Non-fault area power supply recovery method and system considering distributed power supply access
By constructing distribution network topology and machine learning models to evaluate health status, the problem of low power supply recovery efficiency in traditional methods is solved, and rapid recovery and efficient power supply are achieved.
Patent Information
- Application Number
- CN202410936158.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2024-11-26
AI Technical Summary
Traditional distribution network power supply recovery methods are difficult to quickly and accurately determine the fault range and recovery plan for non-fault areas, resulting in low power supply recovery efficiency in non-fault areas and the key nodes cannot restore power supply in time.
By obtaining distribution network data, building a topology structure, isolating the faulty area, using machine learning models to evaluate the health status of non-failed nodes, calculating power supply recovery priorities, and formulating personalized power supply recovery strategies.
It realizes rapid power supply recovery in non-fault areas, improves the power supply reliability and efficiency of the distribution network, ensures that key nodes have priority to restore power supply, and reduces resource waste.
Smart Images

Figure CN119029840A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power distribution network power supply failure recovery, and in particular to a method and system for power supply recovery in a non-fault area taking into account access of distributed power sources. Background Art
[0002] With the transformation of the global energy structure and the rapid development of renewable energy technologies, the proportion of distributed generation (DG) in the power system is increasing. Distributed generation, such as solar photovoltaic, wind power generation, small gas turbines, etc., has the advantages of high flexibility, low pollution, and diverse energy utilization, and has become an effective means to solve the energy crisis and alleviate environmental pollution. However, with the large-scale access of distributed generation, the structure and operation mode of the power grid have changed significantly, bringing new challenges to the power supply restoration capability of the distribution network. Traditional distribution network power supply restoration methods are mostly based on centralized control strategies, relying on the central controller to grasp and calculate global topology information and electrical quantity information in real time to formulate power supply restoration strategies.
[0003] However, due to the distributed and uncertain nature of distributed generation (DGs), traditional methods struggle to quickly and accurately determine the fault scope and restoration plan for non-fault zones. Therefore, developing a method and system for power restoration in non-fault zones that takes DGs into account has important theoretical and practical value. This approach can formulate a reasonable power restoration strategy based on the priority and urgency of nodes, ensuring that critical nodes are restored first, while also improving the reliability and operational efficiency of the entire distribution network. Summary of the Invention
[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.
[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a method for restoring power supply in non-fault areas taking into account the access of distributed power sources to solve the problems of low power restoration efficiency in non-fault areas and failure to restore power to key nodes in a timely manner.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In a first aspect, the present invention provides a method for restoring power supply in a non-fault area taking into account access to distributed power sources, comprising:
[0008] Acquiring distribution network data, constructing a distribution network topology structure based on the distribution network data, and determining a fault area based on the distribution network topology structure;
[0009] Isolating a faulty area in the distribution network topology to obtain a non-faulty area;
[0010] Using a machine learning model to evaluate the health status of the non-faulty nodes in the non-faulty area, obtaining a health status index, and obtaining a timely evaluation value of the non-faulty nodes based on the health status index;
[0011] The power supply restoration priority of the non-fault area is obtained according to the health status index and the timely evaluation value, and a power supply restoration strategy is formulated for the non-fault area according to the power supply restoration priority.
[0012] As a preferred solution of the method for restoring power supply to a non-fault area taking into account the access of distributed power sources described in the present invention, determining the fault area includes:
[0013] Real-time data of the grid nodes in the distribution network topology are obtained. If the real-time data of the grid nodes exceeds a set first threshold range, the grid nodes whose real-time data exceeds the set threshold range are interconnected to obtain a fault area.
[0014] As a preferred solution of the method for restoring power supply in a non-fault area taking into account distributed power supply access according to the present invention, wherein: the health status of the non-fault nodes in the non-fault area is evaluated using a machine learning model, and the health status index is obtained, including:
[0015] Obtaining historical operating data and historical fault records of the non-faulty nodes, and inputting the historical operating data and historical fault records into a machine learning model for training;
[0016] The real-time operation data input value of the non-faulty node is used to make predictions in the trained machine learning model, to obtain the future fault data and health status of the non-faulty node, and to convert the health status into a health status index.
