A digital and intelligent capacitor power quality treatment method, device and medium

Abstract

The application discloses a kind of digital intelligence capacitor electric energy quality treatment method, device and medium, comprising: in response to electric energy quality treatment start signal, the topological structure information of target power network area and multi-source monitoring data are determined, wherein multi-source monitoring data include: the spatial position data of each compensation node based on Beidou positioning system and electrical connection relationship, and the time series electric energy quality operating data of each compensation node;Based on topological structure information and multi-source monitoring data, the operating characteristic information of target power network area is determined, wherein operating characteristic information includes: collaborative management state and single machine compensation state;In response to operating characteristic information, generate control instruction set, control instruction set is used to control the switching state adjustment of target compensation equipment to the target state compatible with target reactive compensation strategy.

Description

Technical Field

[0001] This invention relates to the field of intelligent power quality management technology for power systems, and more specifically, to a digital and intelligent capacitor power quality management method, device, and medium. Background Technology

[0002] The current methods for managing and controlling power quality in power grid capacitors are relatively traditional, mostly relying on electrical timing data of a single node for switching control. They do not take into account the regional topology of the power grid, nor do they incorporate spatial location data of each compensation node obtained by BeiDou positioning and its electrical connection relationship. This makes it impossible to fully perceive the overall operating status of the power grid, and difficult to distinguish between collaborative management and single-unit compensation adaptation scenarios under different operating conditions of the power grid. As a result, the control decisions are one-sided and lack specificity, which easily leads to problems such as low compensation matching degree and poor power quality management effect, and makes it impossible to achieve refined and intelligent reactive power compensation control. Summary of the Invention

[0003] This invention provides a digital and intelligent capacitor power quality management method, device, and medium to at least solve the technical problem that existing power quality management has poor accuracy and adaptability because the compensation and control commands do not match the actual power grid operating conditions and reactive power compensation needs due to the lack of integration of multi-source data on power grid topology information, node spatial location, and electrical connections.

[0004] According to one aspect of the present invention, in order to achieve the above-mentioned objective, a digital and intelligent capacitor power quality management method is provided, comprising: in response to a power quality management initiation signal, determining the topology information and multi-source monitoring data of a target power network area, wherein the multi-source monitoring data includes: spatial location data and electrical connection relationships of each compensation node obtained based on the BeiDou positioning system, and time-series power quality operation data of each compensation node; determining the operation characteristic information of the target power network area based on the topology information and the multi-source monitoring data, wherein the operation characteristic information includes: collaborative management status and single-unit compensation status; and in response to the operation characteristic information, generating a control instruction set, wherein the control instruction set is used to control the switching status of the target compensation equipment to adjust to a target state adapted to the target reactive power compensation strategy.

[0005] Furthermore, the operational characteristics of the target power network area are determined, including: constructing a dynamic topology graph model reflecting the spatial coupling relationship between each compensation node based on spatial location data and electrical connection relationships; extracting spatiotemporal fusion features using a pre-constructed graph-time fusion neural network model based on the dynamic topology graph model and time-series power quality operation data; and determining operational characteristics based on the spatiotemporal fusion features.

[0006] Furthermore, a dynamic topology graph model reflecting the spatial coupling relationship between each compensation node is constructed, including: defining each monitoring node in the target power network area as a graph node, wherein the monitoring node includes at least transformer nodes, distributed power generation nodes, load nodes, and capacitor bank nodes; calculating the spatial association weight between each graph node based on electrical connection relationships and spatial location data, wherein the spatial association weight includes at least electrical coupling weight and spatial geographical distance weight; and constructing a dynamic topology graph model based on the graph nodes and spatial association weights.

[0007] Furthermore, when the target power network area is a wind farm area, the monitoring nodes also include wind turbine nodes, and the spatial correlation weight also includes the spatial influence weight of wind power generation calculated based on the wake effect influence factor.

[0008] Furthermore, a pre-constructed graph-time-series fusion neural network model is used to extract spatiotemporal fusion features, including: inputting the adjacency matrix and node feature matrix of the dynamic topology graph model into the graph convolutional neural network module, performing neighborhood aggregation on the power quality features of each compensation node through graph convolution operations, and extracting a spatial feature tensor reflecting the global spatial coupling situation of the target power network area; inputting time-series power quality operation data into the bidirectional gated loop unit module, extracting historical time-series fluctuation features through the forward gated loop unit, and extracting reverse time-series dependency features through the backward gated loop unit. The reverse time-series dependency features are used to characterize the reverse change pattern of time-series data from back to front within a preset time window before the current moment; concatenating the historical time-series fluctuation features and the reverse time-series dependency features to generate a time-series dynamic feature tensor; and fusing the spatial feature tensor and the time-series dynamic feature tensor to generate spatiotemporal fusion features.

