Intelligent power distribution optimization control method and platform combined with real-time load monitoring

Abstract

The invention provides an intelligent power distribution optimization control method and platform combined with real-time load monitoring, and relates to the technical field of power distribution optimization, and the method comprises the steps: obtaining an equipment topology network, carrying out the real-time load monitoring, and outputting a corresponding load monitoring data set; performing load anomaly analysis on the load monitoring data set to obtain abnormal equipment; constructing an abnormal equipment topology network according to the abnormal equipment and the associated equipment; inputting the load monitoring data set corresponding to the abnormal equipment topology network into the network load flexibility evaluation model for analysis, and outputting a network load flexibility index; and inputting the network load flexible index into a power distribution optimization control module for analysis, and outputting a power distribution control scheme. According to the method and the device, the technical problem that the power distribution control accuracy is affected due to insufficient positioning precision of abnormal equipment caused by lack of deep analysis of the equipment association influence and flexible monitoring means of the load in the prior art is solved, and the accuracy of a power distribution control decision and the stability and the reliability of a power distribution system are improved.

Description

Technical Field

[0001] The present application relates to the field of power distribution optimization technology, and specifically to an intelligent power distribution optimization control method and platform combined with real-time load monitoring. Background Art

[0002] Intelligent power distribution optimization is an important direction for the development of power systems. It uses modern information technology, sensors and data analysis technology to achieve real-time monitoring, optimization management and fault warning of power distribution systems. Existing intelligent power distribution optimization mainly relies on load monitoring of individual devices. Although this method can provide a certain degree of optimization, it lacks consideration of the overall load status of the equipment network and often cannot fully grasp the scope and extent of the impact of equipment failures or abnormalities on the entire distribution network. In addition, existing technologies are limited to viewing abnormal devices in isolation. When optimizing distribution control, they cannot fully consider the potential redundancy and recovery capabilities in the network. When faced with complex networks with multiple devices and multiple levels, distribution control decisions have problems such as insufficient flexibility and slow response speed, which limits the efficiency and reliability of the distribution system. Summary of the invention

[0003] The present application provides an intelligent power distribution optimization control method and platform combined with real-time load monitoring, which solves the technical problem that the existing technology lacks in-depth analysis of the impact of correlations between devices and flexible monitoring methods for loads, resulting in insufficient accuracy in locating abnormal equipment and affecting the accuracy of power distribution control. It achieves the technical effect of improving the accuracy of power distribution control decisions and thereby enhancing the stability and reliability of the power distribution system.

[0004] In view of the above problems, on the one hand, the present application provides an intelligent power distribution optimization control method combined with real-time load monitoring, the method comprising: obtaining a device topology network; performing real-time load monitoring on the device topology network, and outputting a load monitoring data set corresponding to the device topology network; performing load anomaly analysis on the load monitoring data set to obtain abnormal devices; connecting the device topology network, identifying associated devices connected to the abnormal devices, and constructing an abnormal device topology network based on the abnormal devices and the associated devices; inputting the load monitoring data set corresponding to the abnormal device topology network into a network load flexibility evaluation model for analysis, and outputting a network load flexibility index; inputting the network load flexibility index into a distribution optimization control module for analysis, and outputting a distribution control plan.

[0005] On the other hand, the present application also provides an intelligent power distribution optimization control platform combined with real-time load monitoring, the platform comprising: a device topology unit for obtaining a device topology network; a real-time load monitoring unit for performing real-time load monitoring on the device topology network, and outputting a load monitoring data set corresponding to the device topology network; a load anomaly analysis unit for performing load anomaly analysis on the load monitoring data set to obtain abnormal devices; an abnormal device topology unit for connecting the device topology network, identifying associated devices connected to the abnormal devices, and constructing an abnormal device topology network based on the abnormal devices and the associated devices; a load flexibility evaluation unit for inputting the load monitoring data set corresponding to the abnormal device topology network into a network load flexibility evaluation model for analysis, and outputting a network load flexibility index; a power distribution optimization control unit for inputting the network load flexibility index into a power distribution optimization control module for analysis, and outputting a power distribution control plan.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: By obtaining the device topology network, the connection relationship and layout of the equipment in the distribution system are clarified, providing a framework structure for subsequent monitoring and analysis. By performing real-time load monitoring on the device topology network, the load monitoring data set corresponding to the device topology network is obtained in time, providing a data source for discovering potential load anomalies. By performing load anomaly analysis on the load monitoring data set, the abnormal equipment that may have problems is accurately located, providing a target for subsequent targeted analysis and processing. The device topology network is connected, the associated equipment connected to the abnormal equipment is identified, and the abnormal equipment topology network is constructed according to the abnormal equipment and the associated equipment, expanding the focus from a single abnormal equipment to the equipment network associated with it. By constructing the abnormal equipment topology network, the mutual influence between the equipment is fully considered, so that the subsequent analysis is more in line with the actual operation of the distribution network. The load monitoring data set corresponding to the abnormal equipment topology network is input into the network load flexibility evaluation model for analysis. The network load flexibility evaluation model can quantify the flexible characteristics of the network load and output the network load flexibility index. The network load flexibility index provides a quantitative basis for evaluating the adaptability of the distribution network when the load changes, which helps to gain a deeper understanding of the performance of the distribution network. The network load flexibility index is input into the power distribution optimization control module for analysis, and a power distribution control scheme is output to achieve optimization control of intelligent power distribution.

