Power grid security assurance scheduling method and system for cloud computing-assisted line loss monitoring and positioning

Abstract

The invention relates to the related technical field of line loss monitoring, in particular to a power grid safety guarantee scheduling method and system for line loss monitoring and positioning assisted by cloud computing, and the method comprises the steps: connecting a plurality of intelligent power distribution terminals in a target power supply region, configuring a safety regulation and control instruction, and combining the operation data of a power distribution network, and predicting a line loss distribution change trend by using a multi-source line loss coupling model, and configuring an operation mode optimization scheme of the power distribution network in the target power supply area. The method solves the technical problems that mutual influence among loss such as lead resistance loss, transformer iron loss and copper loss cannot be quantified, minimization of the line loss rate is taken as a unique target, and the adaptability of an operation scheduling scheme of a power distribution network is insufficient, realizes a combined target of the line loss rate, the voltage qualification rate and the like, dynamically distributes weights, and improves the reliability of the power distribution network. A sensitive load power guarantee demand screening scheme is combined, the coupling relation of each loss component is accurately simulated, a prediction result is dynamically updated in combination with a sliding time window, the line loss distribution trend prediction error is reduced, and the power supply reliability is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of line loss monitoring, and particularly relates to a power grid safety guarantee dispatching method and system assisted by cloud computing for line loss monitoring and positioning. BACKGROUND

[0002] With the large-scale access of distributed power sources, energy storage devices, electric vehicles and other multi-element loads, the distribution network presents a multi-element collaborative form of source, network, load and storage. As a core index for measuring the operation efficiency of the power grid, the monitoring accuracy and control ability of line loss are directly related to the energy utilization efficiency and the safety and stability of the power grid. The distribution network dispatching needs to reduce line loss while meeting the multi-element demands such as sensitive load power protection and new energy consumption. Through the collaborative linkage of the cloud and the terminal, precise line loss monitoring and dispatching optimization are achieved, which is the key to promoting the transformation of the distribution network from extensive dispatching to lean control, and is significant for improving the safety guarantee capability of the power grid and realizing efficient energy utilization.

[0003] The current line loss monitoring and positioning and safety dispatching method of the distribution network restricts the improvement of the operation efficiency of the power grid. The isolated analysis of line loss components such as conductor resistance loss and transformer loss cannot accurately simulate the mutual influence between the loss components. The line loss prediction deviation is large. The operation data of the distribution network is dispersed in each terminal. Although the high-loss branch can be identified, the line loss monitoring results are not deeply integrated with the operation mode optimization. The dispatching scheme lacks pertinence, and the line loss treatment effect is limited, which seriously affects the safe operation of the power grid. In addition, the dispatching scheme mainly minimizes the line loss rate as the only target. The optimization target is single and has poor adaptability. Key indicators such as voltage qualification rate and power supply reliability are ignored, and the complex power grid scene cannot be adapted.

[0004] In summary, the prior art has the technical problems of being unable to quantify the mutual influence between conductor resistance loss, transformer iron loss and copper loss and other losses, taking minimization of line loss rate as the only target, and poor adaptability of the operation dispatching scheme of the distribution network. SUMMARY

[0005] The present application provides a power grid safety guarantee dispatching method and system assisted by cloud computing for line loss monitoring and positioning, aiming to solve the technical problems of being unable to quantify the mutual influence between conductor resistance loss, transformer iron loss and copper loss and other losses, taking minimization of line loss rate as the only target, and poor adaptability of the operation dispatching scheme of the distribution network in the prior art.

[0006] In view of the above problems, the technical scheme of the present application is: The first aspect of the application provides a power grid safety guarantee scheduling method for cloud computing assisted line loss monitoring and positioning, wherein the method comprises: collecting power distribution network operation data, the power distribution network operation data comprising feeder current, bus voltage, power factor and harmonic distortion rate; constructing a multi-source line loss coupling model, the multi-source line loss coupling model being used to simulate the coupling influence relationship between conductor resistance loss, transformer iron loss and copper loss, reactive power flow loss and harmonic additional loss; connecting a plurality of intelligent power distribution terminals in a target power supply area, and configuring safety control instructions; predicting line loss distribution trend using the multi-source line loss coupling model based on the power distribution network operation data and the safety control instructions; and configuring an operation mode optimization scheme of the power distribution network in the target power supply area according to the line loss distribution trend prediction result, including reactive power compensation switching strategy, tie switch state adjustment and transformer tap position setting.

[0007] Preferably, the multi-source line loss coupling model is trained based on a training data set; and the line loss distribution trend prediction result is dynamically updated using a sliding time window mechanism.

[0008] Preferably, historical operation data in the target power supply area is obtained; based on the historical operation data, historical line loss components are decomposed to separate out basic resistance loss, dynamic reactive power loss and harmonic additional loss components, and the training data set is constructed.

[0009] Preferably, an edge intelligent terminal cluster is deployed in the target power supply area; based on the edge intelligent terminal cluster, a plurality of local power distribution network control strategies are generated, and bidirectional data synchronization is performed with a cloud scheduling center; and the global operation mode optimization scheme is determined by fusing the plurality of local power distribution network control strategies.

