Power transformation path analysis method and system based on shadow carbon price

Abstract

The invention discloses a shadow carbon price-based power transformation path analysis method and system, and relates to the technical field of power transformation path analysis, and the method comprises the following steps: dividing a path in a power transformation process into a plurality of node regions, obtaining the power supply state data of each region, extracting an abnormal power supply coefficient, an equipment overload coefficient and an abnormal communication coefficient from the power supply state data; constructing a power supply fault model based on a neural network by using the power supply abnormal coefficient, the equipment overload coefficient and the communication abnormal coefficient, and generating a power supply fault coefficient; and acquiring a power supply fault coefficient of each node region, drawing a power supply-fault curve graph, judging a region with a fault in the power transformation process based on the power supply-fault curve graph, and performing priority processing. Through power supply fault analysis, the problem that various abnormal faults of power supply cannot be found and eliminated in time in the power transformation process is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power transformation path analysis, and more specifically, to the technical field of power transformation path analysis method and system based on shadow carbon price. Background Art

[0002] Electricity transformation refers to the shift from traditional fossil fuel power generation to more sustainable, low-carbon energy production methods. The continuous maturity and cost reduction of renewable energy technologies such as solar, wind, and hydropower have made these energy sources an important alternative to traditional thermal power. Solar photovoltaic and wind power generation are particularly widely used. The development of energy storage technology, as the fluctuation of power load increases, the progress of energy storage technology (such as lithium batteries, hydrogen energy storage, etc.) has become the key to electricity transformation. Energy storage systems can balance power supply and demand and enhance the flexibility and stability of the system. Smart grids optimize the transmission and distribution of electricity through information technology, automation and communication technology. Digital technology helps to monitor and manage the power grid in real time and improve the accuracy and reliability of power dispatch.

[0003] These technological advances have promoted the transformation of the power system towards a low-carbon, intelligent and flexible direction, providing solid technical support for achieving global energy transformation and addressing climate change.

[0004] The above disclosed technical solutions have at least the following technical problems: Since the power transformation path involves a large amount of engineering work and a wide area during the power grid construction process, various abnormal faults may occur in the power supply during the power transformation process and cannot be discovered and eliminated in time, resulting in engineering problems. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a power transformation path analysis method and system based on shadow carbon price, which solves the problem that various abnormal faults in power supply cannot be discovered and eliminated in time during the power transformation process through power supply fault analysis.

[0006] To achieve the above object, the present invention provides the following technical solutions: The power transformation path analysis method and system based on shadow carbon price is characterized by comprising the following steps: dividing the path in the power transformation process into multiple node areas, obtaining the power supply status data of each area, and extracting the power supply abnormality coefficient, equipment overload coefficient and communication abnormality coefficient from the power supply status data; constructing a power supply fault model based on a neural network for the power supply abnormality coefficient, equipment overload coefficient and communication abnormality coefficient to generate a power supply fault coefficient; obtaining the power supply fault coefficient of each node area, drawing a power supply-fault curve diagram, judging the area where the fault occurs in the power transformation process based on the power supply-fault curve diagram and performing priority processing.

[0007] In a preferred embodiment, the power supply abnormality coefficient is specifically obtained by the following method: acquiring power supply abnormality basic data in real time, the power supply abnormality basic data including the remaining battery capacity and rated capacity, charge and discharge current, and temperature of the energy storage device; measuring noise data and load data in multiple time periods, and obtaining noise abnormality data and load abnormality data when the noise data and load data in multiple time periods are higher than preset stable load data and stable noise data; calculating load forecast abnormality data based on the noise abnormality data and load abnormality data; calculating battery abnormality data of the energy storage device based on the ratio of the remaining battery capacity and the rated capacity of the energy storage device; calculating the energy storage device abnormality coefficient based on the preset energy storage device abnormality formula according to the battery abnormality data, charge and discharge current, and temperature of the energy storage device; calculating the power supply abnormality coefficient based on the preset power supply abnormality formula according to the load forecast abnormality data combined with the energy storage device abnormality coefficient.