[0007] To summarize, this application, by constructing an abnormal equipment topology network and a network load flexibility evaluation model, deeply analyzes the correlation between devices and the network load flexibility, accurately locates abnormal equipment and its impact range, and accurately evaluates the load adaptability of the distribution network, thereby outputting a more reasonable and effective distribution control solution, improving the stability, reliability and ability of the distribution system to cope with load changes, and can also more effectively utilize existing distribution equipment resources and extend the service life of the equipment.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flow chart of an intelligent power distribution optimization control method combined with real-time load monitoring provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the process of constructing an abnormal device topology network in the intelligent power distribution optimization control method combined with real-time load monitoring provided in an embodiment of the present application.

[0011] Figure 3 A schematic diagram of a process for obtaining network load flexibility indicators in an intelligent power distribution optimization control method combined with real-time load monitoring provided in an embodiment of the present application.

[0012] Figure 4 A schematic diagram of the structure of an intelligent power distribution optimization control platform combined with real-time load monitoring provided in an embodiment of the present application.

[0013] Explanation of the reference numerals: device topology unit 10 , real-time load monitoring unit 20 , load abnormality analysis unit 30 , abnormal device topology unit 40 , load flexibility evaluation unit 50 , power distribution optimization control unit 60 . DETAILED DESCRIPTION

[0014] The embodiments of the present application provide an intelligent power distribution optimization control method and platform combined with real-time load monitoring, thereby solving the technical problem that the prior art lacks in-depth analysis of the impact of correlations between devices and flexible monitoring methods for loads, resulting in insufficient accuracy in locating abnormal equipment and affecting the accuracy of power distribution control. This achieves the technical effect of improving the accuracy of power distribution control decisions and thereby enhancing the stability and reliability of the power distribution system.

[0015] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides an intelligent power distribution optimization control method combined with real-time load monitoring, the method comprising: Step S1: Obtain device topology network.

[0016] Specifically, the device topology network refers to the connection relationship diagram of various devices in the power system (such as transformers, circuit breakers, meters, etc.). The device topology network shows the connection mode and structural layout between devices, including the working status and location of the equipment and the electrical connection between the equipment (such as power lines, switches, circuit breakers, etc.). The topology network is usually represented in the form of a graph, in which each device is a node and the connection between devices is an edge.

[0017] Collect and define the topological structure information of all relevant equipment from the equipment database, including substations, distribution boards, load equipment, switchgear, etc., and draw the equipment topology network based on the acquired information. Taking the substation as an example, the equipment topology network can show the power transmission path from the substation to each distribution box and finally to each user. By obtaining the equipment topology network, the structure of the distribution system can be fully understood, providing a basic framework for subsequent load monitoring, abnormal analysis and optimization control.

[0018] Step S2: Perform real-time load monitoring on the device topology network, and output a load monitoring data set corresponding to the device topology network.

[0019] Specifically, a load monitoring data set is a data set consisting of multiple data points, each of which contains the load information of the device at a certain moment, such as current, voltage, power, etc. Load monitoring sensors (such as current sensors, power sensors, etc.) are installed on each device in the device topology network. These sensors will collect the load data of the device in real time, organize and store these load data, and form a load monitoring data set. For example, in the power distribution system of a commercial building, sensors are installed on the distribution boxes and major electrical equipment on each floor. The sensors transmit the collected current and voltage data to the background data acquisition system. The system organizes these data in chronological order and by device number to form a load monitoring data set.

[0020] The load monitoring data set provides the actual data of the equipment load, provides a basis for judging whether the equipment is abnormal, and is the data source for subsequent analysis.

[0021] Step S3: performing load anomaly analysis on the load monitoring data set to obtain abnormal devices.

[0022] Specifically, an abnormal device refers to a device that has problems during load monitoring. For example, if the current of a device exceeds the normal range, it may indicate that the device is overloaded or faulty. Input the load monitoring data set into the data analysis software, and set the range and threshold of the normal load (for example, for a certain device, the normal power range is 50 to 100 watts, the current range is 1A to 2A, etc.). Use the data analysis software to compare the data in the data set one by one. If the data of a certain device is found to be beyond the normal range, it will be determined as an abnormal device. For example, for the power data of a device in a data set, if it is found that it exceeds the upper limit of 100 watts for multiple consecutive moments, the device is determined to be an abnormal device; clustering algorithms can also be used to identify abnormal devices that are different from most devices. Through load anomaly analysis, it is possible to accurately locate devices that may have problems and narrow the scope of subsequent analysis and processing.

[0023] Step S4: connecting the device topology network, identifying the associated devices connected to the abnormal device, and constructing an abnormal device topology network based on the abnormal device and the associated devices.

[0024] Specifically, an associated device is a device that has a connection relationship with an abnormal device in a device topology network. For example, in a circuit, a light bulb is an abnormal device, and switches, fuses, etc. connected in series or in parallel with it are associated devices. An abnormal device topology network refers to a network centered on the abnormal device and including devices directly or indirectly connected to it. According to the device topology network obtained in step S1, find out the devices that have a direct or indirect connection relationship with the abnormal device from the network, and then connect these associated devices according to the connection weight with the abnormal device as the center to construct an abnormal device topology network. For example, in a household power distribution network, a light bulb is an abnormal device, the switch directly connected to it is a first-level associated device, and the distribution box connected to the switch is a second-level associated device. The abnormal device topology network of the light bulb is constructed based on the connection relationship of these devices. The construction process can use graph theory and network analysis technology to analyze the connection relationship between devices, and use graph algorithms (such as depth-first search and breadth-first search) to trace the connection path from the abnormal device to other devices, and then identify and construct the abnormal device topology network.

