Automatic optimization method of distribution network based on multi-source data fusion

Abstract

The invention discloses a distribution network automatic optimization method based on multi-source data fusion, relates to the technical field of power grid optimization, and comprises the following steps: obtaining multi-terminal line topology data of the entire FA line in the distribution network and performing preprocessing; based on the multi-terminal line topology data of the entire FA line in the distribution network, calculating the fixed value verification potential index of each terminal, and calculating the comprehensive priority membership of each terminal to obtain the verification core priority threshold and the verification general priority threshold; based on the fixed value verification potential index of each terminal and the verification core priority threshold and the verification general priority threshold, comparing to obtain fixed value verification nodes of different priorities; constructing a terminal automatic adjustment planning model, and performing multi-level optimization on the distribution network based on the fixed value verification nodes of different priorities, thereby improving the fixed value verification efficiency and accuracy of the distribution network.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid optimization, and more specifically, to a distribution network automatic optimization method based on multi-source data fusion. Background Art

[0002] With the access of renewable energy and the rise of distributed generation, traditional distribution networks face more complex operational challenges. To address these challenges, researchers are committed to developing intelligent and automated solutions to improve the operating efficiency and reliability of distribution systems. In addition, data-driven technologies such as the Internet of Things, big data analysis, and advances in artificial intelligence provide new possibilities for optimizing the management of distribution networks.

[0003] In the process of automatic optimization of the distribution network, the traditional terminal constant value verification can only perform constant value verification on a single terminal. This limitation leads to significant deficiencies in evaluating the commissioning strategy of multiple terminals of the FA line. First, the verification of a single terminal often cannot fully reflect the operating status and risks of the entire line, especially in a multi-terminal system, where the mutual influence and collaborative working relationship between nodes are extremely complex; secondly, the lack of a comprehensive evaluation method for the entire line may lead to the failure to identify potential risks when implementing the commissioning strategy, resulting in insufficient line protection measures and an increased probability of failure. In response to the above problems, the present invention proposes a solution. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an automatic optimization method for a distribution network based on multi-source data fusion, which solves the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The invention discloses an automatic optimization method for a distribution network based on multi-source data fusion, comprising the following steps: obtaining multi-terminal line topology data of an FA line in a distribution network and performing preprocessing; calculating a fixed value verification potential index of each terminal based on the multi-terminal line topology data of the FA line in the distribution network, and calculating a comprehensive priority membership of each terminal to obtain a verification core priority threshold and a verification general priority threshold; obtaining fixed value verification nodes of different priorities by comparing the fixed value verification potential index of each terminal with the verification core priority threshold and the verification general priority threshold; constructing a terminal automatic adjustment planning model, and performing multi-level optimization on the distribution network based on the fixed value verification nodes of different priorities.

[0007] In a preferred embodiment, the calculation of the comprehensive priority membership of each terminal to obtain the core priority threshold and the general priority threshold is specifically as follows: all terminal nodes of the FA line in the distribution network are arranged and combined to obtain a plurality of terminal node combinations; the key influencing indicators of each terminal in the plurality of terminal node combinations are obtained, and the key influencing indicators include the fault response speed, power supply continuity, and load importance of the terminal; the key influencing indicators of each terminal are normalized by Min-Max standardization to obtain the normalized key influencing indicators of each terminal; the normalized key influencing indicators are calculated by the combined weighting method. The comprehensive weight of the key influencing indicators of each terminal is obtained, and based on the comprehensive weight, the comprehensive priority membership of several terminal node combinations is calculated; the comprehensive priority membership of the several terminal node combinations is sorted in descending order, and the several terminal node combinations are clustered using the K-means clustering algorithm to obtain a first terminal node combination, a second terminal node combination, and a third terminal node combination; the intra-group variance and inter-group variance of the first terminal node combination, the second terminal node combination, and the third terminal node combination are calculated; based on the intra-group variance and the inter-group variance, the verification core priority threshold and the verification general priority threshold are respectively obtained.