[0008] In a preferred embodiment, the equipment overload coefficient is specifically obtained by the following method: obtaining the response time and aging rate of the protection device; monitoring and obtaining the temperature limit and cooling system of the transformer in real time, and obtaining the overload coefficient of the transformer through the temperature limit and cooling system of the transformer; collecting transmission lines in different regions, applying high-load voltage on the transmission lines in different regions, and obtaining the current carrying capacity, conductor material coefficient and line temperature rise abnormality coefficient by monitoring the carrying capacity of the power transmission lines under high load conditions; calculating the line overload coefficient according to the current carrying capacity, conductor material coefficient and line temperature rise abnormality coefficient; calculating the equipment overload coefficient according to the response time and aging rate of the protection device combined with the overload coefficient of the transformer and the line overload coefficient based on a preset equipment overload formula.

[0009] In a preferred embodiment, the communication anomaly coefficient is specifically obtained by the following method: obtaining data on electromagnetic wave propagation in a channel, wherein the propagation data includes data frame length, transmission rate, channel length, and electromagnetic wave propagation rate; calculating a transmission delay coefficient based on the data frame length and the transmission rate, and calculating a propagation delay coefficient based on the channel length and the electromagnetic wave propagation rate; obtaining a network delay anomaly coefficient based on a preset network delay anomaly formula according to the transmission delay coefficient and the propagation delay coefficient; obtaining a clock synchronization anomaly coefficient and a data packet loss rate in a power system; calculating a communication anomaly coefficient based on a preset communication anomaly formula according to the network delay anomaly coefficient combined with the clock synchronization anomaly coefficient and the data packet loss rate in the power system.

[0010] In a preferred embodiment, the power supply abnormality coefficient, the equipment overload coefficient and the communication abnormality coefficient are used to construct a power supply fault model based on a neural network to generate a power supply fault coefficient. The specific steps are as follows: obtain historical power supply abnormality coefficients, historical equipment overload coefficients and historical communication abnormality coefficients, perform data cleaning on the historical power supply abnormality coefficients, historical equipment overload coefficients and historical communication abnormality coefficients, process missing values, and perform data standardization; divide the preprocessed data into a training set and a test set, initialize the model based on the neural network, use the training set as the input layer and add the first hidden layer, automatically adjust the parameters and assign weights; use the power supply fault as the output layer, construct a power supply fault model, use the test set to train and evaluate the power supply fault model, and obtain a trained power supply fault model; input the newly acquired power supply abnormality coefficient, equipment overload coefficient and communication abnormality coefficient into the trained power supply fault model to generate a power supply fault coefficient.

[0011] In a preferred embodiment, the power supply failure coefficient of each node area is obtained, a power supply-fault curve is drawn, and the areas where faults occur during the power transformation process are judged based on the power supply-fault curve and priority processing is performed. The specific steps are as follows: the power supply failure coefficient of each node area is obtained, and the power supply failure coefficient of each node area is used as the vertical coordinate and each node area is used as the horizontal coordinate to draw a power supply-fault curve; multiple historical power supply stability coefficients are obtained to calculate an average value, and the average value is used as a reference threshold of the power supply-fault curve; the node areas on the power supply-fault curve that exceed the reference threshold of the power supply-fault curve are marked, and a priority power supply fault troubleshooting table is obtained in a downward gradient order; according to the priority power supply fault troubleshooting table, maintenance personnel are notified of areas with serious power supply faults in a priority manner, and serious node areas are troubleshooted and repaired in a timely manner to ensure the stability of work during the power transformation process.

[0012] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Through neural network technology, the problem of building a power path fault model can be solved by self-learning and pattern recognition, so as to efficiently and accurately predict and diagnose complex faults and improve the reliability and response speed of the system.

[0013] 2. By constructing a power path fault curve diagram, the fault characteristics can be intuitively displayed, helping to quickly locate the problem and improve the accuracy of fault diagnosis and decision-making efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic diagram of the structure of the power transformation path analysis method based on shadow carbon price provided in an embodiment of the present application.

[0015] Figure 2 A schematic diagram of the structure of the power transformation path analysis system based on shadow carbon price provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Embodiment 1, Figure 1 The schematic diagram of the structure of the power transformation path analysis method based on shadow carbon price provided in the embodiment of the present application includes the following steps: S1, divide the path in the power transformation process into multiple node areas, obtain the power supply status data of each area, and extract the power supply abnormality coefficient, equipment overload coefficient and communication abnormality coefficient from the power supply status data.