[0009] Furthermore, based on the spatiotemporal fusion characteristics, operational characteristic information is determined, including: inputting the spatiotemporal fusion characteristics into the fully connected network layer for feature dimensionality reduction and adaptive weight allocation to obtain dimensionality-reduced fusion characteristics; based on the dimensionality-reduced fusion characteristics, determining the operational characteristic information of the target power network area, which is used to characterize whether the target power network area currently meets the conditions for multi-node collaborative governance; when the conditions for multi-node collaborative governance are met, the operational characteristic information is determined to be in a collaborative governance state; when the conditions for multi-node collaborative governance are not met, the operational characteristic information is determined to be in a single-machine compensation state.

[0010] Furthermore, in response to operational characteristic information, a control instruction set is generated, including: when the operational characteristic information is in a collaborative governance state, a global optimized control instruction set is generated based on multi-source monitoring data, which is used to control multiple compensation devices in the target power network area to perform collaborative switching operations; when the operational characteristic information is in a single-unit compensation state, a local independent control instruction set is generated based on multi-source monitoring data, which is used to control a single compensation device in the target power network area to perform independent switching operations.

[0011] Furthermore, after generating the control instruction set in response to the operational characteristic information, the process also includes: acquiring real-time operating condition disturbance data of the target power network area, wherein the real-time operating condition disturbance data includes at least one of load change data, distributed power generation output fluctuation data, and wind turbine wake fluctuation data; dynamically compensating and correcting the control instruction set based on the real-time operating condition disturbance data; and updating the target status of the target compensation equipment based on the corrected control instruction set.

[0012] According to one embodiment of the present invention, a digital intelligent capacitor power quality management device is also provided, comprising:

[0013] The determination module is used to determine the topology information and multi-source monitoring data of the target power network area in response to the power quality management start signal. The multi-source monitoring data includes: spatial location data and electrical connection relationship of each compensation node obtained based on the Beidou positioning system, and time-series power quality operation data of each compensation node.

[0014] The feature module is used to determine the operational feature information of the target power network area based on topology information and multi-source monitoring data. The operational feature information includes: collaborative governance status and individual unit compensation status.

[0015] The generation module is used to generate a set of control instructions in response to the running characteristic information. The set of control instructions is used to control the switching state of the target compensation equipment to adjust to the target state that is compatible with the target reactive power compensation strategy.

[0016] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the storage medium is located to execute the above-described digital intelligent capacitor power quality management method.

[0017] This invention integrates power network topology information, BeiDou positioning node spatial and electrical correlation data, and time-series power quality multi-source monitoring data to accurately identify two types of operational characteristic states of the target power network area: collaborative governance and single-machine compensation. Based on different operational states, it generates appropriate control instruction sets to achieve precise matching between capacitor switching status and target reactive power compensation strategies. This effectively improves the comprehensiveness and accuracy of power network power quality operational status perception, optimizes capacitor reactive power compensation control precision, adapts to the governance needs of different power grid operating conditions, and realizes intelligent, refined, and efficient power quality governance. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0019] Figure 1 This is a flowchart of a digital intelligent capacitor power quality management method according to one embodiment of the present invention;

[0020] Figure 2 This is a structural block diagram of a digital intelligent capacitor power quality management device according to one embodiment of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] According to an embodiment of the present invention, a digital intelligent capacitor power quality management method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] This method embodiment can be executed in an electronic device or similar computing device that includes memory and a processor. Taking operation on a terminal as an example, the terminal may include one or more processors (processors may include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), digital signal processing (DSP) chips, microcontroller units (MCUs), field-programmable gate arrays (FPGAs), neural network processors (NPUs), tensor processors (TPUs), artificial intelligence (AI) type processors, etc.) and memory for storing data. Optionally, the terminal may also include transmission devices, input / output devices, and display devices for communication functions. Those skilled in the art will understand that the above structural description is merely illustrative and does not limit the structure of the terminal. For example, the terminal may include more or fewer components than described above, or have a different configuration than described above.

[0025] The memory can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the intelligent capacitor power quality management method in this embodiment of the invention. The processor executes various functional applications and data processing by running the computer program stored in the memory, thereby realizing the aforementioned intelligent capacitor power quality management method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0026] The transmission device is used to receive or send data via a network. Specific examples of the network mentioned above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0027] Display devices can be, for example, touchscreen liquid crystal displays (LCDs) and touch displays (also referred to as "touchscreens" or "touch displays"). The LCD allows users to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), which allows users to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. Optional human-computer interaction functions include: creating web pages, drawing, word processing, creating electronic documents, playing games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital video, playing digital music, and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0028] Figure 1 This is a flowchart of a digital intelligent capacitor power quality management method according to one embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0029] Step S110: In response to the power quality management activation signal, determine the topology information and multi-source monitoring data of the target power network area. The multi-source monitoring data includes: spatial location data and electrical connection relationships of each compensation node obtained based on the BeiDou positioning system, and time-series power quality operation data of each compensation node. The specific content is as follows:

[0030] In step S110, in this embodiment, the starting trigger condition for the execution of the governance process of the digital intelligent capacitor power quality governance method is the power quality governance start signal. The power quality governance start signal can be generated in various actual working conditions. It can be generated by the operation and maintenance personnel issuing a manual start command, or it can be automatically triggered by the power monitoring platform based on preset power quality anomaly judgment conditions such as voltage exceeding limits and reactive power deviation exceeding standards. When the system receives the power quality governance start signal, it immediately starts the basic information collection and analysis process of the target power network area.

