Power distribution network protection method and system based on cloud computing

Abstract

The invention relates to the technical field of cloud computing, in particular to a power distribution network protection method and system based on cloud computing, and the method comprises the following steps: receiving and analyzing state data from a transformer substation based on a real-time data flow of a cloud computing platform, carrying out the threshold comparison of a current load, and adjusting the current configuration according to a comparison result. And generating real-time load analysis data. According to the invention, transformer substation data is analyzed in real time through the cloud platform, the speed and accuracy of data processing are directly enhanced, load unevenness and fault risks are identified and responded, a network structure is updated in real time, the adaptive capacity of a power grid and the response speed of a system are enhanced, network simulation is carried out by using differentiated load scenes, and node performance is accurately analyzed and compared. The operation efficiency of the power grid is improved, fault point prediction and load fluctuation analysis are carried out by utilizing trend data, the perspectiveness and accuracy of fault processing are remarkably improved, the power grid can quickly and accurately respond in an emergency, and meanwhile, the operation efficiency and the power supply stability are optimized.

Description

Technical Field

[0001] The present invention relates to the field of cloud computing technology, and in particular to a distribution network protection method and system based on cloud computing. Background Art

[0002] Cloud computing is an Internet-based computing technology that enables users to access shared computing resources (such as servers, storage, databases, networks, software, applications, etc.) from a network on demand. This technology supports rapid deployment and elastic scaling of resources, and can dynamically adjust resource usage according to demand, thereby maximizing cost efficiency and flexibility. Cloud computing platforms are usually divided into public clouds, private clouds, and hybrid clouds, each of which is suitable for different business needs and security requirements. The main cloud service models include Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and Software as a Service (SaaS), allowing enterprises of all sizes to choose the appropriate service model according to their specific needs.

[0003] Among them, the cloud computing-based distribution network protection method refers to the use of cloud computing technology to optimize and improve the protection system of the distribution network. This method allows distribution network operators to centrally process and analyze large amounts of data from the entire power grid on a cloud platform to achieve more efficient and reliable fault detection, isolation and recovery. Through cloud computing, the distribution network protection system can achieve faster response time and higher data processing capabilities, thereby improving the overall security and stability of the power grid. The uses of this method mainly include improving the accuracy of power grid fault diagnosis, reducing power outage time and optimizing the operating efficiency of the power grid.

[0004] Although existing technologies provide the basic framework for cloud computing applications, they still have significant deficiencies in real-time data processing and fault response mechanisms. Data analysis in existing systems is often delayed, and fault detection and isolation speed is insufficient, which may cause more extensive grid damage and prolonged recovery time in emergency situations. In addition, existing technologies are not adaptable enough to grid load changes and fault conditions, and usually rely on preset response mechanisms and lack flexibility, which limits their processing capabilities under high load or fault conditions. These deficiencies may lead to unstable power supply, reduced efficiency, and seriously affect user experience. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a distribution network protection method and system based on cloud computing.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a distribution network protection method based on cloud computing, comprising the following steps:

[0007] S1: Based on the real-time data stream of the cloud computing platform, receive and analyze the status data from the substation, compare the threshold value of the current load, adjust the current configuration according to the comparison result, and generate real-time load analysis data;

[0008] S2: Identify the load imbalance and fault risk areas from the real-time load analysis data, redistribute the current for the target transmission line, update the control parameters of the distribution cabinet, and adjust the grid structure by applying the real-time data update protocol to obtain the optimized network topology diagram;

[0009] S3: Utilizing the optimized network topology diagram, performing power grid simulation, analyzing the current flow efficiency of each node, and comparing the performance of multiple nodes by simulating differentiated load scenarios to generate network performance simulation results;

[0010] S4: Based on the network performance simulation results, the monitored data trends are used on the cloud computing platform to predict the fault points, and the parameters of the power grid are adjusted in combination with the future load fluctuation prediction to establish a fault prediction and power grid parameter control plan.

