Static state estimation method, system and equipment of power system and medium

Abstract

The invention discloses an electric power system static state estimation method, system and device and a medium. The method comprises the steps of obtaining a PMUs feature E embedded in a graph of an electric power system; the PMUs feature E embedded into the graph of the power system is input into the trained convolutional neural network model, the static state of the power system is obtained, and the method, the system, the equipment and the medium can improve the accuracy of static state estimation of the power system.

Description

Technical Field

[0001] The present invention belongs to the field of power systems, and relates to a method, system, equipment and medium for estimating the static state of a power system. Background Art

[0002] State estimation is an important means for people to understand, analyze and control the state of power systems. The static state in the power system includes voltage (V), current (I), relative angle (θ), active power (P) and reactive power (Q). In traditional state estimation, the power system is assumed to be quasi-steady state, but with the widespread application of technologies such as distributed generators (DG), smart loads, demand response (DR) and electric vehicle charging units, the dynamics of the power system has increased rapidly, and the quasi-steady state assumption is no longer applicable. It is necessary to improve the accurate estimation of the power system state.

[0003] At present, there have been many studies on static state estimation of power systems. First, Schweppe et al. defined the basic concept of static state estimation in detail "Static State Estimation in Electric Power Systems [J]. Proceedings of the IEEE, 1974, 62 (7): 972-982." The general structure and main functions of static state estimation methods were outlined, and several common numerical solutions were introduced. In 1969, Xu Huai et al. from the Massachusetts Institute of Technology first proposed state estimation based on weighted least squares method "State Estimation in Power Systems Part II: Implementation and Applications [J]. IEEE Transactions on Power Apparatus and Systems, 1970 (3): 353-363." This is one of the most basic algorithms. Soon after, HP Horisberger et al. improved the weighted least squares method based on the experience of power flow calculation and proposed a fast PQ decomposition algorithm in "A Fast Decoupled Static State-Estimator for Electric Power Systems [J]. IEEE Transactions on Power Apparatus and Systems, 1976, 95 (1): 208-215." In 1980, the Beijing Power System conducted a real-time test on state estimation and achieved success "A Review of Power System State Estimation Research [J]. China New Technologies and New Products, 2011 (20): 2." In recent years, the upgrading of monitoring equipment has brought new changes to state estimation, and the introduction of PMUs has brought significant improvements to the performance and capabilities of state estimation. Zhao et al. studied the state estimation problem in large-scale systems, especially the detection of single-line and double-line faults, by using known system topology information combined with PMUs phasor angle measurement in "Multi Area State Estimation Using Synchronized Phasor Measurements [J]. IEEE Transactions on Power Systems, 2005, 20 (2): 611-617."Naziri et al. studied the impact of PMU assembly problems on estimation accuracy in "Hierarchical Robust State Estimation in Power System Using PhasorMeasurement Units[C] / / ISGT 2011.2011:1-6". Considering the difficulty of configuring PMUs in the entire power grid, Zhang et al. studied the hybrid measurement of PMU and SCADA in "State Estimator Tuning for PMU Measurements[C] / / 2011North American Power Symposium.2011:1-4". Model-based methods are also emerging. Baran et al. proposed a branch current state estimation model in "A Review of Power System Dynamic State Estimation Techniques[C] / / 2008JointInternational Conference on Power System Technology and IEEE Power IndiaConference.2008:1-6", the basic idea of ​​which is to convert all measurement types into branch currents. Scholar PJ Huber proposed a robust estimation model in "A Robust Version of the Probability Ratio Test [J]. The Annals of Mathematical Statistics, 1965, 36 (6): 1753-1758." In the process of state estimation, facing the unavoidable gross error phenomenon, the purpose of robust estimation is to explore appropriate estimation methods to minimize the adverse effects of gross errors on the estimation results, in order to obtain the most accurate optimal estimate. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a method, system, device and medium for estimating the static state of an electric power system, which can improve the accuracy of estimating the static state of the electric power system.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme:

[0006] In one aspect, the present invention provides a method for estimating a static state of a power system, comprising:

[0007] Obtain the PMUs features E of the power system graph embedding;

[0008] The PMUs features E embedded in the graph of the power system are input into the trained convolutional neural network model to obtain the static state of the power system.

[0009] The static state estimation method of the power system described in the present invention is further improved in that:

[0010] Furthermore, the process of obtaining the PMUs features E embedded in the graph of the power system is:

[0011] Deploy PMUs on r lines of the power system;

[0012] Obtain PMUs measurement data;

[0013] The PMUs measurement data is combined with the node2vec-based graph embedding to generate the PMUs features E of the power system graph embedding.

[0014] Furthermore, the graph of the power system embeds the PMUs features E = [E1, E2, ..., E m ], where E i is the graph embedding state vector corresponding to the measurement value of the i-th node.