[0008] In a preferred embodiment, the combined weighting method is used to calculate the comprehensive weight of the key influencing indicators of each terminal after normalization, specifically: the primary indicator weight and the secondary indicator weight of the key influencing indicators of each terminal after normalization are calculated separately; the primary indicator weight and the secondary indicator weight of the key influencing indicators of each terminal after normalization are linearly weighted averaged to obtain the comprehensive weight of the key influencing indicators of each terminal after normalization.

[0009] In a preferred embodiment, based on the intra-group variance and the inter-group variance, the verification core priority threshold and the verification general priority threshold are respectively calculated, specifically: the ratio of the intra-group variance and the inter-group variance is calculated, and an adjustment coefficient is set; the ratio of the intra-group variance and the inter-group variance and the adjustment coefficient are multiplied to obtain a threshold partition coefficient; the average value of the first terminal node combination and the second terminal node combination is calculated and added to the threshold partition coefficient to obtain a verification core priority threshold; the average value of the second terminal node combination and the third terminal node combination is calculated and added to the threshold partition coefficient to obtain a verification general priority threshold.

[0010] In a preferred embodiment, based on the comparison of the fixed-value verification potential index of each terminal with the verification core priority threshold and the verification general priority threshold, fixed-value verification nodes of different priorities are obtained, specifically: the fixed-value verification potential index of each terminal is compared with the verification core priority threshold and the verification general priority threshold respectively; the terminal whose fixed-value verification potential index is greater than the verification core priority threshold is classified as a core priority node; the terminal whose fixed-value verification potential index is less than the verification core priority threshold and greater than the verification general priority threshold is classified as a general priority node; the terminal whose fixed-value verification potential index is less than the verification general priority threshold is classified as a low priority node.

[0011] In a preferred embodiment, the terminal automatic adjustment planning model is constructed, and the distribution network is optimized at multiple levels based on the different priority constant value verification nodes, specifically: the number of times each terminal constant value verification fails is calculated to obtain the terminal verification failure rate, and a terminal verification failure threshold is set; when the terminal verification failure rate of the core priority node during the constant value verification process is greater than the terminal verification failure threshold, the terminal automatic adjustment planning model temporarily marks the core priority node as a general priority node and allocates the unfinished constant value verification tasks of the core priority node to the remaining core priority nodes according to the task acceptance principle.

[0012] In a preferred embodiment, the unfinished constant value verification tasks of the core priority nodes are allocated to the remaining core priority nodes according to the task acceptance principle, specifically: the task acceptance priority of the remaining core priority nodes is calculated, and the task acceptance priority of the remaining core priority nodes is sorted in descending order to obtain the remaining core priority nodes after descending order; tasks are preferentially allocated to the remaining core priority nodes with high task acceptance priority until all unfinished tasks are allocated.

[0013] The technical effects and advantages of the automatic optimization method of the distribution network based on multi-source data fusion of the present invention are as follows:

[0014] 1. The present invention helps to gain a deeper understanding of the line connection relationship and potential fault conditions of each terminal by comprehensively acquiring and preprocessing the multi-terminal topological data of the FA line of the distribution network. Based on the topological data analysis, the fixed value verification potential index of each terminal is calculated, and further combined with the priority membership analysis to accurately set the core and general priority thresholds. This priority setting helps to hierarchically identify key and secondary verification nodes, thereby improving the pertinence and efficiency of the verification. The terminal automatic adjustment planning model further constructed can achieve multi-level optimization for verification nodes of different priorities, ensuring the rational allocation of resources and the stability of operation. While improving the adaptability and fault response speed of the distribution network, this method can also effectively reduce the operation and maintenance costs and improve the overall reliability and intelligence level of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a structural schematic diagram of the distribution network automatic optimization method based on multi-source data fusion of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1, Figure 1 The invention provides a method for automatic optimization of a distribution network based on multi-source data fusion, which is characterized by comprising the following steps:

