Mobile substation random scheduling method and system based on big data analysis

Abstract

The application provides a mobile substation random scheduling method and system based on big data analysis, and belongs to the technical field of power system automation, and comprises the following steps: obtaining a composite criticality of a mobile substation to be distributed to each fault power distribution node according to a dynamic deterioration gradient and in combination with power load monitoring data; obtaining the degree centrality of each fault power distribution node in a current power distribution network topology graph; adjusting the degree centrality of each fault power distribution node by using the composite criticality and the dynamic deterioration gradient to obtain a transient adaptive edge weight between each mobile substation to be distributed and each fault power distribution node; and generating a dynamic bipartite graph based on the transient adaptive edge weight to perform optimal matching scheduling on the mobile substation. The application improves the scheduling efficiency of the mobile substation in a complex dynamic environment.

Description

Technical Field

[0001] This invention belongs to the field of power system automation technology, specifically relating to a mobile substation random dispatching method and system based on big data analysis. Background Technology

[0002] As a core physical device for responding to sudden power grid failures, implementing emergency repairs, and providing temporary power backup, the random dispatch efficiency of mobile substations directly determines the resilience and disaster mitigation capabilities of the distribution network under extreme disasters. In scenarios with multiple concurrent failures, since the number of power outage nodes often exceeds the number of available mobile substations, the system needs to address complex resource preemption and priority allocation issues.

[0003] Existing technologies often seek the optimal allocation scheme by constructing a bipartite graph model of a set of mobile substations and a set of fault nodes. However, since the maximum weight matching algorithm of the bipartite graph must pre-set a static scalar as the edge weight based on historical road conditions or fixed spatial distance before performing the matching operation, it suffers from severe weight staticization, resulting in a technical defect that makes it unable to cope with dynamic changes in the environment.

[0004] Therefore, in extreme and complex disaster scenarios such as typhoons and rainstorms, the road network traffic conditions will change dynamically and abruptly with sudden events such as flooding or fallen trees. Moreover, the urgency of power outages in different areas will increase non-linearly over time. Traditional static weight models cannot perceive this road network deterioration and load degradation. This leads to mobile substations often being unable to arrive in time due to traffic congestion after dispatch instructions are issued, or the dispatch plan failing to prioritize reaching the most vulnerable critical nodes, thus missing the best opportunity to ensure power supply. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method and system for random scheduling of mobile substations based on big data analysis.

[0006] To achieve the above objectives, the present invention provides the following technical solution: Obtain the set of mobile substations to be assigned and the set of faulty distribution nodes, and construct the current distribution network topology diagram; obtain the geographical road network data, real-time meteorological data and power load monitoring data corresponding to each faulty distribution node; Based on the geographical road network data and real-time meteorological data corresponding to the faulty power distribution node, the dynamic degradation gradient between the mobile substation to be assigned and each faulty power distribution node is obtained. Based on the dynamic degradation gradient and combined with power load monitoring data, the composite urgency of the mobile substation to be assigned to each faulty distribution node is obtained; the degree centrality of each faulty distribution node in the current distribution network topology is obtained; the degree centrality of each faulty distribution node is adjusted using the composite urgency and dynamic degradation gradient to obtain the transient adaptive edge weight between each mobile substation to be assigned and each faulty distribution node. Optimal matching and scheduling of mobile substations is achieved by generating a dynamic bipartite graph based on transient adaptive edge weights.

[0007] Preferably, the step of obtaining the dynamic degradation gradient between the mobile substation to be assigned and each faulty distribution node based on the geographical road network data and real-time meteorological data corresponding to the faulty distribution node includes: For the m-th basic path between the mobile substation to be assigned and the j-th faulted distribution node, the real-time meteorological disaster index of the m-th basic path is obtained based on the real-time meteorological data corresponding to the faulted distribution node. The product of the baseline speed limit of the m-th basic path and the inverse proportional value of the real-time meteorological disaster index of the m-th basic path is denoted as the dynamic meteorological impact factor of the m-th basic path. The ratio between the segment length of the m-th basic path and the dynamic meteorological influence factor of the m-th basic path is denoted as the dynamic degradation factor of the m-th basic path; the sum of the dynamic degradation factors of all basic paths between the mobile substation to be assigned and the j-th faulty distribution node is taken as the dynamic degradation gradient between the mobile substation to be assigned and the j-th faulty distribution node.