[0015] Furthermore, the graph embedding state vector E corresponding to the measurement value of the i-th node i for:

[0016]

[0017] Among them, z i is the d-dimensional node2vec-based graph embedding vector for the i-th element of the measurement vector z

[0018] Furthermore, the measurement vector z is:

[0019]

[0020] Among them, Y f ∈C r×N is the system admittance matrix, I f is the current vector, A∈R m×N is the relationship matrix between the state vector x and the voltage vector measurement V.

[0021] In a second aspect of the present invention, the present invention provides a static state estimation system for a power system, comprising:

[0022] The first acquisition module is used to acquire the PMUs features E embedded in the graph of the power system;

[0023] The estimation module is used to input the PMUs features E embedded in the graph of the power system into the trained convolutional neural network model to obtain the static state of the power system.

[0024] The static state estimation system of the power system of the present invention is further improved in that:

[0025] Furthermore, the process of obtaining the PMUs features E embedded in the graph of the power system is:

[0026] a configuration module for configuring PMUs on r lines of the power system;

[0027] The second acquisition module is used to acquire PMUs measurement data;

[0028] The generation module is used to combine the PMUs measurement data with the node2vec-based graph embedding to generate the PMUs features E of the graph embedding of the power system.

[0029] Furthermore, the graph of the power system embeds the PMUs features E = [E1, E2, ..., E m ], where E i is the graph embedding state vector corresponding to the measurement value of the i-th node.

[0030] In a third aspect of the present invention, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for estimating the static state of the power system when executing the computer program.

[0031] In a fourth aspect of the present invention, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the power system static state estimation method are implemented.

[0032] The present invention has the following beneficial effects:

[0033] The method, system, device and medium for estimating the static state of the power system described in the present invention combine node embedding and neural network during specific operation, generate a vector expression containing the topological structure of the power system through a graph embedding algorithm, and provide a solid foundation for subsequent analysis. By inputting the generated embedded vector into the CNN convolutional neural network, complex feature extraction of the vector is achieved, which plays a key role in improving the characterization quality of node features, thereby significantly improving the accuracy and reliability of static state estimation and dynamic state estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings constituting 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 an improper limitation of the present invention. In the accompanying drawings:

[0035] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, not all embodiments, and is not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concepts disclosed in the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0037] The accompanying drawings show schematic diagrams of structures according to embodiments disclosed in the present invention. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0038] Embodiment 1

[0039] refer to Figure 1 The static state estimation method of the power system of the present invention comprises the following steps:

[0040] The network topology and PMUs data are fused into a low-dimensional graph embedding feature vector, and then the state estimation is performed through a convolutional neural network to achieve a fine representation of the power grid topology, and to adapt more effectively when the network changes, and to be able to scale efficiently when processing larger networks. The specific principle is as follows Figure 1 As shown:

[0041] Graph-embedded PMUs measurement data E plays a vital role in capturing the complex spatial topological information of the power system. By combining PMUs measurement data with node2vec-based graph embedding, the state vectors of all nodes in the entire power system are generated. This can significantly improve the accuracy of node representation and state estimation, providing more reliable information for the operation and management of the power system.

[0042] Specifically, for a power system with N nodes, the power system has m nodes and r lines equipped with PMUs to provide voltage and current measurement data. The state vector x∈C N×1 Includes the voltage vectors of all nodes. Measurement vector z∈C (m+r)×1 Including the voltage vector at the PMUs installation node, the measurement data model of the PMUs data derived from Ohm's law is:

[0043]

[0044] Among them, Y f ∈C r×N is the system admittance matrix; I f is the current vector; A∈R m×N is the relationship matrix between the state vector x and the voltage vector measurement V. When the voltage vector of node j is the i-th component in the voltage vector measurement, then A i,j =1; otherwise, A i,j =0, where A i,j is the element of A in the i-th row and j-th column, and the relationship between the measurement vectors z and x is:

[0045]

[0046] For each node, compute a d-dimensional node2vec-based graph embedding vector The graph embedding state vector corresponding to the measurement of the i-th node is:

[0047]

[0048] Among them, z i is the ith element of z. For all observable nodes in the power grid, we get the graph embedded PMUs features E = [E1, E2, ..., E m ].

[0049] The CNN estimator is good at extracting hierarchical features from graph embedding data and identifying the unique complex spatial patterns of power systems, thereby ensuring accurate and robust state estimation. CNN uses standard forward and back propagation techniques for feature extraction and parameter update. During the forward propagation process, CNN processes the input data through a convolutional layer and applies a nonlinear activation function to extract relevant features:

[0050] Z [l] =W [l] ·A [l-1] +b [l]

[0051] A [l] =g [l] (Z[l] )

[0052] Update the network parameters by backpropagation. Specifically, the first step is to apply the derivative of the activation function to the input tensor dA [l] To obtain the intermediate value dZ [l] ,have to:

[0053]

[0054] Among them, L is the loss function, x i and are x and The i-th element of , in the process of back propagation, will use a matrix operation method called "full convolution", the specific mathematical expression is:

[0055]

[0056] Where W represents the filter and dZ[m,n] is a scalar obtained from the partial derivatives obtained from the previous layer.

