Power distribution network construction method, system and equipment based on digital twinning and storage medium

Abstract

The invention discloses a power distribution network construction method, system and device based on digital twinning and a storage medium, and relates to the technical field of power systems, and the method comprises the steps: collecting the operation link data of a power distribution network; constructing a power distribution network digital twinborn model based on the power distribution network operation link data; optimizing the prediction and decision-making capability of the digital twin model of the power distribution network, and performing evaluation and verification; the optimized power distribution network digital twinborn model is used for carrying out full-life-cycle dynamic simulation on the power distribution network; in the dynamic simulation process of the whole life cycle of the power distribution network, the operation state of the power grid is analyzed in real time, an optimal scheduling scheme is provided, the state of power grid equipment is monitored in real time, fault hidden dangers are found, fault causes are diagnosed, and a repair scheme is provided. The method further comprises the steps of encrypting sensitive data, backing up important data regularly, establishing a perfect data recovery mechanism and implementing strict access authority management. According to the invention, the operation efficiency, reliability, safety and intelligent level of the power distribution network can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and particularly relates to a method, system, device and storage medium for constructing a distribution network based on digital twin. Background Art

[0002] As an important part of the power system, the distribution network undertakes the task of safely and reliably delivering electric energy from the transmission network to the user side. However, with the acceleration of the urbanization process and the continuous growth of power demand, the distribution network is facing increasing challenges. The traditional methods for constructing and managing the distribution network are difficult to meet the requirements of modern power systems, and it is urgent to introduce new technical means to improve the operation efficiency, safety and reliability of the distribution network. As an emerging information technology, digital twin technology realizes the comprehensive monitoring, optimized operation and auxiliary decision-making of physical entities by constructing virtual mirrors of physical entities. In the construction and management of the distribution network, digital twin technology has broad application prospects.

[0003] Although digital twin technology has shown many advantages in the construction process of the distribution network, there are still some challenges and deficiencies in practical applications. For example, in the process of model construction, lax data quality control is likely to lead to limited model accuracy, which in turn affects the accurate prediction of grid status and the rapid location of faults; at the same time, insufficient algorithm optimization is likely to limit the decision-making support ability, making it difficult to achieve the optimal grid planning, and the accuracy of dispatching decisions is also likely to be affected; in addition, there are still potential risks in data security, which are likely to endanger the safe operation of the distribution network. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, system, device and storage medium for constructing a distribution network based on digital twin to improve the operation efficiency, reliability, safety and intelligent level of the distribution network in view of the above problems in the prior art.

[0005] To achieve the above purpose, the present invention has the following technical solutions: In the first aspect, a method for constructing a distribution network based on digital twin is provided, including: Collecting data on the operation links of the distribution network; Constructing a digital twin model of the distribution network based on the data on the operation links of the distribution network; Optimizing the prediction and decision-making capabilities of the digital twin model of the distribution network and evaluating and validating them; Using the optimized digital twin model of the distribution network to perform dynamic simulation on the whole life cycle of the distribution network.

[0006] As a preferred solution, the data on the operation links of the distribution network includes any one or a combination of multiple of voltage, current, power, temperature and wind speed.

[0007] As a preferred solution, after collecting the data of the operation links of the distribution network, the method for constructing a distribution network based on digital twin further includes a step of performing data quality control on the collected data of the operation links of the distribution network; the data quality control includes cleaning, verifying, and preprocessing the collected data of the operation links of the distribution network; For missing values, methods of filling and deletion are adopted, and at the same time, outlier detection is performed through statistical methods and machine learning algorithms, and correction and deletion are carried out; data verification is used to ensure the consistency of data between different tables or fields, avoid data conflicts or contradictions, verify whether the data values are within the set range, and avoid data errors or anomalies; data preprocessing includes normalizing and standardizing the data, which is used to eliminate the influence of different dimensions on the model and eliminate data fluctuations and noises.

[0008] As a preferred solution, the filling method includes any one or a combination of mean filling, median filling, and interpolation method.

[0009] As a preferred solution, in the step of constructing a distribution network digital twin model based on the data of the operation links of the distribution network, the distribution network digital twin model includes digital twins of physical power grid equipment and digital twins including environment, personnel, and business; The physical power grid equipment includes power transmission, transformation, distribution, and power consumption equipment. By integrating Building Information Modeling (BIM), City Information Modeling (CIM), Grid Information Modeling (GIM), or Smart Grid Common Information Model (SG-CIM), the models in the whole process of planning, design, construction, and operation are made unique and shared in different stages.

[0010] As a preferred solution, in the step of optimizing the prediction and decision-making capabilities of the distribution network digital twin model and conducting evaluation and verification, the optimization algorithms for realizing the optimization of the distribution network digital twin model include any one or a combination of convolutional neural network, recurrent neural network, and transformer in deep learning; the ensemble learning method is used to improve the prediction and decision-making capabilities of the distribution network digital twin model, and the ensemble learning method includes any one or a combination of random forest, gradient boosting tree, and Extreme Gradient Boosting (XGBoost).