[0008] Preferably, the step of obtaining the real-time meteorological disaster index of the m-th basic path based on the real-time meteorological data corresponding to the faulty power distribution node includes: Based on the changes in real-time meteorological data corresponding to the m-th faulty power distribution node within the historical time range, the rainfall impact factor and wind speed impact factor of the m-th basic path at the current moment are obtained. Two preset influencing parameters and This will affect the parameters. The product of the rainfall impact factor of the m-th base path at the current time is denoted as the first product; the impact parameters are... The product of 2 and the wind speed influence factor of the m-th base path at the current moment is denoted as the second product; the sum of the first product and the second product is used as the real-time meteorological disaster index of the m-th base path.

[0009] Preferably, the step of obtaining the rainfall impact factor and wind speed impact factor of the m-th basic path at the current moment based on the changes in real-time meteorological data corresponding to the m-th faulty distribution node within a historical time range includes: By using a third-party meteorological platform, the maximum and minimum rainfall, as well as the maximum and minimum wind speed levels, of the m-th basic path within the past month are obtained. The rainfall and wind speed levels of the m-th basic path at the current moment are normalized using the maximum-minimum value normalization algorithm to obtain the rainfall and wind speed influence factors of the m-th basic path at the current moment.

[0010] Preferably, obtaining the composite urgency level of the mobile substation to be assigned to each faulty distribution node based on the dynamic degradation gradient and combined with power load monitoring data includes: Based on power load monitoring data, obtain the real-time power deficit, rated load demand, and load self-recovery rate of the j-th faulty distribution node; The ratio between the real-time power deficit of the j-th faulty distribution node and the rated load demand is denoted as the real-time power deficit percentage of the j-th faulty distribution node. Based on the dynamic degradation gradient between the mobile substation to be assigned and the j-th faulty distribution node, and the real-time power deficit ratio of the j-th faulty distribution node, the time delay factor of the j-th faulty distribution node is obtained; based on the load self-recovery rate of the j-th faulty distribution node and the time delay factor of the j-th faulty distribution node, the urgency of emergency repair of the j-th faulty distribution node is obtained. The product of the rated load demand of the j-th faulty distribution node and the urgency of repairing the j-th faulty distribution node is used as the composite urgency of the mobile substation to be assigned to the j-th faulty distribution node.

[0011] Preferably, the step of obtaining the real-time power deficit, rated load demand, and load self-recovery rate of the j-th faulty distribution node based on power load monitoring data includes: The system uses advanced smart meter measurement to obtain the rated load demand, real-time active power and rated power of the j-th faulty distribution node; as well as the active power of the energy storage converter of the j-th faulty distribution node in each fault event in the past year. The absolute value of the difference between the real-time active power and the rated power is denoted as the real-time power deficit of the j-th faulty distribution node. The load self-recovery rate of the j-th faulty distribution node is obtained based on the active power and rated load demand of the energy storage converter of the j-th faulty distribution node in each fault event.

[0012] Preferably, the step of obtaining the load self-recovery rate of the j-th faulty distribution node based on the active power and rated load demand of the energy storage converter of the j-th faulty distribution node within each fault event includes: The ratio between the active power of the energy storage converter of the j-th fault distribution node and the rated load demand of the j-th fault distribution node in each fault event is denoted as the load recovery factor of the j-th fault distribution node in each fault event. The normalized value of the mean of the load recovery factors of the j-th faulty distribution node in all fault events over the past year is taken as the load self-recovery rate of the j-th faulty distribution node.

[0013] Preferably, obtaining the degree centrality of each faulty distribution node in the current distribution network topology diagram includes: For any faulty distribution node in the current distribution network topology diagram, the normalized value of the number of all basic paths between all mobile substations to be assigned and any faulty distribution node is used as the degree center of the faulty distribution node.

