Low-voltage power distribution network abnormal state identification method and device, storage medium and equipment

Abstract

The application discloses a low-voltage power distribution network abnormal state identification method and device, a storage medium and equipment. The method comprises the following steps: calculating the current deviation of each monitoring point according to the three-phase current of each monitoring point in the low-voltage power distribution network system; mapping the current deviation into a quantum bit superposition state, and constructing the wave function of the low-voltage power distribution network system through a multi-level quantization direct product operation according to the quantum bit superposition state of each monitoring point; determining the Hamiltonian according to the state variable and the topology configuration parameter of each monitoring point in the low-voltage power distribution network system; calculating the energy expectation value of the low-voltage power distribution network system according to the wave function and the Hamiltonian; comparing the energy expectation value with the preset energy range, and identifying the abnormal state of the low-voltage power distribution network system according to the comparison result. The method of the application realizes accurate and efficient identification and early warning of the system-level abnormal state, and overcomes the defects of high misjudgment rate and difficulty in depicting the correlation relationship of the traditional method.

Description

Technical Field

[0001] This application relates to the field of power system condition monitoring technology, and in particular to a method, device, storage medium and equipment for identifying abnormal conditions in low-voltage distribution networks. Background Technology

[0002] As the final link in the power system, the low-voltage distribution network directly connects to various user loads. Its operational stability is closely related to the reliability of power supply, and it is crucial for ensuring safe and efficient power transmission and meeting user electricity needs. With the development of distributed power generation grid connection, flexible load access, and diversified power loads, the topology of the low-voltage distribution network is becoming increasingly complex, load fluctuations are becoming more frequent, and the probability of abnormal operating conditions such as single-phase grounding, three-phase imbalance, line overload, and equipment failure has significantly increased. If these abnormal conditions are not identified and handled in a timely manner, they can easily lead to power outages, equipment damage, or even electrical fires, resulting in economic losses and impacting people's livelihoods.

[0003] Currently, the identification of abnormal conditions in low-voltage distribution networks mainly relies on traditional monitoring and analysis methods, which can be divided into two categories: one is the threshold judgment method based on a single monitoring point, which involves deploying monitoring equipment in distribution transformer areas and branch nodes to collect electrical parameters such as current and voltage, preset fixed thresholds, and judges an abnormality when the parameters exceed the thresholds; the other is the identification method based on traditional machine learning, which extracts statistical features of electrical parameters and trains a classification model to achieve anomaly identification and diagnosis.

[0004] However, existing methods have many limitations and are difficult to effectively adapt to the operational needs of complex low-voltage distribution networks: First, the single-monitoring-point threshold judgment method only focuses on the parameter changes of a single node, without considering the electrical correlation between monitoring points. It is easily affected by load fluctuations, resulting in high false positive rates and serious missed detections, and cannot achieve system-level global anomaly identification. Second, traditional machine learning methods have limited ability to mine high-dimensional, nonlinear electrical parameter features, making it difficult to adapt to scenarios with dynamic changes in distribution network topology. They are also highly dependent on sample data, and the identification accuracy drops significantly in scenarios with small samples or variable operating conditions. Third, the three-phase currents in low-voltage distribution networks are coupled and correlated. Existing methods mostly adopt a phase-by-phase independent analysis approach, ignoring the joint effect of the three-phase currents, making it difficult to accurately capture coordinated anomalies such as three-phase imbalance. Fourth, existing methods mostly rely on complex feature engineering, with cumbersome calculation processes and high engineering implementation costs, making it difficult to meet the real-time requirements of distribution network anomaly identification. Summary of the Invention

[0005] In view of this, this application provides a method, device, storage medium and equipment for identifying abnormal states in low-voltage distribution networks, which realizes accurate and efficient identification and early warning of system-level abnormal states.

[0006] According to a first aspect of this application, a method for identifying abnormal states in a low-voltage distribution network is provided, the method comprising: Calculate the current deviation of each monitoring point based on the three-phase current of each monitoring point in the low-voltage distribution network system; The current deviation is mapped to a superposition state of qubits, and the wave function of the low-voltage distribution network system is constructed by multi-level direct product operation based on the superposition state of qubits at each monitoring point. The Hamiltonian is determined based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system, wherein the Hamiltonian is used to describe the correlation between each monitoring point in the low-voltage distribution network system. Calculate the expected energy value of the low-voltage distribution network system based on the wave function and the Hamiltonian. The expected energy value is compared with the preset energy range, and the abnormal state of the low-voltage distribution network system is identified based on the comparison result.

[0007] Optionally, the step of calculating the current deviation at each monitoring point based on the three-phase current at each monitoring point in the low-voltage distribution network system includes: The three-phase currents are filtered and normalized. The normalized deviation between the normalized current of each phase and the historical normal mean of the corresponding phase is calculated and used as the current deviation.