[0011] As a preferred solution, in the step of using the optimized distribution network digital twin model to perform dynamic simulation on the whole life cycle of the distribution network, the dynamic simulation includes simulating the topological structure, equipment parameters, and operating status of the power grid, combining the analysis and calculation capabilities of the data middle platform and the capabilities of the technology middle platform, and constructing typical digital twin application scenarios for the four major fields of power grid planning, construction, operation, and customer service.

[0012] As a preferred solution, during the dynamic simulation of the entire life cycle of the distribution network, the operating state of the power grid is analyzed in real time, an optimized scheduling plan is proposed, and the state of power grid equipment is monitored in real time to detect potential faults, diagnose the causes of faults, and propose repair plans.

[0013] As a preferred solution, in the step of analyzing the operating state of the power grid in real time and proposing an optimized scheduling plan, machine learning and artificial intelligence algorithms are integrated, combined with historical data and real-time monitoring information, to analyze the operating state of the power grid in real time and propose an optimized scheduling plan; In the step of monitoring the state of power grid equipment in real time, detecting potential faults, diagnosing the causes of faults, and proposing repair plans, the whole life cycle management of power grid assets is carried out, including equipment state assessment, update plan formulation, and retirement plan formulation.

[0014] As a preferred solution, the method for constructing a distribution network based on digital twin further includes: Encrypt sensitive data to ensure the security of data during transmission and storage, and prevent data leakage and unauthorized access; Regularly back up important data and establish a perfect data recovery mechanism to cope with possible data loss or damage; Implement access control management to ensure that only authorized personnel can access sensitive data.

[0015] As a preferred solution, in the step of encrypting sensitive data, symmetric encryption is used, and the same key is used for encryption and decryption in symmetric encryption.

[0016] As a preferred solution, the symmetric encryption uses the Advanced Encryption Standard (AES) or the Data Encryption Standard (DES); The Advanced Encryption Standard (AES) selects a 192-bit key and uses multi-level encryption.

[0017] In a second aspect, a system for constructing a distribution network based on digital twin is provided, including: An operation link data acquisition module for acquiring distribution network operation link data; A digital twin model construction module for constructing a distribution network digital twin model based on distribution network operation link data; A model optimization and evaluation module for optimizing the prediction and decision-making capabilities of the distribution network digital twin model and conducting evaluation and verification; A dynamic simulation module for performing dynamic simulation of the entire life cycle of the distribution network using the optimized distribution network digital twin model.

[0018] As a preferred solution, the digital twin-based distribution network construction system further includes a data quality control module, which is used to clean, verify, and preprocess the distribution network operation link data collected by the operation link data acquisition module; For missing values, methods of filling and deletion are adopted. At the same time, statistical methods and machine learning algorithms are used to detect outliers, and corrections and deletions are made. Data verification is used to ensure the consistency of data between different tables or fields, avoid data conflicts or contradictions, and verify whether the data values are within the set range to avoid data errors or anomalies. Data preprocessing includes normalizing and standardizing the data, which is used to eliminate the influence of different dimensions on the model and eliminate data fluctuations and noises.

[0019] As a preferred solution, the distribution network digital twin model constructed by the digital twin model construction module includes digital twins of physical power grid equipment and digital twins including environment, personnel, and business; The physical power grid equipment includes power transmission, transformation, distribution, and power consumption equipment. By integrating Building Information Model (BIM), City Information Model (CIM), Grid Information Model (GIM), or Smart Grid Common Information Model (SG-CIM), the models for the entire process of planning, design, construction, and operation are made unique and shared at different stages.

[0020] As a preferred solution, the optimization algorithms adopted by the model optimization and evaluation module include any one or a combination of multiple of convolutional neural network, recurrent neural network in deep learning, and transformers. The model optimization and evaluation module uses the ensemble learning method to improve the prediction and decision-making capabilities of the distribution network digital twin model. The ensemble learning method includes any one or a combination of multiple of random forest, gradient boosting tree, and Extreme Gradient Boosting (XGBoost).

[0021] As a preferred solution, the dynamic simulation module simulates the topological structure, equipment parameters, and operation status of the power grid, and combines the analysis and calculation capabilities of the data middle platform and the capabilities of the technology middle platform to build typical digital twin application scenarios for the four major fields of power grid planning, construction, operation, and customer service.

[0022] As a preferred solution, the digital twin-based distribution network construction system further includes a solution proposal module, which is used to analyze the operation status of the power grid in real time and propose an optimized dispatching solution during the dynamic simulation of the entire life cycle of the distribution network, and to monitor the status of power grid equipment in real time, discover potential fault hazards, diagnose the cause of the fault, and propose a repair solution.

[0023] As a preferred solution, the solution proposal module integrates machine learning and artificial intelligence algorithms, combines historical data and real-time monitoring information, analyzes the operation status of the power grid in real time and proposes an optimized dispatching solution; when the solution proposal module monitors the status of power grid equipment in real time, discovers potential faults, diagnoses the causes of faults and proposes repair solutions, it conducts full life cycle management of power grid assets, including equipment status assessment, update plan formulation and decommissioning plan formulation.