[0014] Preferably, the step of adjusting the degree centrality of each faulty distribution node using composite urgency and dynamic degradation gradient to obtain the transient adaptive edge weights between each mobile substation to be assigned and each faulty distribution node includes: In the formula, This represents the transient adaptive edge weight between the i-th mobile substation to be assigned and the j-th faulty distribution node; This represents the composite urgency level of the i-th mobile substation to be assigned to the j-th faulty distribution node; This represents the dynamic degradation gradient between the i-th mobile substation to be assigned and the j-th faulty distribution node; This represents the logarithmic function with the natural constant as the base.

[0015] The present invention also proposes a mobile substation random dispatch system based on big data analysis, including a memory and a processor, wherein the processor executes a computer program in the memory to implement the steps of the above-mentioned mobile substation random dispatch method based on big data analysis.

[0016] The mobile substation random dispatching method based on big data analysis provided by this invention has the following beneficial effects: This invention obtains the composite urgency of a mobile substation to be assigned to each faulty distribution node based on dynamic degradation gradient and power load monitoring data; obtains the degree centrality of each faulty distribution node in the current distribution network topology; adjusts the degree centrality of each faulty distribution node using composite urgency and dynamic degradation gradient to obtain transient adaptive edge weights between each mobile substation to be assigned and each faulty distribution node; and generates a dynamic bipartite graph based on the transient adaptive edge weights to perform optimal matching and scheduling of the mobile substation. By using a dynamic path degradation gradient, the destructive force of meteorological disasters on the road network is transformed into travel costs. This invention can proactively avoid high-risk road sections such as flooding and blockages, significantly reducing the delay rate of mobile substations during transit and improving the certainty of emergency response. By combining the degree of urgency and the degree centrality of faulty distribution nodes, critical faulty distribution nodes can be identified, realizing intelligent allocation based on urgency rather than simple distance allocation, minimizing load loss under extreme disasters. Attached Figure Description

[0017] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the steps of a mobile substation random dispatching method and system based on big data analysis according to an exemplary embodiment of the present invention. Figure 2 This invention provides a transient adaptive edge weight matrix for a mobile substation random dispatching method and system based on big data analysis, according to an exemplary embodiment. Figure 3 This is a comparison chart of the operational efficiency of the prior art of the mobile substation random dispatching method and system based on big data analysis provided by the present invention according to an exemplary embodiment. Detailed Implementation

[0019] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0020] The technical solutions provided by the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] First, this invention provides a method and system for random dispatching of mobile substations based on big data analysis, specifically as follows: Figure 1 As shown, it includes the following steps: Step S001: Obtain the set of mobile substations to be assigned and the set of faulty distribution nodes, and construct the current distribution network topology diagram; obtain the geographical road network data, real-time meteorological data and power load monitoring data corresponding to each faulty distribution node.

[0022] In one embodiment of the present invention, the set of mobile substations to be allocated and the set of faulty distribution nodes are obtained, and the current distribution network topology diagram is constructed; the specific method for obtaining the geographical road network data, real-time meteorological data and power load monitoring data corresponding to each faulty distribution node is as follows: The power dispatch data network is used to obtain the set of all mobile substations to be assigned and all faulty distribution nodes; and to construct the current distribution network topology diagram; the current distribution network topology diagram describes the network diagram of all mobile substations and all faulty distribution nodes and the lines (edges) connecting them; For any faulty distribution node in the current distribution network topology diagram, the normalized value of the number of all basic paths between all mobile substations to be assigned and any faulty distribution node is used as the degree centrality of the faulty distribution node. This embodiment takes any mobile substation to be assigned as an example for analysis: The system continuously acquires the segment length and baseline speed limit of all basic paths between the mobile substation to be assigned and each faulty power distribution node in real time from the geographic information system and traffic management platform. For any basic path between the mobile substation to be assigned and each faulty distribution node, the maximum and minimum rainfall, as well as the maximum and minimum wind speed levels, are obtained from the historical data of the given basic path over the past month through a third-party meteorological platform. The rainfall and wind speed levels of the given basic path at the current moment are normalized using a maximum-minimum value normalization algorithm to obtain the rainfall impact factor and wind speed impact factor of the given basic path at the current moment. Two preset influencing parameters and In this embodiment, and This example is used for illustration; no specific limitations are set in this embodiment. and It depends on the specific implementation situation; Heavy rainfall can directly and quickly cause water accumulation or even flooding in low-lying areas of roads, which is the most direct cause of vehicles being unable to pass. The main direct hazard of strong winds is that they blow down trees, billboards, and other objects that block roads, and their occurrence is more localized and accidental. Therefore, the impact weight of rainfall is set higher than that of wind. Will affect parameters The product of the rainfall impact factor of any of the base paths at the current moment is denoted as the first product; the impact parameters are... The product of 2 and the wind speed influence factor of any of the base paths at the current moment is denoted as the second product; the sum of the first product and the second product is taken as the real-time meteorological disaster index of any of the base paths. The specific formula is as follows: In the formula, Real-time meteorological disaster index representing the basic path; This indicates the rainfall impact factor of the basic path at the current moment; This indicates the wind speed influence factor of the base path at the current moment; and This indicates the preset influence parameters.