[0031] In this embodiment, after receiving the power quality management start signal, the system first determines the topology information of the target power network area. The target power network area can be a distribution network power supply area, a wind power farm power supply area, or a local power supply network that includes distributed power sources. The topology information records the network layout of various power nodes within the target power network area, including the affiliation, network level, and basic information of various power equipment nodes such as transformers, loads, distributed power sources, and capacitor compensation devices. The topology information can be retrieved from the local power ledger database or obtained in real time through the real-time topology identification module of the power grid, thereby building the network framework foundation for subsequent data analysis.

[0032] In this embodiment, the determination of multi-source monitoring data for the target power network area is carried out simultaneously. The multi-source monitoring data is the core input data for subsequent power quality analysis. Part of the multi-source monitoring data comes from the Beidou positioning system. Each compensation node is equipped with a Beidou positioning terminal device. The Beidou positioning terminal collects the spatial location data of the corresponding compensation node in real time. The spatial location data includes the latitude and longitude coordinates, relative geographical distance and other geographical dimension information of each compensation node. Relying on the Beidou positioning system, the geographical location of the node can be obtained with high accuracy, which is not limited by the traditional method of relying solely on electrical parameters to characterize the actual spatial distribution of the node.

[0033] In this embodiment, the electrical connection relationships of each compensation node are also simultaneously sorted out based on the data collected by the Beidou positioning system. The electrical connection relationship represents the line connection method, the power supply branch to which it belongs, and the hierarchical relationship between different compensation nodes. By binding the spatial location data and the electrical connection relationship together, each compensation node has both geospatial dimension attributes and electrical topology dimension attributes, and the two types of information are no longer separated. This facilitates the subsequent evaluation of the spatial coupling and electrical coupling influence between different compensation nodes.

[0034] In this embodiment, the multi-source monitoring data also includes time-series power quality operation data of each compensation node. The time-series power quality operation data is a sequence of data continuously collected at fixed sampling time intervals. The collection objects are distributed across all compensation nodes within the target power network area. The data types collected include power quality-related operation parameters such as node voltage, current, reactive power, active power, and power factor. The time-series power quality operation data is marked and stored according to timestamps to form a sample sequence under a continuous time window, which can completely reflect the power quality fluctuations of each compensation node over time.

[0035] In this embodiment, after the system completes the acquisition of the above information, it performs data alignment processing on the topology information of the target power network area, the spatial location data and electrical connection relationship of each compensation node output by Beidou positioning, and the time-series power quality operation data of each compensation node. It completes the association matching between multi-source data according to the node number, removes missing values ​​and abnormal jump data that occur during the acquisition process, and completes basic data preprocessing. This provides a reliable data input source for subsequent identification of the operation characteristics information of the target power network area based on topology information and multi-source monitoring data.

[0036] Step S120: Based on topology information and multi-source monitoring data, determine the operational characteristic information of the target power network area. The operational characteristic information includes: collaborative governance status and individual unit compensation status, as detailed below:

[0037] In step S120, in this embodiment, after acquiring the topology information of the target power network area and completing the preprocessing of multi-source monitoring data, the system enters the operation feature information parsing stage. The operation feature information is the core judgment basis for characterizing which capacitor compensation mode is suitable for the current power network. The operation feature information is specifically divided into two categories: collaborative governance status and single-machine compensation status. The system needs to combine multi-source information from topology dimension, BeiDou spatial location dimension, and time-series operation dimension to comprehensively complete the status judgment, rather than relying solely on the electrical quantity of a single node to directly output the result.

[0038] In this embodiment, the topology information provides the basic framework of line connections, subordinate branches, and network hierarchy of each power node within the target power network. It can clarify the electrical affiliation of each compensation node in the entire power grid and distinguish whether there are direct electrical coupling paths between different compensation nodes. The multi-source monitoring data incorporates the spatial location data, electrical connection relationships, and time-series power quality operation data of each compensation node obtained from BeiDou positioning. This can reflect the differences in the geographical distribution of nodes and the time-series fluctuations of voltage, reactive power, and power factor of each node over a period of time. By combining the topology framework with the multi-source monitoring data, the joint input of three types of information—electrical topology, geospatial information, and time-series operation information—is achieved.