[0011] As a further solution of the present invention, the step of acquiring the real-time load analysis data is specifically as follows:

[0012] S111: receiving real-time status data of the substation, collecting and storing current load data in real time based on the cloud computing platform, and generating a real-time status data set;

[0013] S112: extracting current load information from the real-time status data set, performing threshold analysis on the current value, screening out current data exceeding the threshold, and obtaining an abnormal current data set;

[0014] S113: Based on the abnormal current data set, recalculate the current distribution plan and use the improved formula:

[0015]

[0016] Calculate the adjusted current distribution result P and generate real-time load analysis data;

[0017] Among them, I i represents the current value obtained from the abnormal current dataset, w i represents the adjustment weight for the target current scenario, and λ is the adjustment coefficient used to balance the denominator.

[0018] As a further solution of the present invention, the step of obtaining the optimized network topology map is specifically as follows:

[0019] S211: receiving and analyzing the real-time load analysis data, identifying uneven loads and potential fault areas in the power grid, and obtaining risk identification results by quantitatively evaluating load fluctuations and fault probabilities in the areas;

[0020] S212: performing current redistribution on key transmission lines in the power grid according to the key areas identified in the risk identification result, calculating optimized current values ​​of multiple lines, and generating a current adjustment plan;

[0021] S213: Apply the current adjustment scheme to the distribution cabinet control system, and optimize the grid structure by synchronously changing the real-time data update protocol, using the formula:

[0022]

[0023] Calculate the optimized network topology diagram;

[0024] Among them, C i Refers to the current value in the current adjustment scheme, p i Represents the priority of multiple lines in the network, and Δ is the coefficient for adjusting the balance.

[0025] As a further solution of the present invention, the steps of obtaining the network performance simulation results are specifically as follows:

[0026] S311: Performing full network current simulation based on the optimized network topology diagram, analyzing the current flow efficiency under standard operating conditions for multiple nodes, calculating the current flow performance of each node, and generating preliminary current efficiency data;

[0027] S312: applying the preliminary current efficiency data to simulate differentiated load scenarios, simulating multiple load conditions including peaks and valleys, comparing performances of multiple nodes under differentiated conditions, and obtaining simulated differentiated load results;

[0028] S313: Comprehensively evaluate the performance of multiple nodes in the simulated differentiated load results, using the formula:

[0029]

[0030] Calculate the performance index of each node and generate the network performance simulation result E i ;

[0031] Among them, e i Refers to the current efficiency of a single node in the simulation, l i Represents the weight of the node under differentiated load conditions, emphasizing the impact of each node on the overall performance of the network. n is the total number of nodes. It is a normalization process for the number of nodes.

[0032] As a further solution of the present invention, the steps of obtaining the fault prediction and power grid parameter control solution are specifically as follows:

[0033] S411: Analyze the network performance simulation results, identify abnormal trends and potential failure points in the data, and generate failure point prediction data;

[0034] S412: Combine the fault point prediction data and the future load fluctuation prediction model to calculate the adjustment requirements of key nodes in the power grid, using the formula:

[0035] V adj =c·(γ·T f +δ·F p )

[0036] Get a preliminary grid control strategy;

[0037] Among them, V adj is the adjusted grid parameter, c is the adjustment coefficient to match the differentiated network conditions, γ and δ are weight coefficients adjusted to reflect the actual impact of fault trends and load changes, T f represents the fault prediction data, F p Indicates load fluctuation data;

[0038] S413: Apply the preliminary grid control strategy, combined with the real-time monitoring system feedback, optimize the grid operation parameters, ensure the stability and efficiency of the grid, and establish a fault prediction and grid parameter control plan.

[0039] A distribution network protection system based on cloud computing, the distribution network protection system based on cloud computing is used to execute the above-mentioned distribution network protection method based on cloud computing, the system comprises:

[0040] The real-time data analysis module receives the substation status data, compares the current load with the set threshold, adjusts the current distribution configuration according to the current load data, and generates real-time load analysis results;

[0041] The load balancing module identifies the load imbalance and fault risk areas from the real-time load analysis results, performs current redistribution for the target transmission line, updates the distribution cabinet control parameters, and generates updated power grid control parameters;