[0023] For any faulty distribution node, the rated load demand, real-time active power and rated power of the faulty distribution node are obtained through the advanced measurement system of smart meters; as well as the active power of the energy storage converter of the faulty distribution node in each fault event in the past year; the absolute value of the difference between the real-time active power and the rated power is recorded as the real-time power deficit of the faulty distribution node. The ratio between the active power of the energy storage converter of any faulty distribution node and the rated load demand of any faulty distribution node in each fault event is denoted as the load recovery factor of any faulty distribution node in each fault event; the normalized value of the mean of the load recovery factors of any faulty distribution node in all fault events in the past year is taken as the load self-recovery rate of any faulty distribution node. The specific formula is as follows: In the formula, This indicates the load self-recovery rate of the faulty power distribution node; This represents all fault events that occurred at the faulty power distribution node within the past year. This represents the active power of the energy storage converter at the faulty distribution node during the nth fault event. This indicates the rated load demand of the faulty distribution node.

[0024] At this point, we have obtained the set of mobile substations to be assigned and all faulty distribution nodes, as well as the geographical network data, real-time meteorological data and power load monitoring data corresponding to each faulty distribution node.

[0025] Step S002: Based on the geographical road network data and real-time meteorological data corresponding to the faulty power distribution node, obtain the dynamic degradation gradient between the mobile substation to be assigned and each faulty power distribution node.

[0026] It should be noted that under extreme natural disaster conditions, the passage capacity between mobile substations and faulty distribution nodes is not determined by path length, but is nonlinearly affected by meteorological factors such as rainfall and wind speed. Current technologies, when calculating the travel cost of mobile substations, typically use path length or only refer to historical average speeds. This means that when faced with sudden obstacles such as flooded roads or fallen trees, the initially planned shortest path may evolve into an infinitely delayed congested path. Furthermore, relying solely on acquired basic geographic data cannot quantify the sudden changes in passage impedance between mobile substations and faulty distribution nodes.

[0027] Therefore, this embodiment introduces an intermediate indicator that reflects the decline in the health status of a road segment, namely the dynamic degradation gradient of the path. By analyzing the impact of real-time meteorological data on road traffic and combining it with the geographical road network data of the road segment itself, a dynamic degradation gradient that automatically increases with environmental deterioration is constructed. This design logic aims to resolve the contradiction of weight matching distortion under dynamic environmental fluctuations in existing technologies. Through mathematical transformation, static physical spatial constraints are converted into dynamic environmental traffic resistance, providing a benchmark for subsequent assessment of the urgency of emergency repairs, thereby ensuring that scheduling decisions have a forward-looking environmental risk avoidance capability.

