A power distribution network digital twin dynamic perception method and system

Abstract

This invention discloses a dynamic sensing method and system for a digital twin of a distribution network. The method includes: acquiring real-time data on the operation of the distribution network; monitoring node changes and line status changes based on the real-time data; updating the distribution network topology diagram in the established digital twin model of the distribution network in real time based on node and line status changes; analyzing the operating parameters of the distribution network through the digital twin model based on real-time and historical data, and obtaining analysis results; and detecting and locating operational faults in the distribution network through the digital twin model based on the analysis results. This invention provides a dynamic sensing method and system for a digital twin of a distribution network based on multi-dimensional network topology and parameter changes, which can capture and reflect the changing network structure and parameter changes in the distribution network in real time, improve the dynamic sensing capability of the digital twin, and thus support fault early warning and rapid recovery of the distribution network.

Description

Technical Field

[0001] This invention relates to the field of dynamic sensing technology for digital twins of distribution networks, and more specifically, to a dynamic sensing method and system for digital twins of distribution networks. Background Technology

[0002] With the increasing complexity and intelligence of power systems, traditional methods of distribution network monitoring and management can no longer meet the needs of modern power grid operation. Digital twin technology, as an emerging digital technology, is gradually being applied to power systems to improve the operational efficiency and reliability of the power grid.

[0003] Digital twin technology refers to the synchronous updating and interaction between a physical entity and its digital model by establishing a digital model of the physical entity. Specifically, a digital twin is a real-time, dynamic, and high-precision digital model that reflects the state, behavior, and operating environment of the physical entity. The core of digital twin technology lies in data-driven operation. It involves collecting data from the physical entity through sensors, IoT devices, and other means, and inputting this data into the digital model in real time, thereby achieving accurate simulation and prediction of the physical entity.

[0004] A typical digital twin system architecture generally includes the following components:

[0005] Data Acquisition Layer: Responsible for acquiring real-time data from physical entities, including sensor data, historical data, environmental data, etc. This layer has a wide range of data sources, covering various devices and operating environments within the power system.

[0006] Data transmission and processing layer: This layer transmits the collected data to the data processing center via the network for data cleaning, filtering, and preprocessing. Key technologies in this layer include edge computing, distributed computing, and big data processing technologies to ensure the timeliness and accuracy of data processing.

[0007] Digital Twin Model Layer: Based on the preprocessed data, a digital twin model corresponding to the physical entity is established. The core components of the model include physical modeling, data-driven modeling, and simulation algorithms. Physical modeling is mainly based on the physical laws of the power system, while data-driven modeling uses machine learning and artificial intelligence technologies to make predictions and analyses based on historical and real-time data.

[0008] Application and Service Layer: This layer provides users with a visual interface for the digital twin, analytical tools, and a decision support system. Users can monitor, simulate, and control the digital twin through this interface, thereby optimizing the operation of the power system.

[0009] In the field of power distribution networks, digital twin technology has been widely applied to equipment monitoring, fault diagnosis, operation optimization, and intelligent maintenance. For example, a digital twin can monitor the operating status of distribution transformers in real time and provide early warnings of potential faults through predictive analysis, thereby achieving intelligent fault diagnosis and maintenance.

[0010] However, with the expansion and increasing complexity of power distribution networks, the network topology and operating parameters within them are becoming increasingly diverse and dynamic. This places higher demands on digital twin technology, primarily in the following aspects:

[0011] Real-time requirements: Network topology and operating parameters in distribution networks may change frequently, and traditional static digital twin models are difficult to adapt to such dynamic changes. Therefore, how to achieve real-time updates and dynamic sensing of digital twin models has become a key issue.

[0012] Multi-source data fusion: Data in power distribution networks comes from diverse sources, including sensor data, historical operational data, and environmental data. These data typically have different formats and time scales. Effectively fusing this multi-source data into a digital twin is a major challenge for the application of digital twin technology in power distribution networks.

[0013] Massive parallel computing: As the number of nodes in a distribution network increases, the amount of data and computation required for digital twins also grows dramatically. Traditional single-node computing methods are insufficient to meet the real-time simulation and analysis needs of large-scale distribution networks, necessitating the adoption of parallel and distributed computing technologies to improve computational efficiency.

[0014] However, while existing digital twin technology has made some progress in the application of power distribution networks, it still has significant shortcomings in dealing with changes in multi-dimensional network topology and parameters:

[0015] Slow response speed: Existing digital twin systems typically require a long time to update the model when faced with rapid changes in the distribution network topology, resulting in a slow response speed that cannot meet the requirements of real-time monitoring and control.

[0016] Insufficient sensing accuracy: Due to the immaturity of multi-source data fusion technology, existing systems often suffer from data errors and delays when sensing changes in distribution network operating parameters, affecting the accuracy and reliability of digital twins.