[0024] As a preferred solution, the digital twin-based distribution network construction system further includes a data security enhancement module, which is used to encrypt sensitive data, regularly back up important data, establish a perfect data recovery mechanism, and implement access right management; By encrypting sensitive data, the security of data during transmission and storage is ensured, preventing data leakage and unauthorized access; By regularly backing up important data and establishing a perfect data recovery mechanism, it can cope with possible data loss or damage; By implementing access right management, it is ensured that only authorized personnel can access sensitive data.

[0025] In a third aspect, an electronic device is provided, including a processor and a memory, and the processor is used to execute a computer program stored in the memory to implement the digital twin-based distribution network construction method.

[0026] In a fourth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, the digital twin-based distribution network construction method is implemented.

[0027] Compared with the prior art, the first aspect of the present invention has at least the following beneficial effects: The present invention uses the Internet of Things technology to collect data on the operation links of the distribution network in real time, intelligently and remotely through sensors and automation devices. By constructing a digital twin model of the distribution network, the prediction and decision-making capabilities of the digital twin model of the distribution network are optimized and evaluated and verified. The optimized digital twin model of the distribution network is used to conduct dynamic simulation of the whole life cycle of the distribution network, realizing the intelligent management and optimized operation of the distribution network. The digital twin-based distribution network construction method of the present invention improves the operation efficiency, reliability, security and intelligent level of the distribution network, providing strong support for the sustainable development of the power industry.

[0028] Furthermore, the method of the present invention can effectively improve the accuracy and reliability of the digital twin model through comprehensive measures in three aspects: algorithm optimization, data quality control, and model evaluation and verification. Subsequently, the prediction accuracy is improved, and the power grid status, including key parameters such as voltage and current, can be accurately predicted, providing a reliable basis for power grid dispatching and assisting in fault warning and location, shortening the fault handling time. Secondly, the decision-making support ability is enhanced, making the power grid planning more refined, optimizing the layout and equipment configuration, and at the same time providing accurate dispatching decisions to improve the operation efficiency of the power grid. In addition, the operation and maintenance efficiency is also significantly improved. By precisely managing power grid equipment, the operation and maintenance costs are reduced, and remote monitoring and diagnosis are realized, improving safety and convenience. Finally, it promotes the intelligent upgrade of the power grid, provides a solid foundation for the construction of the smart grid, and makes it easier to apply new technologies to the distribution network, promoting the innovation and development of the power grid, realizing automated, intelligent, and digital management, and jointly promoting the efficient, safe, and sustainable development of the distribution network.

[0029] Furthermore, the method of the present invention encrypts sensitive data through the adoption of data encryption technologies such as symmetric encryption, ensuring the security of data during transmission and storage, effectively preventing data leakage and unauthorized access, and providing a solid guarantee for the safe operation of the distribution network. At the same time, important data is regularly backed up and a perfect data recovery mechanism is established, enabling rapid recovery in the event of data loss or damage, ensuring the integrity and availability of data, and reducing the impact of data risks on the operation of the distribution network. In addition, strict access permission management is implemented to ensure that only authorized personnel can access sensitive data, further enhancing data security and avoiding the risk of illegal access and tampering of data. The above data security enhancement measures jointly provide a comprehensive and effective data security guarantee for the method for constructing a distribution network based on digital twins.

[0030] It can be understood that the beneficial effects of the second to fourth aspects above can refer to the relevant descriptions in the first aspect above and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0032] Figure 1 Schematic flowchart of the method for constructing a distribution network based on digital twins in an embodiment of the present invention; Figure 2 Schematic structural diagram of the system for constructing a distribution network based on digital twins in an embodiment of the present invention; Figure 3 Schematic diagram of the physical structure of the electronic device according to an embodiment of the present invention. Detailed implementation manners

[0033] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0034] In view of the technical problems in the prior art that in the process of model construction, loose data quality control easily leads to limited model accuracy, which in turn affects the accurate prediction of the power grid state and the rapid location of faults; at the same time, the lack of algorithm optimization easily limits the decision-making support ability, making it difficult to achieve the optimal power grid planning, and the accuracy of dispatching decisions is also easily affected; in addition, there are still potential risks in data security, which easily endanger the safe operation of the distribution network, an embodiment of the present invention proposes a method for constructing a distribution network based on digital twin. Please refer to Figure 1 , which mainly includes the following steps: Collect data on the operation links of the distribution network; Construct a digital twin model of the distribution network based on the data on the operation links of the distribution network; Optimize the prediction and decision-making capabilities of the digital twin model of the distribution network and conduct evaluation and verification; Use the optimized digital twin model of the distribution network to perform dynamic simulation of the entire life cycle of the distribution network.