[0017] As a preferred solution of the method for restoring power supply in a non-fault area taking into account access to distributed power sources according to the present invention, converting the health status into a health status index includes:
[0018] Setting a conversion threshold, which includes a normal threshold, a warning threshold, and an emergency threshold, and comparing the future fault data of the non-faulty node with the normal threshold, the warning threshold, and the emergency threshold;
[0019] If the future fault data of the non-faulty node is within the normal threshold, or exceeds the normal threshold and is lower than the warning threshold, the non-faulty node has a first-level health status index;
[0020] If the future fault data of the non-faulty node exceeds the warning threshold and is lower than the emergency threshold, the non-faulty node is in a secondary health status index;
[0021] If the future fault data of the non-faulty node exceeds the emergency threshold, the non-faulty node has a level 3 health status index.
[0022] As a preferred solution of the method for restoring power supply in a non-fault area taking into account access to distributed power sources according to the present invention, obtaining the timely evaluation value of the non-fault node based on the health status index includes:
[0023] According to the real-time data of the grid nodes in the distribution network topology, non-fault nodes in the non-fault area connected to the fault node in the fault area, and non-fault nodes in the non-fault area whose real-time data exceeds a set second threshold range are determined as risk nodes;
[0024] A search algorithm is used to obtain multiple power supply paths between non-faulty nodes and risky nodes and distributed power sources, and risk values of non-faulty nodes and risky nodes on the power supply paths are obtained.
[0025] As a preferred solution of the method for restoring power supply to a non-fault area taking into account the access of distributed power sources described in the present invention, it further includes:
[0026] According to the risk value and the health status index, the timely assessment value of each power supply path is calculated, which is expressed as:
[0027]
[0028] Among them, P i is the timely evaluation value of the i-th power supply path in the non-fault area, N is the maximum number of power supply paths in the non-fault area, F ij is the risk value of the jth non-fault node in the i-th power supply path in the non-fault area, Z ij is the health status index of the jth non-fault node in the i-th power supply path in the non-fault area, F ik is the risk value of the kth risk node in the i-th power supply path in the non-fault area, Z ik is the health status index of the kth risk node in the i-th power supply path in the non-fault area.
[0029] As a preferred solution of the method for restoring power supply to a non-fault area taking into account the access of distributed power sources described in the present invention, obtaining the power supply restoration priority of the non-fault area includes:
[0030] According to the health status index and the timely evaluation value, a comprehensive evaluation value of the power supply path is calculated, which is expressed as:
[0031]
[0032] Among them, I i represents the comprehensive evaluation value of the i-th power supply path in the non-fault area, P i is the timely evaluation value of the i-th power supply path in the non-fault area, N is the maximum number of power supply paths in the non-fault area, M represents the maximum number of non-fault nodes on the power supply path in the non-fault area, Q represents the maximum number of risk nodes on the power supply path in the non-fault area, and Z ij is the health status index of the jth non-fault node in the i-th power supply path in the non-fault area, Z ik is the health status index of the kth risk node in the i-th power supply path in the non-fault area;
[0033] The comprehensive evaluation values are arranged to obtain the power supply priority of the non-fault area.
[0034] In a second aspect, the present invention provides a system for restoring power supply to a non-fault area taking into account access to distributed power sources, comprising:
[0035] A fault area acquisition module is used to acquire distribution network data, construct a distribution network topology structure based on the distribution network data, and determine the fault area based on the distribution network topology structure;
[0036] a non-fault area acquisition module, configured to isolate the fault area in the distribution network topology and acquire a non-fault area;
[0037] a calculation and evaluation module, configured to evaluate the health status of the non-faulty nodes in the non-faulty area using a machine learning model, obtain a health status index, and obtain a timely evaluation value of the non-faulty nodes based on the health status index;
[0038] The power supply strategy acquisition module is used to obtain the power supply restoration priority of the non-fault area according to the health status index and the timely evaluation value, and formulate a power supply restoration strategy for the non-fault area according to the power supply restoration priority.