[0039] In this embodiment, the system uses topology information as the foundation of the network architecture, mapping spatial location data and electrical connections from multi-source monitoring data onto the topology. This binds each compensation node in the topology network with corresponding geospatial and electrical attributes, quantifying the strength of spatial and electrical coupling between different compensation nodes and avoiding mutual interference caused by ignoring geographical distribution when using only electrical data. Simultaneously, time-series power quality operation data is matched to corresponding compensation nodes, forming a time-dimensional node sample set, which can capture the fluctuation trends of power quality at each compensation node and the overall region over time.

[0040] In this embodiment, relying on a multi-dimensional input set constructed from topological information and multi-source monitoring data, the system performs feature extraction and situation analysis, comprehensively evaluating the coupling correlation between compensation nodes within the target power network area, the regional load and power fluctuation levels, and the distribution of power quality deviations at each compensation node. When the electrical and spatial coupling between multiple compensation nodes within the area is strong, and local reactive power disturbances spread along the network, affecting the power quality of multiple nodes, and the switching of a single capacitor is insufficient to eliminate the power quality deviation across the entire area, the operating characteristics of the target power network area are determined to be in a collaborative governance state. This state indicates that the current operating conditions are suitable for multiple compensation nodes to cooperate in completing joint reactive power compensation governance.

[0041] In this embodiment, after comprehensive analysis, if the coupling effect between the compensation nodes in the target power network area is weak, the power quality disturbance is limited to the local area of ​​individual nodes, and the disturbance will not spread to other compensation nodes on a large scale, the power quality anomaly can be eliminated by local adjustment of a single compensation node without the need for multiple nodes to cooperate in regulation, then the operating characteristic information of the target power network area is determined to be a single-machine compensation state, which corresponds to the local independent compensation working mode.

[0042] In this embodiment, after the output of operational feature information is completed, the collaborative governance status and single-machine compensation status are marked with corresponding status identifiers. The status identifiers are associated and bound with the current topology information and multi-source monitoring data, so that they can be directly read and called in the subsequent control instruction generation stage, providing a clear status basis for the selection of subsequent capacitor switching strategies.

[0043] Step S140: In response to the operating characteristic information, a control instruction set is generated. The control instruction set is used to adjust the switching state of the target compensation equipment to a target state that is compatible with the target reactive power compensation strategy. The specific content is as follows:

[0044] In step S140, in this embodiment, after the system completes the determination and output of the target power network area operation characteristic information, it uses the operation characteristic information as the core trigger input to start the generation process of the control instruction set. The operation characteristic information is divided into two types: collaborative governance state and single-machine compensation state. Different operation characteristic information corresponds to completely different control logic. The generated control instruction set is an executable control message sent to each target compensation device to drive the capacitor compensation device to complete the switching action, and finally make the actual working state of the device match the target state set by the target reactive power compensation strategy.

[0045] In this embodiment, the system reads the operational characteristic information that has been bound with a timestamp, and at the same time retrieves the topology information and multi-source monitoring data that have been preprocessed in the early stage as the underlying reference for command generation. It does not directly output commands based solely on the status results, but performs calculations in combination with the actual operating data of the power grid to ensure that the output control commands are consistent with the real operating conditions of the target power network area and to avoid the situation where the commands deviate from the actual operating conditions on site.

[0046] In this embodiment, when the identified operating characteristic information is in a collaborative governance state, it means that the current power grid area is suitable for multiple compensation devices to cooperate in joint power quality governance. The system is based on the time-series power quality operation data of each node in the multi-source monitoring data, the spatial location and electrical connection relationship of the node corresponding to Beidou positioning, and the topology information to carry out global reactive power optimization solution. It comprehensively weighs the electrical coupling and spatial coupling effects between each compensation node, calculates the switching control parameters corresponding to each target compensation device, and assembles them into a set of control instructions adapted to the collaborative governance working condition.

[0047] In this embodiment, when the identified operating characteristic information is a single-machine compensation state, it means that the power grid disturbance is limited to the local node range and does not require the participation of multiple devices. The system uses the local time-series power quality operation data of the corresponding compensation node as the main calculation basis, and combines the electrical attributes of the node in the topology network to perform independent reactive power compensation calculation only for the local target compensation device, and generates a set of control instructions for independent adjustment of a single device, without needing to output control actions to other compensation devices in the area.

[0048] In this embodiment, the generated control instruction set contains multiple control sub-instructions. The sub-instructions carry key control fields such as the target compensation device's device number, switching action type, action execution delay, and compensation output level. The core function of the control instruction set is to drive the target compensation device to perform switching operations, adjust the device's switching state, and make the device's actual reactive power compensation capability approach and reach the target state pre-planned by the target reactive power compensation strategy, thereby achieving the adjustment of power quality indicators such as regional voltage and power factor.

[0049] In this embodiment, after the control instruction set is generated, the system will perform boundary verification on the instruction parameters. The verification includes the upper limit of the number of switching operations allowed by the compensation device, the upper and lower limits of reactive power output, and the protection interlocking threshold. Unreasonable instructions that exceed the hardware's allowed operating range will be filtered out. Only after the control instruction set passes the verification will it be sent to the corresponding target compensation device to prevent abnormal operating conditions such as device overload and protection malfunction caused by unreasonable control instructions, and to ensure the safe and reliable execution of the control process.