[0042] The network topology optimization module uses the updated power grid control parameters to adjust the power grid structure, applies the real-time data update protocol, optimizes the power grid structure, generates an optimized network topology diagram, compares the differences before and after the improvement of the power grid structure, and verifies the effectiveness of the structural adjustment;

[0043] The performance simulation module performs power grid simulation based on the network topology diagram, analyzes the current flow efficiency of multiple nodes, simulates differentiated load scenarios, compares the performance of multiple nodes, and generates network performance simulation results;

[0044] The fault prediction and control module predicts the fault point based on the network performance simulation results and the monitoring data trend, predicts future load fluctuations, adjusts the grid parameters, and establishes a fault prediction and grid parameter control plan.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In the present invention, substation data is analyzed in real time through a cloud platform, which directly enhances the speed and accuracy of data processing, identifies and responds to uneven loads and fault risks, updates the network structure in real time, enhances the adaptive capability of the power grid and the system response speed, uses differentiated load scenarios for network simulation, accurately analyzes and compares node performance, improves power grid operation efficiency, uses trend data for fault point prediction and load fluctuation analysis, significantly improves the foresight and accuracy of fault handling, enables the power grid to respond quickly and accurately in emergency situations, and optimizes operation efficiency and power supply stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0048] Figure 2 A flowchart of the steps for obtaining real-time load analysis data of the present invention;

[0049] Figure 3 A flowchart of the steps for obtaining the optimized network topology diagram of the present invention;

[0050] Figure 4 A flowchart of the steps for obtaining the network performance simulation results of the present invention;

[0051] Figure 5 The present invention is a flowchart of the steps for obtaining the fault prediction and power grid parameter control scheme. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0054] Embodiment 1

[0055] See also Figure 1 The present invention provides a technical solution: a distribution network protection method based on cloud computing, comprising the following steps:

[0056] S1: Based on the real-time data stream of the cloud computing platform, receive and analyze the status data from the substation, compare the threshold value of the current load, adjust the current configuration according to the comparison result, and generate real-time load analysis data;

[0057] S2: Identify the load imbalance and fault risk areas from the real-time load analysis data, redistribute the current for the target transmission line, update the control parameters of the distribution cabinet, and adjust the grid structure using the real-time data update protocol to obtain the optimized network topology diagram;

[0058] S3: Use the optimized network topology to perform grid simulation, analyze the current flow efficiency of each node, and compare the performance of multiple nodes by simulating differentiated load scenarios to generate network performance simulation results;

[0059] S4: Based on the network performance simulation results, the monitored data trends are used on the cloud computing platform to predict the fault points, and the parameters of the power grid are adjusted in combination with the future load fluctuation prediction to establish a fault prediction and power grid parameter control plan.

[0060] Real-time load analysis data includes uneven load and fault risk areas. The optimized network topology diagram specifically includes current redistribution configuration and distribution cabinet control parameter update. The network performance simulation results include node current flow efficiency and differentiated load scenario performance comparison. The fault prediction and grid parameter control plan specifically refers to fault point prediction, future load fluctuation prediction, and grid parameter adjustment value.

[0061] See also Figure 2 ,The specific steps for obtaining real-time load analysis data are as follows:

[0062] S111: receiving real-time status data of the substation, collecting and storing current load data in real time based on the cloud computing platform, and generating a real-time status data set;

[0063] The real-time status data of the substation is received, and the real-time status data set R is calculated according to the formula R=f(D, S), where D represents the amount of data collected and S represents the data flow speed;

[0064] Where D represents the amount of current load data received from the substation, and S represents the speed at which data flows into the cloud computing platform.

[0065] Detailed explanation of the formula and the process of formula calculation and derivation:

[0066] The formula R = f(D, S) is a function that simulates data processing, where R represents the real-time status data set obtained after processing. D is the amount of data, which can be obtained by the number of data packets transmitted per second by the monitoring system, for example, 1000 data packets per second, each containing current and voltage values; S is the data flow rate, which can be read from the system monitoring tool and is set to 1GB / second. These two parameters can be combined to calculate the size of the data set for real-time processing. For example, if 1000 data packets are processed, each packet is 1MB, and the data flow rate is 1GB / second, then the time required to process these 1000 data packets is 1 second, so R = 1000MB.