[0028] Preferably, in one embodiment of the present invention, the specific method for obtaining the dynamic degradation gradient between the mobile substation to be assigned and each faulty distribution node based on the geographical road network data and real-time meteorological data corresponding to the faulty distribution node is as follows: For the m-th basic path between the mobile substation to be assigned and the j-th faulty distribution node, the product of the baseline speed limit of the m-th basic path and the inverse proportional value of the real-time meteorological disaster index of the m-th basic path is denoted as the dynamic meteorological impact factor of the m-th basic path; the ratio between the segment length of the m-th basic path and the dynamic meteorological impact factor of the m-th basic path is denoted as the dynamic degradation factor of the m-th basic path; and the sum of the dynamic degradation factors of all basic paths between the mobile substation to be assigned and the j-th faulty distribution node is taken as the dynamic degradation gradient between the mobile substation to be assigned and the j-th faulty distribution node. The specific formula is as follows: In the formula, This represents the dynamic degradation gradient between the mobile substation to be assigned and the j-th faulty distribution node; This represents the number of all basic paths between the mobile substation to be assigned and the j-th faulty distribution node; This represents the length of the m-th basic path between the mobile substation to be assigned and the j-th faulty distribution node. This represents the baseline speed limit of the m-th basic path between the mobile substation to be assigned and the j-th faulty distribution node. This represents the real-time meteorological disaster index of the m-th basic path between the mobile substation to be assigned and the j-th faulty distribution node; This represents an exponential function with the natural constant as its base.

[0029] It should be noted that when the real-time meteorological disaster index increases, the denominator of the formula decreases sharply, which in turn causes the dynamic degradation gradient of the path to rise exponentially. This truly reflects that under extreme weather conditions, the more severe the disaster, the more drastic the increase in travel time on the road section. This allows for the sensitive detection of the nonlinear increase in traffic resistance caused by minor environmental changes.

[0030] At this point, the dynamic degradation gradient between the mobile substation to be assigned and each faulty distribution node is obtained.

[0031] Step S003: Based on the dynamic degradation gradient and combined with power load monitoring data, obtain the composite urgency of the mobile substation to be assigned to each faulty distribution node; obtain the degree centrality of each faulty distribution node in the current distribution network topology diagram; adjust the degree centrality of each faulty distribution node using the composite urgency and dynamic degradation gradient to obtain the transient adaptive edge weight between each mobile substation to be assigned and each faulty distribution node.

[0032] It should be noted that the priority of faulty distribution nodes is often determined solely by the outage capacity or simply by the load deficit. However, in actual disaster scenarios, there is a significant spatiotemporal lag effect. That is, the process of a mobile substation moving is itself a process of continuous deterioration of the node's disaster situation. If the dynamic degradation gradient is not converted into a direct contribution to the power load loss, it is impossible to distinguish between two faulty distribution nodes with the same load deficit but completely different geographical accessibility.

[0033] The urgency level of a node is not fixed but should increase rapidly with travel time. Specifically, it mathematically translates the factor of "deteriorating road conditions leading to slower travel" into the effect of "increased power outage losses." Simultaneously, it considers the node's potential recovery capabilities (such as its own generator) and appropriately lowers the urgency level accordingly. In this way, the system can more accurately identify "vulnerable" nodes that are not only severely affected by power outages but also face difficulties in reaching repair vehicles quickly due to road obstructions. This allows for priority resource allocation, solving the problem of traditional methods failing to accurately determine the order of repairs. This embodiment, through logical analysis, concludes that the composite urgency of a faulty distribution node is not fixed but rather increases rapidly with increasing travel time. When the arrival time of a mobile substation is delayed due to path degradation, the disaster risk of the faulty distribution node increases non-linearly. Therefore, this invention designs a composite urgency level, introduces the road network degradation gradient into the load loss assessment through exponential mapping, and simultaneously uses the self-recovery rate as a suppression factor for correction. This improvement ensures that the dispatching system can more accurately identify those critical power nodes that are not only severely affected by power outages but also have difficulty reaching them quickly due to road obstruction and the inability of repair vehicles to do so. This solves the technical problem of existing technologies being unable to accurately quantify the urgency of repairs when multiple concurrent faults occur.

[0034] Preferably, in one embodiment of the present invention, the specific method for obtaining the composite urgency level of the mobile substation to be assigned to each faulty distribution node based on the dynamic degradation gradient and combined with power load monitoring data is as follows: The ratio between the real-time power deficit of the j-th faulty distribution node and the rated load demand is denoted as the real-time power deficit ratio of the j-th faulty distribution node. Based on the dynamic degradation gradient between the mobile substation to be allocated and the j-th faulty distribution node, and the real-time power deficit ratio of the j-th faulty distribution node, the time delay factor of the j-th faulty distribution node is obtained. Based on the load self-recovery rate of the j-th faulty distribution node and the time delay factor of the j-th faulty distribution node, the urgency of emergency repair of the j-th faulty distribution node is obtained. The product of the rated load demand of the j-th faulty distribution node and the urgency of repairing the j-th faulty distribution node is used as the composite urgency of the mobile substation to be assigned to the j-th faulty distribution node. The specific formula is as follows: In the formula, This indicates the composite urgency of a mobile substation to be assigned to the j-th faulty distribution node. This represents the rated load demand of the j-th faulty distribution node; This represents the dynamic degradation gradient between the mobile substation to be assigned and the j-th faulty distribution node; This represents the real-time power deficit of the j-th faulty distribution node; This represents the load self-recovery rate of the j-th faulty distribution node; This represents the logarithmic function with the natural constant as the base.