[0008] Optionally, mapping the current deviation to a superposition state of qubits includes: The normal ground state probability amplitude corresponding to the current deviation is calculated by a Gaussian mapping function, wherein the normal ground state probability amplitude decreases monotonically as the current deviation increases. The corresponding abnormal excited state probability amplitude is calculated based on the normal ground state probability amplitude, so that the sum of the squares of the normal ground state probability amplitude and the abnormal excited state probability amplitude is 1; Using the normal ground state probability amplitude as the normal ground state weight and the abnormal excited state probability amplitude as the abnormal excited state weight, the superposition state of the qubit representing the single-phase current state is constructed; The superposition state of the qubit is represented as: ; In the formula, For monitoring points of The superposition state of qubits corresponding to the phase current; , They are respectively The normal ground state and abnormal excited state of the phase; , denoted as the probability amplitude of the normal ground state and the abnormal excited state in the superposition state.

[0009] Optionally, the step of constructing the wave function of the low-voltage distribution network system through multi-level direct product operations based on the superposition states of qubits at each monitoring point includes: The quantum bit superposition states of the three-phase current at the same monitoring point are directly productted to generate the overall quantum state of the monitoring point. The wave function of the low-voltage distribution network system is generated by performing a direct product operation on the overall quantum states of each monitoring point within the low-voltage distribution network system.

[0010] Optionally, determining the Hamiltonian based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system includes: The coupling strength of each monitoring point is calculated based on the line impedance between each monitoring point, wherein the coupling strength decreases as the line impedance increases; Calculate the local intensity of each monitoring point based on the load attributes of each monitoring point; The state variables of each monitoring point, the coupling strength, and the local strength are substituted into a preset energy function to calculate the Hamiltonian.

[0011] Optionally, calculating the expected energy value of the low-voltage distribution network system based on the wave function and the Hamiltonian includes: The inner product of the wavefunction, the Hamiltonian, and the conjugate transpose of the wavefunction is performed to obtain the scalar form of the expected energy value.

[0012] Optionally, identifying the abnormal state of the low-voltage distribution network system based on the comparison results includes: If the expected energy value is within the preset energy range, then the low-voltage distribution network system is determined to be in a normal state at the current moment. If the expected energy value exceeds the preset energy range, the low-voltage distribution network system is determined to be in an abnormal state at the current moment, and an early warning message is output. The upper and lower limits of the preset energy range are obtained based on the historical expected energy values ​​of the low-voltage distribution network system during normal operation.

[0013] According to a second aspect of this application, a low-voltage distribution network abnormal state identification device is provided, the device comprising: The deviation calculation module is used to calculate the current deviation of each monitoring point based on the three-phase current of each monitoring point in the low-voltage distribution network system. The quantum mapping module is used to map the current deviation into a superposition state of qubits, and to construct the wave function of the low-voltage distribution network system through a multi-level direct product operation based on the superposition state of qubits at each monitoring point. The modeling module is used to determine the Hamiltonian based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system, wherein the Hamiltonian is used to describe the correlation between each monitoring point in the low-voltage distribution network system. The state identification module is used to calculate the expected energy value of the low-voltage distribution network system based on the wave function and the Hamiltonian; and to compare the expected energy value with a preset energy range, and identify the abnormal state of the low-voltage distribution network system based on the comparison result.

[0014] Optionally, the low-voltage distribution network abnormal state identification device includes: The preprocessing module is used to filter and normalize the three-phase currents; The deviation calculation module is specifically used to calculate the standardized deviation between the normalized current of each phase and the historical normal mean of the corresponding phase, as the current deviation.

[0015] Optionally, the quantum mapping module is specifically used to calculate the normal ground state probability amplitude corresponding to the current deviation through a Gaussian mapping function, wherein the normal ground state probability amplitude monotonically decreases as the current deviation increases; calculate the corresponding abnormal excited state probability amplitude based on the normal ground state probability amplitude, so that the sum of the squares of the normal ground state probability amplitude and the abnormal excited state probability amplitude is 1; and construct the quantum bit superposition state characterizing the single-phase current state by using the normal ground state probability amplitude as the normal ground state weight and the abnormal excited state probability amplitude as the abnormal excited state weight. The superposition state of the qubit is represented as: ; In the formula, For monitoring points of The superposition state of qubits corresponding to the phase current; , They are respectively The normal ground state and abnormal excited state of the phase; , denoted as the probability amplitude of the normal ground state and the abnormal excited state in the superposition state.

[0016] Optionally, the quantum mapping module is specifically used to perform a direct product operation on the superposition states of the qubits of the three-phase current at the same monitoring point to generate the overall quantum state of the monitoring point; and to perform a direct product operation on the overall quantum states of each monitoring point in the low-voltage distribution network system to generate the wave function of the low-voltage distribution network system.

[0017] Optionally, the modeling module is specifically used to calculate the coupling strength of each monitoring point based on the line impedance between each monitoring point, wherein the coupling strength decreases as the line impedance increases; calculate the local strength of each monitoring point based on the load attributes of each monitoring point; and substitute the state variables of each monitoring point, the coupling strength, and the local strength into a preset energy function to calculate the Hamiltonian.

[0018] Optionally, the state recognition module is specifically used to perform an inner product operation on the wave function, the Hamiltonian, and the conjugate transpose of the wave function to obtain the expected energy value in scalar form.

[0019] Optionally, the state recognition module is specifically used to determine that the low-voltage distribution network system is in a normal state at the current moment if the expected energy value is within the preset energy range; and to determine that the low-voltage distribution network system is in an abnormal state at the current moment and output warning information if the expected energy value exceeds the preset energy range. The upper and lower limits of the preset energy range are obtained based on the historical expected energy values ​​of the low-voltage distribution network system during normal operation.