[0018] In this example, the power supply anomaly coefficient refers to the abnormal situation that occurs during the power transformation process due to insufficient or faulty power supply in the context of the gradual increase in the proportion of renewable energy. By obtaining the power supply anomaly coefficient to analyze power supply failures, it is not only possible to quantify and accurately identify failure risks and optimize power system design and operation, but also to improve the accuracy of system reliability assessment, support rapid fault diagnosis and recovery, and promote the intelligent management of power systems. Its data-driven advantage enables power companies to perform system maintenance and decision-making more scientifically, thereby improving the safety and stability of the overall power supply.

[0019] Obtaining the power supply anomaly coefficient has the following advantages for analyzing power supply failures: Quantifying failure risks: The failure coefficient is a quantitative indicator that reflects the degree of failure in the power supply system. By calculating and analyzing it, it can provide accurate data support for the safety assessment of the power system. The power supply abnormality coefficient usually includes parameters such as failure rate, failure duration, and failure frequency. These indicators can quantify the risk level of various types of failures in the power supply process. By monitoring and analyzing these indicators, potential problems can be discovered in a timely manner, thereby achieving early warning and risk prevention.

[0020] Optimizing power system design and operation: The power supply anomaly coefficient can help power engineers make more accurate decisions in system design and optimization. By analyzing the failure coefficients of different types of power equipment in different regions, it is possible to identify high-risk areas for failures in the system, so that targeted improvement measures can be taken. For example, if the failure coefficient of a distribution network is high, measures such as equipment updates, line optimization, or additional power supplies can be taken in that area to improve the reliability of power supply in that area.

[0021] Support fault diagnosis and recovery: The role of the fault coefficient in power system fault diagnosis cannot be ignored. Through statistical analysis of historical fault data, engineers can identify the patterns, laws and causes of faults, providing a basis for quickly locating the source of the fault. This data-driven analysis method not only improves the efficiency of fault diagnosis, but also helps to quickly restore power supply, reduce system downtime and economic losses.

[0022] Improve the accuracy of power system reliability assessment: Traditional power system reliability assessment usually relies on overall system performance indicators, such as system downtime or available capacity. By introducing the concept of failure coefficient, the assessment process can be more refined, taking into account the specific impact of different types of failures on system operation. The power supply anomaly coefficient can help analyze and evaluate the impact of different component or equipment failures on the reliability of the entire system, thereby more accurately assessing the risk level of the system.

[0023] Providing data support for decision-making: Through long-term monitoring of power supply anomaly coefficients, power companies can accumulate a large amount of historical fault data, which can provide a scientific basis for decision-makers. For example, when making decisions on grid expansion, equipment upgrades, or operation and maintenance, the fault coefficient can be used to predict possible system performance and future fault trends, thereby formulating more reasonable investment plans and management strategies.

[0024] Promote intelligent operation and maintenance: In the era of smart grid and big data, obtaining power supply anomaly coefficient can be combined with intelligent monitoring and data analysis tools to achieve more accurate fault prediction and automated operation and maintenance. By real-time monitoring and analysis of power supply anomaly coefficient, hidden dangers in the system can be discovered in time, and the fault repair process can be automatically started. It can even realize automated load scheduling and power distribution, improving the self-healing ability of the overall power grid.

[0025] The specific method for obtaining the power supply abnormality coefficient is as follows: Acquire basic data of power supply anomaly in real time, wherein the basic data of power supply anomaly includes remaining capacity and rated capacity of batteries of energy storage devices, charge and discharge current, and temperature; Measuring noise data and load data in multiple time periods, obtaining abnormal noise data and abnormal load data when the noise data and load data in the multiple time periods are higher than preset stable load data and stable noise data; Load forecast abnormal data is calculated based on noise abnormal data and load abnormal data; The battery abnormality data of the energy storage device is obtained by calculating the ratio of the remaining battery capacity and the rated capacity of the energy storage device; The energy storage device abnormality coefficient is calculated based on the preset energy storage device abnormality formula according to the battery abnormality data, charge and discharge current and temperature of the energy storage device; The power supply abnormality coefficient is calculated based on the load forecast abnormality data and the energy storage device abnormality coefficient based on the preset power supply abnormality formula.

[0026] The specific calculation formula of the abnormal coefficient of the energy storage device is as follows:

[0027] The specific calculation formula of the power supply abnormality coefficient is as follows:

[0028] In the formula, is the power supply anomaly coefficient, is the abnormal noise data of the i-th working period, is the load abnormality data of the i-th working period, where i=1,2,3,...,R, R is an integer, N is the node area, is the abnormal coefficient of energy storage equipment, is the remaining battery capacity, is the rated capacity of the battery, is the charging current, is the discharge current, is the actual temperature of the energy storage device, Rated temperature for energy storage equipment.