[0018] S1, obtaining multi-terminal line topology data of FA lines in the distribution network and preprocessing;

[0019] In this example, the multi-terminal line topology data of the FA line in the distribution network is as follows:

[0020] The multi-terminal line topology data of FA lines in the distribution network includes terminal node information data, line connection relations, electrical parameters, and equipment status data;

[0021] The terminal node information data includes the ID, location, node type (such as transformer, circuit breaker, switch, load point, etc.) and electrical characteristics (such as voltage level, phase sequence, etc.) of each terminal node;

[0022] The line connection relationship includes the line's starting point, end point, topology (such as radial type, ring network type) and connection direction, which helps to establish the overall line connection diagram;

[0023] Electrical parameters include line resistance, reactance, capacitance and other parameters, which are used to analyze power flow, fault current, etc., to ensure accurate electrical characteristics description and subsequent calculation;

[0024] The device status data includes the set parameters of each terminal device (such as overcurrent protection, undervoltage protection, etc.), ensuring that the device can operate according to the preset values ​​under different conditions.

[0025] It should be noted that obtaining multi-terminal line topology data of FA lines in the distribution network provides comprehensive basic information for the intelligent distribution system. Through comprehensive analysis of node information, line connection relationships, electrical parameters, and equipment status data, the operating status and fault distribution of the distribution line can be accurately described, and the overall monitoring and management capabilities of the system can be improved. Real-time acquisition and updating of this data not only facilitates rapid fault location and execution of corresponding controls, but also supports predictive maintenance and optimized scheduling to reduce the risk of failure. At the same time, the fixed value data of each terminal can ensure the safe operation of the equipment and improve the reliability and resilience of the distribution network.

[0026] S2, based on the multi-terminal line topology data of the FA line in the distribution network, calculating the fixed value verification potential index of each terminal, and calculating the comprehensive priority membership of each terminal to obtain the verification core priority threshold and the verification general priority threshold;

[0027] In this example, based on the multi-terminal line topology data of the distribution network, the fixed value verification potential index of each terminal is calculated, specifically:

[0028]

[0029] in, is the fixed value verification potential index of terminal i, , and is the weight coefficient, is the CPU frequency of terminal i, is the memory size of terminal i, is the terminal resource abundance coefficient, and They represent the communication bandwidth and communication delay of terminal i respectively, is a small positive number, is the degree centrality data of terminal i in the topology, is the degree centrality data of the terminal in the topology, The number of connections of the node with the largest number of connections in the distribution network.

[0030] It should be noted that calculating the fixed value verification potential index of each terminal based on the multi-terminal line topology data of the distribution network has significant advantages. This process can quantify the performance and safety of each terminal under specific operating conditions, providing a scientific basis for equipment management and fault warning. By accurately calculating the potential index, potential risk points can be identified, and equipment or lines that may cause failures can be discovered in time, thereby achieving targeted maintenance and adjustments. This method not only improves the operating efficiency of the distribution network, but also enhances its reliability and stability.

[0031] In addition, the calculation of the fixed value verification potential index provides data support for subsequent priority division, making it possible to more clearly identify key nodes and secondary nodes in a complex environment with multiple terminals. This hierarchical management method helps to rationally allocate resources, ensure rapid response when failures occur, and prioritize high-risk areas, thereby minimizing power outage time and economic losses. Ultimately, through this systematic analysis and management, the intelligence level of the distribution network has been significantly improved, laying the foundation for future digital transformation.