[0010] Preferably, line loss rate minimization, voltage qualification rate maximization and power supply reliability index are taken as joint optimization objectives; the joint optimization objectives are dynamically weighted based on the power distribution network operation data to generate a plurality of candidate scheduling schemes; and the global operation mode optimization scheme is determined by comprehensively evaluating the plurality of candidate scheduling schemes.

[0011] Preferably, the plurality of candidate scheduling schemes are prioritized based on sensitive load distribution data and power protection level requirements to set a first screening condition under sensitive load power protection requirements.

[0012] Preferably, high loss branches and high risk nodes are marked, grid key monitoring points are identified, and electrical characteristics corresponding to the grid key monitoring points are determined; the plurality of candidate scheduling schemes are secondarily screened based on the electrical characteristics corresponding to the grid key monitoring points to set a second screening condition.

[0013] In a second aspect, the application provides a power grid safety guarantee scheduling system for cloud computing assisted line loss monitoring and positioning, wherein the system comprises: a power distribution network operation data acquisition module, configured to acquire power distribution network operation data, the power distribution network operation data comprising feeder current, bus voltage, power factor and harmonic distortion rate; a multi-source line loss coupling model construction module, configured to construct a multi-source line loss coupling model, the multi-source line loss coupling model being used to simulate the coupling influence relationship between conductor resistance loss, transformer iron loss and copper loss, reactive power flow loss and harmonic additional loss; a safety control instruction configuration module, configured to connect a plurality of intelligent power distribution terminals in a target power supply area, and configure safety control instructions; a line loss distribution change trend prediction module, configured to predict the line loss distribution change trend based on the power distribution network operation data, the safety control instructions and the multi-source line loss coupling model; and an operation mode optimization scheme configuration module, configured to configure an operation mode optimization scheme of the power distribution network in the target power supply area according to the line loss distribution change trend prediction result, including reactive power compensation switching strategy, tie switch state adjustment and transformer tap position setting.

[0014] In summary, the one or more technical solutions provided in the application achieve the technical effect of taking line loss rate, voltage qualification rate and the like as joint targets and dynamically allocating weights, screening schemes in combination with sensitive load power protection demand, accurately simulating coupling relationships of various loss components, dynamically updating prediction results in combination with a sliding time window, reducing line loss distribution trend prediction error and improving power supply reliability. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only exemplary, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0016] Figure 1 A flowchart of a power grid safety guarantee scheduling method for cloud computing assisted line loss monitoring and positioning is provided for the application.

[0017] Figure 2 A structure diagram of a power grid safety guarantee scheduling system for cloud computing assisted line loss monitoring and positioning is provided for the application.

[0018] Legend: power distribution network operation data acquisition module 11, multi-source line loss coupling model construction module 12, safety control instruction configuration module 13, line loss distribution change trend prediction module 14, and operation mode optimization scheme configuration module 15. DETAILED DESCRIPTION

[0019] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0020] Example 1: The present application will be described in detail below with reference to the accompanying drawings, as follows... Figure 1 As shown, this application provides a power grid safety assurance dispatching method for cloud computing-assisted line loss monitoring and location, the method comprising: Data on the operation of the power distribution network is collected, including feeder current, bus voltage, power factor, and harmonic distortion rate. A multi-source line loss coupling model is constructed to simulate the coupling effect between conductor resistance loss, transformer iron and copper losses, reactive power flow loss, and harmonic additional loss.

[0021] In one embodiment, collecting distribution network operation data refers to collecting key electrical parameter data generated during the operation of the distribution network through devices such as sensors and smart meters; feeder current refers to the current value flowing through the feeder of the distribution network, reflecting the load condition of the line; bus voltage is the voltage level on the bus, reflecting the power supply quality of the power grid; power factor is the ratio of actual power to apparent power in the power grid, reflecting the power utilization efficiency of the power grid; harmonic distortion rate is the ratio of harmonic voltage or current to fundamental voltage or current in the power grid, used to assess the power quality of the power grid; the multi-source line loss coupling model can comprehensively consider the mutual influence between various line loss components such as conductor resistance loss, transformer iron loss and copper loss, reactive power flow loss, and harmonic additional loss; the coupling influence relationship means that these line loss components do not exist in isolation, but interact and influence each other. For example, reactive power flow loss will affect the copper loss of the transformer, and an increase in harmonic distortion rate will lead to an increase in conductor resistance loss.

[0022] Optionally, by deploying sensors and smart meters at key nodes of the distribution network, data such as feeder current, bus voltage, power factor, and harmonic distortion rate can be collected. Furthermore, key nodes of the distribution network include substations, distribution lines, and user terminals. If the data collected in the distribution network shows that a certain section of feeder has a high current value and a low power factor, it means that there is a large reactive power loss in that section of the line.

[0023] By using a multi-source line loss coupling model, the mutual influence relationship between conductor resistance loss, transformer iron loss and copper loss, reactive power flow loss and harmonic additional loss is quantified and simulated. It is determined that under specific current and voltage conditions, the transformer copper loss changes with the reactive power flow. This simulation of the coupling relationship makes line loss prediction more scientific and accurate, and can more comprehensively reflect the actual operation of the distribution network. These data provide support for operation mode optimization, enabling dispatching schemes to be more precisely targeted at actual problems, thereby effectively reducing line losses and improving power grid operation efficiency.