[0035] In a possible implementation manner, the Internet of Things technology is used to collect data on the operation links of the distribution network in real time. The data on the operation links of the distribution network includes voltage, current, power, temperature, and wind speed, etc. The intelligent acquisition system can use advanced sensors and automation equipment, and use technologies such as wireless communication, 5G (fifth-generation mobile communication technology), and NB-IoT (NarrowBand Internet of Things) to achieve intelligent and remote acquisition of the operation state of the distribution network.

[0036] In a possible implementation manner, after collecting the data on the operation links of the distribution network, it further includes the step of performing data quality control on the collected data on the operation links of the distribution network. The data quality control includes cleaning, verifying, and preprocessing the collected data on the operation links of the distribution network.

[0037] For missing values, methods of filling and deletion are adopted. At the same time, outliers are detected through statistical methods and machine learning algorithms, and corrected and deleted; data verification is used to ensure the consistency of data between different tables or fields, avoid data conflicts or contradictions, verify whether the data values are within the set range, and avoid data errors or anomalies; data preprocessing includes normalizing and standardizing the data, which is used to eliminate the influence of different dimensions on the model and eliminate data fluctuations and noise.

[0038] Furthermore, the filling methods include mean filling, median filling, and interpolation method, etc.

[0039] In a possible implementation manner, a digital twin model of the distribution network is constructed based on the data of the distribution network operation link after data quality control. The digital twin model of the distribution network includes digital twins of physical power grid equipment and digital twins including environment, personnel, and business. Among them, the physical power grid equipment includes transmission, substation, distribution, and power consumption equipment. By integrating Building Information Modeling (BIM), City Information Modeling (CIM), Grid Information Modeling (GIM), or Smart Grid Common Information Model (SG-CIM), the models in the whole process of planning, design, construction, and operation are made unique and shared in different stages.

[0040] In a possible implementation manner, in the process of optimizing the prediction and decision-making capabilities of the digital twin model of the distribution network and evaluating and verifying it, the optimization algorithms for optimizing the digital twin model of the distribution network include convolutional neural networks, recurrent neural networks, and transformers in deep learning. At the same time, the ensemble learning method is used to improve the prediction and decision-making capabilities of the digital twin model of the distribution network. The ensemble learning method includes random forest, gradient boosting tree, Extreme Gradient Boosting (XGBoost), etc. When evaluating and verifying the digital twin model of the distribution network, the performance and accuracy of the model are detected, corresponding problems are discovered and solved in time, and the reliability of the model is improved.

[0041] In a possible implementation manner, a simulation system is used to perform dynamic simulation of the entire life cycle of the distribution network. The dynamic simulation includes simulating the topological structure, equipment parameters, and operating status of the power grid, providing strong support for the planning, design, operation and maintenance, and optimization of the power grid. Combining the analysis and calculation capabilities of the data middle platform and the capabilities of technology middle platforms such as artificial intelligence and unified video, typical digital twin application scenarios are constructed for the four major fields of power grid planning, construction, operation, and customer service.

[0042] In a possible implementation manner, during the process of performing dynamic simulation of the entire life cycle of the distribution network, the operating status of the power grid is analyzed in real time and an optimized dispatching plan is proposed, and the status of power grid equipment is monitored in real time to discover potential faults, diagnose the causes of faults, and propose repair plans.

[0043] Furthermore, during the intelligent decision-making support process, the application layer provides intelligent decision-making support based on simulation analysis and machine learning to achieve refined control of power grid operation. By analyzing the real-time operation status of the power grid and using advanced simulation and prediction technologies, it provides efficient decision-making support for power grid operation management. The intelligent optimization system integrates machine learning and artificial intelligence algorithms, combines historical data and real-time monitoring information, automatically analyzes the operation efficiency of the power grid, and proposes an optimized dispatching plan.

[0044] Furthermore, during the operation and maintenance management process, the operation and maintenance management system is used to monitor the status of power grid equipment in real time to timely detect potential faults, automatically diagnose the cause of the faults, and propose repair plans. The whole-life cycle management system conducts whole-life cycle management of power grid assets, including equipment status assessment, update plan formulation, and retirement plan formulation.

[0045] In a possible implementation manner, data security enhancement measures are further included, including: Encrypt sensitive data to ensure the security of data during transmission and storage, prevent data leakage and unauthorized access; Regularly back up important data and establish a perfect data recovery mechanism to cope with possible data loss or damage; Implement access control management to ensure that only authorized personnel can access sensitive data.

[0046] Furthermore, in the step of encrypting sensitive data, symmetric encryption is adopted, and the same key is used for encryption and decryption in symmetric encryption.

[0047] In a possible implementation manner, the symmetric encryption adopts the Advanced Encryption Standard (AES) or the Data Encryption Standard (DES). In the embodiment of the present invention, the Advanced Encryption Standard (AES) selects a 192-bit key to increase the cracking difficulty and improve security, and multi-level encryption is adopted to further increase the cracking difficulty.