[0032] In this example, the comprehensive priority membership of each terminal is calculated to obtain the core priority threshold and the general priority threshold, which are:

[0033] All terminal nodes of the FA lines in the distribution network are arranged and combined to obtain several terminal node combinations;

[0034] Acquire key impact indicators of each terminal in the plurality of terminal node combinations, wherein the key impact indicators include fault response speed, power supply continuity, and load importance of the terminal;

[0035] Normalizing the key influencing indicators of each terminal by using Min-Max normalization to obtain the normalized key influencing indicators of each terminal;

[0036] The combined weighting method is used to calculate the comprehensive weight of the key influencing indicators of each terminal after the normalization, and based on the comprehensive weight, the comprehensive priority membership of a combination of several terminal nodes is calculated;

[0037] Sorting the comprehensive priority memberships of the plurality of terminal node combinations in descending order, and clustering the plurality of terminal node combinations using a K-means clustering algorithm to obtain a first terminal node combination, a second terminal node combination, and a third terminal node combination;

[0038] Calculating the within-group variance and between-group variance of the first terminal node combination, the second terminal node combination, and the third terminal node combination;

[0039] Based on the within-group variance and the between-group variance, a verification core priority threshold and a verification general priority threshold are respectively obtained.

[0040] In this example, the combined weighting method is used to calculate the normalized comprehensive weight of the key influencing indicators of each terminal, specifically:

[0041] Respectively calculating the primary indicator weight and the secondary indicator weight of the key influencing indicator of each terminal after the normalization;

[0042] The normalized primary indicator weights and secondary indicator weights of the key influencing indicators of each terminal are linearly weighted averaged to obtain the normalized comprehensive weights of the key influencing indicators of each terminal.

[0043] It should be noted that calculating the normalized primary and secondary indicator weights of each terminal's key influencing indicators and obtaining the comprehensive weights through linear weighted average has important advantages. First, the normalization process can eliminate the dimensional influence between different indicators, so that each indicator can be compared under the same standard, ensuring the scientificity and rationality of the weight calculation. By clarifying the weights of the primary and secondary indicators, the importance and contribution of each terminal in the overall system can be analyzed more deeply, providing data support for decision-making; the application of the linear weighted average method enables indicators at different levels to comprehensively reflect the key impact of each terminal, helping managers make more targeted decisions in resource allocation and optimal scheduling. This method effectively improves the comprehensiveness and accuracy of indicator analysis, and can provide a basis for subsequent monitoring and adjustment. Overall, this process enhances the intelligent management capabilities of the distribution network and ensures the stability and efficiency of the system.

[0044] In this example, the comprehensive priority memberships of the plurality of terminal node combinations are sorted in descending order, and the plurality of terminal node combinations are clustered using the K-means clustering algorithm to obtain a first terminal node combination, a second terminal node combination, and a third terminal node combination, specifically:

[0045] The descending sorting and K-means clustering analysis of the comprehensive priority membership of the terminal node combinations in the distribution network is a systematic process aimed at improving the management efficiency of the distribution network. First, the comprehensive priority membership data of each terminal node is collected and cleaned to ensure the accuracy and consistency of the data. Then, a list of node combinations with high and low priorities is generated through the descending sorting operation, which lays the foundation for the subsequent clustering analysis. Subsequently, the K-means clustering algorithm is used to cluster the terminal node combinations, determine the number of clusters and standardize the relevant features. By initializing K-means, iterating the allocation and update stages, continuously optimizing the cluster centers, and finally dividing the terminal node combinations into the first, second and third terminal node combinations.

[0046] It should be noted that descending sorting and K-means clustering analysis of the comprehensive priority membership of terminal node combinations in the distribution network have significant advantages. First, by descending sorting, the priority of each terminal node combination can be clearly identified, which provides an intuitive basis for subsequent management and decision-making. The sorted data helps managers quickly determine which node combinations should be given priority in maintenance and fault response, thereby improving the operating efficiency of the distribution network.

[0047] Secondly, the K-means clustering algorithm is used to further subdivide these node combinations so that terminal nodes of different priorities can be reasonably grouped. By clustering the node combinations, terminals with similar characteristics can be effectively identified, which facilitates the optimization of resource allocation and the formulation of scheduling strategies. Such grouping not only enhances the intelligent management capabilities of the system, but also improves the pertinence of fault location and response measures.