[0050] Based on steps S110 to S140 above, in the embodiments of the present invention, by integrating the spatial location data of compensation nodes, electrical connection relationships, and time-series power quality operation data of each node obtained by Beidou positioning, and combining the topological structure information of the target power network area, the regional operation status can be accurately identified. It can adaptively distinguish between collaborative governance status and single-machine compensation status and generate corresponding and suitable control instruction sets, driving the switching status of the target compensation equipment to match the target reactive power compensation strategy. This breaks through the limitation of traditional single-node local compensation control ignoring the spatial correlation and electrical coupling of nodes, effectively avoiding over-compensation and under-compensation problems under multi-node operating conditions, significantly improving the accuracy and operating condition adaptability of power quality governance in the target power network area, and ensuring that power quality indicators such as regional voltage, reactive power, and power factor are stably up to standard.

[0051] The digital intelligent capacitor power quality management method of the present invention determines the operational characteristic information of the target power network area, including: constructing a dynamic topology graph model reflecting the spatial coupling relationship between each compensation node based on spatial location data and electrical connection relationship; extracting spatiotemporal fusion features using a pre-constructed graph-time fusion neural network model based on the dynamic topology graph model and time-series power quality operation data; and determining the operational characteristic information based on the spatiotemporal fusion features.

[0052] In this embodiment, when determining the operational characteristics of the target power network area, a dynamic topology graph model reflecting the spatial coupling relationship between compensation nodes is constructed based on spatial location data and electrical connection relationships. Based on the dynamic topology graph model and time-series power quality operation data, a pre-constructed graph-time-series fusion neural network model is used to extract spatiotemporal fusion features. Then, based on these spatiotemporal fusion features, the operational characteristics are determined. This embodiment uses a dynamic topology graph model to represent the spatial coupling relationship between compensation nodes and leverages a graph-time-series fusion neural network model to extract spatiotemporal fusion features to determine operational characteristics. This approach simultaneously considers the spatial electrical coupling relationship between nodes and their time-series dynamic changes, effectively improving the reliability of power network operational characteristic identification.

[0053] Specifically, a dynamic topology graph model reflecting the spatial coupling relationship between each compensation node is constructed, including: defining each monitoring node in the target power network area as a graph node, wherein the monitoring node includes at least transformer nodes, distributed power generation nodes, load nodes, and capacitor bank nodes; calculating the spatial association weight between each graph node based on electrical connection relationships and spatial location data, wherein the spatial association weight includes at least electrical coupling weight and spatial geographical distance weight; and constructing a dynamic topology graph model based on the graph nodes and spatial association weights.

[0054] In this embodiment, when constructing a dynamic topology graph model reflecting the spatial coupling relationship between compensation nodes, each monitoring node in the target power network area is defined as a graph node. These monitoring nodes include at least transformer nodes, distributed power generation nodes, load nodes, and capacitor bank nodes. Based on electrical connection relationships and spatial location data, spatial association weights between graph nodes are calculated. These spatial association weights include at least electrical coupling weights and spatial geographical distance weights. A dynamic topology graph model is then constructed based on the graph nodes and spatial association weights. This embodiment defines multiple types of power equipment as graph nodes and combines electrical connection relationships and spatial location data to calculate spatial association weights including electrical coupling weights and spatial geographical distance weights to build a dynamic topology graph model. This approach simultaneously considers electrical topology constraints and geographical spatial influences, accurately reflecting the strength of coupling between nodes.

[0055] In this embodiment, when the target power network area is a wind power generation area, the monitoring nodes also include wind turbine generator nodes, and the spatial correlation weight also includes the wind power generation spatial influence weight calculated based on the wake effect influence factor.

[0056] In this embodiment, when the target power network area is a wind farm area, the monitoring nodes also include wind turbine generator nodes, and the spatial correlation weights also include wind power spatial influence weights calculated based on the wake effect influence factor. This embodiment adds wind turbine generator nodes to the wind farm scenario and introduces wind power spatial influence weights obtained based on the wake effect influence factor. This allows the unique wake disturbance coupling effect of wind farms to be incorporated into the topology modeling considerations, improving the fit of the wind farm area topology model to actual operating conditions.

[0057] Furthermore, a pre-constructed graph-time-series fusion neural network model is used to extract spatiotemporal fusion features, including: inputting the adjacency matrix and node feature matrix of the dynamic topology graph model into the graph convolutional neural network module, performing neighborhood aggregation on the power quality features of each compensation node through graph convolution operations, and extracting a spatial feature tensor reflecting the global spatial coupling situation of the target power network area; inputting time-series power quality operation data into the bidirectional gated loop unit module, extracting historical time-series fluctuation features through the forward gated loop unit, and extracting reverse time-series dependency features through the backward gated loop unit. The reverse time-series dependency features are used to characterize the reverse change pattern of time-series data from back to front within a preset time window before the current moment; concatenating the historical time-series fluctuation features and the reverse time-series dependency features to generate a time-series dynamic feature tensor; and fusing the spatial feature tensor and the time-series dynamic feature tensor to generate spatiotemporal fusion features.