[0067] S112: extracting current load information from the real-time status data set, performing threshold analysis on the current value, screening out current data exceeding the threshold, and obtaining an abnormal current data set;

[0068] Among them, the current load information is extracted, and the abnormal current data set E is calculated according to the formula E=g(C, T), where C represents the current load value and T represents the threshold value;

[0069] Where C represents the current value extracted from the real-time status data set, and T represents the set current abnormal threshold.

[0070] Detailed explanation of the formula and the process of formula calculation and derivation:

[0071] The formula E = g(C, T) is used to identify current data C that exceeds the threshold T and generate an abnormal current data set E. For example, if the threshold T is set to 500 amperes, and the current value C extracted from the data set is 600 amperes, these values ​​will be marked as abnormal. The specific calculation process is as follows: suppose that there are current values ​​C = [450, 500, 550, 600] amperes in the data set, and the threshold T = 500 amperes, then the current values ​​that exceed the threshold are 550 and 600 amperes, so the abnormal current data set E = [550, 600] amperes.

[0072] S113: Recalculate the current distribution plan based on the abnormal current data set, using the formula:

[0073]

[0074] Calculate the adjusted current distribution result P and generate real-time load analysis data;

[0075] Among them, I i represents the current value obtained from the abnormal current dataset, w i represents the adjustment weight for the target current scenario, and λ is the adjustment coefficient used to balance the denominator.

[0076] formula:

[0077]

[0078] Detailed explanation of the formula and the process of formula calculation and derivation:

[0079] This formula is used to recalculate the current distribution scheme based on the abnormal current data set, where P represents the calculated new current distribution result. The parameters include: I i is the value of each current data point, w i is the adjustment weight of the corresponding current data point, n is the number of data points, and λ is an adjustment coefficient used in the balance calculation.

[0080] For example, there are the following current data points I = [550, 600], the weight of each point is set to w = [1.2, 0.8], the total number of data points n = 2, and the adjustment coefficient λ = 0.5. The calculation process of the formula is:

[0081] Calculate the weighted value for each data point: 550×1.2 2 =792 and 600×0.8 2 =384.

[0082] Calculate the total weighted value and denominator: 792+384=1176, and the denominator is 2+0.5=2.5.

[0083] Current distribution results

[0084] This result shows that by adjusting the weights and referring to the abnormal conditions of the current data points, a balanced current distribution result can be recalculated, which helps to optimize the load management of the entire power system.

[0085] See also Figure 3 , the specific steps for obtaining the optimized network topology map are:

[0086] S211: receiving and analyzing real-time load analysis data, identifying uneven loads and potential fault areas in the power grid, and obtaining risk identification results by quantitatively evaluating load fluctuations and fault probabilities in the areas;

[0087] Among them, current redistribution is performed on key transmission lines in the power grid according to the formula P i =C i ×R i Calculate the optimal current value P of multiple lines i .

[0088] Where P i represents the optimized current value of the i-th transmission line, C i Represents the initial current value, R i Represents the current regulation factor.

[0089] Detailed explanation of the formula and the process of formula calculation and derivation:

[0090] When redistributing the current, refer to the initial current C of each line. i and current adjustment factor R i , calculate the optimal current value P for each line i For example, the initial current C of a line i For 100A, the current adjustment factor R i is 0.8, then the optimized current P i The calculation process is as follows:

[0091] P i =100A×0.8=80A

[0092] This means that, based on the risk assessment results, the current on the line is reduced by 20% to match the load demand in the grid.

[0093] S212: performing current redistribution on key transmission lines in the power grid according to the key areas identified in the risk identification results, calculating optimized current values ​​of multiple lines, and generating a current adjustment plan;

[0094] Among them, the current adjustment scheme is applied to the distribution cabinet control system, according to the formula Calculate the updated total current distribution S.

[0095] Where S represents the total current distribution, P i represents the optimized current value of the i-th transmission line, and n is the total number of lines.