[0035] It should be noted that the composite urgency reflects the deterioration of load loss over time. When the dynamic degradation gradient of the path increases or the proportion of real-time power deficit at the faulty distribution node increases, the exponential term will rapidly amplify the composite urgency. Conversely, if the faulty distribution node has a high load self-recovery rate, the logarithmic term will naturally deduct the urgency accordingly. This logic accurately quantifies the differentiated repair urgency caused by dynamic traffic delays to different faulty distribution nodes.

[0036] It should be noted that if the composite severity level is directly used as the weight for bipartite graph matching, the system may select high-risk nodes in the distance while ignoring important nodes nearby. This could lead to mobile substations being unable to provide timely power support during long-distance travel, wasting valuable emergency time. The structural characteristics of the power grid mean that the impact of power outages at different nodes on overall stability varies. Therefore, the final edge weights need to establish a negative feedback mechanism between severity level, node importance, and travel cost. To address this, degree centrality is introduced as an adjustment coefficient, and path degradation gradient is used as a penalty term to construct a transient adaptive edge weight. This weight reduces the weight of excessively high-risk matching edges, guiding the system to find the optimal resource allocation scheme that offers both high repair value and rapid arrival. Through a dynamic redirection mechanism, the system can adjust the substation's travel route in real time based on changes in weights, thus achieving a complete closed loop from perception to decision-making to execution.

[0037] Preferably, in one embodiment of the present invention, the degree centrality of each faulty distribution node is adjusted using composite urgency and dynamic degradation gradient, and the specific formula for obtaining the transient adaptive edge weight between each mobile substation to be assigned and each faulty distribution node is as follows: In the formula, This represents the transient adaptive edge weight between the i-th mobile substation to be assigned and the j-th faulty distribution node; This represents the composite urgency level of the i-th mobile substation to be assigned to the j-th faulty distribution node; This represents the dynamic degradation gradient between the i-th mobile substation to be assigned and the j-th faulty distribution node; This represents the logarithmic function with the natural constant as the base.

[0038] It should be noted that when the composite urgency level increases or the degree centrality of the faulty distribution node is high, the numerator increases and the edge weight increases, indicating that the faulty distribution node is both urgent and located at a critical hub in the power grid topology, thus having high allocation value. However, when the dynamic degradation gradient of the path is too large, the linear penalty mechanism of the denominator will reduce the overall edge weight. This logic solves the limitation of using traditional static distance as weight, ensuring that high-value and fast-reachable matching edges receive the highest priority, avoiding scheduling that discards nearby edges for distant ones.

[0039] Please see Figure 2 The figure shows the transient adaptive edge weight matrix of the mobile substation random dispatch method based on big data analysis. The figure shows the final matching score after the weight formula is corrected. The value of each cell integrates the importance of the power grid topology, the composite urgency, and the passage cost. The higher the value, the higher the allocation priority. This matrix breaks the traditional blind logic of going to the nearest one and ensures that resources are directed to faulty distribution nodes that are important, urgent, and actually reachable.

[0040] At this point, the transient adaptive edge weights between each mobile substation to be assigned and each faulty distribution node are obtained.

[0041] Step S004: Generate a dynamic bipartite graph based on transient adaptive edge weights to perform optimal matching and scheduling of mobile substations.