[0017] Low computational efficiency: In large-scale power distribution network scenarios, the computational burden of digital twins is extremely heavy. Existing systems are unable to efficiently process massive amounts of data, resulting in low computational efficiency and affecting the overall system performance.

[0018] Therefore, a technology is needed to realize dynamic sensing technology for digital twins of distribution networks based on changes in multi-network topology and parameters. Summary of the Invention

[0019] The present invention provides a method and system for dynamic sensing of a digital twin of a distribution network, in order to solve the problem of how to achieve dynamic sensing of a digital twin of a distribution network based on changes in multi-dimensional network topology and parameters.

[0020] To address the above problems, this invention provides a dynamic sensing method for a digital twin of a distribution network, the method comprising:

[0021] Acquire real-time data on the operation of the distribution network, and monitor node changes and line status changes of the distribution network based on the real-time data;

[0022] The distribution network topology diagram in the established distribution network digital twin model is updated in real time based on the node changes and line status changes.

[0023] Based on the real-time and historical data, the operating parameters of the distribution network are analyzed using the digital twin model of the distribution network to obtain the analysis results.

[0024] Based on the analysis results, the operational faults of the distribution network are detected and located using the digital twin model of the distribution network.

[0025] Preferably, the method further includes preprocessing the real-time data, including: removing outliers from the real-time data and removing noise from the real-time data using a low-pass filter.

[0026] Preferably, the real-time updating of the distribution network topology diagram in the established distribution network digital twin model based on the node changes and line status changes includes:

[0027] The power distribution network topology is traversed using a dynamic update algorithm to remove failed edges and add new edges.

[0028] Calculate the shortest path for each node in the updated distribution network topology graph.

[0029] Preferably, the analysis of the operating parameters of the distribution network based on the real-time data and historical data through the distribution network digital twin model includes:

[0030] The operating parameters are predicted using a long short-term memory network.

[0031] Preferably, the method further includes: training the long short-term memory network using a loss function, wherein the loss function is:

[0032]

[0033] Where L is the loss function, representing the degree of difference between the predicted and actual values. The LSTM model is trained by minimizing this loss function to improve prediction accuracy. t is the time step index, representing the t-th time in the data sequence. T is the total length of the time series, representing the number of time steps in the dataset. x t+1 This represents the true value at time step t+1, i.e., the actual measured value of the distribution network operating parameters (such as voltage, current, power factor, etc.) at a future moment. The predicted value at time step t+1 is the value of the distribution network operating parameters predicted by the LSTM model based on the previous input data at a future time.

[0034] Preferably, the step of detecting and locating operational faults in the distribution network using the distribution network digital twin model based on the analysis results includes:

[0035] By fusing topology change data T and operating parameter change data P from the distribution network topology diagram using a Bayesian network, operational faults can be detected and located.

[0036] P(F|T,P)∝P(T|F)·P(P|F)·P(F)

[0037] Here, P(F|T, P) represents the probability distribution of a fault occurrence given topology change data T and parameter change data P. This is the result we aim to obtain through Bayesian network fusion analysis, used to infer the likelihood of a fault occurring under the current network topology and parameter conditions. P(T|F) represents the probability of topology change data occurring under fault conditions. It indicates the probability that the distribution network topology will undergo a specific change when a fault occurs, which can be obtained based on the statistical relationship between historical fault data and topology changes. P(P|F) represents the probability of parameter change data occurring under fault conditions. That is, the probability that the distribution network operating parameters will exhibit a specific change when a fault occurs, which can also be learned from historical data. P(F) is the prior probability of a fault occurrence, i.e., the probability of a fault occurring without considering any topology or parameter change data, usually estimated based on historical fault statistics.

[0038] Preferably, the method further includes updating the Bayesian network:

[0039]

[0040] Wherein, P(X) t+1 |θ) represents the data X observed at time step t+1 under the given parameter θ. t+1 The probability. It describes the likelihood of the current observed data occurring under specific parameter settings, based on assumptions made by the probabilistic model regarding the data generation process. P(θ|X) 1：tGiven observation data X from time step 1 to t 1：t Given that θ is a parameter, the prior probability distribution of θ. This is a probability estimate of the parameter before new data arrives, reflecting prior knowledge or experience. P(X) t+1 |X 1：t Given observation data X from time step 1 to t 1：t Under the condition that time step t+1 is observed, data X is obtained. t+1 The probability is P(θ|X). This is a normalization constant that ensures the sum of the posterior probability distributions is 1. It is used in the calculation to adjust the proportional relationships of the probabilities so that the posterior probability distribution satisfies the probability axioms. 1：t+1 Let X be the observation data from time step 1 to t+1. 1：t+1 Under the given conditions, this is the posterior probability distribution of the parameters. This is the parameter probability distribution updated with new data, used to more accurately estimate the state of the distribution network.