[0020] According to a third aspect of this application, a readable storage medium is provided on which a program or instructions are stored, which, when executed by a processor, implement the steps of the above-described method for identifying abnormal states in a low-voltage distribution network.

[0021] According to a fourth aspect of this application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described low-voltage distribution network abnormal state identification method.

[0022] By mapping the three-phase current deviations at each monitoring point to a superposition state of qubits and constructing a system wave function, a high-dimensional state representation of the distribution network from phase-by-phase, single-point, to global levels is achieved, thus preserving the joint state information of the three-phase currents. Based on this, the Ising model is used to define the system Hamiltonian according to the actual topology and line parameters. The complex multidimensional electrical characteristics are transformed into a physically meaningful energy expectation value through the inner product operation of the wave function and the Hamiltonian. The comparison between the energy expectation value and historical normal ranges allows for accurate and efficient identification and early warning of system-level abnormal states. This overcomes the shortcomings of the single-point threshold method, which suffers from high false positive rates and a single perception dimension due to its inability to characterize the physical relationships between nodes, effectively reducing both false positive and false negative rates. While reducing reliance on sample data, it better adapts to scenarios with dynamic topology changes, meeting the accuracy requirements for identification in scenarios with small samples or variable operating conditions. Furthermore, the use of linear algebra and matrix operations for anomaly detection simplifies the computational process of complex feature engineering, helping to reduce engineering implementation costs and meet real-time requirements.

[0023] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating the low-voltage distribution network abnormal state identification method provided in an embodiment of this application is shown. Figure 2 This paper shows a structural block diagram of a low-voltage distribution network abnormal state identification device provided in an embodiment of this application; Figure 3 A schematic diagram of the electronic structure of a computer device provided in an embodiment of this application is shown. Detailed Implementation

[0025] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0026] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0027] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “attached” to another element, it can be directly connected or attached to the other element, or there may be intermediate elements present. Furthermore, the term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0028] Exemplary embodiments according to this application will now be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in many different forms and should not be construed as being limited to the embodiments set forth herein. It should be understood that these embodiments are provided so that the disclosure of this application is thorough and complete, and that the concept of these exemplary embodiments is fully conveyed to those skilled in the art.

[0029] This embodiment provides a method for identifying abnormal states in a low-voltage distribution network, such as... Figure 1 As shown, the method includes: Step 101: Calculate the current deviation of each monitoring point based on the three-phase current of each monitoring point in the low-voltage distribution network system.

[0030] Specifically, multiple monitoring points are deployed in the low-voltage distribution network system. These monitoring points are located at key locations such as the main switch of the distribution transformer area, branch lines, and user access terminals, and are used to collect three-phase current data in real time. After collecting the three-phase current data, the three-phase current data of each monitoring point is time-aligned with the topology state variables according to the timestamp to obtain the time-aligned three-phase current of each monitoring point.

[0031] In this embodiment, by comparing the difference between the real-time acquired three-phase current and the reference value, the deviation quantity that reflects the system fluctuation characteristics is extracted. This eliminates the dimensional influence caused by the difference in load capacity at different monitoring points, ensuring the consistency of the state characterization.

[0032] In practical applications, step 101, which is to calculate the current deviation of each monitoring point based on the three-phase current of each monitoring point in the low-voltage distribution network system, specifically includes: filtering and normalizing the three-phase current; calculating the standardized deviation between the normalized current of each phase and the historical normal average value of the corresponding phase, as the current deviation.

[0033] Specifically, the normalized three-phase current is: ; ; Standardization bias, i.e.: ; In the formula, For normalization Phase current; For the original Phase current; , They are respectively Minimum and maximum values ​​of phase current under historical normal dataset; , , They are phase A, phase B, and phase C, respectively. For monitoring points of Standardized deviation of phase current from its historical normal mean; For monitoring points Normalized Phase current; For monitoring points of The mean of phase current in historical normal datasets; For monitoring points of The standard deviation of phase current under historical normal dataset, which is the three-phase current time series data of the low-voltage distribution network system under normal operating conditions and the time period of the current sequence to be detected.

[0034] In this embodiment, filtering is first used to remove potential noise interference from the current data, and the filtered three-phase currents are then normalized to map each phase current data to the range [0, 1], thus eliminating the influence of dimensions. This improves the quality of the current data and makes the current states of all monitoring points comparable. Then, using the historical normal average as a benchmark, the current of each phase is compared with the corresponding historical normal average to obtain the current deviation. This allows the calculated current deviation to more accurately reflect whether the three-phase current is in an abnormal state, providing a more reliable and accurate data foundation for subsequent identification of abnormal states in low-voltage distribution networks based on current deviation.