[0039] In a third aspect, the present invention provides a computing device, comprising:
[0040] memory and processor;
[0041] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the non-fault area power supply restoration method taking into account the access of distributed power sources are implemented.
[0042] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for restoring power supply to a non-fault area taking into account the access of distributed power sources.
[0043] Compared with the existing technology, the beneficial effects of the present invention are as follows: the present invention realizes rapid power restoration in non-fault areas by constructing a distribution network topology, isolating fault areas, evaluating non-fault areas and determining power supply restoration priorities, as well as formulating personalized power supply restoration strategies, thereby significantly improving the power supply reliability and efficiency of the distribution network; the present invention sets a priority for each power supply path, adopts different power supply restoration strategies for different power supply paths, pays more attention to key nodes and improves timeliness, thereby improving power supply restoration efficiency and reducing resource waste. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort. Among them:
[0045] Figure 1 The figure is a schematic diagram of the overall flow of a method for restoring power supply to a non-fault area taking into account access to distributed power sources according to an embodiment of the present invention. DETAILED DESCRIPTION
[0046] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.
[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0048] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.
[0049] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.
[0050] Furthermore, in the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the systems or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0051] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.
[0052] Example 1
[0053] Reference Figure 1 , which is an embodiment of the present invention, provides a method for restoring power supply in a non-fault area taking into account the access of distributed power sources, comprising:
[0054] S100: Acquire distribution network data, construct a distribution network topology according to the distribution network data, and determine the fault area according to the distribution network topology;
[0055] Preferably, real-time data of the grid nodes in the distribution network topology is obtained, and if the real-time data of the grid nodes exceeds a set first threshold range, the grid nodes whose real-time data exceeds the set threshold range are interconnected to obtain the fault area;
[0056] Specifically, the distribution network data includes grid node voltage, current, network layout and node connection relationship, etc. The grid nodes in the distribution network topology mainly include user nodes, large branch line nodes and trunk line nodes; the faulty nodes are detected by detection equipment, which can be sensors, monitoring equipment, etc., to monitor the real-time data of each node in the topology. If the real-time data of the current node is abnormal, it proves that the current node has failed. The current node with a fault can be quickly found through the topology structure, and the faulty node can be found by setting a threshold. When the real-time data of the current node is not within the threshold range, it is determined that the current node has failed.
[0057] In an embodiment of the present application, for the first threshold range of the present invention, the degree of deviation of the real-time data of the power grid node from the normal value is expressed in the form of a percentage. For example, if the normal voltage range of a power grid node is 90V to 110V, the first threshold range is set to 10% above 110V or 10% below 90V, that is, when the voltage exceeds 121V or is below 79V, it is considered that the power grid node may be in a fault state; the specific threshold range should be set according to the actual operation conditions and historical fault data of the distribution network. The above is only a design example made according to the present invention. The actual first threshold range should be flexibly adjusted according to the specific needs and actual conditions of different distribution networks to ensure that abnormal conditions in the real-time data of the power grid node can be accurately and effectively identified.
[0058] S102: Isolate the fault area in the distribution network topology to obtain a non-fault area;
[0059] Specifically, when a fault occurs at a user node, the circuit breaker installed at the user performs a current quick-break protection action to quickly cut off the current at the fault point and achieve power outage in the fault area;
[0060] When a fault occurs at a large branch line node, the circuit breaker installed at the outgoing line end of the large branch line node will perform a time-limited quick-trip protection action. This means that after detecting the fault current, the circuit breaker will operate after a set delay time (such as several hundred milliseconds to several seconds) to distinguish between transient faults and permanent faults. Reclosing will be performed after a set interval. If the fault is transient, the reclosing will succeed and the system will restore power. If the fault is permanent, the reclosing will fail, and further fault location and processing will be required.
[0061] When a fault occurs at a main line node, the circuit breaker installed at the outgoing end of the main line node will perform current quick-break protection, and the section switch will trip due to voltage loss. After a set interval, the circuit breaker, section switch, and tie switch will be reclosed to complete power outage of the faulty section.