[0024] Connect multiple smart distribution terminals within the target power supply area and configure safety control commands; based on the power distribution network operation data and the safety control commands, use the multi-source line loss coupling model to predict the trend of line loss distribution changes; according to the prediction results of the line loss distribution trend changes, configure an optimization scheme for the operation mode of the power distribution network within the target power supply area, including reactive power compensation switching strategy, tie switch status adjustment and transformer tap position setting.

[0025] In one embodiment, multiple smart distribution terminals within the target power supply area refer to intelligent devices installed in the power distribution network, possessing data acquisition, communication, and control functions. These smart distribution terminals can monitor the power grid's operating status in real time and execute dispatch instructions. Connecting multiple smart distribution terminals means integrating them into a unified dispatch system through a communication network to achieve data sharing and collaborative control. Configuring safety control instructions refers to setting specific control instructions for the smart distribution terminals according to the safety requirements of power grid operation, including adjusting equipment operating parameters and controlling switch states, with the aim of ensuring that the power grid operates in a safe and stable state.

[0026] Line loss distribution trend prediction refers to predicting the trend of line loss under different operating conditions based on a multi-source line loss coupling model, combined with real-time collected distribution network operation data and safety control instructions. This includes changes in the total amount of line loss and the distribution of line loss in different areas and on different equipment. Operation mode optimization scheme refers to formulating specific power grid operation optimization strategies based on the predicted line loss distribution trend. These strategies include reactive power compensation switching strategies, tie switch status adjustments, and transformer tap settings. Furthermore, reactive power compensation switching strategies optimize the power factor of the power grid by switching reactive power compensation devices. Tie switch status adjustments optimize the topology of the power grid by changing the status of tie switches. Transformer tap settings optimize the voltage level by adjusting transformer taps. Essentially, this involves changing the turns ratio of the high-voltage or low-voltage windings to achieve step-wise regulation of the output voltage, thereby suppressing additional line losses caused by voltage deviation.

[0027] Optionally, within the target power supply area, multiple smart distribution terminals are connected to the cloud dispatch center via a communication network. These smart distribution terminals can collect real-time power grid operation data and upload it to the cloud. Simultaneously, the dispatch center sends safety control commands to the terminals according to the power grid's safe operation requirements. Specifically, if the smart terminals detect that the voltage in a certain area is too low, the dispatch center can send commands to the smart terminals in that area to adjust the switching status of the reactive power compensation device to improve the voltage level. This connection and command configuration mechanism enables coordinated action between the cloud and the terminals, ensuring that the power grid operates in a safe and stable state.

[0028] Based on the collected distribution network operation data and safety control instructions, a multi-source line loss coupling model is used to predict the trend of line loss distribution changes, providing a basis for subsequent optimization schemes. This allows for the early detection of potential line loss problems, improving the foresight and targeting of dispatching. Based on the predicted trend of line loss distribution changes, specific operation mode optimization schemes are formulated. Furthermore, the following optimization measures are taken: First, the switching strategy of reactive power compensation devices is adjusted to increase reactive power compensation capacity, improve the power factor, and reduce reactive power flow losses; second, the status of tie switches is adjusted from closed to open, optimizing the grid topology and reducing conductor resistance losses; third, the transformer tap position is adjusted, increasing the bus voltage by one tap and reducing transformer copper losses. Preferably, these optimization measures effectively reduce line losses, improve grid operating efficiency, and ensure the safe and stable operation of the grid.

[0029] Furthermore, this application provides a method for constructing a multi-source line loss coupling model, the method comprising: The multi-source line loss coupling model is trained based on the training dataset; at the same time, a sliding time window mechanism is used to dynamically update the prediction results of the line loss distribution change trend.

[0030] In one embodiment, the training dataset refers to the dataset used to train the multi-source line loss coupling model, including historical operating data and corresponding line loss data. Through decomposition and organization, it can reflect the relationship between different line loss components, providing a foundation for model training. Furthermore, the historical operating data includes historical current, voltage, and power factor, while different line loss components include basic resistance loss, dynamic reactive power loss, and harmonic-added loss. The sliding time window mechanism refers to setting a fixed time window, which slides forward continuously over time, updating the data within the window, thereby reflecting changes in the power grid operating status in real time and ensuring the timeliness and accuracy of line loss prediction results.

[0031] Optionally, historical operating data can be obtained from the target power supply area, including parameters such as feeder current, bus voltage, power factor, and harmonic distortion rate, as well as corresponding line loss data. By analyzing and decomposing this historical data, components such as basic resistance loss, dynamic reactive power loss, and harmonic additional loss can be separated to construct a training dataset. Through data analysis, basic resistance loss, dynamic reactive power loss, and harmonic additional loss are decomposed, and these data are organized into a training dataset for training the multi-source line loss coupling model.

[0032] In the training process of the multi-source line loss coupling model, machine learning algorithms, including neural networks and support vector machines, are used to fit the training dataset and establish the coupling relationship between various line loss components. Furthermore, through neural network training, the model learns the mutual influence relationship between various line loss components under different current, voltage, and power factor conditions. This training process based on historical data enables the model to accurately simulate the coupling relationship of line losses, providing a basis for line loss prediction. The operating state of the power grid is dynamically changing, so it is necessary to update the prediction results of the line loss distribution trend in real time. The sliding time window mechanism sets a fixed time window, and as time goes by, the window slides forward continuously, updating the data within the window. Based on this data, the trained multi-source line loss coupling model is used to predict the line loss distribution trend. As time goes by, the window slides to the next hour, new data enters the window, and the multi-source line loss coupling model re-predicts based on the new data, updating the line loss distribution trend.