[0025] By constructing an abnormal device topology network, the impact of abnormal devices on the entire system can be identified, providing more accurate data for subsequent load flexibility assessment and power distribution optimization.

[0026] Step S5: inputting the load monitoring data set corresponding to the abnormal device topology network into the network load flexibility evaluation model for analysis, and outputting the network load flexibility index.

[0027] Specifically, the network load flexibility assessment model is a model used to assess the adaptability and resilience of network loads in the face of changes. For example, the network load flexibility assessment model can quantitatively assess the flexibility of the distribution network when increasing or decreasing the load based on factors such as the connection relationship between devices and the load change law. The network load flexibility index is a quantitative index obtained through the analysis of the network load flexibility assessment model, which is used to measure the load flexibility of the distribution network.

[0028] Data related to the abnormal device topology network is screened out from the load monitoring data set obtained in step S2, and these data are input into the network load flexibility evaluation model. The model calculates the input data according to a pre-set algorithm (for example, considering the connection relationship between devices, historical load data, device capacity and other factors), and finally outputs the network load flexibility index. For example, in a power distribution network of a park, for a local abnormal device topology network, the model calculates the network load flexibility index based on the load utilization rate, historical load average, current power, current fluctuation rate and connection weight between devices.

[0029] By calculating the network load flexibility index, the load flexibility of the abnormal equipment topology network is quantified, which provides a basis for evaluating the ability of the distribution network to cope with load changes.

[0030] Step S6: input the network load flexibility index into the power distribution optimization control module for analysis, and output a power distribution control solution.

[0031] Specifically, the distribution optimization control module is a software module used to formulate and adjust the distribution control plan based on information such as network load flexibility indicators. The module can automatically adjust parameters such as current, voltage, and power based on the input information to ensure the efficient and stable operation of the power system. The network load flexibility indicators are input into the distribution optimization control module. After receiving the network load flexibility indicators, the distribution optimization control module combines the pre-set distribution rules (such as ensuring the power supply priority of important equipment, avoiding overload, etc.) and other related parameters (such as the current total power supply, load demand forecast of each device, etc.), analyzes and calculates through internal algorithms (such as linear programming or genetic algorithms), and finally outputs the distribution control plan. For example, in a hospital's power distribution system, based on the network load flexibility indicators and the importance and load demand forecast of each medical device, the distribution optimization control module formulates a distribution control plan that prioritizes the power supply of equipment in important areas such as operating rooms and intensive care units, while reasonably allocating power to other areas.

[0032] An optimized power distribution control scheme is formulated according to the network load flexibility index, which improves the stability and reliability of the power distribution system and optimizes the allocation of power distribution resources.

[0033] Furthermore, step S6 also includes: Step S61: Determine whether the number of abnormal devices is greater than or equal to 2.

[0034] Step S62: If the number of the abnormal devices is greater than or equal to 2, multiple abnormal device topology networks corresponding to the multiple abnormal devices are obtained.

[0035] Step S63: outputting a plurality of network load flexibility indicators corresponding to the plurality of abnormal device topology networks.

[0036] Step S64: input the plurality of network load flexibility indicators into the power distribution optimization control module for analysis, and output a hierarchical power distribution control scheme according to the indicator sizes of the plurality of network load flexibility indicators.

[0037] Specifically, the hierarchical power distribution control scheme is a power distribution control scheme formulated based on the size of the network load flexibility index corresponding to the topological network of multiple abnormal devices. The scheme divides the power distribution control into levels, and different levels correspond to different abnormal devices and their related network conditions, so as to achieve more refined and targeted power distribution optimization control. For example, in a large commercial complex, there are abnormalities in the power distribution equipment in multiple areas. According to the size of the network load flexibility index corresponding to each area, the basic power demand of the area with poor index (weak load adaptability) is prioritized, and at the same time, flexible power allocation is carried out for the area with better index, forming a hierarchical power distribution control scheme.

[0038] The abnormal devices determined in the previous step S3 are counted and counted, and a counter or a simple list counting function is used to determine whether the number of abnormal devices reaches 2 or more.

[0039] If the number of abnormal devices is greater than or equal to 2, for each abnormal device, identify the associated devices related to it based on the device topology network, so as to construct multiple abnormal device topology networks corresponding to multiple abnormal devices. For example, in the power distribution system of a residential area, there are two abnormal devices, namely a distribution box in a building and a lighting controller in a public area. For the distribution box, find the associated devices such as the meters and main switches of each unit connected to it to build the abnormal device topology network; for the lighting controller, find the associated devices such as lamps and sensors connected to it to build its abnormal device topology network. By constructing a corresponding abnormal device topology network for each abnormal device, a corresponding network structure foundation is provided for the subsequent accurate analysis of the situations of multiple abnormal devices, so that the relationship between each abnormal device and its related devices can be fully considered.

[0040] According to the analysis method of step S5, the load monitoring data set corresponding to each abnormal device topology network is respectively input into the network load flexibility evaluation model to obtain respective network load flexibility indicators, which provide a basis for subsequent hierarchical power distribution control.