[0048] In addition, the clustering results provide important support for real-time monitoring and predictive maintenance of the distribution network, ensuring that key nodes receive priority attention, which helps reduce the risk of power outages and economic losses. Overall, this process significantly improves the management efficiency and safety of the distribution network through systematic data analysis and processing, laying a solid foundation for future digital transformation.

[0049] In this example, the intra-group variance and inter-group variance of the first terminal node combination, the second terminal node combination, and the third terminal node combination are calculated as follows:

[0050]

[0051]

[0052]

[0053] in, is the between-group variance, is the number of terminal combinations, is the number of terminals in the ith terminal combination, is the overall average of all terminal combinations, is the average value of the ith terminal combination, is the within-group variance, is the priority membership of the jth terminal in the i-th terminal combination, and N is the number of all terminals.

[0054] It should be noted that calculating the intra-group variance and inter-group variance of the first, second, and third terminal node combinations is an important step in evaluating the clustering effect, which has obvious advantages. The intra-group variance reflects the similarity between nodes within each combination. A lower intra-group variance means that the feature consistency between nodes is strong, indicating that the clustering effect is good. This helps to verify the effectiveness of different terminal node combinations and ensure the rationality of resource allocation; on the other hand, the inter-group variance measures the differences between different combinations. A higher inter-group variance indicates that the feature differences between groups are obvious, which can effectively distinguish nodes of different categories. This difference enhances the pertinence of the management and maintenance of the distribution network, so that key nodes can be more accurately located during fault warning and resource scheduling. By comprehensively analyzing the intra-group and inter-group variances, managers can better understand the clustering results, optimize decisions, and improve the operating efficiency and reliability of the distribution network.

[0055] In this example, based on the intra-group variance and inter-group variance, the core priority threshold of the verification and the general priority threshold of the verification are respectively obtained, specifically:

[0056] Calculating the ratio of the within-group variance to the between-group variance and setting an adjustment coefficient;

[0057] Multiplying the ratio of the intra-group variance to the inter-group variance and the adjustment coefficient to obtain a threshold division coefficient;

[0058] Calculating an average value of the first terminal node combination and the second terminal node combination and adding the average value to the threshold division coefficient to obtain a verification core priority threshold;

[0059] An average value of the second terminal node combination and the third terminal node combination is calculated and added to the threshold division coefficient to obtain a general priority threshold for verification.

[0060] It should be noted that the verification core priority threshold and the verification general priority threshold based on the intra-group variance and inter-group variance are important means to improve the efficiency of distribution network management. First, the setting of the verification core priority threshold can effectively identify the most critical terminal node combinations, which usually have low intra-group variance, which means that they are highly consistent and stable in characteristics. This enables managers to give priority to these high-priority nodes, optimize maintenance and fault response strategies, and thus reduce potential fault risks; on the other hand, the verification general priority threshold helps identify relatively minor node combinations to ensure the reasonable allocation of resources. By setting these two thresholds, managers can establish clear boundaries between nodes of different priorities and enhance the flexibility and responsiveness of the distribution network. This hierarchical management not only improves the pertinence and effectiveness of decision-making, but also helps to improve the operational reliability of the entire system, providing a solid foundation for the intelligence and optimization of the distribution network.

[0061] S3, obtaining fixed value verification nodes of different priorities based on the comparison of the fixed value verification potential index of each terminal with the verification core priority threshold and the verification general priority threshold;

[0062] In this example, based on the comparison between the fixed value verification potential index of each terminal and the verification core priority threshold and the verification general priority threshold, different priority fixed value verification nodes are obtained, specifically:

[0063] Comparing the fixed value verification potential index of each terminal with the verification core priority threshold and the verification general priority threshold respectively;

[0064] Terminals whose fixed value verification potential index is greater than the verification core priority threshold are classified as core priority nodes; terminals whose fixed value verification potential index is less than the verification core priority threshold and greater than the verification general priority threshold are classified as general priority nodes; terminals whose fixed value verification potential index is less than the verification general priority threshold are classified as low priority nodes.