[0041] Based on another aspect of the present invention, the present invention provides a dynamic sensing system for a digital twin of a distribution network, the system comprising:

[0042] The network topology sensing unit is used to acquire real-time data on the operation of the distribution network, monitor node changes and line status changes based on the real-time data, and update the distribution network topology diagram in the established digital twin model of the distribution network in real time based on the node changes and line status changes.

[0043] The parameter change sensing unit is used to analyze the operating parameters of the distribution network based on the real-time data and historical data through the digital twin model of the distribution network, and obtain the analysis results.

[0044] The fusion analysis unit is used to detect and locate operational faults in the distribution network based on the analysis results using the digital twin model of the distribution network.

[0045] Preferably, the network topology sensing unit is further configured to preprocess the real-time data, including: removing outliers from the real-time data and removing noise from the real-time data using a low-pass filter.

[0046] Preferably, the network topology sensing unit is used to update the distribution network topology diagram in the established distribution network digital twin model in real time based on the node changes and the line status changes, and is also used to:

[0047] The power distribution network topology is traversed using a dynamic update algorithm to remove failed edges and add new edges.

[0048] Calculate the shortest path for each node in the updated distribution network topology graph.

[0049] Preferably, the parameter change sensing unit is used to analyze the operating parameters of the distribution network based on the real-time data and historical data through the distribution network digital twin model, and is also used to:

[0050] The operating parameters are predicted using a long short-term memory network.

[0051] Preferably, the parameter change sensing unit is further configured to train the long short-term memory network using a loss function, wherein the loss function is:

[0052]

[0053] Where L is the loss function, representing the degree of difference between the predicted and actual values. The LSTM model is trained by minimizing this loss function to improve prediction accuracy. t is the time step index, representing the t-th time in the data sequence. T is the total length of the time series, representing the number of time steps in the dataset. x t+1 This represents the true value at time step t+1, i.e., the actual measured value of the distribution network operating parameters (such as voltage, current, power factor, etc.) at a future moment. The predicted value at time step t+1 is the value of the distribution network operating parameters predicted by the LSTM model based on the previous input data at a future time.

[0054] Preferably, the fusion analysis unit is used to detect and locate operational faults in the distribution network based on the analysis results using the distribution network digital twin model, and is further used to:

[0055] By fusing topology change data T and operating parameter change data P from the distribution network topology diagram using a Bayesian network, operational faults can be detected and located.

[0056] P(F|T,P)∝P(T|F)·P(P|F)·P(F)

[0057] Here, P(F|T, P) represents the probability distribution of a fault occurrence given topology change data T and parameter change data P. This is the result we aim to obtain through Bayesian network fusion analysis, used to infer the likelihood of a fault occurring under the current network topology and parameter conditions. P(T|F) represents the probability of topology change data occurring under fault conditions. It indicates the probability that the distribution network topology will undergo a specific change when a fault occurs, which can be obtained based on the statistical relationship between historical fault data and topology changes. P(P|F) represents the probability of parameter change data occurring under fault conditions. That is, the probability that the distribution network operating parameters will exhibit a specific change when a fault occurs, which can also be learned from historical data. P(F) is the prior probability of a fault occurrence, i.e., the probability of a fault occurring without considering any topology or parameter change data, usually estimated based on historical fault statistics.

[0058] Preferably, the fusion analysis unit is further used to update the Bayesian network:

[0059]

[0060] Wherein, P(X) t+1 |θ) represents the data X observed at time step t+1 under the given parameter θ. t+1 The probability. It describes the likelihood of the current observed data occurring under specific parameter settings, based on assumptions made by the probabilistic model regarding the data generation process. P(θ|X) 1：t Given observation data X from time step 1 to t 1：t Given that θ is a parameter, the prior probability distribution of θ. This is a probability estimate of the parameter before new data arrives, reflecting prior knowledge or experience. P(X) t+1 |X 1：t Given observation data X from time step 1 to t 1：t Under the condition that time step t+1 is observed, data X is obtained. t+1 The probability is P(θ|X). This is a normalization constant that ensures the sum of the posterior probability distributions is 1. It is used in the calculation to adjust the proportional relationships of the probabilities so that the posterior probability distribution satisfies the probability axioms. 1：t+1 Let X be the observation data from time step 1 to t+1. 1：t+1 Under the given conditions, this is the posterior probability distribution of the parameters. This is the parameter probability distribution updated with new data, used to more accurately estimate the state of the distribution network.

[0061] In another aspect, the present invention provides a computer-readable storage medium storing a computer program for executing a dynamic sensing method for a digital twin of a power distribution network.

[0062] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor and a memory; wherein,

[0063] The memory is used to store the processor-executable instructions;

[0064] The processor is configured to read the executable instructions from the memory and execute the instructions to implement a dynamic sensing method for a digital twin of a power distribution network.