[0041] Multiple network load flexibility indicators are input into the power distribution optimization control module for analysis. After receiving multiple network load flexibility indicators, the power distribution optimization control module sorts the abnormal devices and their related networks according to the indicator size. A hierarchical power distribution control plan is formulated according to the pre-set hierarchical strategy (for example, the smaller the indicator, the worse the load adaptability, and priority is given to power supply or special power allocation). For example, in a large office building, there are multiple floors with abnormal power distribution equipment. According to the size of the network load flexibility indicators of each floor, the basic power demand of the floor with the worst indicator is prioritized, such as the minimum power consumption of lighting and office equipment, and then other floors are reasonably allocated according to the remaining power situation.

[0042] By formulating a hierarchical power distribution control plan, the accuracy and rationality of power distribution optimization control in complex power distribution situations (where multiple abnormal devices exist) are improved, and the overall stability and reliability of the power distribution system are better guaranteed.

[0043] Further, such as Figure 2 As shown, step S4 includes: Step S41: connecting the device topology network, identifying the first-level associated device and the second-level associated device connected to the abnormal device, wherein the first-level associated device is a device directly connected to the abnormal device, and the second-level associated device is a device indirectly connected to the abnormal device.

[0044] Step S42: Obtain the primary connection weight corresponding to the primary associated device.

[0045] Step S43: Obtain the secondary connection weight corresponding to the secondary associated device.

[0046] Step S44: Taking the abnormal device as the connection center, the first-level associated device and the second-level associated device are connected according to the first-level connection weight and the second-level connection weight to construct the abnormal device topology network.

[0047] Specifically, from the acquired device topology network data, starting from the abnormal device, find the devices directly connected to it as the first-level associated devices, and then find the devices connected to these first-level associated devices as the second-level associated devices. The search process can use the path search algorithm in graph theory, such as breadth-first search (BFS) or depth-first search (DFS), to determine the connection level of the device. By identifying the first-level and second-level associated devices, the impact range of the abnormal device on the distribution system can be more accurately identified, providing detailed network structure information for subsequent network analysis and control strategies.

[0048] The primary connection weight is a value used to measure the importance of the connection relationship between the primary associated device and the abnormal device. The secondary connection weight is a value used to measure the importance of the connection relationship between the secondary associated device and the abnormal device. The connection weight of the primary associated device is determined based on the pre-set weight determination rules, combined with factors such as the type of equipment, power, and potential impact on the load of abnormal equipment. For example, for a data center's power distribution system, if the server (primary associated equipment) has high power and has a large impact on the load of the total distribution cabinet (abnormal equipment), its primary connection weight is determined to be 0.7 according to the weight setting rules (such as based on factors such as power ratio); while small office equipment (primary associated equipment) has low power and has little impact on the load of the total distribution cabinet, and its primary connection weight is determined to be 0.3.

[0049] Similar to the method of obtaining the first-level weight, the connection weight of the second-level associated device is obtained based on the relevant characteristics of the device (such as power, indirect impact on abnormal device load, etc.) and pre-set weight determination rules.

[0050] Taking the abnormal device as the core, the first-level associated devices and the second-level associated devices are connected according to the first-level connection weight and the second-level connection weight to build an abnormal device topology network. The specific connection method can be implemented through network construction software or algorithms. For example, the abnormal device topology network is constructed according to the weighted graph construction method in graph theory. Among them, the node represents the device, the edge represents the connection, the edge weight represents the strength or importance of the connection, and the thickness of the connection line or the depth of color is used to indicate the size of the weight (for example, the thicker the line or the darker the color, the greater the weight).

[0051] By constructing an abnormal device topology network, we can more comprehensively understand the relationship between abnormal devices and surrounding devices, provide more suitable analysis objects for subsequent operations such as network load flexibility evaluation, and thus locate problem areas more accurately and formulate more effective control strategies to deal with abnormal situations.

[0052] Furthermore, after constructing the abnormal device topology network, the following is also included: Step S45: connecting the device topology network to perform connection integrity judgment on the abnormal device topology network to obtain a connection integrity index.

[0053] Step S46: If the connection integrity index is less than a preset connection integrity, identifying flexibility-related devices, wherein the flexibility-related devices are connection devices that have a greater impact on the load of the abnormal device.

[0054] Step S47: updating the abnormal device topology network according to the flexible related devices to obtain an updated abnormal device topology network.

[0055] Specifically, the connection integrity index is a quantitative index that measures the degree of connection between nodes in a topological network, and is usually used to evaluate the robustness and reliability of a topological network. In an embodiment of the present application, the connection integrity index is a quantitative value used to measure the degree of connection integrity of an abnormal device topological network. The constructed abnormal device topological network is compared and analyzed with the original device topological network. Check whether the device connection relationship in the abnormal device topological network is consistent with the corresponding part in the device topological network, and count the ratio of the number of normally connected device connections to the total number of connected devices to obtain the connection integrity index. For example, in a power distribution network in an industrial plant, the original device topological network shows that the abnormal device (a distribution box) has a connection relationship with 5 associated devices. In the constructed abnormal device topological network, it is found that 4 connections are normal after inspection, so the connection integrity index is 4÷5=0.8. By obtaining the connection integrity index, it is possible to promptly discover whether there are problems such as missing connections in the abnormal device topological network during the construction process, providing a basis for subsequent network optimization.