[0035] Understandably, adaptive median filtering is the preferred method for filtering. Compared to ordinary mean filtering, adaptive median filtering can dynamically adjust the size of the filtering window based on local noise characteristics. While effectively eliminating impulse noise, it preserves the edge features of the current waveform to the greatest extent possible, avoiding the masking of fault abrupt signals due to excessive smoothing. In practice, the minimum and maximum sizes of the filtering window are set. Using a single current sampling point as the center, the current data within the current window is selected, and the median, minimum, and maximum values ​​are calculated. If the center sampling point is determined to be a noise point, the window size is expanded and the determination is repeated until the window reaches its maximum size or is determined to be non-noise. Finally, the median current value of the current in the current window replaces the noise point. If it is non-noise, the original value is retained. This process is repeated for all current sampling points, and the filtered three-phase current sequence is finally output.

[0036] Step 102: Map the current deviation to a superposition state of qubits, and construct the wave function of the low-voltage distribution network system through a multi-level direct product operation based on the superposition state of qubits at each monitoring point.

[0037] In this embodiment, the current deviation is mapped to a superposition of qubit states, realizing a mapping from a single numerical value to a two-dimensional probability amplitude space. Through multi-level direct product operations, the discrete monitoring points and the quantum local states of each phase are integrated into a unified system wavefunction. This allows for exponential holographic encoding of the three-phase current states and their combinations at all monitoring points within the system without losing any local node state information. The state correlation between any two monitoring points is implicitly embedded in the structure of the high-dimensional wavefunction, solving the problem of traditional methods struggling to characterize complex coupling relationships between multiple nodes and improving the sensitivity for identifying hidden fault characteristics.

[0038] In practical applications, step 102 maps the current deviation to a superposition state of qubits. Specifically, this includes: calculating the normal ground state probability amplitude corresponding to the current deviation using a Gaussian mapping function; calculating the corresponding abnormal excited state probability amplitude based on the normal ground state probability amplitude, such that the sum of the squares of the normal ground state probability amplitude and the abnormal excited state probability amplitude is 1; and constructing a superposition state of qubits representing the single-phase current state by using the normal ground state probability amplitude as the normal ground state weight and the abnormal excited state probability amplitude as the abnormal excited state weight.

[0039] Among them, the normal ground state probability amplitude decreases monotonically as the current deviation increases.

[0040] In this embodiment, current deviation is used as an input variable. Utilizing the high sensitivity of the Gaussian function in the central region and the smooth decay characteristics of the edge region, current fluctuations in physical space are transformed into rotation angles (probability amplitudes) in Hilbert space. The probability amplitudes of anomalous excited states are calculated based on the normalization conditions of quantum mechanics, and a superposition state of qubits is constructed. This allows for a more nuanced reflection of minute deviations and uncertainties in the state through continuous probabilistic characterization. It eliminates the need to design separate features for anomalies such as power grid circuit breaks, leakage, and harmonic interference. System faults can be detected in advance through the deviation of probability amplitudes, greatly simplifying the logical redundancy of system situation modeling. This reduces the dependence of low-voltage distribution network anomaly identification on sample data and provides better adaptability to early, weak anomalies and complex operating condition changes.

[0041] Specifically, the normal ground-state probability amplitude corresponding to the current deviation is calculated using the following formula: ; The abnormal excited state probability amplitude corresponding to the normal ground state probability amplitude is calculated using the following formula: ; Therefore, the current deviation The smaller the value, the more normal the current. When The closer to 1, the higher the normal probability. The higher the probability, the lower the probability of an anomaly. The higher the value, the more quantized the current state can be represented.

[0042] The superposition state of this qubit can be represented as: ; In the formula, For monitoring points of The probability that the phase is in the normal ground state; For monitoring points of The probability that a phase is in an abnormal excited state; For monitoring points of Phase current deviation; For monitoring points of The superposition state of qubits corresponding to the phase current; , They are respectively The normal ground state and abnormal excited state of the phase; , denoted as the probability amplitude of the normal ground state and the abnormal excited state in the superposition state.

[0043] In practical applications, step 102 involves constructing the wave function of the low-voltage distribution network system based on the superposition state of the qubits at each monitoring point through a multi-level direct product operation. Specifically, this includes: performing a direct product operation on the superposition state of the qubits of the three-phase currents at the same monitoring point to generate the overall quantum state of the monitoring point; and performing a direct product operation on the overall quantum states of each monitoring point within the low-voltage distribution network system to generate the wave function of the low-voltage distribution network system.

[0044] In this embodiment, the superposition state of each phase current is a two-dimensional vector (single quantum bit). By performing a direct product operation on the superposition states of the three-phase currents within the same monitoring point, these two-dimensional vectors are combined into a higher-dimensional vector (global quantum state) to represent the joint state of the three-phase currents at the entire monitoring point. Based on the physical connection logic of the distribution network, the global quantum states of all monitoring points across the network are coupled by a second direct product, thereby deriving a global wave function describing the spatiotemporal evolution of the entire system. This transforms fragmented monitoring data into a unified complex vector with global coherence, and replaces the massive feature-anomaly rule table with the complex vector, achieving accurate quantization of the probability of normal or abnormal currents. This helps enhance the system's characterization depth for complex nonlinear fault behaviors such as cross-phase disturbances and cross-node evolution, enabling anomaly identification to better adapt to complex scenarios.

[0045] Specifically, the overall quantum state is represented as: ; Through quantum direct product operation The two-dimensional single-qubit superposition states of the three phases at the monitoring point are combined into 2 3 =8-dimensional joint quantum state, which can completely characterize the 8 joint states of three-phase current, such as all three phases are normal, phases A and B are normal and phase C is abnormal, etc.