[0065] This invention provides a method and system for dynamic sensing of a distribution network digital twin. The method includes: acquiring real-time data on the operation of the distribution network; monitoring node changes and line status changes based on the real-time data; updating the distribution network topology diagram in the established distribution network digital twin model in real time based on node and line status changes; analyzing the operating parameters of the distribution network through the distribution network digital twin model based on real-time and historical data, and obtaining analysis results; and detecting and locating operational faults in the distribution network through the distribution network digital twin model based on the analysis results. This invention provides a method and system for dynamic sensing of a distribution network digital twin based on changes in multi-dimensional network topology and parameters, which can capture and reflect the changing network structure and parameter changes in the distribution network in real time, improve the dynamic sensing capability of the digital twin, and thus support real-time monitoring, fault early warning, and rapid recovery of the distribution network. Attached Figure Description

[0066] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures:

[0067] Figure 1 This is a flowchart of a dynamic sensing method for a digital twin of a power distribution network according to a preferred embodiment of the present invention.

[0068] Figure 2 A flowchart of a dynamic sensing method for digital twins of distribution networks oriented towards changes in multi-network topology and parameters according to a preferred embodiment of the present invention; and

[0069] Figure 3 This is a structural diagram of a digital twin dynamic sensing system for a power distribution network according to a preferred embodiment of the present invention. Detailed Implementation

[0070] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0071] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0072] Figure 1 This is a flowchart of a dynamic sensing method for a digital twin of a power distribution network according to a preferred embodiment of the present invention.

[0073] This invention proposes a dynamic sensing method for distribution network digital twins that addresses changes in multi-network topology and parameters. The aim is to overcome the limitations of existing technologies, enhance the real-time dynamic sensing capability of distribution network digital twins, and thus better serve the intelligent management and optimization of the power grid.

[0074] This invention provides a dynamic sensing method for digital twins of distribution networks based on changes in multi-network topology and parameters. It can capture and reflect the changes in the network structure and parameters in the distribution network in real time, improve the dynamic sensing capability of the digital twin, and thus support real-time monitoring, fault early warning and rapid recovery of the distribution network.

[0075] The core of this invention lies in proposing a dynamic sensing method for digital twins of distribution networks accommodating changes in multi-dimensional network topology and parameters. By comprehensively utilizing advanced graph theory, semantic network representation, machine learning, and data fusion techniques, this invention can effectively address the complex and ever-changing network structures and real-time parameter variations in distribution networks. The following sections will elaborate on the various components and implementation methods of this invention, and introduce mathematical models and algorithm descriptions to enhance the accuracy and operability of the technology.

[0076] like Figure 1 As shown, this invention provides a dynamic sensing method for a digital twin of a distribution network, the method comprising:

[0077] Step 101: Obtain real-time data on the operation of the distribution network, and monitor changes in node status and line status of the distribution network based on the real-time data;

[0078] Preferably, the method further includes preprocessing the real-time data, including: removing outliers from the real-time data and removing noise from the real-time data using a low-pass filter.

[0079] Step 102: Update the distribution network topology diagram in the established distribution network digital twin model in real time based on node changes and line status changes;

[0080] Preferably, the distribution network topology diagram in the established distribution network digital twin model is updated in real time based on node changes and line status changes, including:

[0081] The distribution network topology graph is traversed based on a dynamic update algorithm, and failed edges are removed and new edges are added.

[0082] Calculate the shortest path for each node in the updated distribution network topology graph.

[0083] This invention includes a network topology sensing unit:

[0084] 1) Functional Description: This unit monitors the status changes of each node and line in the distribution network in real time, including the addition of new nodes, node failures, and the connection status of lines. Based on graph theory, the network topology sensing module constructs and dynamically updates the topology model of the distribution network, ensuring that the model can reflect the actual structure of the physical network in real time.

[0085] 2) Technical Implementation: Utilizing graph databases (such as Neo4j) and parallel computing technology, this unit can efficiently handle topology updates for large-scale distribution networks. The core algorithm for topology updates is based on the shortest path algorithm and the maximum flow algorithm. Let the topology of the distribution network be graph G(V,E), where V represents the set of nodes and E represents the set of edges. The dynamic update algorithm is described by the following pseudocode:

[0086]

[0087] Step 103: Based on real-time and historical data, analyze the operating parameters of the distribution network using a digital twin model of the distribution network and obtain the analysis results;

[0088] Preferably, based on real-time and historical data, the operating parameters of the distribution network are analyzed using a digital twin model of the distribution network, including:

[0089] Predicting operating parameters using a long short-term memory network.