[0029] It should be noted that in the process of power transformation, the power supply of energy storage equipment is important. When the abnormal coefficient of energy storage equipment becomes larger and larger, and the abnormal load forecast data becomes larger and larger, the abnormal coefficient of power supply will become larger and larger, which will lead to insufficient power supply or failure in the process of power transformation. Therefore, obtaining these coefficients plays an important role in analyzing power supply failures.

[0030] The equipment overload factor refers to the degree to which the equipment in the power system exceeds the rated capacity during the power transformation process. It is an important parameter to evaluate the degree to which the power system equipment exceeds the rated capacity during operation. It is usually used in the design, monitoring and optimization of power systems, especially when the system faces load fluctuations and the proportion of renewable energy generation increases. The overload factor can help power engineers and operators understand the operation of equipment under high load conditions and take appropriate measures to prevent equipment damage or excessive wear.

[0031] Obtaining the equipment overload factor has the following advantages for analyzing power supply failures: Accurately assess equipment load: By monitoring and obtaining the overload factor of the equipment, you can accurately understand the current load status of the equipment. When the overload factor exceeds the design capacity of the equipment, the equipment may cause temperature rise, mechanical damage and other problems due to overload, which may lead to failure or shutdown. Therefore, regularly obtaining the overload factor of the equipment will help to promptly detect equipment with excessive load and provide a strong basis for preventing power supply failures.

[0032] Predict failure risks and intervene in advance: Monitoring the overload factor not only helps to understand the working status of the equipment in real time, but also provides data support for predicting possible failure risks. When the overload factor of the equipment is continuously high, it may indicate that the equipment load is in an overloaded operating state for a long time, increasing the probability of failure. By analyzing historical data and combining the trend changes of the overload factor, it is possible to predict the type of failure that may occur in the equipment, and to carry out maintenance or optimize the operation strategy in advance, thereby effectively avoiding power supply interruptions or accidents.

[0033] Optimize equipment scheduling and load distribution: Obtaining the overload coefficient of the equipment can also help the power system make more scientific decisions on scheduling and load distribution. For overloaded equipment, the dispatch center can adjust the load of other equipment, or distribute the load more reasonably through load transfer, etc., to avoid overload operation of a single device. This can not only improve the overall reliability of the power system, but also extend the service life of the equipment and reduce the failure rate caused by overload.

[0034] Helps formulate equipment maintenance strategies: The monitoring data of equipment overload coefficient also provides a scientific basis for equipment maintenance. When the overload coefficient of the equipment is at a high level for a long time, maintenance personnel can adjust the equipment's maintenance cycle, repair plan or replacement plan in a timely manner based on the data. For overloaded equipment, it may be necessary to increase the frequency of regular inspections and maintenance to ensure that the equipment does not cause serious failures due to overload and to ensure the stability of power supply.

[0035] Improve fault location and diagnosis of power systems: When a power system fails, the possible source of the fault can be quickly identified by analyzing the overload factor of the equipment. Equipment with abnormal overload factors is often a potential cause of the fault. By combining overload data with information such as fault type and occurrence time, the scope of the fault can be narrowed, the troubleshooting and recovery time can be shortened, and the fault response capability of the power system can be improved.

[0036] In summary, by obtaining the overload factor of the equipment, we can more accurately evaluate the equipment load condition, predict the risk of failure, optimize scheduling and load distribution, and provide important support for equipment maintenance and fault diagnosis, thereby improving the reliability and stability of the power system and reducing the occurrence of power supply failures.

[0037] The specific method for obtaining the equipment overload coefficient is as follows: Obtain the response time and aging rate of the protection device; Monitor and obtain the temperature limit and cooling system of the transformer in real time, and obtain the overload factor of the transformer through the temperature limit and cooling system of the transformer; Collect data from transmission lines in different regions, apply high-load voltages to transmission lines in different regions, and obtain current carrying capacity, conductor material coefficient, and line temperature rise abnormality coefficient by monitoring the carrying capacity of power transmission lines under high load conditions; The line overload coefficient is calculated according to the current carrying capacity, the conductor material coefficient and the line temperature rise abnormality coefficient; The equipment overload factor is calculated based on the preset equipment overload formula according to the response time and aging rate of the protection device combined with the overload factor of the transformer and the line overload factor.