[0048] The AES (Advanced Encryption Standard) is a widely used symmetric encryption algorithm to replace the original DES encryption algorithm. The AES algorithm is ingeniously designed and can achieve efficient encryption and decryption operations while ensuring security. AES adopts a relatively long key length (128 bits, 192 bits, or 256 bits), which increases the cracking difficulty and thus ensures the security of data. The structure of the AES algorithm is relatively simple and clear, which is convenient for developers to understand and implement. Due to its characteristics of high efficiency, security, and easy implementation, the AES algorithm has been widely used in fields such as Internet communication, e-commerce, and mobile applications.

[0049] DES (Data Encryption Standard) is a traditional symmetric-key encryption algorithm. DES converts 64-bit plaintext blocks into 64-bit ciphertext through multiple rounds of operations for encryption. DES uses a 56-bit key for encryption (where 8 bits are used for parity checking), so its security is relatively low compared to modern encryption algorithms. The encryption process of DES is relatively simple and straightforward, but it is thus vulnerable to various attack methods (such as brute-force attacks, differential attacks, etc.). Although the DES algorithm is no longer widely used, it may still be seen in some old systems. However, due to security issues, new systems usually prefer to adopt more secure modern encryption algorithms such as the AES algorithm.

[0050] The method for constructing a distribution network based on digital twins in the embodiments of the present invention uses Internet of Things technology to collect the operation data of each link of the distribution network in real time, and cleans, verifies, and preprocesses the collected data. Then, based on the processed data, a digital twin model of the distribution network is constructed. At the same time, by continuously researching and optimizing algorithms and adopting more advanced models and technologies, the prediction and decision-making capabilities of the digital twin model are improved, and the digital twin model is evaluated and verified regularly to detect the performance and accuracy of the model, discover and solve problems in a timely manner, and improve the reliability of the model. Then, a simulation system is used to conduct dynamic simulation of the entire life cycle of the distribution network, and the application layer provides intelligent decision support based on simulation analysis and machine learning to achieve refined management and control of power grid operation. The operation and maintenance management system monitors the status of power grid equipment in real time to detect potential faults, automatically diagnose the cause of the faults, and propose repair solutions. In this process, the method of the present invention also encrypts sensitive data through data security enhancement measures, backs up important data regularly, establishes a perfect data recovery mechanism, and implements strict access right management to provide comprehensive and effective data security protection for the method of constructing a distribution network based on digital twins.

[0051] The method for constructing a distribution network based on digital twins of the present invention can effectively improve the accuracy and reliability of the model through comprehensive measures in three aspects: algorithm optimization, data quality control, and model evaluation and verification.

[0052] The benefits of improving the accuracy and reliability of the model for the construction of a distribution network based on digital twins include improving prediction accuracy, enhancing decision-making support capabilities, improving operation and maintenance efficiency, and promoting intelligent upgrading, as follows: I. Improving prediction accuracy Accurately predicting the power grid status: A high-precision model can more accurately predict the actual operation status of the distribution network, including changes in voltage, current, and power, providing a reliable basis for power grid dispatching and operation; Fault warning and location: Through the digital twin model, the health status of power grid equipment can be monitored in real time, potential faults can be detected in a timely manner, and the fault points can be accurately located, thus shortening the fault handling time and reducing power outage losses; II. Enhancing decision-making support capabilities Optimizing power grid planning: Based on the high-precision digital twin model, more refined planning and design of the distribution network can be carried out, optimizing the power grid layout and equipment configuration, and improving the power supply capacity and reliability of the power grid; Intelligent dispatching and control: Reliable models can provide accurate decision-making support for power grid dispatching, realize the optimal allocation and intelligent control of power resources, and improve the operation efficiency and stability of the power grid; III. Improving operation and maintenance efficiency Precise operation and maintenance management: Through the digital twin model, precise management of power grid equipment can be carried out, including equipment status monitoring, preventive maintenance, fault handling, etc., reducing operation and maintenance costs and improving operation and maintenance efficiency; Remote monitoring and diagnosis: With the help of high-precision models, remote monitoring and fault diagnosis of power grid equipment can be realized, reducing the number of on-site inspections and repairs, and improving the safety and convenience of operation and maintenance work; IV. Promoting intelligent upgrading Driving the intelligence of the power grid: High-precision and reliable digital twin models are an important foundation for the intelligence of the power grid, which can support the construction and development of the smart grid and realize the automated, intelligent and digital management of the power grid; Supporting the application of new technologies: With the improvement of model accuracy and reliability, it is easier to apply new technologies to the construction and operation of the distribution network, promoting the innovation and development of the power grid. The new technologies include artificial intelligence, big data, and the Internet of Things.

[0053] In summary, the method for constructing a distribution network based on digital twins according to the present invention realizes the intelligent management and optimized operation of the distribution network through the comprehensive application of various technical means such as Internet of Things technology, data quality control, digital twin model construction, model accuracy improvement, simulation prediction and optimization, intelligent decision-making support, operation and maintenance management, and data security enhancement. This method improves the operation efficiency, reliability, safety and intelligence level of the distribution network, providing strong support for the sustainable development of the power industry.