[0062] Through the action of the above-mentioned circuit breaker, the fault area is isolated, thereby obtaining a non-fault area.
[0063] S104: Using a machine learning model to evaluate the health status of non-faulty nodes in the non-faulty area, obtain a health status index, and obtain a timely evaluation value of the non-faulty nodes based on the health status index;
[0064] Preferably, historical operation data and historical fault records of non-faulty nodes are obtained, and the historical operation data and historical fault records are input into a machine learning model for training;
[0065] Specifically, historical operating data includes: operating parameters of non-faulty nodes: temperature, pressure, vibration, current, voltage, etc. of non-faulty node equipment; performance data of non-faulty nodes: response time, throughput, efficiency, etc. of grid node equipment; load conditions of non-faulty nodes: working hours, operating cycles, usage frequency, etc. of non-faulty node equipment; historical fault records include: time, location, type, operating parameters, status information, repair time, replacement parts, repair measures, severity, etc. of the fault; using historical operating data and historical fault records, each node is continuously monitored and analyzed to assess its current node health status and potential fault risks;
[0066] Preferably, the real-time operating data of the non-faulty nodes is input into a trained machine learning model for prediction, the future fault data and health status of the non-faulty nodes are obtained, and the health status is converted into a health status index;
[0067] Specifically, the above historical operation data and historical fault records are cleaned to remove noise, outliers, and duplicate data; data is extracted from the preprocessed historical operation data and historical fault records and assembled into a training set. The training set includes node locations, historical operation data of nodes, and historical fault records of nodes. The data in the training set is also labeled with node data and the fault data corresponding to the nodes. This is used as the training set, and a machine learning model is used to learn the relationship between nodes and node faults, thereby obtaining a trained machine learning model;
[0068] In an embodiment of the present application, by obtaining the real-time operating data of the nodes in the non-fault area and inputting it into a trained machine learning model for prediction, the future operating state of the non-fault node is output. The future operating state of the non-fault node includes the fault data of the non-fault node. The fault data of the non-fault node is analyzed to obtain the fault type and fault cause of the non-fault node. Fault types include minor faults, moderate faults and major faults; the fault causes corresponding to minor faults may include aging and wear of components, environmental factors, unstable power supply, etc.; the fault causes corresponding to moderate faults may include damage to key components, circuit breaker failure, human factors, etc.; the fault causes corresponding to major faults may include damage to major equipment, external environmental factors, aging equipment, etc. The future operating state of the node is converted to a healthy state, and the healthy state includes safety, fault warning and failure; the health state of the node is determined to be any of safety, fault warning and failure based on the fault type and fault cause, and the healthy state is determined based on the predicted fault type and fault cause.
[0069] Preferably, a conversion threshold is set, the conversion threshold including a normal threshold, a warning threshold and an emergency threshold, and the future fault data of the non-faulty node is compared with the normal threshold, the warning threshold and the emergency threshold;
[0070] It should be noted that the conversion threshold is set based on each parameter in the historical operating data. For each parameter in the historical data, the normal threshold, warning threshold, and emergency threshold are determined based on historical data analysis. Each parameter of the predicted fault data is compared with its corresponding conversion threshold to obtain the health status index.