[0058] In this embodiment, a pre-constructed graph-time-series fusion neural network model is used to extract spatiotemporal fusion features, including: inputting the adjacency matrix and node feature matrix of the dynamic topology graph model into a graph convolutional neural network module, performing neighborhood aggregation on the power quality features of each compensation node through graph convolution operations, and extracting a spatial feature tensor reflecting the global spatial coupling situation of the target power network area; inputting time-series power quality operation data into a bidirectional gated loop unit module, extracting historical time-series fluctuation features through a forward gated loop unit, and extracting reverse time-series dependency features through a backward gated loop unit. The reverse time-series dependency features are used to characterize the reverse change pattern of time-series data from back to front within a preset time window before the current moment; concatenating the historical time-series fluctuation features and the reverse time-series dependency features to generate a time-series dynamic feature tensor; and fusing the spatial feature tensor and the time-series dynamic feature tensor to generate spatiotemporal fusion features. This embodiment uses a graph convolutional neural network to extract spatial features and utilizes a bidirectional gated recurrent unit to simultaneously acquire positive historical fluctuations and reverse temporal dependence features and complete spatiotemporal feature fusion. This can fully explore the spatial coupling and temporal bidirectional change patterns of power grid nodes and obtain spatiotemporal fusion features with stronger representation capabilities.

[0059] In this embodiment, based on spatiotemporal fusion features, operational characteristic information is determined, including: inputting the spatiotemporal fusion features into a fully connected network layer for feature dimensionality reduction and adaptive weight allocation to obtain dimensionality-reduced fusion features; based on the dimensionality-reduced fusion features, determining the operational characteristic information of the target power network area, which is used to characterize whether the target power network area currently meets the conditions for multi-node collaborative governance; when the conditions for multi-node collaborative governance are met, the operational characteristic information is determined to be in a collaborative governance state; when the conditions for multi-node collaborative governance are not met, the operational characteristic information is determined to be in a single-machine compensation state.

[0060] In this embodiment, operational characteristic information is determined based on spatiotemporal fusion features, including: inputting the spatiotemporal fusion features into a fully connected network layer for feature dimensionality reduction and adaptive weight allocation to obtain dimensionality-reduced fusion features; based on the dimensionality-reduced fusion features, determining the operational characteristic information of the target power network region, which characterizes whether the target power network region currently meets the conditions for multi-node collaborative governance; when the conditions for multi-node collaborative governance are met, the operational characteristic information is determined to be in a collaborative governance state; when the conditions for multi-node collaborative governance are not met, the operational characteristic information is determined to be in a single-machine compensation state. This embodiment performs dimensionality reduction and adaptive weight allocation on the spatiotemporal fusion features through a fully connected network layer, and then judges the conditions for multi-node collaborative governance based on the dimensionality-reduced fusion features, which can realize intelligent differentiation between the collaborative governance state and the single-machine compensation state, improving the intelligence level and reliability of the judgment results in the governance mode judgment.

[0061] Specifically, in response to operational characteristic information, a control instruction set is generated, including: when the operational characteristic information is in a collaborative governance state, a global optimized control instruction set is generated based on multi-source monitoring data, which is used to control multiple compensation devices in the target power network area to perform collaborative switching operations; when the operational characteristic information is in a single-machine compensation state, a local independent control instruction set is generated based on multi-source monitoring data, which is used to control a single compensation device in the target power network area to perform independent switching operations.

[0062] In this embodiment, a control instruction set is generated in response to operational characteristic information. This includes: when the operational characteristic information indicates a collaborative governance state, a globally optimized control instruction set is generated based on multi-source monitoring data. This globally optimized control instruction set is used to control multiple compensation devices in the target power network area to perform collaborative switching operations; when the operational characteristic information indicates a single-machine compensation state, a locally independent control instruction set is generated based on multi-source monitoring data. This locally independent control instruction set is used to control a single compensation device in the target power network area to perform an independent switching operation. This embodiment generates a globally optimized control instruction set and a locally independent control instruction set for the collaborative governance state and the single-machine compensation state, respectively. This allows for flexible selection of multi-device collaborative switching or single-device independent switching control methods based on the actual operating conditions of the power grid, improving the operational condition adaptability of the capacitor power quality governance control strategy.