[0046] The wave function is expressed as: ; In the formula, For monitoring points The overall quantum state; This is a quantum state direct product operation; , , monitoring points The superposition state of quantum bits corresponding to the A-phase, B-phase, and C-phase currents; It is a wave function; This represents the total number of monitoring points.

[0047] The wavefunction employs a three-level hierarchical direct product structure. The first level is a phase-split quantum state: the three-phase currents A, B, and C at each monitoring point are mapped to a single-qubit superposition state. , , The first level represents the normal or abnormal probability of each phase independently; the second level is the quantum state of the monitoring point: the three-phase quantum states of each monitoring point are directly productted to obtain the overall quantum state of that monitoring point. The first level fully preserves the joint state information of the three phases at each monitoring point, such as combinations like AB phase normal and C phase abnormal. The second level is the system quantum state: the overall quantum state of all monitoring points is directly productted to finally generate the wave function of the low-voltage distribution network system. This hierarchical structure design not only fully preserves the joint state information of the three-phase current at each monitoring point, but also integrates the global state of all monitoring points, realizing a precise quantum characterization of the low-voltage distribution network system from local to global, and providing a high-fidelity global state carrier for subsequent Hamiltonian modeling and system energy expectation value calculation.

[0048] Step 103: Determine the Hamiltonian based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system.

[0049] Hamiltonian is used to describe the correlation between monitoring points in a low-voltage distribution network system.

[0050] Specifically, state variables are physical quantities used to characterize the operating status of each monitoring point. For example, the switching states corresponding to the three-phase currents A, B, and C, the switching states of the main switch of the distribution transformer area, the branch switches, and the user inlet switches are used as state variables. This facilitates real-time correction of the electrical connectivity between monitoring points. For instance, when a branch switch is open, the electrical connection between that branch monitoring point and the main switch monitoring point of the distribution transformer area is directly invalidated, ensuring that the coupling strength calculation of the Ising model in subsequent steps fully reflects the actual operating state.

[0051] In this embodiment, the Hamiltonian is determined by combining the state variables of each monitoring point with the topology configuration parameters, which can comprehensively and accurately reflect the interactions between the various parts of the system. This enables the system to effectively identify abnormal states under various complex and changing topology conditions, making it more adaptable than traditional machine learning methods.

[0052] In practical application scenarios, step 103, which is to determine the Hamiltonian based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system, specifically includes: calculating the coupling strength of each monitoring point based on the line impedance between each monitoring point; calculating the local strength of each monitoring point based on the load attributes of each monitoring point; and substituting the state variables, coupling strength, and local strength of each monitoring point into the preset energy function to calculate the Hamiltonian.

[0053] The coupling strength decreases as the line impedance increases. Coupling strength characterizes the degree of electrical connection between any two monitoring points; the smaller the impedance, the greater the coupling strength, and the stronger the interaction between the two monitoring points. Local strength quantifies the weight of a single node's influence on the system energy, and is determined by both the node's load importance and its rated power percentage.

[0054] Specifically, the coupling strength and local strength can be calculated using the following formulas: ; ; In the formula, For monitoring points With monitoring points Line impedance of the line; For monitoring points With monitoring points The resistance of the circuit; For monitoring points With monitoring points Reactance of the line; For monitoring points The load importance weight is a priority coefficient set according to the importance of each monitoring point. It can be reasonably set according to the application scenario. For example, the weight of monitoring points for hospitals is higher than the weight of monitoring points for residents. For monitoring points The rated load power, i.e. the load capacity of the monitoring point; This refers to the rated total load power of the low-voltage distribution network system.

[0055] In this embodiment, line impedance is inversely mapped to the coupling strength between nodes, and load attributes are transformed into local strengths characterizing the inherent properties of nodes. This allows the physical topology constraints of the power grid and operating environment parameters to be parameterized and embedded into a preset energy function, constructing a Hamiltonian adapted to the characteristics of low-voltage distribution networks. This quantifies the electrical correlation strength between monitoring points and assigns higher weights to the abnormal influences of important load nodes, achieving a clearly defined energy-based modeling of the distribution network system state. This transforms the complex problem of determining the operating state of the distribution network into a problem of assessing the stability of system energy. It not only accurately characterizes the nonlinear, highly coupled current interactions in low-voltage distribution networks, enhancing the model's sensitivity to changes in grid topology, but also avoids the limitations of traditional methods that treat each node as an independent entity.

[0056] It is worth mentioning that the state variable can be represented using the Pauli z operator, which can be determined based on the relative magnitudes of the probabilities of the normal ground state and the abnormal excited state in the superposition of the qubits at the monitoring point. Specifically, when the probability of the normal ground state is greater than the probability of the abnormal excited state, the monitoring point is determined to be in a normal state, and the state variable takes a value of +1; conversely, the monitoring point is determined to be in an abnormal state, and the state variable takes a value of -1.

[0057] Specifically, the Hamiltonian can be expressed as: ; In the formula, For Hamiltonian, For monitoring points With monitoring points The coupling strength between them; , monitoring points Monitoring points Pauli z operator; For monitoring points Local intensity.