[0096] Detailed explanation of the formula and the process of formula calculation and derivation:

[0097] When the current adjustment scheme is applied to the distribution cabinet control system, the sum of the current values ​​of all lines needs to be calculated to update the system parameters. For example, the power grid includes three lines, and the adjusted current value P of multiple lines is i If they are 80A, 70A, and 90A respectively, the total current S is calculated as follows:

[0098] S=80A+70A+90A=240A

[0099] The calculation result S shows that after discussion and adjustment, the total current that the distribution cabinet needs to handle is 240A to ensure balanced and safe current distribution of the entire system.

[0100] S213: Apply the current adjustment scheme to the distribution cabinet control system, synchronize changes through the real-time data update protocol, optimize the grid structure, and use the formula:

[0101]

[0102] Calculate the optimized network topology diagram;

[0103] Among them, C i Refers to the current value in the current adjustment scheme, p i Represents the priority of multiple lines in the network, and Δ is the coefficient for adjusting the balance.

[0104] formula:

[0105]

[0106] Detailed explanation of the formula and the process of formula calculation and derivation:

[0107] In the formula, the new parameter T required for the optimized network topology is calculated. The formula refers to the adjusted current value C of each transmission line by weighted average. i and their respective priorities p i , and an adjustment factor Δ is introduced to balance the overall calculation.

[0108] For example, the power grid system includes three lines, and the current value C after multi-line adjustment i 80A, 70A, 90A respectively, priority p i They are 1.2, 1.0, and 1.1 respectively, and the adjustment coefficient Δ is 3. The calculation process of T is as follows:

[0109]

[0110] The result T indicates that after adjusting the current and priority weight, the average current value that should be adjusted per regulation cycle is approximately 44.17 A, which helps to optimize the network topology and maintain system stability.

[0111] See also Figure 4 ,The specific steps for obtaining the network performance simulation results are:

[0112] S311: Perform full network current simulation based on the optimized network topology, analyze the current flow efficiency under standard operating conditions for multiple nodes, calculate the current flow performance of each node, and generate preliminary current efficiency data;

[0113] Among them, the current flow efficiency of multiple nodes is analyzed according to the formula Calculate the resistance R of each node i .

[0114] In the formula, R i represents the resistance of node i, V i represents the voltage at node i under standard operating conditions, I i Represents the current at node i.

[0115] Detailed explanation of the formula and the process of formula calculation and derivation:

[0116] Ohm's law is used here, where the resistance R i is the voltage V i and current I i The ratio of represents the resistance of current passing through the node. Set the node voltage V i is 10 volts, the current I i is 2 amperes, then the resistor R i The calculation is as follows:

[0117]

[0118] The results show that the resistance of node i at the current voltage and current is 5 ohms, which reflects the difficulty of current passing through the node and is directly related to the task of analyzing the efficiency of current flow.

[0119] S312: applying the preliminary current efficiency data to simulate differentiated load scenarios, simulating various load conditions including peaks and valleys, comparing the performance of multiple nodes under differentiated conditions, and obtaining simulated differentiated load results;

[0120] Among them, comparing the performance of multiple nodes under differentiated load scenarios, according to the formula Calculate the performance differentiation index E of each node diff .

[0121] In the formula, E diff Represents the differentiation index of node performance, E peak and E valley Represents the efficiency at peak and valley loads, E avg is the average efficiency.

[0122] Detailed explanation of the formula and the process of formula calculation and derivation:

[0123] The formula is designed to measure the volatility of node performance under differentiated load conditions. Taking specific data as an example, the efficiency E of a node under peak load is set to peak The efficiency at low load is 95%. valley The average efficiency is 55%. avg For 75%:

[0124]

[0125] The results show that the performance of the node varies greatly under the differentiated load scenario, and the differentiation index is 0.533, which means that the node is highly sensitive to load changes, which is consistent with the step S313: Comprehensively evaluate the performance of multiple nodes in the simulation of differentiated load results, using the formula:

[0126]

[0127] Calculate the performance index of each node and generate the network performance simulation result E i ;

[0128] Among them, e i Refers to the current efficiency of a single node in the simulation, l i Represents the weight of the node under differentiated load conditions, emphasizing the impact of each node on the overall performance of the network. n is the total number of nodes. It is a normalization process for the number of nodes.