[0090] Preferably, the method further includes: training the Long Short-Term Memory network using a loss function, wherein the loss function is:

[0091]

[0092] Where L is the loss function, representing the degree of difference between the predicted and actual values. The LSTM model is trained by minimizing this loss function to improve prediction accuracy. t is the time step index, representing the t-th time in the data sequence. T is the total length of the time series, representing the number of time steps in the dataset. x t+1 This represents the true value at time step t+1, i.e., the actual measured value of the distribution network operating parameters (such as voltage, current, power factor, etc.) at a future moment. The predicted value at time step t+1 is the value of the distribution network operating parameters predicted by the LSTM model based on the previous input data at a future time.

[0093] This invention includes a parameter change sensing module:

[0094] 1) Functional Description: The parameter change sensing module is responsible for real-time monitoring of the operating parameters of the distribution network, such as voltage, current, and power factor. This module improves the accuracy of the data through adaptive filtering and data cleaning techniques, and utilizes machine learning technology to predict parameters and detect anomalies.

[0095] 2) Technical Implementation: Parameter prediction and anomaly detection are performed by combining Kalman filtering and LSTM (Long Short-Term Memory) models. Assume the input data sequence is X = {x1, x2, ..., x...}. t The output of the LSTM model is the predicted value. The predictive model is trained by minimizing the following loss function:

[0096]

[0097] Step 104: Based on the analysis results, detect and locate operational faults in the distribution network using a digital twin model of the distribution network.

[0098] Preferably, based on the analysis results, the operation faults of the distribution network are detected and located using a digital twin model of the distribution network, including:

[0099] By fusing topology change data T and operating parameter change data P from the distribution network topology diagram using a Bayesian network, operational faults can be detected and located.

[0100] P(F|T,P)∝P(T|F)·P(P|F)·P(F)

[0101] Here, P(F|T, P) represents the probability distribution of a fault occurrence given topology change data T and parameter change data P. This is the result we aim to obtain through Bayesian network fusion analysis, used to infer the likelihood of a fault occurring under the current network topology and parameter conditions. P(T|F) represents the probability of topology change data occurring under fault conditions. It indicates the probability that the distribution network topology will undergo a specific change when a fault occurs, which can be obtained based on the statistical relationship between historical fault data and topology changes. P(P|F) represents the probability of parameter change data occurring under fault conditions. That is, the probability that the distribution network operating parameters will exhibit a specific change when a fault occurs, which can also be learned from historical data. P(F) is the prior probability of a fault occurrence, i.e., the probability of a fault occurring without considering any topology or parameter change data, usually estimated based on historical fault statistics.

[0102] Preferably, the method further includes updating the Bayesian network:

[0103]

[0104] Wherein, P(X) t+1 |θ) represents the data X observed at time step t+1 under the given parameter θ. t+1 The probability. It describes the likelihood of the current observed data occurring under specific parameter settings, based on assumptions made by the probabilistic model regarding the data generation process. P(θ|X) 1：t Given observation data X from time step 1 to t 1：t Given that θ is a parameter, the prior probability distribution of θ. This is a probability estimate of the parameter before new data arrives, reflecting prior knowledge or experience. P(X) t+1 |X 1：t Given observation data X from time step 1 to t 1：t Under the condition that time step t+1 is observed, data X is obtained. t+1 The probability is P(θ|X). This is a normalization constant that ensures the sum of the posterior probability distributions is 1. It is used in the calculation to adjust the proportional relationships of the probabilities so that the posterior probability distribution satisfies the probability axioms. 1：t+1 Let X be the observation data from time step 1 to t+1. 1：t+1 Under the given conditions, this is the posterior probability distribution of the parameters. This is the parameter probability distribution updated with new data, used to more accurately estimate the state of the distribution network.

[0105] This invention includes a fusion analysis module:

[0106] 1) Functional Description: The fusion analysis module comprehensively analyzes the outputs from the network topology and parameter change sensing modules, providing fault warnings, performance assessments, and optimization suggestions. The core of this module is a multi-source data fusion algorithm, which integrates data from different sources to output a system-level status assessment.

[0107] 2) Technical Implementation: Bayesian networks are used for multi-source data fusion and fault inference. Let the topology change data be T, and the parameter change data be P. The fused fault probability distribution can be expressed as:

[0108] P(F|T,P)∝P(T|F)·P(P|F)·P(F)

[0109] The model detects and locates faults by maximizing the posterior probability.

[0110] The dynamic sensing method for digital twins of distribution networks based on changes in multi-network topology and parameters provided by this invention specifically includes the following steps:

[0111] 1. Data Acquisition and Preprocessing:

[0112] 1) Description: Real-time data collection of parameters such as voltage, current, and temperature is achieved through a sensor network in the power distribution network. After preprocessing at edge computing nodes, the data is transmitted to the central processing unit for further processing.

[0113] 2) Technical details: The Z-score method is used to remove outliers, a low-pass filter is used to remove noise, and data fragmentation and batch processing techniques are used to optimize transmission and computation efficiency.