[0057] In addition to the convolutional layer, the convolutional neural network also includes a maximum pooling layer to reduce the tensor size for improved computational efficiency, where the pooling layer achieves this by selecting the maximum value of each input region to ensure the accuracy of the gradient, which plays an important role in the back-propagation process. Finally, CNNs typically include two layers of fully connected networks for efficient feature extraction and state estimation. The accuracy of state estimation can be evaluated by indicators such as the root mean square error (RMSE) and standard deviation (STD), which are used to evaluate the difference between the estimated value and the actual value and the variability of the estimation error:

[0058]

[0059] The STD metric quantifies the variability or dispersion of a set of values, specifically:

[0060]

[0061] Among them, σ i represents the estimation error of the i-th node, is the average value of the estimation error.

[0062] Embodiment 2

[0063] The static state estimation system of the power system of the present invention comprises:

[0064] The first acquisition module is used to acquire the PMUs features E embedded in the graph of the power system;

[0065] The estimation module is used to input the PMUs features E embedded in the graph of the power system into the trained convolutional neural network model to obtain the static state of the power system.

[0066] As an implementation mode of the present invention, the process of obtaining the PMUs feature E embedded in the graph of the power system is:

[0067] a configuration module for configuring PMUs on r lines of the power system;

[0068] The second acquisition module is used to acquire PMUs measurement data;

[0069] The generation module is used to combine the PMUs measurement data with the node2vec-based graph embedding to generate the PMUs features E of the graph embedding of the power system.

[0070] As an implementation mode of the present invention, the graph of the power system embeds the PMUs features E=[E1, E2, ..., E m ], where E i is the graph embedding state vector corresponding to the measurement value of the i-th node.

[0071] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0072] Embodiment 3

[0073] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for estimating the static state of the power system are implemented, for example, including: obtaining the PMUs feature E of the power system graph embedding; inputting the PMUs feature E of the power system graph embedding into the trained convolutional neural network model to obtain the static state of the power system. The memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc. The processor, the network interface, and the memory are interconnected through an internal bus, which may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard architecture bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include a program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0074] Embodiment 4

[0075] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for estimating the static state of a power system are implemented, for example, including: obtaining the PMUs feature E of the graph embedded in the power system; inputting the PMUs feature E of the graph embedded in the power system into a trained convolutional neural network model to obtain the static state of the power system. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include a read-only memory (ROM), a hard disk, a flash memory, an optical disk, a magnetic disk, etc.

[0076] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0077] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0080] The above embodiment is only one of the implementation methods that can realize the technical solution of the present invention. The scope of protection claimed by the present invention is not limited only to this embodiment, but also includes changes, replacements and other implementation methods that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention.

Claims

1. A method for estimating the static state of a power system, characterized in that: include: Obtain the PMUs features E of the power system graph embedding; The PMUs features E embedded in the graph of the power system are input into the trained convolutional neural network model to obtain the static state of the power system.

2. The method for estimating the static state of a power system according to claim 1, characterized in that: The process of obtaining the PMUs features E embedded in the graph of the power system is as follows: Deploy PMUs on r lines of the power system; Obtain PMUs measurement data; The PMUs measurement data is combined with the node2vec-based graph embedding to generate the PMUs features E of the power system graph embedding.

3. The method for estimating the static state of a power system according to claim 2, characterized in that: The graph of the power system embeds the PMUs features E = [E1, E2, ..., E m ], where E i is the graph embedding state vector corresponding to the measurement value of the i-th node.

4. The method for estimating the static state of a power system according to claim 3, characterized in that: The graph embedding state vector E corresponding to the measurement value of the i-th node i for: Among them, z i is the d-dimensional node2vec-based graph embedding vector for the i-th element of the measurement vector z 5. The method for estimating the static state of a power system according to claim 4, characterized in that: The measurement vector z is: Among them, Y f ∈C r×N is the system admittance matrix, I f is the current vector, A∈R m×N is the relationship matrix between the state vector x and the voltage vector measurement V.

6. A power system static state estimation system, characterized in that: include: The first acquisition module is used to acquire the PMUs features E embedded in the graph of the power system; The estimation module is used to input the PMUs features E embedded in the graph of the power system into the trained convolutional neural network model to obtain the static state of the power system.

7. The power system static state estimation system according to claim 6, characterized in that: The process of obtaining the PMUs features E embedded in the graph of the power system is as follows: a configuration module for configuring PMUs on r lines of the power system; The second acquisition module is used to acquire PMUs measurement data; The generation module is used to combine the PMUs measurement data with the node2vec-based graph embedding to generate the PMUs features E of the graph embedding of the power system.

8. The power system static state estimation system according to claim 7, characterized in that: The graph of the power system embeds the PMUs features E = [E1, E2, ..., E m ], where E i is the graph embedding state vector corresponding to the measurement value of the i-th node.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for estimating the static state of a power system as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for estimating the static state of a power system as claimed in any one of claims 1 to 5 are implemented.

Images