[0063] Furthermore, after generating the control instruction set in response to the operational characteristic information, the process also includes: acquiring real-time operating condition disturbance data of the target power network area, wherein the real-time operating condition disturbance data includes at least one of load change data, distributed power generation output fluctuation data, and wind turbine wake fluctuation data; dynamically compensating and correcting the control instruction set based on the real-time operating condition disturbance data; and updating the target status of the target compensation equipment based on the corrected control instruction set.

[0064] In this embodiment, after generating the control instruction set in response to operational characteristic information, the method further includes: acquiring real-time operating condition disturbance data of the target power network area, wherein the real-time operating condition disturbance data includes at least one of load change data, distributed power generation output fluctuation data, and wind turbine wake fluctuation data; dynamically compensating and correcting the control instruction set based on the real-time operating condition disturbance data; and updating the target state of the target compensation equipment based on the corrected control instruction set. This embodiment collects various types of real-time operating condition disturbance data to dynamically compensate and correct the control instruction set and update the target state of the compensation equipment, enabling timely response to sudden power grid disturbances, reducing control deviations caused by sudden operating condition changes, and improving the anti-disturbance capability of the power quality management process.

[0065] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0066] This invention also provides a digital intelligent capacitor power quality management device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0067] Figure 2 According to one embodiment of the present invention, a digital intelligent capacitor power quality management device includes:

[0068] The determination module 201 is used to determine the topology information and multi-source monitoring data of the target power network area in response to the power quality management start signal. The multi-source monitoring data includes: spatial location data and electrical connection relationship of each compensation node obtained based on the Beidou positioning system, and time-series power quality operation data of each compensation node.

[0069] Feature module 202 is used to determine the operational feature information of the target power network area based on topology information and multi-source monitoring data. The operational feature information includes: collaborative governance status and single-unit compensation status.

[0070] The generation module 203 is used to generate a control instruction set in response to the operating characteristic information. The control instruction set is used to control the switching state of the target compensation equipment to adjust to the target state that is compatible with the target reactive power compensation strategy.

[0071] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0072] According to one embodiment of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the above-described intelligent capacitor power quality management method during operation.

[0073] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0074] Step S1: In response to the power quality management start signal, determine the topology information and multi-source monitoring data of the target power network area. The multi-source monitoring data includes: spatial location data and electrical connection relationship of each compensation node obtained based on the Beidou positioning system, and time-series power quality operation data of each compensation node.

[0075] Step S2: Based on topology information and multi-source monitoring data, determine the operational characteristic information of the target power network area, including: collaborative governance status and individual unit compensation status;

[0076] Step S3: In response to the operating characteristic information, a control instruction set is generated. The control instruction set is used to control the switching state of the target compensation equipment to adjust to the target state that is compatible with the target reactive power compensation strategy.

[0077] According to one embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the storage medium is located to execute the above-described digital intelligent capacitor power quality management method.

[0078] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0079] Step S1: In response to the power quality management start signal, determine the topology information and multi-source monitoring data of the target power network area. The multi-source monitoring data includes: spatial location data and electrical connection relationship of each compensation node obtained based on the Beidou positioning system, and time-series power quality operation data of each compensation node.

[0080] Step S2: Based on topology information and multi-source monitoring data, determine the operational characteristic information of the target power network area, including: collaborative governance status and individual unit compensation status;

[0081] Step S3: In response to the operating characteristic information, a control instruction set is generated. The control instruction set is used to control the switching state of the target compensation equipment to adjust to the target state that is compatible with the target reactive power compensation strategy.

[0082] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0083] According to one embodiment of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the above-described digital intelligent capacitor power quality management method.

[0084] Optionally, in this embodiment, the above-mentioned computer program product can be configured as a computer program that performs the following steps:

[0085] Step S1: In response to the power quality management start signal, determine the topology information and multi-source monitoring data of the target power network area. The multi-source monitoring data includes: spatial location data and electrical connection relationship of each compensation node obtained based on the Beidou positioning system, and time-series power quality operation data of each compensation node.

[0086] Step S2: Based on topology information and multi-source monitoring data, determine the operational characteristic information of the target power network area, including: collaborative governance status and individual unit compensation status;

[0087] Step S3: In response to the operating characteristic information, a control instruction set is generated. The control instruction set is used to control the switching state of the target compensation equipment to adjust to the target state that is compatible with the target reactive power compensation strategy.

[0088] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0089] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0091] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0092] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0093] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0094] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A digital and intelligent capacitor power quality management method, characterized in that, include: In response to the power quality management activation signal, the topology information and multi-source monitoring data of the target power network area are determined. The multi-source monitoring data includes: spatial location data and electrical connection relationship of each compensation node obtained based on the Beidou positioning system, and time-series power quality operation data of each compensation node. Based on the topology information and the multi-source monitoring data, the operational characteristic information of the target power network area is determined, wherein the operational characteristic information includes: collaborative governance status and single-unit compensation status; In response to the operational characteristic information, a set of control instructions is generated. The set of control instructions is used to control the switching state of the target compensation equipment to adjust to the target state that is compatible with the target reactive power compensation strategy.