[0058] It is worth mentioning that, This is a coupling term used to characterize the electrical correlation strength between monitoring points. The closer the electrical distance between two monitoring points (impedance), the stronger the correlation. (smaller) The larger the value, the stronger the interaction between monitoring points. If... and When the signs are the same (states are consistent), the phase is negative, the system energy decreases, and the physical law of more stable state coordination of distribution network nodes under low voltage load is applied. This is a local field strength term used to characterize the load importance weight of a single monitoring point, and the more important the load (…). The larger the value, the higher the proportion of rated power. The larger the value, the more abnormal the monitoring point is. The more significant the effect on system energy, the better.

[0059] Step 104: Calculate the expected energy value of the low-voltage distribution network system based on the wave function and Hamiltonian.

[0060] In this embodiment, the energy expectation value is the product of combining the system state (wave function) with the system physical model (Hamiltonian). Through inner product operations, the high-dimensional wave function is compressed into the energy expectation value, realizing a global quantitative representation of the overall operating state of the distribution network. This allows the energy expectation value to comprehensively reflect the coordination and stability of the entire network node state, fundamentally overcoming the shortcomings of the traditional single-point threshold method, which ignores the correlation between nodes and has a high rate of false positives and false negatives.

[0061] In practical applications, the expected energy value of a low-voltage distribution network system is calculated based on the wave function and Hamiltonian. Specifically, this involves performing an inner product operation on the wave function, Hamiltonian, and the conjugate transpose of the wave function to obtain the expected energy value in scalar form.

[0062] Specifically, the expected energy value can be expressed as: ; In the formula, This represents the expected energy value. This is an inner product operation; It is a wave function; For Hamiltonian.

[0063] In this embodiment, the Hamiltonian is applied to the right-hand side of the system wavefunction to obtain a new quantum state. This process involves using an energy model to measure the system's state distribution. Then, the new quantum state is multiplied by the left-hand side of the system wavefunction to obtain an overall abnormal energy scalar value (expected energy value) corresponding to the current state of the low-voltage distribution network. When the distribution network is operating normally, the states of each monitoring point are coordinated and stable, and the expected energy value is within the historically normal low range. When an anomaly occurs in the distribution network, such as an overload at a node or a line fault, the consistency of the node states is disrupted, and the expected energy value increases significantly.

[0064] Step 105: Compare the expected energy value with the preset energy range, and identify the abnormal state of the low-voltage distribution network system based on the comparison results.

[0065] The low-voltage distribution network abnormal state identification method provided in this application maps the three-phase current deviations at each monitoring point to a superposition state of qubits and constructs a system wave function, achieving a high-dimensional state representation of the distribution network from phase-by-phase, single-point, to global levels, thus fully preserving the joint state information of the three-phase currents. Based on this, the system Hamiltonian is defined using the Ising model based on the actual topology and line parameters, and the complex multidimensional electrical characteristics are transformed into an energy expectation value with clear physical meaning through the inner product operation of the wave function and the Hamiltonian. The method uses the comparison results of the energy expectation value and historical normal ranges to accurately and efficiently identify and warn of system-level abnormal states. This overcomes the shortcomings of the single-point threshold method, which suffers from high false positive rates and a single perception dimension due to its inability to characterize the physical relationships between nodes, effectively reducing both false positive and false negative rates. While reducing dependence on sample data, it can better adapt to scenarios with dynamic topology changes and meet the identification accuracy requirements in scenarios with small samples or variable operating conditions. Moreover, the anomaly judgment is achieved through linear algebra and matrix operations, simplifying the calculation process of complex feature engineering, helping to reduce engineering implementation costs and meet real-time requirements.

[0066] In one embodiment, step 105, which identifies the abnormal state of the low-voltage distribution network system based on the comparison result, specifically includes: if the expected energy value is within a preset energy range, then the low-voltage distribution network system is determined to be in a normal state at the current moment; if the expected energy value exceeds the preset energy range, then the low-voltage distribution network system is determined to be in an abnormal state at the current moment, and an early warning message is output.

[0067] In this embodiment, anomaly detection is achieved by comparing the current energy value with the historical normal operating energy range. If the expected energy value is within the range, it indicates that the system is operating stably; if it exceeds the range, it indicates that the system has experienced abnormal fluctuations. This judgment method is logically simple and intuitive, avoiding the drawbacks of the "box decision" approach in traditional machine learning methods. It provides interpretable diagnostic criteria for operation and maintenance personnel, enabling accurate and efficient identification and early warning of system-level abnormal states.

[0068] The upper and lower limits of the preset energy range are based on the statistical analysis of historical energy expectation values ​​during normal operation of the low-voltage distribution network system. This allows for the inclusion of more samples from typical operating scenarios in the identification of power grid anomalies, avoiding the problem of insufficient sample size due to overly restrictive operating conditions. In other words, the larger the sample size, the more accurately the calculated minimum and maximum energy expectation values ​​reflect the true energy boundaries of normal operation of the low-voltage distribution network, naturally avoiding threshold setting errors caused by small data samples. This facilitates accurate and efficient identification of low-voltage distribution network anomalies using a simplified extreme value range determination rule, balancing theoretical rigor with ease of engineering implementation. For example, in the normal operation sample, the historical energy expectation value sequence E(t) is calculated, and its mean Es and standard deviation Eσ are taken; the normal range is defined as [Es...]. [k·Eσ, Es+ k·Eσ]; or the maximum value in the historical energy expectation sequence E(t) is taken as the upper limit of the preset energy range, and the minimum value is taken as the lower limit of the preset energy range.