[0071] If the future fault data of a non-faulty node is within the normal threshold, or exceeds the normal threshold and is lower than the warning threshold, the non-faulty node has a level 1 health status index;
[0072] If the future fault data of a non-faulty node exceeds the warning threshold and is lower than the emergency threshold, the non-faulty node is in the secondary health status index;
[0073] If the future fault data of a non-faulty node exceeds the emergency threshold, the non-faulty node will be in the third level health status index;
[0074] In the embodiment of the present application, the first-level health status index of all nodes whose future fault data of non-faulty nodes is within the normal threshold range, exceeds the normal threshold and is lower than the warning threshold is preferably X1, the second-level health status index of all nodes whose future fault data of non-faulty nodes exceeds the warning threshold and is lower than the emergency threshold is preferably X2, and the third-level health status index of all nodes whose future fault data of non-faulty nodes exceeds the emergency threshold is preferably X3, X3>X2>X1;
[0075] Furthermore, the conversion threshold of this embodiment is [A1, ..., Ae, ..., Aq, ..., Ay, ..., A Z 】, the conversion threshold range includes the normal threshold Ai, the warning threshold Aj and the emergency threshold An, the normal threshold is: Ae = μ + K1 * σ; the warning threshold is: Aq = μ + K2 * σ; the emergency threshold is: Ay = μ + n * σ; wherein μ represents the mean calculated based on the historical operating data, σ represents the standard deviation calculated based on the historical operating data, K1 represents the adjustment coefficient of the normal threshold, K2 represents the adjustment coefficient of the warning threshold, n represents the adjustment coefficient of the emergency threshold, n>K2>K1, and the preferred embodiment of this embodiment is: K1 = 2, K2 = 3.
[0076] Preferably, based on the real-time data of the grid nodes in the distribution network topology, non-fault nodes in the non-fault area connected to the fault node in the fault area, and non-fault nodes in the non-fault area whose real-time data exceeds a set second threshold range are determined as risk nodes;
[0077] In an embodiment of the present application, the second threshold range is set as follows: by analyzing the historical operating data in the historical data of each node in the topology structure, the statistical quantities such as the average value and standard deviation of the historical data are obtained, and the abnormal threshold is set based on this; illustratively, if the data follows a normal distribution, the average value plus or minus n times the standard deviation can be used as the abnormal threshold. This embodiment also sets a fluctuation range for the real-time data of each node in the non-fault area, and the fluctuation range is preferably ±5%. When the real-time data in the non-fault area exceeds 5% of the upper limit of the abnormal threshold or is lower than 5% of the lower limit of the abnormal threshold, the current real-time data is determined to be abnormal data;
[0078] A search algorithm is used to obtain multiple power supply paths between non-faulty nodes and risky nodes and distributed power sources, and the risk values of non-faulty nodes and risky nodes on the power supply paths are obtained;
[0079] Preferably, the timely assessment value of each power supply path is calculated based on the risk value and the health status index, which is expressed as:
[0080]
[0081] Among them, P i is the timely evaluation value of the i-th power supply path in the non-fault area, N is the maximum number of power supply paths in the non-fault area, F ij is the risk value of the jth non-fault node in the i-th power supply path in the non-fault area, Z ij is the health status index of the jth non-fault node in the i-th power supply path in the non-fault area, F ik is the risk value of the kth risk node in the i-th power supply path in the non-fault area, Z ikis the health status index of the kth risk node in the i-th power supply path in the non-fault area;
[0082] It should be noted that the present invention conducts a comprehensive health status assessment of non-fault nodes in non-fault areas through a machine learning model, and obtains an accurate health status index. The health status index not only reflects the current operating status of the node, but also predicts its future operating status and potential fault risks; based on this index and the risk value of the node, the technical solution further calculates the timely evaluation value of each power supply path, providing strong support for the stable operation of the power grid; by real-time monitoring and prediction of the health status of non-fault nodes, potential faults can be discovered and resolved in a timely manner to avoid the expansion of faults and the impact on the normal operation of the power grid; at the same time, considering the risk value and health status index of the node, the stability of the power supply path can be more comprehensively evaluated, providing a scientific basis for the formulation of fault recovery and power supply recovery strategies for the power grid, which will significantly improve the power supply reliability and efficiency of the power grid and reduce the impact of faults on the operation of the power grid.