[0114] 2. Real-time topology update algorithm:

[0115] 1) Description: The real-time topology update algorithm is used to dynamically adjust the topology of the digital twin to ensure that the model can reflect changes in the physical network in a timely manner.

[0116] 2) Technical Details: Based on incremental graph algorithms, such as incremental Dijkstra's algorithm, it handles newly added or removed edges and nodes. For each topology update, the shortest paths to important nodes are recalculated and the model is updated. Specific pseudocode is described below:

[0117]

[0118]

[0119] 3. Dynamic parameter monitoring and analysis:

[0120] 1) Description: By utilizing historical data and real-time monitoring data, the system dynamically predicts changes in power grid parameters and detects potential anomalies in advance.

[0121] 2) Technical Details: A Bayesian update-based prediction model is used for state estimation and anomaly detection. Each time new data arrives, the model updates the parameter distribution using Bayesian rules to improve prediction accuracy.

[0122]

[0123] 4. System Optimization and Feedback:

[0124] 1) Description: Based on real-time monitoring and analysis results, optimization strategies are provided and fed back into the actual operation of the distribution network. System performance is continuously optimized through a closed-loop control mechanism.

[0125] 2) Technical Details: Complex optimization calculations are performed through a cloud computing platform, utilizing reinforcement learning algorithms (such as Q-learning) to optimize the power grid's operating parameters. The system dynamically adjusts its strategies based on feedback data to maximize the stability and efficiency of the power grid operation.

[0126] Through the above design and implementation methods, this invention provides a complete, accurate, and dynamic digital twin sensing and management solution for distribution networks, which can effectively cope with the complexity and dynamism of distribution networks.

[0127] The method provided by this invention enables the digital twin of a distribution network to perceive dynamic changes in network topology and parameters more efficiently and accurately. This invention not only improves the reliability and stability of distribution network operation but also reduces the risk of failures caused by delays or misjudgments, thereby ensuring the continuity and security of power supply services.

[0128] This invention is verified through a practical application example of an urban power distribution network. The results show that this invention can update the digital twin model in real time when the network topology changes and parameters fluctuate, and provide optimized operation strategies to ensure the efficient and stable operation of the power distribution network.

[0129] This invention provides a dynamic sensing method for a digital twin of a distribution network based on changes in multi-dimensional network topology and parameters. Through a network topology sensing module, a parameter change sensing module, and a fusion analysis module, it enables real-time dynamic sensing and accurate modeling of the distribution network.

[0130] 1) In the network topology awareness module, for monitoring the distribution network topology, when faced with situations such as the addition of new nodes, node failures, or changes in line connection status, this algorithm executes a dynamic update algorithm based on shortest path algorithms (such as Dijkstra's algorithm) and maximum flow algorithms. This algorithm first efficiently traverses the topology graph, accurately identifies and removes failed edges to ensure the accuracy of the network structure; then, it adds new edges to reflect changes in the actual network topology; finally, it recalculates the shortest path for each node, providing critical path information for subsequent network analysis.

[0131] 2) In the parameter change perception module, during parameter prediction and anomaly detection, the LSTM (Long Short-Term Memory) model from machine learning techniques is used. This is achieved by minimizing a specific loss function during training. By continuously adjusting the model parameters, accurate prediction and timely anomaly detection of distribution network operating parameters (such as voltage, current, power factor, etc.) can be achieved.

[0132] 3) In the fusion analysis module, this method calculates the fused fault probability distribution (P(F|T, P)∝P(T|F)·P(P|F)·P(F)) based on Bayesian network principles. During fault inference, the Maximum Posterior Probability (MAP) algorithm is used for fault detection and location. Specifically, all possible fault states are traversed, the posterior probability of each state is calculated, and the state with the highest probability is selected as the inference result, thereby accurately inferring the probability and location of the fault.

[0133] The modules in this invention work together to ensure that the digital twin of the distribution network can accurately reflect the dynamic changes of the actual power grid, thereby improving the security and operational efficiency of the distribution network.

[0134] Figure 3 This is a structural diagram of a digital twin dynamic sensing system for a power distribution network according to a preferred embodiment of the present invention.

[0135] like Figure 3 As shown, the present invention provides a dynamic sensing system for a digital twin of a power distribution network, the system comprising:

[0136] The network topology sensing unit 301 is used to acquire real-time data of the distribution network operation, monitor node changes and line status changes of the distribution network based on the real-time data, and update the distribution network topology diagram in the established digital twin model of the distribution network in real time based on node changes and line status changes.

[0137] Preferably, the network topology sensing unit 301 is also used to preprocess real-time data, including: removing outliers from the real-time data and removing noise from the real-time data using a low-pass filter.

[0138] Preferably, the network topology sensing unit 301 is used to update the distribution network topology diagram in the established distribution network digital twin model in real time based on node changes and line status changes, and is also used for:

[0139] The distribution network topology graph is traversed based on a dynamic update algorithm, and failed edges are removed and new edges are added.