[0065] It should be noted that based on the comparison of the fixed value check potential index of each terminal with the core priority threshold and the general priority threshold, the fixed value check nodes of different priorities can be effectively identified and classified. This process has many advantages. First, through this hierarchical management, the core priority nodes are clearly identified, and the fixed value check potential index of these nodes is higher than the core priority threshold, indicating that they play a vital role in the system. Giving priority to these nodes will help to respond quickly when a fault occurs, reduce the impact of the fault, and ensure the stable operation of the power grid; secondly, for general priority nodes, the fixed value check potential index of these terminals is between the core and general priority thresholds, indicating that their importance and risk are relatively low, but they still need to be monitored and managed. Reasonable allocation of resources for these nodes can improve the pertinence of maintenance work and optimize the efficiency of resource use. Although low-priority nodes have lower risks, they cannot be ignored. Timely attention and maintenance will avoid potential failure risks. Through such a systematic classification, managers can more clearly formulate and adjust operation and maintenance strategies, improve overall operation efficiency and safety, enhance the intelligent management capabilities of distribution networks, and lay a solid foundation for long-term development.

[0066] S4, constructing a terminal automatic adjustment planning model, and performing multi-level optimization on the distribution network based on the different priority setting verification nodes.

[0067] In this example, a terminal automatic adjustment planning model is constructed, and the distribution network is optimized at multiple levels based on the different priority setting verification nodes, specifically:

[0068] Calculate the number of times each terminal constant value check fails, obtain the terminal check failure rate, and set the terminal check failure threshold;

[0069] When the terminal verification failure rate of the core priority node during the constant value verification process is greater than the terminal verification failure threshold, the terminal automatic adjustment planning model temporarily marks the core priority node as a general priority node and allocates the unfinished constant value verification tasks of the core priority node to the remaining core priority nodes according to the task acceptance principle.

[0070] In this example, when the terminal verification failure rate of the core priority node during the fixed value verification process is greater than the terminal verification failure threshold, the terminal automatic adjustment planning model temporarily marks the core priority node as a general priority node and allocates the unfinished fixed value verification tasks of the core priority node to the remaining core priority nodes according to the task acceptance principle, specifically:

[0071] When the verification failure rate of the core priority node exceeds the set terminal verification failure threshold during the fixed value verification process, it is temporarily marked as a general priority node, and the unfinished fixed value verification task is assigned to other core priority nodes. This strategy has significant advantages. This mechanism effectively improves the flexibility and robustness of the distribution network. First, the core node that fails the verification is adjusted to a general priority node in a timely manner, which ensures the adaptive ability of the system in the face of potential risks and helps to maintain the overall security and stability; secondly, the unfinished verification task is reallocated to other core priority nodes through the task acceptance principle, which can optimize the efficiency of resource utilization. In this way, not only the continuity and timeliness of the verification task are guaranteed, but also other core nodes that are operating normally can complete the task collaboratively when the load allows, thereby avoiding the overall performance degradation of the system due to the failure of a single node; in addition, this dynamic adjustment mechanism provides managers with a clear operation and maintenance strategy, enabling them to respond quickly to the status of different nodes and reduce downtime. At the same time, it also enhances the intelligence level of the distribution network, helps to achieve more efficient management and monitoring, and thus improves the reliability and economy of the overall operation.

[0072] In this example, the unfinished fixed value verification tasks of the core priority nodes are allocated to the remaining core priority nodes according to the task acceptance principle, specifically:

[0073] Calculating the task acceptance priorities of the remaining core priority nodes, and sorting the task acceptance priorities of the remaining core priority nodes in descending order to obtain the remaining core priority nodes after sorting in descending order;

[0074] Prioritize the assignment of tasks to the remaining core priority nodes with high task acceptance priority until all unfinished tasks are assigned.

[0075] It should be noted that the process of allocating the unfinished fixed value verification tasks of the core priority nodes to the remaining core priority nodes according to the task acceptance principle has significant advantages. First, by calculating the task acceptance priority of the remaining core priority nodes and sorting them in descending order, the scientificity and effectiveness of task allocation are ensured. Prioritizing the allocation of tasks to nodes with high acceptance priority helps to improve resource utilization efficiency and ensure that key nodes can efficiently complete tasks when the load allows.