[0054] Please refer to Figure 2 , another embodiment of the present invention also proposes a system for constructing a distribution network based on digital twins, including: An operation link data acquisition module 201 for acquiring distribution network operation link data; A digital twin model construction module 202 for constructing a distribution network digital twin model based on the distribution network operation link data; The model optimization and evaluation module 203 is used to optimize the prediction and decision-making capabilities of the distribution network digital twin model and conduct evaluation and verification. The dynamic simulation module 204 is used to perform dynamic simulation of the entire life cycle of the distribution network using the optimized distribution network digital twin model.

[0055] In a possible implementation manner, the distribution network construction system based on digital twin of the present invention embodiment further includes a data quality control module 206, which is used to clean, verify, and preprocess the distribution network operation link data collected by the operation link data acquisition module 201. For missing values, filling and deletion methods are adopted, and at the same time, outliers are detected through statistical methods and machine learning algorithms, and corrected and deleted; data verification is used to ensure the consistency of data between different tables or fields, avoid data conflicts or contradictions, and verify whether the data values are within the set range to avoid data errors or anomalies; data preprocessing includes normalizing and standardizing the data, which is used to eliminate the influence of different dimensions on the model and eliminate data fluctuations and noise.

[0056] In a possible implementation manner, the distribution network digital twin model constructed by the digital twin model construction module 202 includes digital twins of physical power grid devices and digital twins including environment, personnel, and business. The physical power grid devices include power transmission, transformation, distribution, and power consumption devices. By integrating building information model BIM, city information model CIM, power grid information model GIM, or smart grid general information model SG-CIM, the models in the whole process of planning, design, construction, and operation are made unique and shared in different stages.

[0057] In a possible implementation manner, the optimization algorithms adopted by the model optimization and evaluation module 203 include any one or a combination of convolutional neural network, recurrent neural network in deep learning, and transformers. The model optimization and evaluation module 203 uses the ensemble learning method to improve the prediction and decision-making capabilities of the distribution network digital twin model, and the ensemble learning method includes any one or a combination of random forest, gradient boosting tree, and extreme gradient boosting XGBoost.

[0058] When the model optimization and evaluation module 203 evaluates and verifies the distribution network digital twin model, it detects the performance and accuracy of the model and discovers and solves corresponding problems.

[0059] In a possible implementation manner, the dynamic simulation module 204 simulates the topological structure, device parameters, and operation status of the power grid, combines the analysis and calculation capabilities of the data middle platform and the capabilities of the technology middle platform, and constructs typical digital twin application scenarios for the four major fields of power grid planning, construction, operation, and customer service.

[0060] In a possible implementation, the power distribution network construction system based on digital twin according to the embodiments of the present invention further includes a solution proposal module 205, which is used to analyze the operation state of the power grid in real time and propose an optimized dispatching solution during the dynamic simulation of the entire life cycle of the power distribution network, and to monitor the state of power grid equipment in real time, detect potential faults, diagnose the causes of faults and propose repair solutions.

[0061] Furthermore, the solution proposal module 205 integrates machine learning and artificial intelligence algorithms, combines historical data and real-time monitoring information, analyzes the operation state of the power grid in real time and proposes an optimized dispatching solution. When the solution proposal module 205 monitors the state of power grid equipment in real time, detects potential faults, diagnoses the causes of faults and proposes repair solutions, it conducts full life cycle management of power grid assets, including equipment state assessment, update plan formulation and decommissioning plan formulation.

[0062] In a possible implementation, the power distribution network construction system based on digital twin according to the embodiments of the present invention further includes a data security enhancement module 207, which is used to encrypt sensitive data, regularly back up important data, establish a perfect data recovery mechanism, and implement access right management; By encrypting sensitive data, the security of the data during transmission and storage is ensured, preventing data leakage and unauthorized access; By regularly backing up important data and establishing a perfect data recovery mechanism, it can cope with possible data loss or damage; By implementing access right management, it is ensured that only authorized personnel can access sensitive data.

[0063] Furthermore, when the data security enhancement module 207 encrypts sensitive data, symmetric encryption is used. Symmetric encryption uses the same key for encryption and decryption. The symmetric encryption adopts the Advanced Encryption Standard AES or the Data Encryption Standard DES. The data security enhancement module 207 of the embodiments of the present invention selects a 192-bit key for the Advanced Encryption Standard AES to increase the cracking difficulty and improve security, and multi-level encryption is used to further increase the cracking difficulty.

[0064] Figure 3 Illustrates a schematic diagram of the physical structure of an electronic device, such as Figure 3As shown in the figure, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 complete communication with each other through the communication bus 340. The processor 310 may call the logical instructions in the memory 330 to execute a method for constructing a distribution network based on digital twins. The method includes collecting data on the operation links of the distribution network; constructing a digital twin model of the distribution network based on the data on the operation links of the distribution network; optimizing the prediction and decision-making capabilities of the digital twin model of the distribution network and conducting evaluation and verification; and using the optimized digital twin model of the distribution network to perform dynamic simulation of the entire life cycle of the distribution network.