[0042] Preferably, in one embodiment of the present invention, the specific method for optimal matching and scheduling of mobile substations based on a dynamic bipartite graph generated by transient adaptive edge weights is as follows: Using the set of mobile substations as the left vertex of a dynamic bipartite graph and the set of faulty distribution nodes as the right vertex, a global matching weight matrix is ​​constructed using transient adaptive edge weights. Then, the maximum weight matching algorithm of the bipartite graph is executed to solve for the maximum weight matching scheme at the current moment, and a scheduling command is issued. During the operation of the mobile substation, the real-time transient adaptive edge weights are continuously obtained in a loop. Based on the latest global matching weight matrix, the maximum weight matching algorithm of the bipartite graph is re-executed for dynamic redirection, thereby completing the anti-sudden random scheduling of the entire mobile substation.

[0043] The maximum weight matching algorithm for bipartite graphs is a well-known concept, and will not be elaborated upon in this embodiment.

[0044] Please see Figure 3 It shows a comparison of the operational efficiency of existing technologies for mobile substation random dispatching methods based on big data analysis; This concludes the embodiment.

[0045] Another embodiment of the present invention provides a mobile substation random dispatch system based on big data analysis. The system includes a memory and a processor. When the processor executes the computer program in the memory, it performs the above steps S001 to S004.

[0046] It should be noted that the specific embodiments described above enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. Therefore, although the present invention has been described in detail in this specification, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the present invention; and all technical solutions and improvements that do not depart from the spirit and scope of the present invention are covered within the protection scope of the patent of the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A mobile substation random dispatching method based on big data analysis, characterized in that, The method includes: Obtain the set of mobile substations to be assigned and the set of faulty distribution nodes, and construct the current distribution network topology diagram; obtain the geographical road network data, real-time meteorological data and power load monitoring data corresponding to each faulty distribution node; Based on the geographical road network data and real-time meteorological data corresponding to the faulty power distribution node, the dynamic degradation gradient between the mobile substation to be assigned and each faulty power distribution node is obtained. Based on the dynamic degradation gradient and combined with power load monitoring data, the composite urgency of the mobile substation to be assigned to each faulty distribution node is obtained; the degree centrality of each faulty distribution node in the current distribution network topology is obtained; the degree centrality of each faulty distribution node is adjusted using the composite urgency and dynamic degradation gradient to obtain the transient adaptive edge weight between each mobile substation to be assigned and each faulty distribution node. Optimal matching and scheduling of mobile substations is achieved by generating a dynamic bipartite graph based on transient adaptive edge weights.

2. The mobile substation random dispatching method based on big data analysis according to claim 1, characterized in that, The step of obtaining the dynamic degradation gradient between the mobile substation to be assigned and each faulty distribution node based on the geographical road network data and real-time meteorological data corresponding to the faulty distribution node includes: For the m-th basic path between the mobile substation to be assigned and the j-th faulted distribution node, the real-time meteorological disaster index of the m-th basic path is obtained based on the real-time meteorological data corresponding to the faulted distribution node. The product of the baseline speed limit of the m-th basic path and the inverse proportional value of the real-time meteorological disaster index of the m-th basic path is denoted as the dynamic meteorological impact factor of the m-th basic path. The ratio between the segment length of the m-th basic path and the dynamic meteorological influence factor of the m-th basic path is denoted as the dynamic degradation factor of the m-th basic path; the sum of the dynamic degradation factors of all basic paths between the mobile substation to be assigned and the j-th faulty distribution node is taken as the dynamic degradation gradient between the mobile substation to be assigned and the j-th faulty distribution node.

3. The mobile substation random dispatching method based on big data analysis according to claim 2, characterized in that, The step of obtaining the real-time meteorological disaster index of the m-th basic path based on the real-time meteorological data corresponding to the faulty power distribution node includes: Based on the changes in real-time meteorological data corresponding to the m-th faulty power distribution node within the historical time range, the rainfall impact factor and wind speed impact factor of the m-th basic path at the current moment are obtained. Two preset influencing parameters and This will affect the parameters. The product of the rainfall impact factor of the m-th base path at the current time is denoted as the first product; the impact parameters are... The product of 2 and the wind speed influence factor of the m-th base path at the current moment is denoted as the second product; the sum of the first product and the second product is used as the real-time meteorological disaster index of the m-th base path.