[0056] The preset connection integrity is a connection quality standard that is preset to ensure the stability and reliability of the distribution system. This standard defines the minimum degree of connection between nodes in the device topology network. When the connection integrity index is less than the preset connection integrity, the connection of the topology network is considered incomplete, and there may be a potential risk of load imbalance or failure. At this time, it is necessary to further identify those flexible related devices that have a greater impact on the load of abnormal devices from the connected devices in the device topology network. Flexible related devices are usually devices that have a greater impact on the load of abnormal devices and can adjust or alleviate the load. These devices can intervene when the load is too heavy to alleviate the load pressure of abnormal devices and help the distribution system return to normal. For example, in a distribution network, if a device in a substation fails, but the surrounding backup generators or distribution lines can provide partial load support, then these backup devices are considered to be flexible related devices.

[0057] The identified flexible related devices are included in the abnormal device topology network, and the topology structure is updated, including adjusting the connection weights in the network, adding or deleting nodes and edges, etc., to obtain the updated abnormal device topology network. This updated abnormal device topology network is a new topology network model that takes into account the influence of flexible related devices, and more accurately reflects the load adjustment and recovery capabilities of the entire distribution system, thereby providing more accurate data support for subsequent load flexibility evaluation and distribution optimization control, thereby improving the accuracy of distribution control decisions.

[0058] Further, such as Figure 3 As shown, step S5 includes: Step S51: Analyze the load monitoring data set corresponding to the abnormal device topology network, and output multiple load feature vectors, wherein the multiple load feature vectors include load utilization, historical load average, current power, current fluctuation rate, and connection weights between devices.

[0059] Step S52: constructing a eigenvector matrix according to the multiple load eigenvectors.

[0060] Step S53: obtaining a characteristic weight matrix, and calculating the flexibility index of the characteristic vector matrix according to the characteristic weight matrix to obtain a network load flexibility index.

[0061] Specifically, the load characteristic vector is a set of vectors used to describe the load situation of the abnormal device topology network, including load utilization, historical load average, current power, current fluctuation rate, and connection weights between devices. In an abnormal device topology network of a power system, the load utilization rate indicates the proportion of the current load of a certain device to its maximum load capacity; the historical load average is the average load level of the device over the past period of time; the current power is the actual power consumption of the device; the current fluctuation rate reflects the degree of current fluctuation; and the connection weight between devices reflects the importance of the connection relationship between devices. The characteristic vector matrix is ​​a matrix composed of multiple load characteristic vectors arranged in a certain order. The characteristic weight matrix is ​​a matrix used to measure the importance of each load characteristic vector in calculating the network load flexibility index.

[0062] Relevant data is extracted from the load monitoring data set corresponding to the abnormal device topology network, and load feature vectors such as load utilization, historical load average, current power, current fluctuation rate, and connection weight between devices are calculated using data analysis methods. For example, for an abnormal device topology network of a power system, by analyzing the device load data in the load monitoring data set, the load utilization (current load / maximum load capacity), historical load average (average load over a period of time), current power (real-time power consumption), current fluctuation rate (degree of current fluctuation), and connection weight between devices (extracted from the abnormal device topology network) of each device can be calculated. By analyzing the load monitoring data set, multiple load feature vectors are obtained, which can fully reflect the load conditions of the abnormal device topology network and provide a data basis for the subsequent construction of the feature vector matrix and calculation of network load flexibility indicators.

[0063] Arrange the obtained multiple load feature vectors in a certain order to construct a feature vector matrix. For example, if there are 5 load feature vectors, namely load utilization, historical load average, current power, current fluctuation rate, and connection weight between devices, and each vector has n elements (corresponding to n devices or nodes), then the feature vector matrix is ​​a 5×n matrix, in which each row represents a load feature vector and each column corresponds to the relevant load feature value of a device or node.

[0064] According to the load characteristics of the equipment and the contribution of each characteristic to the load flexibility (i.e., load regulation capability), a characteristic weight matrix is ​​generated. The elements in this matrix represent the weights of each load characteristic vector when calculating the network load flexibility index. The characteristic weight matrix can be determined based on expert experience, historical data, or machine learning algorithms. The flexibility index of the characteristic vector matrix is ​​calculated according to the characteristic weight matrix to obtain the network load flexibility index. The calculation process can be completed by weighted summation, matrix multiplication, and other calculation methods.

[0065] By calculating the network load flexibility index, the load flexibility of the abnormal equipment topology network can be quantified. This index can reflect the adaptability and stability of the network in the face of load changes, provide a basis for subsequent power distribution optimization control, improve the accuracy of power distribution control decisions, and thus improve the stability and reliability of the power distribution system.

[0066] Further, step S53 includes: Step S531: performing weighted calculation on the characteristic vector matrix according to the characteristic weight matrix to obtain N load flexibility indicators corresponding to the N devices in the abnormal device topology network.

[0067] Step S532: Calculate M edge load flexibility indices according to the N load flexibility indices.

[0068] Step S533: Calculate the connectivity of the abnormal device topology network and output a flexible connectivity index.

[0069] Step S534: performing a network global calculation on the M edge load flexibility indices according to the flexible connectivity index, and outputting a network load flexibility index.