[0065] In addition, when the logical instructions in the above-mentioned memory 330 can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0066] Another embodiment of the present invention further provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for constructing a distribution network based on digital twins provided in the above-mentioned embodiment.

[0067] The embodiment of the present invention further provides a computer-readable storage medium. The computer-readable storage medium stores at least one instruction. When the at least one instruction is executed by a processor, the method for constructing a distribution network based on digital twins as described above is implemented.

[0068] The computer program includes computer program code. The computer program code may be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable storage medium may include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code. It should be noted that the content included in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals. For the convenience of description, only the parts related to the embodiments of the present invention are shown above. For specific technical details not disclosed, please refer to the method part of the embodiments of the present invention. The computer-readable storage medium is non-transitory and can be stored in a storage device formed by various electronic devices and can implement the execution process recorded in the method of the embodiments of the present invention.

[0069] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, 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 memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems) and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be realized by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0071] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, so that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide steps for realizing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the specific implementation manners of the present invention can still be modified or equivalently replaced, and any modification or equivalent replacement without departing from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for constructing a distribution network based on digital twin, characterized in that Including: Collecting data on the operation links of the distribution network; Constructing a digital twin model of the distribution network based on the data of the operation links of the distribution network; Optimizing the prediction and decision-making capabilities of the digital twin model of the distribution network and conducting evaluation and verification; Using the optimized digital twin model of the distribution network to conduct dynamic simulation of the entire life cycle of the distribution network.

2. The method for constructing a distribution network based on digital twin according to claim 1, wherein: The data on the operation links of the distribution network includes any one or a combination of voltage, current, power, temperature, and wind speed.

3. The method for constructing a distribution network based on digital twin according to claim 1, wherein: After collecting the data on the operation links of the distribution network, it further includes the step of performing data quality control on the collected data on the operation links of the distribution network; the data quality control includes cleaning, verifying, and preprocessing the collected data on the operation links of the distribution network; For missing values, methods of filling and deletion are adopted, and at the same time, outlier detection is performed through statistical methods and machine learning algorithms, and corrections and deletions are made; Data verification is used to ensure the consistency of data between different tables or fields, avoid data conflicts or contradictions, and verify whether the data values are within the set range to avoid data errors or anomalies; Data preprocessing includes normalizing and standardizing the data, which is used to eliminate the influence of different dimensions on the model and eliminate data fluctuations and noises.

4. The method for constructing a distribution network based on digital twins according to claim 3, wherein: The filling methods include any one or a combination of mean filling, median filling, and interpolation methods.

5. The method for constructing a distribution network based on digital twins according to claim 1, wherein: In the step of constructing a digital twin model of the distribution network based on the data of the operation links of the distribution network, the digital twin model of the distribution network includes digital twins of physical power grid equipment and digital twins including environment, personnel, and business; The physical power grid equipment includes power transmission, transformation, distribution, and power consumption equipment. By integrating Building Information Modeling (BIM), City Information Modeling (CIM), Grid Information Modeling (GIM), or Smart Grid Common Information Model (SG-CIM), the models in the whole process of planning, design, construction, and operation are made unique and shared in different stages.

6. The method for constructing a distribution network based on digital twins according to claim 1, wherein: In the step of optimizing the prediction and decision-making capabilities of the digital twin model of the distribution network and conducting evaluation and verification, the optimization algorithms for realizing the optimization of the digital twin model of the distribution network include any one or a combination of convolutional neural network, recurrent neural network, and transformer in deep learning; the ensemble learning method is used to improve the prediction and decision-making capabilities of the digital twin model of the distribution network, and the ensemble learning method includes any one or a combination of random forest, gradient boosting tree, and Extreme Gradient Boosting (XGBoost).

7. The method for constructing a distribution network based on digital twins according to claim 1, characterized in that: In the step of using the optimized digital twin model of the distribution network to conduct dynamic simulation of the entire life cycle of the distribution network, the dynamic simulation includes simulating the topological structure, equipment parameters, and operating status of the power grid, combining the analysis and calculation capabilities of the data middle platform and the capabilities of the technology middle platform, and constructing typical digital twin application scenarios for the four major fields of power grid planning, construction, operation, and customer service.

8. The method for constructing a distribution network based on digital twin according to claim 1, wherein: During the process of conducting dynamic simulation of the entire life cycle of the distribution network, the operating status of the power grid is analyzed in real time and an optimized dispatching plan is proposed, and at the same time, the status of power grid equipment is monitored in real time to discover potential faults, diagnose the causes of faults, and propose repair plans.

9. The method for constructing a distribution network based on digital twin according to claim 8, wherein: In the step of analyzing the operation state of the power grid in real time and proposing an optimized dispatching scheme, machine learning and artificial intelligence algorithms are integrated, combined with historical data and real-time monitoring information, to analyze the operation state of the power grid in real time and propose an optimized dispatching scheme; In the step of monitoring the state of power grid equipment in real time, discovering potential faults, diagnosing the causes of faults and proposing repair schemes, the whole life cycle management of power grid assets is carried out, including equipment state assessment, update plan formulation and decommissioning scheme formulation.