[0140] Calculate the shortest path for each node in the updated distribution network topology graph.

[0141] The parameter change sensing unit 302 is used to analyze the operating parameters of the distribution network based on real-time data and historical data through the digital twin model of the distribution network, and obtain the analysis results.

[0142] Preferably, the parameter change sensing unit 302 is used to analyze the operating parameters of the distribution network based on real-time data and historical data through a digital twin model of the distribution network, and is also used for:

[0143] Predicting operating parameters using a long short-term memory network.

[0144] Preferably, the parameter change sensing unit 302 is also used to train the long short-term memory network using a loss function, wherein the loss function is:

[0145]

[0146] Where L is the loss function, representing the degree of difference between the predicted and actual values. The LSTM model is trained by minimizing this loss function to improve prediction accuracy. t is the time step index, representing the t-th time in the data sequence. T is the total length of the time series, representing the number of time steps in the dataset. x t+1 This represents the true value at time step t+1, i.e., the actual measured value of the distribution network operating parameters (such as voltage, current, power factor, etc.) at a future moment. The predicted value at time step t+1 is the value of the distribution network operating parameters predicted by the LSTM model based on the previous input data at a future time.

[0147] The fusion analysis unit 303 is used to detect and locate operational faults in the distribution network based on the analysis results using a digital twin model of the distribution network.

[0148] Preferably, the fusion analysis unit 303 is used to detect and locate operational faults in the distribution network based on the analysis results using a digital twin model of the distribution network, and is also used to:

[0149] By fusing topology change data T and operating parameter change data P from the distribution network topology diagram using a Bayesian network, operational faults can be detected and located.

[0150] P(F|T,P)∝P(T|F)·P(P|F)·P(F)

[0151] Here, P(F|T, P) represents the probability distribution of a fault occurrence given topology change data T and parameter change data P. This is the result we aim to obtain through Bayesian network fusion analysis, used to infer the likelihood of a fault occurring under the current network topology and parameter conditions. P(T|F) represents the probability of topology change data occurring under fault conditions. It indicates the probability that the distribution network topology will undergo a specific change when a fault occurs, which can be obtained based on the statistical relationship between historical fault data and topology changes. P(P|F) represents the probability of parameter change data occurring under fault conditions. That is, the probability that the distribution network operating parameters will exhibit a specific change when a fault occurs, which can also be learned from historical data. P(F) is the prior probability of a fault occurrence, i.e., the probability of a fault occurring without considering any topology or parameter change data, usually estimated based on historical fault statistics.

[0152] Preferably, the fusion analysis unit 303 is also used to update the Bayesian network:

[0153]

[0154] Wherein, P(X) t+1 |θ) represents the data X observed at time step t+1 under the given parameter θ. t+1 The probability. It describes the likelihood of the current observed data occurring under specific parameter settings, based on assumptions made by the probabilistic model regarding the data generation process. P(θ|X) 1：t Given observation data X from time step 1 to t 1：t Given that θ is a parameter, the prior probability distribution of θ. This is a probability estimate of the parameter before new data arrives, reflecting prior knowledge or experience. P(X) t+1 |X 1：t Given observation data X from time step 1 to t 1：t Under the condition that time step t+1 is observed, data X is obtained. t+1 The probability is P(θ|X). This is a normalization constant that ensures the sum of the posterior probability distributions is 1. It is used in the calculation to adjust the proportional relationships of the probabilities so that the posterior probability distribution satisfies the probability axioms. 1：t+1 Let X be the observation data from time step 1 to t+1. 1：t+1 Under the given conditions, this is the posterior probability distribution of the parameters. This is the parameter probability distribution updated with new data, used to more accurately estimate the state of the distribution network.

[0155] The present invention provides a computer-readable storage medium storing a computer program for executing a dynamic sensing method for a digital twin of a power distribution network.

[0156] This invention provides an electronic device, which includes: a processor and a memory; wherein,

[0157] Memory, used to store processor-executable instructions;

[0158] A processor is used to read executable instructions from memory and execute the instructions to implement a dynamic sensing method for a digital twin of a power distribution network.

[0159] The preferred embodiment of the present invention provides a dynamic sensing system for a digital twin of a distribution network, which corresponds to another preferred embodiment of the present invention providing a dynamic sensing method for a digital twin of a distribution network. These will not be described in detail here.

[0160] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0161] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0162] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0163] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0164] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0165] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0166] The invention has been described with reference to a few embodiments. However, as will be known to those skilled in the art, and as defined in the appended claims, other embodiments besides those disclosed above fall equivalently within the scope of the invention.

[0167] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the art, unless otherwise expressly defined herein. All references to “a / the / the [device, component, etc.]” ​​are openly interpreted as at least one instance of said device, component, etc., unless otherwise expressly stated. The steps of any method disclosed herein need not be performed in the exact order disclosed unless explicitly stated otherwise.