[0070] Specifically, the eigenvector matrix is ​​weighted according to the predetermined feature weight matrix. Each element in the feature weight matrix represents the importance of the corresponding feature in calculating the load flexibility index. By multiplying each element in the eigenvector matrix by its corresponding feature weight, the load flexibility index of each device can be obtained. Assuming that there are N devices in the abnormal device topology network, N is a positive integer, the feature vectors of the N devices in the eigenvector matrix are weighted by the feature weight matrix, and N load flexibility indicators corresponding to the N devices can be obtained. For example, assuming that the feature weight matrix is ​​a 5×5 diagonal matrix, the elements on the diagonal are 0.3, 0.2, 0.2, 0.1, and 0.2 (corresponding to the weights of load utilization, historical load average, current power, current fluctuation rate, and connection weights between devices), and the eigenvector matrix is ​​a 5×N matrix, then by multiplying the feature weight matrix with the eigenvector matrix, a 1×N matrix can be obtained, and the elements in this matrix are the values ​​of the load flexibility index on each device or node.

[0071] In a topological network, devices are connected to each other through edges. The edge load flexibility index is a quantitative measure of the adaptability and flexibility of the connection lines between devices in the face of load changes. By calculating the load flexibility of these edges, the load transfer and regulation capabilities of each edge can be evaluated. According to the load flexibility indicators of N devices obtained in the previous step, the connection (edge) between each device is used as the unit of calculation to evaluate the load flexibility of the connection between devices and calculate M edge load flexibility indicators. The specific calculation process is as follows: For each pair of connected devices (that is, each edge) in the abnormal device topology network, the weighted average is performed according to the load flexibility indicators of each pair of connected devices and the connection weight to obtain the edge load flexibility index. The edge load flexibility index reflects the load regulation capability of the connection between devices, and can reflect the flexibility and load transfer capability of the connected devices.

[0072] In a device topology network, connectivity indicates the connection strength and accessibility between nodes (devices) in the network. A network with better connectivity means that load adjustment and information transmission between devices are more flexible. The flexible connectivity index is a measure of the connection efficiency of each device in the device network, reflecting the mutual coordination and responsiveness between devices. Algorithms such as the shortest path calculation and network flow analysis in graph theory can be used to calculate the connected components of the network as flexible connectivity indicators to reflect the load adjustment capability of the entire network.

[0073] The connectivity calculation results are combined with the edge load flexibility index to perform global calculations, comprehensively evaluate the load flexibility of the entire network, and output the total load flexibility index of the network. This index can comprehensively reflect the regulation ability of the entire network under load fluctuations and help formulate an optimized power distribution plan. For example, the product of the flexible connectivity index and the sum of all edge load flexibility indicators can be used as the network load flexibility index.

[0074] Furthermore, in step S533, the expression for calculating the connectivity of the abnormal device topology network is: ;in, is the flexible connectivity index of the abnormal device topology network G, which is used to measure the connectivity efficiency between nodes in the network, N is the number of devices in the abnormal device topology network, is the shortest path length from node i to node j, when The shorter it is, the higher the connectivity efficiency between node i and node j is. Sum the connectivity efficiencies of all different pairs of nodes.

[0075] Specifically, we can use the formula Calculate the connectivity of the abnormal device topology network and determine the flexible connectivity index. In this formula, is the flexible connectivity index of the abnormal device topology network G, which is used to measure the connectivity efficiency between nodes in the network. N is the number of devices in the abnormal device topology network. is the shortest path length from node i to node j, when The shorter it is, the higher the connectivity efficiency between node i and node j is. Sum the connectivity efficiencies of all different pairs of nodes.

[0076] When calculating connectivity, firstly, according to the device connection relationship in the abnormal device topology network, the shortest path algorithm in graph theory (such as Dijkstra algorithm or Floyd-Warshall algorithm) is used to calculate the shortest path length between all devices in the topology network. Next, the reciprocal of the shortest path length between each pair of devices is calculated. In a topological network, the smaller the shortest path length between two devices, the higher the efficiency of information transmission and load regulation. After that, the reciprocal paths between all pairs of devices are summed up to obtain the total reciprocal sum. This sum represents the connectivity strength of the entire device topology network. The higher the sum, the more efficient the connection between devices in the device topology network. Finally, substitute the calculated value into the above formula to solve and obtain the flexible connectivity index . Indicates the flexible connectivity of the entire device network. The higher the value, the smoother the collaboration and information flow between devices. The device network can better cope with load changes and abnormal situations and has stronger adaptive capabilities.

[0077] By calculating the flexible connectivity index, key nodes and potential weak links in the network can be identified, providing important decision support for distribution optimization control and improving the adaptability and recovery capacity of the entire distribution system in a targeted manner.

[0078] In summary, the intelligent power distribution optimization control method combined with real-time load monitoring provided in the embodiments of the present application has the following technical effects: By obtaining the device topology network, the connection relationship and layout of the equipment in the distribution system are clarified, providing a framework structure for subsequent monitoring and analysis. By performing real-time load monitoring on the device topology network, the load monitoring data set corresponding to the device topology network is obtained in time, providing a data source for discovering potential load anomalies. By performing load anomaly analysis on the load monitoring data set, the abnormal equipment that may have problems is accurately located, providing a target for subsequent targeted analysis and processing. Considering the equipment associated with the abnormal equipment, the first-level and second-level associated equipment connected to the abnormal equipment are identified from the device topology network, and the network is constructed according to the corresponding connection weights, expanding the focus from a single abnormal equipment to the equipment network associated with it, so that the analysis is no longer limited to a single abnormal equipment, but takes into account the impact of the equipment around the abnormal equipment on it, which is more in line with the situation of mutual connection of equipment in the actual distribution network. In addition, by judging the connection integrity and updating the abnormal equipment topology network, the accuracy of the network structure can be further ensured and the reliability of subsequent analysis can be improved. By analyzing the load monitoring data set of the abnormal equipment topology network, multiple load feature vectors are obtained, and a feature vector matrix is ​​constructed. Then, the network load flexibility index is calculated in combination with the characteristic weight matrix. The network load flexibility index provides a quantitative basis for evaluating the adaptability of the distribution network when the load changes, which helps to gain a deeper understanding of the performance of the distribution network. The network load flexibility index is input into the distribution optimization control module, and the distribution control scheme is output according to the number of abnormal devices and other conditions to achieve the optimization control of intelligent distribution. If the number of abnormal devices is greater than or equal to 2, a hierarchical distribution control scheme will also be output to deal with complex distribution conditions in a more detailed manner.