[0076] This approach also enhances the flexibility and responsiveness of the system, ensuring that unfinished verification tasks are processed in a timely manner, and avoiding the degradation of overall system performance due to individual node failures. In addition, by optimizing task allocation, managers can better control the workload of nodes and reduce operational risks. Overall, this allocation mechanism improves the adaptive ability and stability of the distribution network, and provides a guarantee for the efficient operation of the system.

[0077] In this example, the task acceptance priority of the remaining core priority nodes is calculated as follows:

[0078] in, Receive the priority for the task of the i-th remaining core priority node, is the remaining resource ratio of the i-th remaining core priority node, is the verification failure rate of the i-th remaining core priority node, is the task completion success rate of the i-th remaining core priority node, , and is the weight coefficient.

[0079] It should be noted that calculating the task acceptance priority of the remaining core priority nodes is a key step in the process of optimizing task allocation, which has obvious advantages. First, by evaluating the task acceptance priority of each node, the capabilities of each node under the current workload and resource status can be scientifically reflected, thereby ensuring the rationality and efficiency of task allocation. This evaluation not only takes into account the current status of the node, but also can dynamically adapt to resource changes in different situations, thereby improving the flexibility of the system.

[0080] Secondly, clarifying the task acceptance priority allows managers to quickly identify the nodes that are most suitable for taking on additional tasks, optimize resource allocation, and reduce the risk of failure due to overload. In addition, this process also enhances the collaboration between nodes, so that the overall work efficiency can be improved. During the peak period of tasks, priority is given to nodes with strong acceptance capabilities, which can ensure the timely completion of key tasks, thereby improving the operational reliability and stability of the distribution network. Overall, this mechanism provides a solid foundation for the intelligent management of the distribution system and ensures the efficient operation of the system.

[0081] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0082] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0083] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0084] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0085] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0086] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A distribution network automatic optimization method based on multi-source data fusion, characterized in that: The following steps are involved: Obtain multi-terminal line topology data of FA lines in the distribution network and perform preprocessing; Based on the multi-terminal line topology data of the FA line in the distribution network, the fixed value verification potential index of each terminal is calculated, and the comprehensive priority membership of each terminal is calculated to obtain the verification core priority threshold and the verification general priority threshold; The calculation of the fixed value verification potential index of each terminal is obtained by the following calculation formula: In the formula, is the fixed value verification potential index of terminal i, , and is the weight coefficient, is the CPU frequency of terminal i, is the memory size of terminal i, is the terminal resource abundance coefficient, and They represent the communication bandwidth and communication delay of terminal i respectively, is a small positive number, is the degree centrality data of terminal i in the topology, is the degree centrality data of the terminal in the topology, is the number of connections of the node with the largest number of connections in the distribution network; All terminal nodes of the FA lines in the distribution network are arranged and combined to obtain several terminal node combinations; Obtaining key impact indicators of each terminal in the plurality of terminal node combinations; Normalizing the key influencing indicators of each terminal by using Min-Max normalization to obtain the normalized key influencing indicators of each terminal; The combined weighting method is used to calculate the normalized comprehensive weight of the key influencing indicators of each terminal, and based on the comprehensive weight, the comprehensive priority membership of several terminal node combinations is calculated; Sorting the comprehensive priority memberships of the plurality of terminal node combinations in descending order; And clustering the plurality of terminal node combinations using a K-means clustering algorithm to obtain a first terminal node combination, a second terminal node combination, and a third terminal node combination; Calculating the within-group variance and between-group variance of the first terminal node combination, the second terminal node combination, and the third terminal node combination; Calculating the ratio of the within-group variance to the between-group variance and setting an adjustment coefficient; Multiplying the ratio of the intra-group variance to the inter-group variance and the adjustment coefficient to obtain a threshold division coefficient; Calculating an average value of the first terminal node combination and the second terminal node combination and adding the average value to the threshold division coefficient to obtain a verification core priority threshold; Calculating an average value of the second terminal node combination and the third terminal node combination and adding the average value to the threshold division coefficient to obtain a general priority threshold for verification; Based on the comparison of the fixed value verification potential index, the verification core priority threshold and the verification general priority threshold of each terminal, different priority fixed value verification nodes are obtained; A terminal automatic adjustment planning model is constructed, and the distribution network is optimized at multiple levels based on the different priority setting verification nodes.