4. The mobile substation random dispatching method based on big data analysis according to claim 3, characterized in that, The method of obtaining the rainfall and wind speed impact factors of the m-th basic path at the current moment based on the changes in real-time meteorological data corresponding to the m-th faulty power distribution node within a historical time range includes: By using a third-party meteorological platform, the maximum and minimum rainfall, as well as the maximum and minimum wind speed levels, of the m-th basic path within the past month are obtained. The rainfall and wind speed levels of the m-th basic path at the current moment are normalized using the maximum-minimum value normalization algorithm to obtain the rainfall and wind speed influence factors of the m-th basic path at the current moment.

5. The mobile substation random dispatching method based on big data analysis according to claim 1, characterized in that, The method of obtaining the composite urgency level of the mobile substation to be assigned to each faulty distribution node based on the dynamic degradation gradient and combined with power load monitoring data includes: Based on power load monitoring data, obtain the real-time power deficit, rated load demand, and load self-recovery rate of the j-th faulty distribution node; The ratio between the real-time power deficit of the j-th faulty distribution node and the rated load demand is denoted as the real-time power deficit percentage of the j-th faulty distribution node. Based on the dynamic degradation gradient between the mobile substation to be assigned and the j-th faulty distribution node, and the real-time power deficit ratio of the j-th faulty distribution node, the time delay factor of the j-th faulty distribution node is obtained; based on the load self-recovery rate of the j-th faulty distribution node and the time delay factor of the j-th faulty distribution node, the urgency of emergency repair of the j-th faulty distribution node is obtained. The product of the rated load demand of the j-th faulty distribution node and the urgency of repairing the j-th faulty distribution node is used as the composite urgency of the mobile substation to be assigned to the j-th faulty distribution node.

6. The mobile substation random dispatching method based on big data analysis according to claim 5, characterized in that, The step of obtaining the real-time power deficit, rated load demand, and load self-recovery rate of the j-th faulty distribution node based on power load monitoring data includes: The system uses advanced smart meter measurement to obtain the rated load demand, real-time active power and rated power of the j-th faulty distribution node; as well as the active power of the energy storage converter of the j-th faulty distribution node in each fault event in the past year. The absolute value of the difference between the real-time active power and the rated power is denoted as the real-time power deficit of the j-th faulty distribution node. The load self-recovery rate of the j-th faulty distribution node is obtained based on the active power and rated load demand of the energy storage converter of the j-th faulty distribution node in each fault event.

7. The mobile substation random dispatching method based on big data analysis according to claim 6, characterized in that, The step of obtaining the load self-recovery rate of the j-th faulty distribution node based on the active power and rated load demand of the energy storage converter of the j-th faulty distribution node in each fault event includes: The ratio between the active power of the energy storage converter of the j-th fault distribution node and the rated load demand of the j-th fault distribution node in each fault event is denoted as the load recovery factor of the j-th fault distribution node in each fault event. The normalized value of the mean of the load recovery factors of the j-th faulty distribution node in all fault events over the past year is taken as the load self-recovery rate of the j-th faulty distribution node.

8. The mobile substation random dispatching method based on big data analysis according to claim 1, characterized in that, The process of obtaining the degree centrality of each faulty distribution node in the current distribution network topology diagram includes: For any faulty distribution node in the current distribution network topology diagram, the normalized value of the number of all basic paths between all mobile substations to be assigned and any faulty distribution node is used as the degree center of the faulty distribution node.

9. The mobile substation random dispatching method based on big data analysis according to claim 1, characterized in that, The process of adjusting the degree centrality of each faulty distribution node using composite urgency and dynamic degradation gradient to obtain the transient adaptive edge weights between each mobile substation to be assigned and each faulty distribution node includes: In the formula, This represents the transient adaptive edge weight between the i-th mobile substation to be assigned and the j-th faulty distribution node; This represents the composite urgency level of the i-th mobile substation to be assigned to the j-th faulty distribution node; This represents the dynamic degradation gradient between the i-th mobile substation to be assigned and the j-th faulty distribution node; This represents the logarithmic function with the natural constant as the base.

10. A mobile substation random dispatch system based on big data analysis, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the computer program is executed by the processor, it implements the steps of the mobile substation random dispatching method based on big data analysis as described in any one of claims 1-9.

Images