[0083] S106: Obtain the power supply restoration priority of the non-fault area based on the health status index and the timely assessment value, and formulate a power supply restoration strategy for the non-fault area based on the power supply restoration priority;
[0084] Preferably, the comprehensive evaluation value of the power supply path is calculated based on the health status index and the timely evaluation value, which is expressed as:
[0085]
[0086] Among them, I i represents the comprehensive evaluation value of the i-th power supply path in the non-fault area, P i is the timely evaluation value of the i-th power supply path in the non-fault area, N is the maximum number of power supply paths in the non-fault area, M represents the maximum number of non-fault nodes on the power supply path in the non-fault area, Q represents the maximum number of risk nodes on the power supply path in the non-fault area, and Z ij is the health status index of the jth non-fault node in the i-th power supply path in the non-fault area, Z il is the health status index of the kth risk node in the i-th power supply path in the non-fault area;
[0087] Preferably, the comprehensive evaluation values are arranged to obtain the power supply priority of the non-fault area;
[0088] In the embodiment of the present application, the calculation results of the comprehensive evaluation values are arranged in descending order to form a result data set [I1, ..., I N ], the order of the calculation results in the result data set is the power supply priority of the non-faulty nodes. Specifically, I1 has the highest power supply priority, I NThe power supply priority is the lowest; when a fault occurs in the fault area and the fault area is isolated, the power supply path with the highest power supply priority carries critical services and a large number of important loads, which is vital to public safety and needs to be restored as soon as possible.
[0089] In the embodiment of the present application, for the power supply path I1 with the highest power supply priority in the result data set, the power supply strategy that can be adopted is: immediately mobilize all necessary restoration resources, give priority to critical facilities and important loads, monitor the stability of the power grid, and take necessary measures to prevent the spread of the fault;
[0090] For any power supply path I in the medium power supply priority in the result data set L ,The power supply strategy that can be adopted is as follows: after the power supply path I1 is restored, the remaining resources can be quickly deployed to these areas. Based on the load demand and topology, a gradual restoration plan can be developed, giving priority to restoring residential and commercial areas to reduce the impact on society and
[0091] For the power supply path I with lower power supply priority in the result data set N ,The power supply strategy that can be adopted is as follows: after the power supply paths mentioned above are restored, the remaining resources will be used for the restoration work in these areas, the load demand and grid stability will be assessed, and an appropriate restoration plan will be developed. Temporary power supply measures, such as mobile generators, may also be considered to meet basic needs.
[0092] The above is an illustrative embodiment of a method for restoring power to a non-fault area taking into account distributed power generation access. It should be noted that the technical solution of the system for restoring power to a non-fault area taking into account distributed power generation access and the technical solution of the method for restoring power to a non-fault area taking into account distributed power generation access share the same concept. For details not described in detail in the technical solution of the system for restoring power to a non-fault area taking into account distributed power generation access in this embodiment, please refer to the description of the technical solution of the method for restoring power to a non-fault area taking into account distributed power generation access.
[0093] In this embodiment, the power supply restoration system for non-fault areas taking into account the access of distributed power sources includes:
[0094] A fault area acquisition module is used to acquire distribution network data, construct a distribution network topology based on the distribution network data, and determine the fault area based on the distribution network topology;
[0095] A non-fault area acquisition module is used to isolate the fault area in the distribution network topology and obtain the non-fault area;
[0096] A calculation and evaluation module is used to evaluate the health status of non-faulty nodes in non-faulty areas using a machine learning model, obtain a health status index, and obtain timely evaluation values of non-faulty nodes based on the health status index;
[0097] The power supply strategy acquisition module is used to obtain the power supply restoration priority of the non-fault area according to the health status index and the timely evaluation value, and formulate a power supply restoration strategy for the non-fault area according to the power supply restoration priority.
[0098] This embodiment further provides a computing device, applicable to a case where power supply is restored to a non-fault area taking into account the access of distributed power sources, including:
[0099] Memory and processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the non-fault area power supply restoration method taking into account the access of distributed power sources as proposed in the above embodiment.
[0100] This embodiment further provides a storage medium having a computer program stored thereon. When the program is executed by a processor, the method for restoring power supply to a non-fault area taking into account access to distributed power sources as proposed in the above embodiment is implemented.
[0101] The storage medium proposed in this embodiment and the method for realizing power supply restoration in non-fault areas taking into account distributed power supply access proposed in the above embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.
[0102] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer's floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.
[0103] Example 2
[0104] Referring to Table 1-2, an embodiment of the present invention provides a power supply restoration method for a non-fault area taking into account the access of distributed power sources. In order to verify its beneficial effects, experimental simulation results are provided.