2. The intelligent capacitor power quality management method according to claim 1, characterized in that, Determining the operational characteristic information of the target power network area includes: Based on the spatial location data and the electrical connection relationship, a dynamic topology model reflecting the spatial coupling relationship between each compensation node is constructed. Based on the dynamic topology graph model and the time-series power quality operation data, spatiotemporal fusion features are extracted using a pre-constructed graph-time-series fusion neural network model; Based on the spatiotemporal fusion features, the operational feature information is determined.

3. The intelligent capacitor power quality management method according to claim 2, characterized in that, Construct a dynamic topology graph model that reflects the spatial coupling relationship between the compensation nodes, including: Each monitoring node in the target power network area is defined as a graph node, wherein the monitoring node includes at least transformer nodes, distributed power generation nodes, load nodes, and capacitor bank nodes; Based on the electrical connection relationship and the spatial location data, calculate the spatial association weight between each graph node, wherein the spatial association weight includes at least electrical coupling weight and spatial geographical distance weight; The dynamic topology graph model is constructed based on the graph nodes and the spatial association weights.

4. The intelligent capacitor power quality management method according to claim 3, characterized in that, When the target power network area is a wind farm area, the monitoring node also includes a wind turbine node, and the spatial correlation weight also includes the wind power spatial influence weight calculated based on the wake effect influence factor.

5. The intelligent capacitor power quality management method according to claim 2, characterized in that, Spatiotemporal fusion features are extracted using a pre-built graph temporal fusion neural network model, including: The adjacency matrix and node feature matrix of the dynamic topology graph model are input into the graph convolutional neural network module. The power quality features of each compensation node are aggregated in the neighborhood through graph convolution operation to extract the spatial feature tensor that reflects the global spatial coupling situation of the target power network area. The time-series power quality operation data is input into the bidirectional gated loop unit module. The historical time-series fluctuation characteristics are extracted through the forward gated loop unit, and the reverse time-series dependency characteristics are extracted through the backward gated loop unit. The reverse time-series dependency characteristics are used to characterize the reverse change pattern of time-series data from back to front within a preset time window before the current moment. The historical temporal fluctuation features are concatenated with the inverse temporal dependency features to generate a temporal dynamic feature tensor; The spatial feature tensor and the temporal dynamic feature tensor are fused to generate the spatiotemporal fusion feature.

6. The intelligent capacitor power quality management method according to claim 2, characterized in that, Based on the spatiotemporal fusion features, the operational feature information is determined, including: The spatiotemporal fusion features are input into a fully connected network layer for feature dimensionality reduction and adaptive weight allocation to obtain dimensionality-reduced fusion features. Based on the dimensionality reduction and fusion features, the operational characteristic information of the target power network area is determined. The operational characteristic information is used to characterize whether the target power network area currently meets the conditions for multi-node collaborative governance. When the multi-node collaborative governance conditions are met, the operational characteristic information is determined to be the collaborative governance state; When the conditions for multi-node collaborative governance are not met, the operational characteristic information is determined to be the single-machine compensation state.

7. The intelligent capacitor power quality management method according to claim 1, characterized in that, In response to the operational characteristic information, a set of control instructions is generated, including: When the operational characteristic information is the collaborative governance state, a global optimization control instruction set is generated based on the multi-source monitoring data. The global optimization control instruction set is used to control multiple compensation devices in the target power network area to perform collaborative switching operations. When the operating characteristic information is the single-machine compensation state, a local independent control instruction set is generated based on the multi-source monitoring data. The local independent control instruction set is used to control a single compensation device in the target power network area to perform independent switching operations.

8. The intelligent capacitor power quality management method according to claim 1, characterized in that, After generating the control instruction set in response to the aforementioned operational characteristic information, the method further includes: Acquire real-time operating condition disturbance data of the target power network area, wherein the real-time operating condition disturbance data includes at least one of load change data, distributed power generation output fluctuation data, and wind turbine wake fluctuation data; Based on the real-time operating condition disturbance data, the control instruction set is dynamically compensated and corrected. Based on the revised set of control instructions, the target state of the target compensation device is updated.

9. A digital intelligent capacitor power quality management device, characterized in that, include: The determination module is used to determine the topology information and multi-source monitoring data of the target power network area in response to the power quality management start signal. The multi-source monitoring data includes: spatial location data and electrical connection relationship of each compensation node obtained based on the Beidou positioning system, and time-series power quality operation data of each compensation node. The feature module is used to determine the operational feature information of the target power network area based on the topology information and the multi-source monitoring data, wherein the operational feature information includes: collaborative governance status and single-unit compensation status; The generation module is used to generate a set of control instructions in response to the operating characteristic information. The set of control instructions is used to control the switching state of the target compensation equipment to adjust to the target state that is compatible with the target reactive power compensation strategy.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the digital intelligent capacitor power quality management method of any one of claims 1 to 8.

Images