[0033] Preferably, by using a sliding time window mechanism, it is found that as the charging load of electric vehicles in a certain area increases, the feeder current gradually rises, leading to an increase in conductor resistance loss. By updating the prediction results in a timely manner, the dispatching system can adjust the switching strategy of reactive power compensation devices in advance, optimize the power grid operation mode, and thus effectively reduce line losses and improve the power grid operation efficiency and safety. This dynamic update mechanism can reflect the changes in the power grid operation status in real time, ensuring the timeliness and accuracy of the line loss prediction results.

[0034] Furthermore, this application provides a method based on a training dataset, the method comprising: Acquire historical operating data within the target power supply area; based on the historical operating data, decompose the historical line loss components to separate the basic resistance loss, dynamic reactive power loss, and harmonic additional loss components, and construct the training data set.

[0035] In one embodiment, acquiring historical operating data within the target power supply area refers to collecting operating data from past periods from devices such as the power grid management system, smart meters, and sensors within the target power supply area. This historical operating data includes electrical parameters such as feeder current, bus voltage, power factor, and harmonic distortion rate, as well as corresponding line loss data, reflecting the state of the power grid under different operating conditions. Historical line loss component decomposition refers to the process of analyzing historical line loss data and separating different line loss components. Basic resistance loss refers to energy loss caused by conductor resistance, which is proportional to the square of the current. Dynamic reactive power loss refers to loss caused by reactive power flow, which is closely related to voltage and power factor. Harmonic-induced additional loss refers to extra loss caused by harmonic current or voltage, which is related to the harmonic distortion rate in the power grid. By decomposing these line loss components, the relationships between the components can be understood more clearly, providing support for constructing a training dataset.

[0036] Optionally, historical operating data from the past year can be extracted from the power grid management system of the target power supply area, including parameters such as feeder current, bus voltage, power factor, and harmonic distortion rate. This reflects the state of the distribution network under different operating conditions and provides a basis for decomposing line loss components. By collecting this data, a comprehensive understanding of the historical operation of the power grid can be obtained, providing rich information for model training and optimization. Mathematical models and algorithms can be used to decompose historical line loss data, separating basic resistance loss, dynamic reactive power loss, and harmonic additional loss components. This decomposition process makes the relationship between the various line loss components clearer, providing a basis for constructing a training dataset.

[0037] By decomposing historical line loss components, a training dataset containing different line loss components and their corresponding operating parameters is constructed. This training dataset provides rich samples for training the multi-source line loss coupling model, enabling the model to learn the coupling relationships between various line loss components, thereby improving the accuracy and scientific nature of line loss prediction. Furthermore, through the training dataset, the model learns the mutual influence relationship between reactive power flow loss and base resistance loss under different power factor and voltage conditions, providing strong support for line loss prediction and power grid operation optimization.

[0038] Furthermore, this application provides an optimization scheme for the operation mode of the distribution network within the target power supply area, the method comprising: Within the target power supply area, an edge intelligent terminal cluster is deployed; based on the edge intelligent terminal cluster, multiple local distribution network control strategies are generated and bidirectional data synchronization is performed with the cloud dispatch center; the multiple local distribution network control strategies are integrated to determine the global operation mode optimization scheme.

[0039] In one embodiment, an edge intelligent terminal cluster refers to a group of intelligent terminal devices deployed at the edge layer of a power distribution network. These devices have data acquisition, processing, and control functions, enabling them to monitor the operating status of the local power grid in real time and execute local control strategies. Through distributed deployment, the edge intelligent terminal cluster can achieve rapid response and refined management of the local power distribution network. The local power distribution network control strategy refers to the optimization strategy formulated for the local power distribution network area. These strategies are based on the local data collected by the edge intelligent terminals and take into account the operating characteristics and needs of the local power grid, such as reactive power compensation, voltage regulation, and load balancing. The purpose of the local control strategy is to optimize the operating efficiency and reliability of the local power grid.

[0040] Two-way data synchronization refers to the data interaction between the edge intelligent terminal cluster and the cloud dispatch center. The cloud dispatch center can send global control commands to the edge terminals, and the edge terminals will feed back local control strategies and operating data to the cloud in real time, realizing two-way information flow and collaborative optimization. The global operation mode optimization scheme refers to the optimal operation scheme covering the entire target power supply area after comprehensively considering multiple local control strategies. The global operation mode optimization scheme achieves the optimal operation of the overall power grid by integrating local strategies and balancing global indicators such as line loss, voltage qualification rate, and power supply reliability.

[0041] Optionally, within the target power supply area, multiple edge intelligent terminals are deployed according to the topology and operational requirements of the distribution network. These edge intelligent terminals are distributed at key nodes such as substations, distribution lines, and user terminals, covering different user areas and key nodes. They can collect local power grid operation data in real time, such as current, voltage, and power factor. Each terminal can independently monitor the operating status of its area and execute local control strategies according to preset rules, such as adjusting the switching status of reactive power compensation devices to optimize the power factor of the local power grid.