[0105] In order to verify the effectiveness of the power supply restoration method for non-fault areas taking into account the access of distributed power sources of the present invention, experiments were conducted using software simulation.
[0106] First, a simulated distribution network consisting of 50 grid nodes and 10 distributed generation units was constructed using power system simulation software. The initial parameters and operating status of the distribution network were set to ensure the authenticity of the simulation. Next, a fault point was artificially set in the simulated distribution network, triggering the fault protection mechanism. The faulty area was isolated from the distribution network by simulating the operation of a circuit breaker.
[0107] The random forest algorithm is trained on the historical operating data and fault records of non-fault nodes in the distribution network. The random forest algorithm is chosen because it performs well in classification problems and can handle a large number of input features.
[0108] The training dataset contains 1,825 daily operating data and fault records for each non-faulty node over the past year. Each record includes characteristics such as node voltage, current, and power. The real-time operating data of non-faulty nodes is input into the model to obtain the health status index of the non-faulty area. The test results are shown in Table 1, where ten nodes are selected as examples.
[0109] Table 1 Node health status values
[0110] Node number Health Status Index Node number Health Status Index node1 Level 1 node 6 Level 3 node 2 Level 2 node 7 Level 2 node 3 Level 1 node 8 Level 1 node 4 Level 2 node 9 Level 3 node 5 Level 1 node 10 Level 2
[0111] On this basis, a search algorithm was used to find multiple power supply paths between non-faulty nodes and risky nodes and distributed power sources. The timely evaluation value of each power supply path was calculated based on the risk value and health status index. The comprehensive evaluation value of the power supply path was calculated by combining the timely evaluation value and health status index, as shown in Table 2, taking five of the paths as an example;
[0112] Table 2 Power supply priority results
[0113] Power supply path number Timely evaluation value Comprehensive evaluation value Power supply priority Path1 0.88 0.86 1 Path2 0.72 0.70 2 Path3 0.56 0.55 3 Path4 0.65 0.62 4 Path5 0.48 0.45 5
[0114] Based on the comprehensive evaluation values in Table 2, a power supply restoration strategy for non-fault areas was formulated and implemented in a simulated distribution network. The effectiveness of the power supply restoration method for non-fault areas taking into account distributed generation access was observed through software simulation experiments. The experimental results show that this method can accurately assess the health status of non-fault nodes, identify risk nodes and power supply paths, and formulate an effective power supply restoration strategy, which provides strong technical support for fault recovery and power supply restoration in actual distribution networks.
[0115] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A method for restoring power supply in a non-fault area taking into account the access of distributed power sources, characterized in that: include: Acquire distribution network data, construct a distribution network topology structure according to the distribution network data, and determine a fault area according to the distribution network topology structure; Isolating the fault area in the distribution network topology to obtain a non-fault area; Using a machine learning model to evaluate the health status of the non-faulty nodes in the non-faulty area, obtaining a health status index, and obtaining a timely evaluation value of the non-faulty nodes based on the health status index; The power supply restoration priority of the non-fault area is obtained according to the health status index and the timely evaluation value, and a power supply restoration strategy is formulated for the non-fault area according to the power supply restoration priority.
2. The method for restoring power supply in a non-fault area taking into account the access of distributed power sources as claimed in claim 1, characterized in that: Determine the fault area including, Real-time data of the grid nodes in the distribution network topology are obtained. If the real-time data of the grid nodes exceeds a set first threshold range, the grid nodes whose real-time data exceed the set threshold range are interconnected to obtain a fault area.
3. The method for restoring power supply in a non-fault area taking into account the access of distributed power sources as claimed in claim 1, characterized in that: The health status of the non-faulty nodes in the non-faulty area is evaluated by using a machine learning model to obtain a health status index including: Obtaining historical operation data and historical fault records of the non-faulty nodes, and inputting the historical operation data and historical fault records into a machine learning model for training; The real-time operation data input value of the non-faulty node is predicted in the trained machine learning model to obtain the future fault data and health status of the non-faulty node, and the health status is converted into a health status index.