10. The method for constructing a distribution network based on digital twins according to claim 1, wherein: It also includes: Encrypt sensitive data to ensure the security of data during transmission and storage, prevent data leakage and unauthorized access; Regularly back up important data and establish a perfect data recovery mechanism to deal with possible data loss or damage; Implement access control management to ensure that only authorized personnel can access sensitive data.

11. The method for constructing a distribution network based on digital twins according to claim 10, wherein: In the step of encrypting sensitive data, symmetric encryption is adopted, and the same key is used for encryption and decryption in symmetric encryption.

12. The method for constructing a distribution network based on digital twin according to claim 11, wherein: The symmetric encryption adopts the Advanced Encryption Standard AES or the Data Encryption Standard DES; The Advanced Encryption Standard AES selects a 192-bit key and adopts multi-level encryption.

13. A power distribution network construction system based on digital twin, characterized in that, It includes: An operation link data acquisition module for acquiring the operation link data of the distribution network; A digital twin model construction module for constructing a distribution network digital twin model based on the operation link data of the distribution network; A model optimization evaluation module for optimizing the prediction and decision-making capabilities of the distribution network digital twin model and conducting evaluation and verification; A dynamic simulation module for dynamically simulating the whole life cycle of the distribution network using the optimized distribution network digital twin model.

14. The digital-twin-based distribution network construction system according to claim 13, wherein: It also includes a data quality control module for cleaning, verifying and preprocessing the operation link data of the distribution network acquired by the operation link data acquisition module; For missing values, the methods of filling and deletion are adopted, and at the same time, outliers are detected through statistical methods and machine learning algorithms, and corrected and deleted; Data verification is used to ensure the consistency of data between different tables or fields, avoid data conflicts or contradictions, and verify whether the data values are within the set range to avoid data errors or anomalies; Data preprocessing includes normalizing and standardizing the data to eliminate the influence of different dimensions on the model and eliminate data fluctuations and noises.

15. The digital twin-based distribution network construction system according to claim 13, wherein: The distribution network digital twin model constructed by the digital twin model construction module includes the digital twin of physical power grid equipment and the digital twin including environment, personnel and business; The physical power grid equipment includes power transmission, transformation, distribution and power consumption equipment. By integrating the Building Information Model BIM, City Information Model CIM, Power Grid Information Model GIM or Smart Grid General Information Model SG-CIM, the models in the whole process of planning, design, construction and operation are unique and shared in different stages.

16. The digital twin-based distribution network construction system according to claim 13, wherein: The optimization algorithms adopted by the model optimization and evaluation module include any one or a combination of convolutional neural networks, recurrent neural networks in deep learning, and transformers; the model optimization and evaluation module uses ensemble learning methods to improve the prediction and decision-making capabilities of the distribution network digital twin model, and the ensemble learning methods include any one or a combination of random forests, gradient boosting trees, and extreme gradient boosting XGBoost.

17. The digital twin-based distribution network construction system according to claim 13, wherein: The dynamic simulation module simulates the topological structure, equipment parameters, and operating status of the power grid, and combines the analysis and calculation capabilities of the data middle platform and the capabilities of the technology middle platform to build typical digital twin application scenarios for the four major fields of power grid planning, construction, operation, and customer service.

18. The digital-twin-based distribution network construction system according to claim 13, wherein: It also includes a solution proposal module, which is used to analyze the operating status of the power grid in real time and propose an optimized scheduling solution during the dynamic simulation of the entire life cycle of the distribution network, and to monitor the status of power grid equipment in real time, detect potential faults, diagnose the causes of faults, and propose repair solutions.

19. The digital twin-based distribution network construction system according to claim 18, wherein: The solution proposal module integrates machine learning and artificial intelligence algorithms, combines historical data and real-time monitoring information, analyzes the operating status of the power grid in real time, and proposes an optimized scheduling solution; when the solution proposal module monitors the status of power grid equipment in real time, detects potential faults, diagnoses the causes of faults, and proposes repair solutions, it conducts full life cycle management of power grid assets, including equipment status assessment, update plan formulation, and retirement plan formulation.

20. The digital-twin-based distribution network construction system according to claim 13, wherein: It also includes a data security enhancement module, which is used to encrypt sensitive data, regularly back up important data, establish a perfect data recovery mechanism, and implement access control management; By encrypting sensitive data, it ensures the security of data during transmission and storage, preventing data leakage and unauthorized access; By regularly backing up important data and establishing a perfect data recovery mechanism, it can cope with possible data loss or damage; By implementing access control management, it ensures that only authorized personnel can access sensitive data.

21. An electronic device, characterized in that, It includes a processor and a memory. The processor is used to execute the computer program stored in the memory to implement the digital twin-based distribution network construction method according to any one of claims 1 to 12.

22. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, it implements the digital twin-based distribution network construction method according to any one of claims 1 to 12.

Images