[0042] Based on local data collected by the edge intelligent terminal cluster, multiple local control strategies are generated. Furthermore, the edge terminal detects that the voltage in its area is low. By analyzing the data, the edge intelligent terminal generates a local control strategy, suggesting increasing the switching capacity of the reactive power compensation device to improve the voltage level. At the same time, the terminal synchronizes this control strategy and related data to the cloud dispatch center. The cloud dispatch center then sends global control instructions to the edge terminal according to the global operation objectives, adjusting the status of the tie switch to optimize the power grid topology. Through bidirectional data synchronization, the edge terminal and the cloud dispatch center can exchange information in real time, achieving coordinated optimization of local and global aspects.

[0043] The cloud-based dispatch center receives local control strategies from multiple edge intelligent terminals and performs fusion analysis on these strategies. Furthermore, considering three local regions within the distribution network, each region's edge terminals generate local control strategies: Region 1 suggests increasing reactive power compensation capacity to improve the power factor; Region 2 suggests adjusting transformer taps to optimize voltage levels; and Region 3 suggests changing the tie switch status to reduce line losses. The cloud-based dispatch center comprehensively considers these local strategies and, combined with global operational goals, generates a global operational optimization scheme through an optimization algorithm. Specifically, the determined global optimization scheme includes: increasing reactive power compensation capacity in Region 1; adjusting transformer taps upwards in Region 2; and changing the tie switch status in Region 3 to optimize the grid topology. By fusing these local strategies, the global optimization scheme can balance the needs of each local region, achieving optimal operation of the entire distribution network and improving grid operating efficiency and reliability.

[0044] Furthermore, this application provides a method for determining an optimized global operation mode by integrating the aforementioned multiple local distribution network control strategies, the method comprising: Minimizing line loss rate, maximizing voltage qualification rate, and power supply reliability indicators are taken as joint optimization objectives; based on the power distribution network operation data, the joint optimization objectives are dynamically weighted to generate multiple candidate scheduling schemes; the multiple candidate scheduling schemes are comprehensively evaluated to determine the global operation mode optimization scheme.

[0045] In one embodiment, the joint optimization objective refers to considering multiple objectives simultaneously during the optimization process. These objectives are typically interrelated and may conflict, including minimizing line loss rate, maximizing voltage qualification rate, and optimizing power supply reliability indicators. These objectives collectively determine the overall performance of the power grid operation. Minimizing line loss rate reduces power grid operating costs, maximizing voltage qualification rate improves power supply quality, and optimizing power supply reliability indicators reduces outage time and improves user satisfaction. Dynamic weight allocation refers to assigning different weights to each optimization objective based on real-time power grid operation data and specific scenario requirements. The dynamic adjustment of weights allows the optimization process to flexibly respond to different operating conditions and priority requirements. Candidate scheduling schemes refer to multiple possible power grid operation schemes generated based on the joint optimization objective and dynamic weight allocation. Each scheme attempts to find a balance between different objectives, but the specific optimization direction and effect differ. Comprehensive evaluation refers to a comprehensive analysis and comparison of multiple candidate scheduling schemes, considering the degree to which each scheme meets the joint optimization objective, and determining the optimal global operation mode optimization scheme. Comprehensive evaluation typically involves multiple indicator evaluation methods, such as the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation.

[0046] Optionally, minimizing line loss rate, maximizing voltage qualification rate, and optimizing power supply reliability indicators can be used as joint optimization objectives. These reflect the economy, power quality, and reliability of power grid operation and are key indicators for measuring power grid performance. Furthermore, minimizing line loss rate can reduce power grid operating costs and improve energy utilization efficiency; maximizing voltage qualification rate can ensure stable voltage at the user end and improve power supply quality; and optimizing power supply reliability indicators can reduce power outage time and improve user satisfaction. By incorporating these objectives into the joint optimization framework, the overall power grid operation status can be optimized.

[0047] Based on real-time collected power distribution network operation data, the weights of the joint optimization objectives are dynamically adjusted. Furthermore, the power distribution network operation data includes current, voltage, and power factor. When the grid load is high and the voltage fluctuation is large, the weight of the voltage qualification rate can be increased to ensure power supply quality. During periods of low load, the weight of the line loss rate can be appropriately increased to further reduce operating costs. According to the dynamic weight allocation, multiple candidate scheduling schemes are generated using optimization algorithms including genetic algorithms and particle swarm optimization. Each scheme attempts to find a balance between different objectives, and the specific optimization direction and effect are different.

[0048] Multiple candidate scheduling schemes are comprehensively evaluated, considering the degree to which each scheme meets the joint optimization objective. Furthermore, the analytic hierarchy process (AHP) is used to evaluate the candidate schemes, employing line loss rate, voltage qualification rate, and power supply reliability as evaluation indicators. A comprehensive score for each scheme is calculated based on dynamic weight allocation. By comparing the comprehensive scores, the scheme with the highest score is selected as the global operation optimization scheme. Through comprehensive evaluation, the optimized scheme can be ensured to achieve the best balance between economy, power quality, and reliability, thereby realizing the global optimized operation of the power grid. Preferably, this improves the economy and reliability of power grid operation. Through dynamic weight allocation and comprehensive evaluation, the flexibility and adaptability of the optimized scheme are enhanced, enabling it to better cope with complex and ever-changing power grid operation scenarios.