[0129] formula:

[0130]

[0131] Detailed explanation of the formula and the process of formula calculation and derivation:

[0132] The formula is used to calculate the comprehensive performance index E of all nodes in the network i , where e i represents the current efficiency of a single node, l i It represents the load factor of the node, normalized by taking the square root of the number of nodes n.

[0133] Taking specific data as an example, there are 4 nodes in the network, and the current efficiency of multiple nodes is e i are 0.9, 0.85, 0.95 and 0.8 respectively, and the corresponding load factors l are 1.0, 0.9, 1.1 and 0.95 respectively:

[0134]

[0135] The results show that after comprehensive reference to current efficiency and load factors, the average performance index of the entire network is 1.735. The numerical value reflects the overall performance of the entire power grid under the current simulation conditions and is directly related to the task of generating network performance simulation results in the step.

[0136] See also Figure 5 ,The specific steps for obtaining fault prediction and power grid parameter control scheme are:

[0137] S411: Analyze network performance simulation results, identify abnormal trends and potential failure points in the data, and generate failure point prediction data;

[0138] Among them, the network performance simulation results obtained through the cloud computing platform are analyzed to identify abnormal trends and potential failure points in the data. According to the formula D = ∑ (d i × i ), calculate the fault point prediction data.

[0139] Where D represents the comprehensive fault point data, d i Represents the abnormal indicator of a single data point, w i Represents the weight of the data point.

[0140] Detailed explanation of the formula and the process of formula calculation and derivation:

[0141] In the formula, it is necessary to quantify the abnormal index d of each data point i , determined by comparing the real-time monitoring data with the predetermined threshold. Weight w i It is assigned based on the importance of the data point or the potential risk of impact on the system, determined by a real-time risk assessment model. For example, if the outlier value of a data point exceeds the set threshold, its weight will be relatively high.

[0142] The abnormal indicators of the three data points monitored by the system are set to 1.5, 2.0 and 0.5, and the corresponding weights are 0.3, 0.6 and 0.1 respectively. The calculation process of the fault point prediction data D is as follows:

[0143] D=(1.5×0.3)+(2.0×0.6)+(0.5×0.1)=0.45+1.2+0.05=1.7

[0144] The results show that the comprehensive fault point data is 1.7, which reflects the result of comprehensive evaluation of the currently monitored data points based on their importance and abnormality level in real-time evaluation.

[0145] S412: Combine the fault point prediction data and the future load fluctuation prediction model to calculate the adjustment requirements of key nodes in the power grid, using the formula:

[0146] V adj =c·(γ·Tf +δ·F p )

[0147] Get a preliminary grid control strategy;

[0148] Among them, V adj is the adjusted grid parameter, c is the adjustment coefficient to match the differentiated network conditions, γ and δ are weight coefficients adjusted to reflect the actual impact of fault trends and load changes, T f represents the fault prediction data, F p Indicates load fluctuation data;

[0149] formula:

[0150] V adj =c·(γ·T f +δ·F p )

[0151] Detailed explanation of the formula and the process of formula calculation and derivation:

[0152] The formula is used to determine the adjustment parameter values ​​of key nodes in the power grid to cope with predicted faults and load fluctuations. f and F p Provided by the real-time monitoring system, the weights γ and δ are dynamically adjusted according to the severity of the fault and the impact of the load. The adjustment coefficient c is set according to the operating conditions and technical specifications of the power grid.

[0153] Set the fault prediction data T f is 1.7, load fluctuation data F p is 2.0, the weight γ is 0.7, δ is 0.3, and the adjustment coefficient c is set to 1.5. The calculation process of the preliminary power grid regulation strategy is as follows:

[0154] V adj =1.5×(1.7×0.7+2.0×0.3)=1.5×(1.19+0.6)=1.5×1.79=2.685

[0155] The results show that the adjusted power grid parameter V adj It is 2.685, which represents the intensity of the control strategy that needs to be implemented based on the comprehensive analysis of current fault prediction and load fluctuation.