4. The method for restoring power supply in a non-fault area taking into account the access of distributed power sources as claimed in claim 3, characterized in that: Converting the health status into a health status index comprises, Setting a conversion threshold, the conversion threshold including a normal threshold, a warning threshold and an emergency threshold, and comparing the future fault data of the non-faulty node with the normal threshold, the warning threshold and the emergency threshold; If the future fault data of the non-faulty node is within the normal threshold, or exceeds the normal threshold and is lower than the warning threshold, the non-faulty node has a first-level health status index; If the future fault data of the non-faulty node exceeds the warning threshold and is lower than the emergency threshold, the non-faulty node is a secondary health status index; If the future fault data of the non-faulty node exceeds the emergency threshold, the non-faulty node has a level 3 health status index.
5. The method for restoring power supply to a non-fault area taking into account the access of distributed power sources as claimed in claim 2 or 4, characterized in that: Based on the health status index, obtaining the timely evaluation value of the non-faulty node includes: According to the real-time data of the grid nodes in the distribution network topology structure, non-fault nodes in the non-fault area connected to the fault nodes in the fault area, and non-fault nodes in the non-fault area whose real-time data exceeds a set second threshold range are determined as risk nodes; A search algorithm is used to obtain multiple power supply paths between non-faulty nodes and risky nodes and distributed power sources, and risk values of non-faulty nodes and risky nodes on the power supply paths are obtained.
6. The method for restoring power supply in a non-fault area taking into account the access of distributed power sources as claimed in claim 5, characterized in that: Also includes, According to the risk value and the health status index, the timely assessment value of each power supply path is calculated, which is expressed as: Among them, P i is the timely evaluation value of the i-th power supply path in the non-fault area, N is the maximum number of power supply paths in the non-fault area, and F ij is the risk value of the jth non-faulty node in the i-th power supply path in the non-faulty area, Z ij is the health status index of the jth non-faulty node in the i-th power supply path in the non-faulty area, F ik is the risk value of the kth risk node in the ith power supply path in the non-fault area, Z ik is the health status index of the kth risk node in the i-th power supply path in the non-fault area.
7. The method for restoring power supply in a non-fault area taking into account the access of distributed power sources as claimed in claim 6, characterized in that: Obtaining the power restoration priority of the non-fault area includes: According to the health status index and the timely evaluation value, a comprehensive evaluation value of the power supply path is calculated, which is expressed as: Among them, I i represents the comprehensive evaluation value of the ith power supply path in the non-fault area, P i is the timely evaluation value of the i-th power supply path in the non-fault area, N is the maximum number of power supply paths in the non-fault area, M represents the maximum number of non-fault nodes on the power supply path in the non-fault area, Q represents the maximum number of risk nodes on the power supply path in the non-fault area, and Z ij is the health status index of the jth non-faulty node in the i-th power supply path in the non-faulty area, Z ik is the health status index of the kth risk node in the i-th power supply path in the non-fault area; The comprehensive evaluation values are arranged to obtain the power supply priority of the non-fault area.
8. A system for restoring power supply in a non-fault area taking into account the access of distributed power sources, characterized in that: include, A fault area acquisition module is used to acquire distribution network data, construct a distribution network topology structure according to the distribution network data, and determine the fault area according to the distribution network topology structure; A non-fault area acquisition module, used to isolate the fault area in the distribution network topology structure and acquire the non-fault area; A calculation and evaluation module, used to evaluate the health status of the non-faulty nodes in the non-faulty area by using a machine learning model, obtain a health status index, and obtain a timely evaluation value of the non-faulty nodes based on the health status index; A power supply strategy acquisition module is used to obtain the power supply restoration priority of the non-fault area according to the health status index and the timely evaluation value, and formulate a power supply restoration strategy for the non-fault area according to the power supply restoration priority.
9. An electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the non-fault area power supply restoration method taking into account the access of distributed power sources as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for restoring power supply to a non-fault area taking into account access to distributed power sources as described in any one of claims 1 to 7.