[0079] In general, the embodiments of the present application comprehensively and systematically consider the connection relationship, load conditions, and mutual influence of devices in the power distribution network, and can more accurately locate abnormal devices and their influence on surrounding devices, and more accurately quantify and evaluate the load flexibility characteristics of the power distribution network. Through hierarchical power distribution control schemes and other methods, it is possible to better cope with complex power distribution situations, improve the stability and reliability of the power distribution system, optimize the allocation of power distribution resources, and enhance the adaptability of the power distribution network to load changes.

[0080] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides an intelligent power distribution optimization control platform combined with real-time load monitoring, and the platform includes: The device topology unit 10 is used to obtain a device topology network.

[0081] The real-time load monitoring unit 20 is used to perform real-time load monitoring on the device topology network and output a load monitoring data set corresponding to the device topology network.

[0082] The load anomaly analysis unit 30 is used to perform load anomaly analysis on the load monitoring data set to obtain abnormal devices.

[0083] The abnormal device topology unit 40 is used to connect the device topology network, identify the associated device connected to the abnormal device, and construct the abnormal device topology network according to the abnormal device and the associated device.

[0084] The load flexibility evaluation unit 50 is used to input the load monitoring data set corresponding to the abnormal device topology network into the network load flexibility evaluation model for analysis, and output a network load flexibility index.

[0085] The power distribution optimization control unit 60 is used to input the network load flexibility index into the power distribution optimization control module for analysis and output a power distribution control solution.

[0086] Furthermore, the power distribution optimization control unit 60 of the embodiment of the present application is also used to perform the following steps: Determine whether the number of abnormal devices is greater than or equal to 2; if the number of abnormal devices is greater than or equal to 2, obtain multiple abnormal device topology networks corresponding to the multiple abnormal devices; output multiple network load flexibility indicators corresponding to the multiple abnormal device topology networks; input the multiple network load flexibility indicators into the power distribution optimization control module for analysis, and output a hierarchical power distribution control plan according to the indicator sizes of the multiple network load flexibility indicators.

[0087] Furthermore, the abnormal device topology unit 40 in the embodiment of the present application is also used to perform the following steps: Connect the device topology network, identify the first-level associated device and the second-level associated device connected to the abnormal device, wherein the first-level associated device is a device directly connected to the abnormal device, and the second-level associated device is a device indirectly connected to the abnormal device; obtain the first-level connection weight corresponding to the first-level associated device; obtain the second-level connection weight corresponding to the second-level associated device; take the abnormal device as the connection center, connect the first-level associated device and the second-level associated device according to the first-level connection weight and the second-level connection weight, and build the abnormal device topology network.

[0088] Furthermore, the abnormal device topology unit 40 in the embodiment of the present application is also used to perform the following steps: Connect the device topology network to judge the connection integrity of the abnormal device topology network and obtain a connection integrity index; if the connection integrity index is less than a preset connection integrity, identify flexible related devices, wherein the flexible related devices are connection devices that have a greater impact on the load of the abnormal device; update the abnormal device topology network according to the flexible related devices to obtain an updated abnormal device topology network.

[0089] Furthermore, the load flexibility evaluation unit 50 in the embodiment of the present application is also used to perform the following steps: The load monitoring data set corresponding to the abnormal device topology network is analyzed to output multiple load feature vectors, wherein the multiple load feature vectors include load utilization, historical load average, current power, current fluctuation rate, and connection weight between devices; a feature vector matrix is ​​constructed according to the multiple load feature vectors; a feature weight matrix is ​​obtained, and flexibility index calculation is performed on the feature vector matrix according to the feature weight matrix to obtain a network load flexibility index.

[0090] Furthermore, the step of calculating the flexibility index of the feature vector matrix according to the feature weight matrix includes: The characteristic vector matrix is ​​weightedly calculated according to the characteristic weight matrix to obtain N load flexibility indicators corresponding to N devices in the abnormal device topology network; M edge load flexibility indicators are calculated according to the N load flexibility indicators; connectivity calculation is performed on the abnormal device topology network to output a flexible connectivity indicator; network global calculation is performed on the M edge load flexibility indicators according to the flexible connectivity indicator to output a network load flexibility indicator.

[0091] Furthermore, the expression for calculating the connectivity of the abnormal device topology network is: ;in, is the flexible connectivity index of the abnormal device topology network G, which is used to measure the connectivity efficiency between nodes in the network, N is the number of devices in the abnormal device topology network, is the shortest path length from node i to node j, when The shorter it is, the higher the connectivity efficiency between node i and node j is. Sum the connectivity efficiencies of all different pairs of nodes.