[0156] S413: Apply preliminary grid control strategies, combined with real-time monitoring system feedback, optimize grid operation parameters, ensure grid stability and efficiency, and establish fault prediction and grid parameter control solutions.

[0157] Among them, the parameter adjustment strategy is applied to the actual power grid control system to optimize the power grid operation parameters. Compute fault prediction and grid parameter control schemes.

[0158] In the formula, S i represents the performance index of the control scheme, k is the system efficiency coefficient, V adj is the adjusted grid parameter, and u represents the system stability adjustment coefficient.

[0159] Detailed explanation of the formula and the process of formula calculation and derivation:

[0160] The formula reflects the adjusted grid parameter V adj The effect after implementation in the actual control system, where V adj The square term expresses the nonlinear influence of parameter adjustment, while the coefficients k and u are determined according to the design specifications and operating environment of the power grid.

[0161] Set the V calculated from the previous adj is 2.685, the system efficiency coefficient k is 0.85, the system stability adjustment coefficient u is 1.1, and the calculation process of the performance index S of the control scheme is as follows:

[0162] S i =0.85×(2.685 2 ×1.1)

[0163] =0.85×(7.207225×1.1)

[0164] =0.85×7.9279475

[0165] =6.738755375

[0166] The results show that the adjusted power grid parameter V adj After implementation, it can significantly affect the performance index S of the power grid i , express the overall effect of the power grid control plan and enhance the power grid's adaptability to future changes and system stability.

[0167] A distribution network protection system based on cloud computing, the distribution network protection system based on cloud computing is used to execute the above-mentioned distribution network protection method based on cloud computing, the system includes:

[0168] The real-time data analysis module receives the substation status data, compares the current load with the set threshold, adjusts the current distribution configuration according to the current load data, and generates real-time load analysis results;

[0169] The load balancing module identifies the load imbalance and fault risk areas from the real-time load analysis results, performs current redistribution for the target transmission lines, updates the distribution cabinet control parameters, and generates updated grid control parameters;

[0170] The network topology optimization module uses the updated grid control parameters to adjust the grid structure, applies the real-time data update protocol, optimizes the grid structure, generates an optimized network topology diagram, compares the differences before and after the improvement of the grid structure, and verifies the effectiveness of the structural adjustment;

[0171] The performance simulation module performs power grid simulation based on the network topology diagram, analyzes the current flow efficiency of multiple nodes, simulates differentiated load scenarios, compares the performance of multiple nodes, and generates network performance simulation results;

[0172] The fault prediction and control module predicts fault points based on the network performance simulation results and the monitoring data trends, predicts future load fluctuations, adjusts grid parameters, and establishes fault prediction and grid parameter control plans.

[0173] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A distribution network protection method based on cloud computing, characterized in that: The following steps are involved: Based on the real-time data stream of the cloud computing platform, it receives and analyzes the status data from the substation, compares the threshold value of the current load, adjusts the current configuration according to the comparison result, and generates real-time load analysis data; Identify the load imbalance and fault risk areas from the real-time load analysis data, redistribute the current for the target transmission line, update the control parameters of the distribution cabinet, and adjust the grid structure using the real-time data update protocol to obtain an optimized network topology diagram; Utilizing the optimized network topology diagram, performing power grid simulation, analyzing the current flow efficiency of each node, and generating network performance simulation results by simulating differentiated load scenarios and comparing the performance of multiple nodes; According to the network performance simulation results, the monitored data trends are used on the cloud computing platform to predict the fault points, and the parameters of the power grid are adjusted in combination with the future load fluctuation prediction to establish a fault prediction and power grid parameter control plan.

2. The distribution network protection method based on cloud computing according to claim 1, characterized in that: The steps for obtaining the real-time load analysis data are specifically as follows: Receive real-time status data of the substation, collect and store current load data in real time based on the cloud computing platform, and generate real-time status data sets; Extracting current load information from the real-time status data set, performing threshold analysis on the current value, screening out current data exceeding the threshold, and obtaining an abnormal current data set; Based on the abnormal current data set, the current distribution scheme is recalculated using the improved formula: Calculate the adjusted current distribution result P and generate real-time load analysis data; Among them, I i represents the current value obtained from the abnormal current dataset, w i represents the adjustment weight for the target current scenario, and λ is the adjustment coefficient used to balance the denominator.