Claims

1. A dynamic sensing method for a digital twin of a distribution network, the method comprising: Acquire real-time data on the operation of the distribution network, and monitor node changes and line status changes of the distribution network based on the real-time data; The distribution network topology diagram in the established distribution network digital twin model is updated in real time based on the node changes and line status changes. Based on the real-time and historical data, the operating parameters of the distribution network are analyzed using the digital twin model of the distribution network to obtain analysis results, including: The operating parameters are predicted using a long short-term memory network; The Long Short-Term Memory network is trained using a loss function, which is: ， Where L is the loss function, t is the time step index, representing the t-th time in the data sequence, T is the total length of the time series, and x t+1 For the actual value at time step t+1, This is the predicted value at time step t+1; Based on the analysis results, the operation faults of the distribution network are detected and located using the digital twin model of the distribution network, including: Topological change data of a power distribution network topology graph by a Bayesian network T and operating parameter change data P fusion, detection and localization of operating faults: ∝ in, Given topology change data T and parameter change data P, this represents the probability distribution of fault occurrence. This represents the probability of topology change data occurring under fault conditions. This represents the probability of parameter changes occurring under fault conditions. The prior probability of a failure occurring is the probability of a failure occurring without considering any changes in topology or parameters.

2. The method of claim 1, further comprising pre-processing the real-time data, including: Remove outliers from the real-time data by using a low-pass filter to remove noise from the real-time data.

3. The method according to claim 1, wherein the real-time updating of the distribution network topology diagram in the established distribution network digital twin model based on the node changes and the line status changes comprises: The power distribution network topology is traversed using a dynamic update algorithm to remove failed edges and add new edges. Calculate the shortest path for each node in the updated distribution network topology graph.

4. The method according to claim 1, further comprising updating the Bayesian network: wherein For given parameters Under the condition of observation, data at time step t+1 was observed. The probability of; Given observation data from time step 1 to t Under the condition, parameters The prior probability distribution; Given observation data from time step 1 to t Under the condition of observation, data at time step t+1 was observed. The probability of; Given observation data from time step 1 to t+1 Under the given conditions, the posterior probability distribution of the parameters.

5. A dynamic sensing system for a digital twin of a distribution network, the system comprising: The network topology sensing unit is used to acquire real-time data on the operation of the distribution network and monitor changes in node and line status of the distribution network based on the real-time data. The distribution network topology diagram in the established distribution network digital twin model is updated in real time based on the node changes and line status changes. The parameter change sensing unit is used to analyze the operating parameters of the distribution network based on the real-time data and historical data through the distribution network digital twin model, obtain the analysis results, and is also used for: The operating parameters are predicted using a long short-term memory network; It is also used to train the Long Short-Term Memory network using a loss function, wherein the loss function is: ， Where L is the loss function, t is the time step index, representing the t-th time in the data sequence, T is the total length of the time series, and x t+1 For the actual value at time step t+1, This is the predicted value at time step t+1; The fusion analysis unit is used to detect and locate operational faults in the distribution network based on the analysis results using the digital twin model of the distribution network, and is also used for: Topological change data of a power distribution network topology graph by a Bayesian network T and operating parameter change data P fusion, detection and localization of operating faults: ∝ in, Given topology change data T and parameter change data P, this represents the probability distribution of fault occurrence. This represents the probability of topology change data occurring under fault conditions. This represents the probability of parameter changes occurring under fault conditions. The prior probability of a failure occurring is the probability of a failure occurring without considering any changes in topology or parameters.

6. The system according to claim 5, wherein the network topology sensing unit is further configured to preprocess the real-time data, including: Remove outliers from the real-time data by using a low-pass filter to remove noise from the real-time data.

7. The system according to claim 5, wherein the network topology sensing unit is configured to update the distribution network topology diagram in the established distribution network digital twin model in real time based on the node changes and the line status changes, and is further configured to: The power distribution network topology is traversed using a dynamic update algorithm to remove failed edges and add new edges. Calculate the shortest path for each node in the updated distribution network topology graph.

8. The system according to claim 5, wherein the fusion analysis unit is further configured to update the Bayesian network: wherein, For given parameters Under the condition of observation, data at time step t+1 was observed. The probability of; Given observation data from time step 1 to t Under the condition, parameters The prior probability distribution; Given observation data from time step 1 to t Under the condition of observation, data at time step t+1 was observed. The probability of; Given observation data from time step 1 to t+1 Under the given conditions, the posterior probability distribution of the parameters.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program for performing the method according to any one of claims 1-4.

10. An electronic device, comprising: The electronic device includes: a processor and a memory; wherein, The memory is used to store the processor-executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of any one of claims 1-4.

Images