[0092] Through the above detailed description of the intelligent power distribution optimization control method combined with real-time load monitoring in this specification, those skilled in the art can clearly know that the intelligent power distribution optimization control platform combined with real-time load monitoring in this embodiment, for the platform disclosed in Example 2, since it corresponds to the method disclosed in Example 1, it has corresponding functional units and beneficial effects, and the relevant parts can be referred to the method part description.

[0093] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent power distribution optimization control method combined with real-time load monitoring, characterized in that: The method comprises: Get device topology network; Performing real-time load monitoring on the device topology network and outputting a load monitoring data set corresponding to the device topology network; Performing load anomaly analysis on the load monitoring data set to obtain abnormal devices; Connecting the device topology network, identifying associated devices connected to the abnormal device, and constructing an abnormal device topology network based on the abnormal device and the associated devices; Inputting the load monitoring data set corresponding to the abnormal device topology network into the network load flexibility evaluation model for analysis, and outputting the network load flexibility index; The network load flexibility index is input into the power distribution optimization control module for analysis, and a power distribution control solution is output.

2. The method according to claim 1, characterized in that The network load flexibility index is input into the power distribution optimization control module for analysis, and the method further includes: Determine whether the number of abnormal devices is greater than or equal to 2; If the number of the abnormal devices is greater than or equal to 2, obtaining multiple abnormal device topology networks corresponding to the multiple abnormal devices; Outputting a plurality of network load flexibility indicators corresponding to the plurality of abnormal device topology networks; The multiple network load flexibility indicators are input into the power distribution optimization control module for analysis, and a hierarchical power distribution control scheme is output according to the indicator sizes of the multiple network load flexibility indicators.

3. The method according to claim 1, characterized in that Construct an abnormal device topology network, including: Connecting the device topology network, identifying a first-level associated device and a second-level associated device connected to the abnormal device, wherein the first-level associated device is a device directly connected to the abnormal device, and the second-level associated device is a device indirectly connected to the abnormal device; Obtaining a primary connection weight corresponding to the primary associated device; Obtaining a secondary connection weight corresponding to the secondary associated device; Taking the abnormal device as a connection center, the first-level associated device and the second-level associated device are connected according to the first-level connection weight and the second-level connection weight to construct the abnormal device topology network.

4. The method according to claim 3, characterized in that Building an abnormal device topology network, the method also includes: Connecting the device topology network to perform connection integrity judgment on the abnormal device topology network to obtain a connection integrity index; If the connection integrity indicator is less than a preset connection integrity, identifying a flexibility-related device, wherein the flexibility-related device is a connection device that has a greater impact on the load of the abnormal device; The abnormal device topology network is updated according to the flexible related devices to obtain an updated abnormal device topology network.

5. The method according to claim 1, characterized in that The load monitoring data set corresponding to the abnormal device topology network is input into the network load flexibility evaluation model for analysis, and the network load flexibility index is output. The method includes: Analyze the load monitoring data set corresponding to the abnormal device topology network, and output multiple load feature vectors, wherein the multiple load feature vectors include load utilization, historical load average, current power, current fluctuation rate, and connection weight between devices; According to the multiple load characteristic vectors, construct a characteristic vector matrix; A characteristic weight matrix is ​​obtained, and flexibility index calculation is performed on the characteristic vector matrix according to the characteristic weight matrix to obtain a network load flexibility index.

6. The method according to claim 5, characterized in that The flexibility index of the characteristic vector matrix is ​​calculated according to the characteristic weight matrix, and the method includes: Performing weighted calculation on the characteristic vector matrix according to the characteristic weight matrix to obtain N load flexibility indicators corresponding to N devices in the abnormal device topology network; Calculating M edge load flexibility indices according to the N load flexibility indices; Calculating the connectivity of the abnormal device topology network and outputting a flexible connectivity index; A network global calculation is performed on the M edge load flexibility indicators according to the flexible connectivity indicator, and a network load flexibility indicator is output.

7. The method according to claim 6, characterized in that The expression for calculating the connectivity of the abnormal device topology network is: ;in, is the flexible connectivity index of the abnormal device topology network G, which is used to measure the connectivity efficiency between nodes in the network, N is the number of devices in the abnormal device topology network, is the shortest path length from node i to node j, when The shorter it is, the higher the connectivity efficiency between node i and node j is. Sum the connectivity efficiencies of all different pairs of nodes.

8. Intelligent power distribution optimization control platform combined with real-time load monitoring, characterized by: The platform is used to execute the intelligent power distribution optimization control method combined with real-time load monitoring according to any one of claims 1 to 7, comprising: A device topology unit, used to obtain a device topology network; A real-time load monitoring unit, used to perform real-time load monitoring on the device topology network and output a load monitoring data set corresponding to the device topology network; A load anomaly analysis unit, used to perform load anomaly analysis on the load monitoring data set to obtain abnormal devices; An abnormal device topology unit is used to connect the device topology network, identify the associated device connected to the abnormal device, and construct an abnormal device topology network based on the abnormal device and the associated device; A load flexibility evaluation unit, configured to input a load monitoring data set corresponding to the abnormal device topology network into a network load flexibility evaluation model for analysis, and output a network load flexibility index; The power distribution optimization control unit is used to input the network load flexibility index into the power distribution optimization control module for analysis and output a power distribution control solution.

Images