2. The method for automatic optimization of distribution network based on multi-source data fusion according to claim 1 is characterized in that: The combined weighting method is used to calculate the normalized comprehensive weight of the key influencing indicators of each terminal, specifically: Calculate the normalized primary indicator weight and secondary indicator weight of each terminal's key influencing indicator respectively; The normalized primary indicator weights and secondary indicator weights of the key influencing indicators of each terminal are linearly weighted averaged to obtain the normalized comprehensive weights of the key influencing indicators of each terminal.

3. The method for automatic optimization of distribution network based on multi-source data fusion according to claim 2 is characterized in that: Based on the comparison of the fixed value verification potential index, the verification core priority threshold and the verification general priority threshold of each terminal, different priority fixed value verification nodes are obtained, specifically: Comparing the fixed value verification potential index of each terminal with the verification core priority threshold and the verification general priority threshold respectively; Classify the terminals whose fixed value verification potential index is greater than the verification core priority threshold as core priority nodes; Terminals whose fixed value verification potential index is less than the verification core priority threshold and greater than the verification general priority threshold are classified as general priority nodes; Terminals whose fixed value verification potential index is less than the verification general priority threshold are classified as low priority nodes.

4. The method for automatic optimization of distribution network based on multi-source data fusion according to claim 3 is characterized in that: The terminal automatically adjusts the planning model, and performs multi-level optimization on the distribution network based on the different priority fixed value verification nodes, specifically: Calculate the number of times each terminal constant value check fails, obtain the terminal check failure rate, and set the terminal check failure threshold; When the terminal verification failure rate of the core priority node during the fixed value verification process is greater than the terminal verification failure threshold, the terminal automatic adjustment planning model temporarily marks the core priority node as a general priority node; And the unfinished fixed value verification tasks of the core priority nodes are allocated to the remaining core priority nodes according to the task acceptance principle.

5. The method for automatic optimization of distribution network based on multi-source data fusion according to claim 4 is characterized in that: The unfinished fixed value verification tasks of the core priority nodes are allocated to the remaining core priority nodes according to the task acceptance principle, specifically: Calculate the task acceptance priorities of the remaining core priority nodes, and sort the task acceptance priorities of the remaining core priority nodes in descending order to obtain the remaining core priority nodes after sorting in descending order; Prioritize the assignment of tasks to the remaining core priority nodes with high task acceptance priority until all unfinished tasks are assigned.

6. The method for automatic optimization of distribution network based on multi-source data fusion according to claim 5 is characterized in that: The within-group variance and between-group variance of the first terminal node combination, the second terminal node combination, and the third terminal node combination are calculated, specifically: In the formula, is the between-group variance, is the number of terminal combinations, is the number of terminals in the ith terminal combination, is the overall average of all terminal combinations, is the average value of the ith terminal combination, is the within-group variance, is the priority membership of the jth terminal in the i-th terminal combination, and N is the number of all terminals.

7. The method for automatic optimization of distribution network based on multi-source data fusion according to claim 6 is characterized in that: The task acceptance priority of the calculation remaining core priority nodes is specifically: In the formula, Receive the priority for the task of the i-th remaining core priority node, is the remaining resource ratio of the i-th remaining core priority node, is the verification failure rate of the i-th remaining core priority node, is the task completion success rate of the i-th remaining core priority node, , and is the weight coefficient.

Images