[0049] Furthermore, this application provides a method for dynamically assigning weights to the joint optimization objective to generate multiple candidate scheduling schemes, the method comprising: Based on the distribution data of sensitive loads and the power supply guarantee level requirements, the multiple candidate scheduling schemes are prioritized, and the first screening condition under the power supply guarantee requirements of sensitive loads is set.

[0050] In one embodiment, sensitive load distribution data refers to the distribution of loads in the power grid that have high requirements for power quality and reliability, such as hospitals, data centers, and important industrial users. This includes information such as their geographical location, electricity demand, and power supply lines. This data is used to identify which areas or users in the power grid have special requirements for the stability and quality of power supply. Power supply guarantee level requirements refer to the requirements for classifying the power supply guarantee level based on the importance and sensitivity of users' electricity consumption. The power supply guarantee level directly affects the formulation of power grid operation optimization schemes, ensuring that the power supply needs of high-priority users are met first. Priority ranking refers to the process of ranking multiple candidate scheduling schemes based on sensitive load distribution data and power supply guarantee level requirements. Schemes with higher priority can better meet the power supply guarantee needs of sensitive loads, ensuring the safety and quality of power supply for users. When comprehensively evaluating candidate scheduling schemes, the first screening condition is based on the power supply guarantee needs of sensitive loads, used to initially screen out scheduling schemes that meet the high-priority power supply guarantee requirements.

[0051] Optionally, during the power grid operation optimization process, the distribution data of sensitive loads are collected, including their location, power demand, and power supply line information; based on the sensitive load distribution data and power supply level requirements, combined with the power grid topology and real-time operating status, the impact of each candidate dispatching scheme on the power supply guarantee of sensitive loads is analyzed; and based on the power supply level requirements of sensitive loads, multiple candidate dispatching schemes are prioritized.

[0052] A first screening condition is set based on the power supply requirements of sensitive loads. Furthermore, when comprehensively evaluating candidate dispatch schemes, this first screening condition is applied. The first screening condition requires that candidate schemes must meet the power supply requirements of high-priority sensitive loads, thus initially screening out dispatch schemes that can meet the power supply requirements of sensitive loads. Preferably, by prioritizing sensitive loads based on their distribution data and power supply level requirements, and setting the first screening condition, it is possible to ensure that the power grid operation optimization scheme first meets the power supply needs of high-priority users, improving the reliability and security of power grid operation, while also providing support for comprehensive optimization decisions.

[0053] Furthermore, the method described in this application also includes: High-loss branches and high-risk nodes are marked, key power grid monitoring points are identified, and the electrical characteristics corresponding to the key power grid monitoring points are determined. Based on the electrical characteristics corresponding to the key power grid monitoring points, the multiple candidate scheduling schemes are screened a second time, and a second screening condition is set.

[0054] In one embodiment, a high-loss branch refers to a line or branch in the power grid with high line loss, usually caused by excessive current, high conductor resistance, or unreasonable reactive power flow. Marking high-loss branches helps to identify the main energy loss points in the power grid. A high-risk node refers to a critical node in the power grid that may cause power outages or power quality degradation due to faults, voltage instability, or other abnormal conditions. It is usually located in areas with concentrated loads or in critical positions in the power grid topology.

[0055] Key power grid monitoring points refer to monitoring locations that have a significant impact on the power grid's operating status, including high-loss branches, high-risk nodes, and sensitive load connection points. The electrical characteristics of key power grid monitoring points can reflect the overall operating status of the power grid. Furthermore, electrical characteristics include voltage, current, and power factor. Electrical characteristics refer to the electrical parameters of key power grid monitoring points, used to evaluate the operating status of the power grid and the effectiveness of optimized dispatching schemes, including voltage level, current magnitude, power factor, and harmonic content. The second screening condition refers to further screening candidate dispatching schemes based on the first screening condition, ensuring that the optimized scheme can effectively improve the weak links of the power grid based on the electrical characteristics of the key power grid monitoring points.

[0056] Optionally, during power grid operation, high-loss branches and high-risk nodes are marked through real-time monitoring and data analysis. Furthermore, data collected by smart terminals is used to analyze the line loss of each branch. If a branch has a significantly higher line loss rate than other branches, it is marked as a high-loss branch. At the same time, through fault prediction and voltage stability analysis, nodes that cause power outages due to faults or voltage fluctuations are identified and marked as high-risk nodes.

[0057] Identifying key monitoring points in the power grid and determining their corresponding electrical characteristics includes: identifying key monitoring points in the power grid, including the ends of long-distance feeders, the low-voltage side of heavy-load transformers, harmonic source access points, and tie switch nodes; analyzing the active power flow, reactive power compensation gap, and three-phase imbalance at key monitoring points in high-loss branches, and configuring a first feature vector corresponding to the key monitoring point; analyzing the voltage over-limit duration, short-circuit capacity margin, and total harmonic distortion rate at key monitoring points in high-risk nodes, and configuring a second feature vector corresponding to the key monitoring point; and fusing the first and second feature vectors to determine the electrical characteristics corresponding to the key monitoring points in the power grid.

