domain knowledge" and further improves the accuracy of the state estimator.
[0083] This embodiment provides a data-enhanced state estimation system for a low-observable distribution network. In terms of computing time, an accelerated solution strategy of a branch-and-bound algorithm based on enhanced optimization is proposed, so as to solve the power flow embedded projection cone data enhancement optimization model in a shorter time.
[0084] It should be noted here that each module in this embodiment corresponds to each step in Example 1 one by one, and the specific implementation process is the same, which will not be repeated here.
[0085] Embodiment 3
[0086] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the data enhancement state estimation method for a low-observable distribution network as described in the first embodiment above are implemented.
[0087] Embodiment 4
[0088] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the data enhancement state estimation method for a low-observable distribution network as described in the first embodiment above are implemented.
[0089] Embodiment 5
[0090] This embodiment provides a computer program product, which is a computer program product containing a computer program. When a processor executes the computer program, the steps in the data enhancement state estimation method for a low-observable distribution network as described in the above-mentioned embodiment 1 are implemented.
[0091] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.
[0092] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.
[0093] The above is only a preferred embodiment of the present application and does not constitute any form of obstruction to the present application. Any simple modifications or equivalent changes made to the above embodiments based on the technical essence of the present application shall fall within the protection scope of the present application.
Claims
1. A data-enhanced state estimation method for a low-observable distribution network, characterized in that: include: Obtaining a low-rank measurement matrix of a distribution network, wherein the low-rank measurement matrix includes measurement variables of a plurality of nodes; Based on the low-rank measurement matrix, a data-enhanced measurement matrix is obtained by solving a power flow embedding projection cone data enhancement optimization model; Based on the measurement matrix after data enhancement, the state estimation value is obtained; Among them, the power flow embedding projected cone data enhancement optimization model adopts linearized power flow constraints; The power flow embedding projection cone data enhancement optimization model is: Where: M is the low-rank measurement matrix; X is the completed measurement matrix of the low-rank measurement matrix M; the subscript ψ is the set of observable elements in the matrix; is the unknown matrix; represents the loss function; Υ is the orthogonal projection matrix; 0 represents the all-zero matrix; I k and I n denote k-dimensional and n-dimensional identity matrices respectively; λ is a parameter that controls the sensitivity of X to noise; k is a hyperparameter that limits the rank of X; Y 00 and Y 0L is the node admittance matrix; w is the non-relaxed zero-load voltage vector; A and C are constant matrices; v and s collect the non-relaxed voltage and non-relaxed power injection respectively; v0 and s0 collect the relaxed voltage and relaxed power injection respectively; τ Re , τ Im ,γ,α Re and α Im Collect measurement noise; ω ε is the relevant weight of each constraint allowable value ε; n and m represent the number of nodes and the number of measurement variables, respectively; Re(·) and Im(·) represent the real part and imaginary part of a quantity, respectively; and Respectively represent Y 00 , v0, Y 0L and the conjugate of v; ||·|| F Represents the F-norm of a matrix.
2. A data enhanced state estimation method for a low observable distribution network according to claim 1, characterized in that: The solution of the power flow embedded projection cone data enhancement optimization model adopts a branch and bound algorithm based on enhanced optimization.
3. The data enhanced state estimation method for a low observable distribution network according to claim 1, characterized in that: The measured variables include real and imaginary parts of voltage, voltage amplitude, active power injection and reactive power injection.
4. The data enhanced state estimation method for a low observable distribution network according to claim 1, characterized in that: The power flow embedded projection cone data augmentation optimization model satisfies the constraints during the solution process: Where x is a unit vector; U i is the i-th column of U; for The i-th column of b i and is the constraint limit of the branch; U represents an n×k unknown matrix; Represents the current relaxed solution.
5. A data-enhanced state estimation system for a low-observable distribution network, characterized in that: include: A data acquisition module is configured to: acquire a low-rank measurement matrix of a distribution network, wherein the low-rank measurement matrix includes measurement variables of a plurality of nodes; A data enhancement module is configured to: based on the low-rank measurement matrix, obtain a data-enhanced measurement matrix by solving a power flow embedded projection cone data enhancement optimization model; A state estimation module is configured to: obtain a state estimation value based on the measurement matrix after data enhancement; Among them, the power flow embedding projected cone data enhancement optimization model adopts linearized power flow constraints; The power flow embedding projection cone data enhancement optimization model is: Where: M is the low-rank measurement matrix; X is the completed measurement matrix of the low-rank measurement matrix M; the subscript ψ is the set of observable elements in the matrix; is the unknown matrix; represents the loss function; Υ is the orthogonal projection matrix; 0 represents the all-zero matrix; I k and I n denote k-dimensional and n-dimensional identity matrices respectively; λ is a parameter that controls the sensitivity of X to noise; k is a hyperparameter that limits the rank of X; Y 00 and Y 0L is the node admittance matrix; w is the non-relaxed zero-load voltage vector; A and C are constant matrices; v and s collect the non-relaxed voltage and non-relaxed power injection respectively; v0 and s0 collect the relaxed voltage and relaxed power injection respectively; τ Re , τ Im ,γ,α Re and α Im Collect measurement noise; ω ε is the relevant weight of each constraint allowable value ε; n and m represent the number of nodes and the number of measurement variables, respectively; Re(·) and Im(·) represent the real part and imaginary part of a quantity, respectively; and Respectively represent Y 00 , v0, Y 0L and the conjugate of v; ||·|| F Represents the F-norm of a matrix.
6. A data enhanced state estimation system for a low observable distribution network as claimed in claim 5, characterized in that: The solution of the power flow embedded projection cone data enhancement optimization model adopts a branch and bound algorithm based on enhanced optimization.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the data enhancement state estimation method for a low-observable distribution network as described in any one of claims 1 to 4 are implemented.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the data enhanced state estimation method for a low-observable distribution network as described in any one of claims 1-4 are implemented.
9. A computer program product, which is a computer program product containing a computer program, characterized in that When the processor executes the computer program, the steps in the data enhanced state estimation method for a low-observable distribution network as described in any one of claims 1 to 4 are implemented.