[0069] The low-voltage distribution network abnormal state identification method provided in this application embodiment can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0070] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0071] Furthermore, such as Figure 2 As shown, as a specific implementation of the above-mentioned low-voltage distribution network abnormal state identification method, this application embodiment provides a low-voltage distribution network abnormal state identification device 200, which includes: a deviation calculation module 201, a quantum mapping module 202, a modeling module 203, and a state identification module 204.

[0072] Among them, the deviation calculation module 201 is used to calculate the current deviation of each monitoring point based on the three-phase current of each monitoring point in the low-voltage distribution network system. The quantum mapping module 202 is used to map the current deviation into a superposition state of qubits, and to construct the wave function of the low-voltage distribution network system through a multi-level direct product operation based on the superposition state of qubits at each monitoring point. Modeling module 203 is used to determine Hamiltonian quantities based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system. Hamiltonian quantities are used to describe the correlation between each monitoring point in the low-voltage distribution network system. The state identification module 204 is used to calculate the expected energy value of the low-voltage distribution network system based on the wave function and Hamiltonian; and to compare the expected energy value with the preset energy range, and identify the abnormal state of the low-voltage distribution network system based on the comparison result.

[0073] Furthermore, the low-voltage distribution network abnormality identification device includes: The preprocessing module (not shown in the figure) is used to filter and normalize the three-phase current. The deviation calculation module 201 is specifically used to calculate the standardized deviation between the normalized current of each phase and the historical normal mean of the corresponding phase, as the current deviation.

[0074] Furthermore, the quantum mapping module 202 is specifically used to calculate the normal ground state probability amplitude corresponding to the current deviation through a Gaussian mapping function, wherein the normal ground state probability amplitude monotonically decreases as the current deviation increases; calculate the corresponding abnormal excited state probability amplitude based on the normal ground state probability amplitude, so that the sum of the squares of the normal ground state probability amplitude and the abnormal excited state probability amplitude is 1; and construct a quantum bit superposition state characterizing the single-phase current state by using the normal ground state probability amplitude as the normal ground state weight and the abnormal excited state probability amplitude as the abnormal excited state weight. The superposition state of a quantum bit is represented as: ; In the formula, For monitoring points of The superposition state of qubits corresponding to the phase current; , They are respectively The normal ground state and abnormal excited state of the phase; , denoted as the probability amplitude of the normal ground state and the abnormal excited state in the superposition state.

[0075] Furthermore, the quantum mapping module 202 is specifically used to perform a direct product operation on the superposition state of the qubits of the three-phase current at the same monitoring point to generate the overall quantum state of the monitoring point; and to perform a direct product operation on the overall quantum states of each monitoring point in the low-voltage distribution network system to generate the wave function of the low-voltage distribution network system.

[0076] Furthermore, the modeling module 203 is specifically used to calculate the coupling strength of each monitoring point based on the line impedance between each monitoring point, wherein the coupling strength decreases as the line impedance increases; calculate the local strength of each monitoring point based on the load attributes of each monitoring point; and substitute the state variables, coupling strength, and local strength of each monitoring point into a preset energy function to calculate the Hamiltonian.

[0077] Furthermore, the state recognition module 204 is specifically used to perform an inner product operation on the wave function, Hamiltonian, and conjugate transpose of the wave function to obtain the expected energy value in scalar form.

[0078] Furthermore, the state recognition module 204 is specifically used to determine that the low-voltage distribution network system is in a normal state at the current moment if the expected energy value is within the preset energy range; and to determine that the low-voltage distribution network system is in an abnormal state at the current moment if the expected energy value exceeds the preset energy range, and to output early warning information. The upper and lower limits of the preset energy range are obtained based on the historical expected energy values ​​of the low-voltage distribution network system during normal operation.

[0079] Specific limitations regarding the low-voltage distribution network abnormality identification device can be found in the limitations of the low-voltage distribution network abnormality identification method described above, and will not be repeated here. Each module in the aforementioned low-voltage distribution network abnormality identification device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0080] Based on the above, Figure 1 Accordingly, embodiments of this application also provide a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figure 1 The method for identifying abnormal states in low-voltage distribution networks is shown.

[0081] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0082] Based on the above, Figure 1 The method shown, and Figure 2 The virtual device embodiment shown is designed to achieve the above objectives, such as... Figure 3 As shown in the figure, this application embodiment also provides a computer device 300, which includes a processor 301 and a memory 302. The memory 302 stores a program or instructions that can run on the processor 301. When the program or instructions are executed by the processor 301, they implement the above-mentioned... Figure 1 The method for identifying abnormal states in low-voltage distribution networks is shown.

[0083] The memory 302 can be used to store software programs and various data. The memory 302 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 302 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 302 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0084] Processor 301 may include one or more processing units; optionally, processor 301 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 301.

[0085] Computer equipment can specifically include personal computers, servers, network devices, etc.