[0058] Identify key monitoring points in the power grid, including the starting and ending points of high-loss branches, high-risk nodes, and sensitive load access points. For example, a high-loss branch might start at a substation outlet and end in an industrial park; a high-risk node might be a distribution node in a large commercial area; and a sensitive load access point might be the power supply inlet for a hospital. Determine the electrical characteristics of these key monitoring points, such as voltage level, current magnitude, power factor, and harmonic content. Perform a second screening based on these electrical characteristics, setting second screening criteria. Based on these characteristics, further screen the candidate dispatch schemes from the initial screening. For example, after the first screening criteria, two candidate dispatch schemes remain: Scheme A: Prioritizes power supply to sensitive loads, but the optimization effect on high-loss branches is generally limited; Scheme B: While ensuring power supply to sensitive loads, optimizes the line loss of high-loss branches, but slightly affects the voltage stability of high-risk nodes.

[0059] Based on the electrical characteristics of key power grid monitoring points, a second screening condition is set. Candidate schemes can reduce the line loss rate of high-loss branches and ensure that voltage fluctuations at high-risk nodes are within a limited range. By comparing schemes A and B, it is found that although scheme B has a slight impact on the voltage stability of high-risk nodes, it can reduce the line loss rate of high-loss branches, thus meeting the second screening condition. Therefore, scheme B, through secondary screening, becomes the superior dispatching scheme. Preferably, by marking high-loss branches and high-risk nodes, key power grid monitoring points are identified, and secondary screening is performed based on their electrical characteristics to further optimize the dispatching scheme, ensuring the reliability of power grid operation. While focusing on the power supply needs of sensitive loads, the optimization of weak links in the power grid is also considered, improving the overall operational performance of the power grid.

[0060] In summary, the beneficial effects of the embodiments of this application are: This application utilizes data collected from the power distribution network, including feeder current, bus voltage, power factor, and harmonic distortion rate. A multi-source line loss coupling model is constructed to simulate the coupling effects between conductor resistance loss, transformer iron and copper losses, reactive power flow losses, and harmonic-induced additional losses. Multiple intelligent distribution terminals within the target power supply area are connected, and safety control commands are configured. Based on the power distribution network operation data and safety control commands, the multi-source line loss coupling model is used to predict the trend of line loss distribution changes. Based on the predicted trend of line loss changes, an optimization scheme for the operation mode of the power distribution network within the target power supply area is configured, including reactive power compensation switching strategies, tie switch status adjustments, and transformer tap settings. This application provides a power grid safety assurance scheduling method and system for cloud computing-assisted line loss monitoring and positioning. It achieves the technical effect of accurately simulating the coupling relationship of various loss components by using line loss rate and voltage qualification rate as joint objectives and dynamically allocating weights, combined with a sensitive load power supply demand screening scheme, and dynamically updating the prediction results using a sliding time window. This reduces the prediction error of line loss distribution trends and improves power supply reliability.

[0061] Example 2, based on the same inventive concept as the power grid security dispatching method for cloud computing-assisted line loss monitoring and location in the foregoing examples, such as... Figure 2 As shown, this application provides a power grid safety assurance dispatching system for cloud computing-assisted line loss monitoring and location, the system comprising: The power distribution network operation data acquisition module 11 is used to acquire power distribution network operation data, which includes feeder current, bus voltage, power factor and harmonic distortion rate.

[0062] The multi-source line loss coupling model construction module 12 is used to construct a multi-source line loss coupling model, which is used to simulate the coupling effect relationship between conductor resistance loss, transformer iron loss and copper loss, reactive power flow loss and harmonic additional loss.

[0063] The safety control command configuration module 13 is used to connect multiple smart power distribution terminals within the target power supply area and configure safety control commands.

[0064] The line loss distribution change trend prediction module 14 is used to predict the line loss distribution change trend based on the power distribution network operation data and the safety control instructions, using the multi-source line loss coupling model.

[0065] The operation mode optimization scheme configuration module 15 is used to configure the operation mode optimization scheme of the distribution network in the target power supply area based on the prediction results of the line loss distribution change trend. This includes reactive power compensation switching strategy, tie switch status adjustment and transformer tap position setting.

[0066] Furthermore, the multi-source line loss coupling model construction module 12 is used to perform the following method: The multi-source line loss coupling model is trained based on the training dataset; at the same time, a sliding time window mechanism is used to dynamically update the prediction results of the line loss distribution change trend.

[0067] Furthermore, the multi-source line loss coupling model construction module 12 is also used to perform the following method: Acquire historical operating data within the target power supply area; based on the historical operating data, decompose the historical line loss components to separate the basic resistance loss, dynamic reactive power loss, and harmonic additional loss components, and construct the training data set.

[0068] Furthermore, the operation mode optimization scheme configuration module 15 is used to execute the following method: Within the target power supply area, an edge intelligent terminal cluster is deployed; based on the edge intelligent terminal cluster, multiple local distribution network control strategies are generated and bidirectional data synchronization is performed with the cloud dispatch center; the multiple local distribution network control strategies are integrated to determine the global operation mode optimization scheme.

[0069] Furthermore, the operation mode optimization scheme configuration module 15 is also used to execute the following method: Minimizing line loss rate, maximizing voltage qualification rate, and power supply reliability indicators are taken as joint optimization objectives; based on the power distribution network operation data, the joint optimization objectives are dynamically weighted to generate multiple candidate scheduling schemes; the multiple candidate scheduling schemes are comprehensively evaluated to determine the global operation mode optimization scheme.