3. The cloud computing-based distribution network protection method according to claim 2, characterized in that: The steps for obtaining the optimized network topology map are specifically as follows: Receiving and analyzing the real-time load analysis data, identifying uneven loads and potential fault areas in the power grid, and obtaining risk identification results by quantitatively evaluating load fluctuations and fault probabilities in the areas; According to the key areas identified in the risk identification results, current redistribution is performed on key transmission lines in the power grid, optimized current values ​​of multiple lines are calculated, and a current adjustment plan is generated; The current adjustment scheme is applied to the distribution cabinet control system, and the real-time data update protocol is synchronously changed to optimize the grid structure, using the formula: Calculate the optimized network topology; Among them, C i Refers to the current value in the current adjustment scheme, p i Represents the priority of multiple lines in the network, and Δ is the coefficient for adjusting the balance.

4. The distribution network protection method based on cloud computing according to claim 3 is characterized in that: The steps for obtaining the network performance simulation results are specifically as follows: Based on the optimized network topology, a full network current simulation is performed, the current flow efficiency under standard operating conditions is analyzed for multiple nodes, the current flow performance is calculated node by node, and preliminary current efficiency data is generated; Applying the preliminary current efficiency data to simulate differentiated load scenarios, simulating multiple load conditions including peaks and valleys, comparing the performance of multiple nodes under differentiated conditions, and obtaining simulated differentiated load results; The performance of multiple nodes in the simulated differentiated load results is comprehensively evaluated using the formula: Calculate the performance index of each node and generate the network performance simulation result E i ; Among them, e i Refers to the current efficiency of a single node in the simulation, l i Represents the weight of the node under differentiated load conditions, emphasizing the impact of each node on the overall performance of the network. n is the total number of nodes. It is a normalization process for the number of nodes.

5. The distribution network protection method based on cloud computing according to claim 4 is characterized in that: The steps for obtaining the fault prediction and power grid parameter control scheme are specifically as follows: Analyze the network performance simulation results, identify abnormal trends and potential failure points in the data, and generate failure point prediction data; Combining the fault point prediction data and the future load fluctuation prediction model, the adjustment requirements of key nodes in the power grid are calculated using the formula: V adj =c·(γ·T f +δ·F p ) Get a preliminary grid control strategy; Among them, V adj is the adjusted grid parameter, c is the adjustment coefficient to match the differentiated network conditions, γ and δ are weight coefficients adjusted to reflect the actual impact of fault trends and load changes, T f represents the fault prediction data, F p Indicates load fluctuation data; Apply the preliminary grid control strategy, combined with real-time monitoring system feedback, to optimize grid operation parameters, ensure grid stability and efficiency, and establish fault prediction and grid parameter control solutions.

6. A distribution network protection system based on cloud computing, characterized in that: According to the cloud computing-based distribution network protection method according to any one of claims 1 to 5, the system comprises: The real-time data analysis module receives the substation status data, compares the current load with the set threshold, adjusts the current distribution configuration according to the current load data, and generates real-time load analysis results; The load balancing module identifies the load imbalance and fault risk areas from the real-time load analysis results, performs current redistribution for the target transmission line, updates the distribution cabinet control parameters, and generates updated power grid control parameters; The network topology optimization module uses the updated power grid control parameters to adjust the power grid structure, applies the real-time data update protocol, optimizes the power grid structure, generates an optimized network topology diagram, compares the differences before and after the improvement of the power grid structure, and verifies the effectiveness of the structural adjustment; The performance simulation module performs power grid simulation based on the network topology diagram, analyzes the current flow efficiency of multiple nodes, simulates differentiated load scenarios, compares the performance of multiple nodes, and generates network performance simulation results; The fault prediction and control module predicts the fault point based on the network performance simulation results and the monitoring data trend, predicts future load fluctuations, adjusts the grid parameters, and establishes a fault prediction and grid parameter control plan.

Images