[0038] The specific calculation formula of the equipment overload coefficient is as follows:

[0039] In the formula, Y is the equipment overload factor, is the line temperature rise abnormality coefficient, d is the conductor material coefficient, is the insulation rate of the wire material, is the current carrying capacity, is the response time of the protection device, is the overload factor of the transformer, is the overload factor of the transformer, is the aging rate of the protection device.

[0040] It should be noted that the overload factor of a transformer is used to evaluate its ability to carry a load exceeding the rated load in a short period of time. Long-term overload operation will affect the life and safety of the transformer, so timely monitoring and management are required. The overload factor of a power transmission line indicates the carrying capacity of the transmission line under high load conditions. The overload factor is usually related to the current carrying capacity of the line, the material of the conductor, the temperature rise of the line, and the protection settings of the system. Line overload will not only cause voltage drop, but may also cause line overheating and equipment damage, so the overload capacity of the line needs to be considered. These data play an important role in analyzing the overload factor of the equipment.

[0041] The communication anomaly coefficient refers to the fact that modern power grids are becoming increasingly automated and rely on information technology for monitoring and dispatching. If the communication network fails, the control system may fail, making it impossible to detect and respond to power grid failures in a timely manner. Power grid monitoring systems usually transmit data through optical fiber, wireless communication, and other methods. If the communication link fails, data cannot be transmitted in a timely manner, which may cause the dispatching system to be unable to obtain real-time data, resulting in dispatch errors or delayed responses. During the power dispatching process, if the data transmission of the monitoring equipment or sensor has problems such as packet loss and garbled data, the correct data will not be obtained, resulting in incorrect dispatching decisions or system failure.

[0042] Obtaining the communication anomaly coefficient has the following advantages for analyzing power supply failures: Improve the accuracy of fault detection: The operating state of the power system is complex, the fault types are diverse, and many faults occur on the communication link between power equipment. The communication anomaly coefficient is obtained by quantitatively analyzing the communication quality and stability between power equipment. When a power supply failure occurs, the communication link is usually affected. By monitoring these anomaly coefficients, the source of the fault can be quickly and accurately identified. In particular, some hidden faults may not be directly reflected in the operating state of the power equipment, but through the fluctuation of the abnormal communication coefficient, problems can be discovered in advance and measures can be taken to avoid further expansion of the fault.

[0043] Realize real-time monitoring and prediction: The power system requires an efficient real-time monitoring and prediction mechanism, especially in large-scale power grids, where there are many devices and wide areas, and the probability and complexity of failures are greatly increased. The communication anomaly coefficient can detect potential failure points early in system operation by real-time monitoring of the signal transmission quality between devices. For example, anomalies such as signal loss, delay or instability in the communication link may indicate that certain equipment is at risk of failure. Capturing this information in a timely manner can help make system adjustments or prevent failures in advance, reducing the impact of failures on power supply.

[0044] Optimize fault location and recovery of power systems: Traditional fault diagnosis methods usually rely on physical monitoring indicators of power equipment, such as voltage, current, temperature, etc., while the communication anomaly coefficient can serve as a supplementary means to provide more intuitive and comprehensive data support. In the event of a fault, the power system can accurately locate the area or equipment where the fault occurred by analyzing abnormal fluctuations on the communication link, which helps to quickly restore power supply. Especially in complex power networks, the communication anomaly coefficient can effectively narrow the scope of troubleshooting, reduce recovery time, and improve system reliability and stability.

[0045] Improve the overall resilience of the power system: The reliability of the power system depends not only on the status of the equipment, but also on the information transmission and coordination within the system. The communication anomaly coefficient can help operation and maintenance personnel monitor and evaluate the communication health status within the power system, discover potential communication problems in advance, and effectively avoid power supply failures caused by communication interruptions. By optimizing the communication link and improving the communication efficiency and fault tolerance of the system, the power system's ability to respond to sudden failures can be significantly improved, and the overall resilience of the system can be enhanced.

[0046] Reduce operation and maintenance costs: By obtaining the communication anomaly coefficient, power companies can achieve more accurate fault diagnosis and prediction, reducing a large amount of manual intervention and ineffective equipment inspection in traditional fault diagnosis. This not only improves operation and maintenance efficiency, but also effectively reduces fault repair costs. In addition, timely discovery and resolution of problems in the communication link can avoid false alarms or delayed maintenance caused by poor communication, further optimizing the configuration of operation and maintenance resources.