[0070] Furthermore, the operation mode optimization scheme configuration module 15 is also used to execute the following method: Based on the distribution data of sensitive loads and the power supply guarantee level requirements, the multiple candidate scheduling schemes are prioritized, and the first screening condition under the power supply guarantee requirements of sensitive loads is set.

[0071] Furthermore, the operation mode optimization scheme configuration module 15 is also used to execute the following method: High-loss branches and high-risk nodes are marked, key power grid monitoring points are identified, and the electrical characteristics corresponding to the key power grid monitoring points are determined. Based on the electrical characteristics corresponding to the key power grid monitoring points, the multiple candidate scheduling schemes are screened a second time, and a second screening condition is set.

[0072] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0073] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0074] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A power grid security guarantee scheduling method for cloud computing assisted line loss monitoring positioning, characterized in that, The method comprises: Collecting power distribution network operation data, the power distribution network operation data comprising feeder current, bus voltage, power factor and harmonic distortion rate; Building a multi-source line loss coupling model for simulating the coupling influence relationship between conductor resistance loss, transformer iron loss and copper loss, reactive power flow loss and harmonic additional loss; Connecting a plurality of intelligent power distribution terminals in a target power supply area and configuring safety control instructions; Based on the power distribution network operation data and the safety control instructions, using the multi-source line loss coupling model to predict line loss distribution trend; According to the line loss distribution trend prediction result, configuring an operation mode optimization scheme of the power distribution network in the target power supply area, including reactive power compensation switching strategy, tie switch state adjustment and transformer tap setting.

2. The cloud computing aided line loss monitoring and positioning power grid security assurance scheduling method of claim 1, wherein, Building a multi-source line loss coupling model, the method comprising: Based on a training data set, training the multi-source line loss coupling model; At the same time, using a sliding time window mechanism to dynamically update the line loss distribution trend prediction result.

3. The cloud computing aided line loss monitoring and positioning power grid security assurance scheduling method of claim 2, wherein, Based on a training data set, the method comprises: Obtaining historical operation data in a target power supply area; Based on the historical operation data, decomposing historical line loss components to separate out basic resistance loss, dynamic reactive loss and harmonic additional loss components, and building the training data set.

4. The cloud computing aided line loss monitoring and positioning based power grid security assurance scheduling method of claim 2, wherein, Configuring an operation mode optimization scheme of the power distribution network in the target power supply area, the method comprising: Deploying an edge intelligent terminal cluster in the target power supply area; Based on the edge intelligent terminal cluster, generating a plurality of local power distribution network control strategies and performing bidirectional data synchronization with a cloud dispatch center; Fusing the plurality of local power distribution network control strategies to determine a global operation mode optimization scheme.

5. The cloud computing aided line loss monitoring and positioning based power grid security dispatching method of claim 4, wherein, Fusing the plurality of local power distribution network control strategies to determine a global operation mode optimization scheme, the method comprising: Minimizing line loss rate, maximizing voltage qualification rate and power supply reliability index as joint optimization objectives; According to the power distribution network operation data, dynamically allocating weights to the joint optimization objectives to generate a plurality of candidate scheduling schemes; Comprehensively evaluating the plurality of candidate scheduling schemes to determine a global operation mode optimization scheme.

6. The cloud computing aided line loss monitoring and positioning based power grid security assurance scheduling method of claim 5, wherein, Dynamically allocating weights to the joint optimization objectives to generate a plurality of candidate scheduling schemes, the method comprising: Based on sensitive load distribution data and power protection level requirements, prioritizing the plurality of candidate scheduling schemes to set a first screening condition under sensitive load power protection requirements.

7. The cloud computing aided line loss monitoring and positioning based power grid security dispatching method of claim 6, wherein, The method further comprises: Marking high-loss branches and high-risk nodes, identifying key grid monitoring points and determining electrical characteristics corresponding to the key grid monitoring points; According to the electrical characteristics corresponding to the key grid monitoring points, secondarily screening the plurality of candidate scheduling schemes to set a second screening condition.

8. A power grid security assurance dispatching system assisted by cloud computing for line loss monitoring and positioning, characterized in that, A power grid safety guarantee scheduling method for implementing the cloud computing assisted line loss monitoring and positioning of any one of claims 1-7, the system comprising: A power distribution network operation data acquisition module for acquiring power distribution network operation data, the power distribution network operation data comprising feeder current, bus voltage, power factor and harmonic distortion rate; The multi-source line loss coupling model construction module is configured to construct a multi-source line loss coupling model for simulating the coupling influence relationship between the conductor resistance loss, the transformer iron loss and copper loss, the reactive power flow loss, and the harmonic additional loss; The safety regulation instruction configuration module is configured to connect a plurality of intelligent power distribution terminals in the target power supply area and configure safety regulation instructions; The line loss distribution change trend prediction module is configured to predict the line loss distribution change trend based on the power distribution network operation data, the safety regulation instructions, and the multi-source line loss coupling model. The operation mode optimization scheme configuration module is configured to configure an operation mode optimization scheme of the power distribution network in the target power supply area according to the line loss distribution change trend prediction result, including a reactive power compensation switching strategy, a tie switch state adjustment, and a transformer tap setting.

Images