[0086] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB ports, card reader ports, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0087] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0088] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platform, or it can be implemented by hardware.

[0089] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0090] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. A method for identifying abnormal states in a low-voltage distribution network, characterized in that, The method includes: Calculate the current deviation of each monitoring point based on the three-phase current of each monitoring point in the low-voltage distribution network system; The current deviation is mapped to a superposition state of qubits, and the wave function of the low-voltage distribution network system is constructed by multi-level direct product operation based on the superposition state of qubits at each monitoring point. The Hamiltonian is determined based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system, wherein the Hamiltonian is used to describe the correlation between each monitoring point in the low-voltage distribution network system. Calculate the expected energy value of the low-voltage distribution network system based on the wave function and the Hamiltonian. The expected energy value is compared with the preset energy range, and the abnormal state of the low-voltage distribution network system is identified based on the comparison result.

2. The method for identifying abnormal states in low-voltage distribution networks according to claim 1, characterized in that, The calculation of the current deviation at each monitoring point based on the three-phase current at each monitoring point in the low-voltage distribution network system includes: The three-phase currents are filtered and normalized. The normalized deviation between the normalized current of each phase and the historical normal mean of the corresponding phase is calculated and used as the current deviation.

3. The method for identifying abnormal states in low-voltage distribution networks according to claim 1, characterized in that, The step of mapping the current deviation to a superposition state of qubits includes: The normal ground state probability amplitude corresponding to the current deviation is calculated by a Gaussian mapping function, wherein the normal ground state probability amplitude decreases monotonically as the current deviation increases. The corresponding abnormal excited state probability amplitude is calculated based on the normal ground state probability amplitude, so that the sum of the squares of the normal ground state probability amplitude and the abnormal excited state probability amplitude is 1; Using the normal ground state probability amplitude as the normal ground state weight and the abnormal excited state probability amplitude as the abnormal excited state weight, the superposition state of the qubit representing the single-phase current state is constructed; The superposition state of the qubit is represented as: ； In the formula, For monitoring points of The superposition state of qubits corresponding to the phase current; , They are respectively The normal ground state and abnormal excited state of the phase; , denoted as the probability amplitude of the normal ground state and the abnormal excited state in the superposition state.

4. The method for identifying abnormal states in low-voltage distribution networks according to claim 1, characterized in that, The construction of the wave function of the low-voltage distribution network system based on the superposition states of qubits at each monitoring point through multi-level direct product operations includes: The quantum bit superposition states of the three-phase current at the same monitoring point are directly productted to generate the overall quantum state of the monitoring point. The wave function of the low-voltage distribution network system is generated by performing a direct product operation on the overall quantum states of each monitoring point within the low-voltage distribution network system.

5. The method for identifying abnormal states in low-voltage distribution networks according to claim 4, characterized in that, The determination of the Hamiltonian quantity based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system includes: The coupling strength of each monitoring point is calculated based on the line impedance between each monitoring point, wherein the coupling strength decreases as the line impedance increases; Calculate the local intensity of each monitoring point based on the load attributes of each monitoring point; The state variables of each monitoring point, the coupling strength, and the local strength are substituted into a preset energy function to calculate the Hamiltonian.

6. The method for identifying abnormal states in a low-voltage distribution network according to any one of claims 1 to 5, characterized in that, The calculation of the energy expectation value of the low-voltage distribution network system based on the wave function and the Hamiltonian includes: The inner product of the wavefunction, the Hamiltonian, and the conjugate transpose of the wavefunction is performed to obtain the scalar form of the expected energy value.

7. The method for identifying abnormal states in a low-voltage distribution network according to any one of claims 1 to 5, characterized in that, The step of identifying the abnormal state of the low-voltage distribution network system based on the comparison results includes: If the expected energy value is within the preset energy range, then the low-voltage distribution network system is determined to be in a normal state at the current moment. If the expected energy value exceeds the preset energy range, the low-voltage distribution network system is determined to be in an abnormal state at the current moment, and an early warning message is output. The upper and lower limits of the preset energy range are obtained based on the historical expected energy values ​​of the low-voltage distribution network system during normal operation.

8. A device for identifying abnormal conditions in a low-voltage distribution network, characterized in that, The device includes: The deviation calculation module is used to calculate the current deviation of each monitoring point based on the three-phase current of each monitoring point in the low-voltage distribution network system. The quantum mapping module is used to map the current deviation into a superposition state of qubits, and to construct the wave function of the low-voltage distribution network system through a multi-level direct product operation based on the superposition state of qubits at each monitoring point. The modeling module is used to determine the Hamiltonian based on the state variables and topology configuration parameters of each monitoring point in the low-voltage distribution network system, wherein the Hamiltonian is used to describe the correlation between each monitoring point in the low-voltage distribution network system. The state identification module is used to calculate the expected energy value of the low-voltage distribution network system based on the wave function and the Hamiltonian; and, The expected energy value is compared with the preset energy range, and the abnormal state of the low-voltage distribution network system is identified based on the comparison result.

9. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the low-voltage distribution network abnormal state identification method as described in any one of claims 1 to 7.

10. 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, it implements the low-voltage distribution network abnormal state identification method as described in any one of claims 1 to 7.

Images