[0047] The communication anomaly coefficient is specifically obtained as follows: Acquire data on electromagnetic wave propagation in a channel, wherein the propagation data includes data frame length, transmission rate, channel length, and electromagnetic wave propagation rate; The transmission delay coefficient is calculated based on the data frame length and the transmission rate, and the propagation delay coefficient is calculated based on the channel length and the propagation rate of the electromagnetic wave; According to the transmission delay coefficient and the propagation delay coefficient, a network delay anomaly coefficient is obtained based on a preset network delay anomaly formula; Obtain clock synchronization anomaly coefficient and data packet loss rate in the power system; The communication anomaly coefficient is calculated based on the network delay anomaly coefficient combined with the clock synchronization anomaly coefficient and the data packet loss rate in the power system based on the preset communication anomaly formula.

[0048] The communication anomaly coefficient is specifically calculated as follows:

[0049] In the formula, is the communication anomaly coefficient, bi is the data frame length, is the transmission rate, m is the channel length, ms is the propagation rate of electromagnetic waves, is the clock synchronization anomaly coefficient, is the data packet loss rate.

[0050] It should be noted that the clock synchronization anomaly coefficient will cause data packets to be disordered, lost or delayed. In severe cases, it will cause the system to be unable to exchange information normally, resulting in communication link failure. Network congestion, hardware failure or unstable network connection will cause data packet loss. In power transformation, especially in remote monitoring and control, a large amount of real-time data needs to be transmitted through communication links, and any packet loss may affect the integrity of data transmission. The lost data may include status information, sensor data or control instructions of power equipment, resulting in the system being unable to respond in time, and power equipment operation abnormalities or scheduling errors may occur, leading to instability or failure of the communication link. In power transformation, with the access of distributed energy and the widespread application of smart meters and sensors, the amount of data transmission increases, and the network load may also increase accordingly, causing communication link delays. High latency will lead to the loss of real-time data transmission, especially in key applications such as power dispatching and load management. Excessive latency will cause system response lags, which may cause timeout or failure of the communication link.

[0051] S2, constructing a power supply fault model based on a neural network using the power supply abnormality coefficient, the equipment overload coefficient and the communication abnormality coefficient to generate a power supply fault coefficient. The specific steps are as follows: Obtaining historical power supply abnormality coefficients, historical equipment overload coefficients, and historical communication abnormality coefficients, performing data cleaning on the historical power supply abnormality coefficients, historical equipment overload coefficients, and historical communication abnormality coefficients, processing missing values, and performing data standardization; The preprocessed data is divided into training set and test set. Based on the neural network initialization model, the training set is used as the input layer and the first hidden layer is added. The parameters are automatically adjusted and weighted. Taking the power supply fault as the output layer, constructing a power supply fault model, and using the test set to train and evaluate the power supply fault model to obtain a trained power supply fault model; The newly acquired power supply anomaly coefficient, equipment overload coefficient and communication anomaly coefficient are input into the trained power supply fault model to generate a power supply fault coefficient.

[0052] The specific calculation formula of the power supply failure model is as follows:

[0053] In the formula, is the power supply failure coefficient, is the power supply abnormality coefficient, Y is the equipment overload coefficient, is the communication anomaly coefficient, , , are weight parameters respectively.

[0054] It should be noted that when the power supply abnormality coefficient, communication abnormality coefficient, and equipment overload coefficient become larger and larger, it means that the power supply failure coefficient is becoming more and more obvious.

[0055] S3, obtain the power supply failure coefficient of each node area, draw a power supply-failure curve, and determine the areas where failures occur during the power transformation process based on the power supply-failure curve and prioritize them. The specific steps are as follows: Obtain the power supply failure coefficient of each node area, use the power supply failure coefficient of each node area as the ordinate and each node area as the abscissa to draw a power supply-failure curve; Obtaining a plurality of historical power supply stability coefficients to calculate an average value, and using the average value as a reference threshold value of a power supply-fault curve graph; Marking the node areas on the power supply-fault curve graph that exceed the reference threshold of the power supply-fault curve graph, and obtaining a priority power supply fault troubleshooting table in a downward gradient order; According to the priority power supply fault troubleshooting table, maintenance personnel are notified of areas with serious power supply faults in priority, and fault troubleshooting and repairs are carried out in serious node areas in a timely manner to ensure the stability of work during the power transformation process.

[0056] Embodiment 2, Figure 2 The schematic diagram of the structure of the power transformation path analysis system based on shadow carbon price provided in the embodiment of the present application includes a power supply status data acquisition module, a power supply fault model construction module, and a power supply fault coefficient processing module. There are links between the modules: A power supply status data acquisition module is used to divide the path in the power transformation process into multiple node areas, obtain the power supply status data of each area, and extract the power supply abnormality coefficient, equipment overload coefficient and communication abnormality coefficient from the power supply status data; A power supply fault model building module, used to build a power supply fault model based on a neural network using the power supply abnormality coefficient, the equipment overload coefficient and the communication abnormality coefficient to generate a power supply fault coefficient; The power supply fault coefficient processing module is used to obtain the power supply fault coefficient of each node area, draw a power supply-fault curve diagram, and determine the areas where faults occur during the power transformation process based on the power supply-fault curve diagram and perform priority processing.

[0057] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0058] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0059] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0060] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0061] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0062] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The power transformation path analysis method based on shadow carbon price is characterized by: The steps include: Divide the path in the power transformation process into multiple node areas, obtain power supply status data of each area, and extract power supply abnormality coefficient, equipment overload coefficient and communication abnormality coefficient from the power supply status data; The power supply abnormality coefficient, the equipment overload coefficient and the communication abnormality coefficient are used to construct a power supply fault model based on a neural network to generate a power supply fault coefficient; Obtain the power supply failure coefficient of each node area, draw a power supply-failure curve, and determine the areas where failures occur during the power transformation process based on the power supply-failure curve and perform priority processing.

2. The power transformation path analysis method based on shadow carbon price according to claim 1 is characterized in that: The specific method for obtaining the power supply abnormality coefficient is as follows: Acquire basic data of power supply anomaly in real time, wherein the basic data of power supply anomaly includes remaining capacity and rated capacity of batteries of energy storage devices, charge and discharge current, and temperature; Measuring noise data and load data in multiple time periods, obtaining abnormal noise data and abnormal load data when the noise data and load data in the multiple time periods are higher than preset stable load data and stable noise data; Load forecast abnormal data is calculated based on noise abnormal data and load abnormal data; The battery abnormality data of the energy storage device is obtained by calculating the ratio of the remaining battery capacity and the rated capacity of the energy storage device; The energy storage device abnormality coefficient is calculated based on the preset energy storage device abnormality formula according to the battery abnormality data, charge and discharge current and temperature of the energy storage device; The power supply abnormality coefficient is calculated based on the load forecast abnormality data and the energy storage device abnormality coefficient based on the preset power supply abnormality formula.

3. The power transformation path analysis method based on shadow carbon price according to claim 1 is characterized in that: The specific method for obtaining the equipment overload coefficient is as follows: Obtain the response time and aging rate of the protection device; Monitor and obtain the temperature limit and cooling system of the transformer in real time, and obtain the overload factor of the transformer through the temperature limit and cooling system of the transformer; Collect data from transmission lines in different regions, apply high-load voltages to transmission lines in different regions, and obtain current carrying capacity, conductor material coefficient, and line temperature rise abnormality coefficient by monitoring the carrying capacity of power transmission lines under high load conditions; The line overload coefficient is calculated according to the current carrying capacity, the conductor material coefficient and the line temperature rise abnormality coefficient; The equipment overload factor is calculated based on the preset equipment overload formula according to the response time and aging rate of the protection device combined with the overload factor of the transformer and the line overload factor.

4. The power transformation path analysis method based on shadow carbon price according to claim 1 is characterized in that: The communication anomaly coefficient is specifically obtained as follows: Acquire data on electromagnetic wave propagation in a channel, wherein the propagation data includes data frame length, transmission rate, channel length, and electromagnetic wave propagation rate; The transmission delay coefficient is calculated based on the data frame length and the transmission rate, and the propagation delay coefficient is calculated based on the channel length and the propagation rate of the electromagnetic wave; According to the transmission delay coefficient and the propagation delay coefficient, a network delay anomaly coefficient is obtained based on a preset network delay anomaly formula; Obtain clock synchronization anomaly coefficient and data packet loss rate in the power system; The communication anomaly coefficient is calculated based on the network delay anomaly coefficient combined with the clock synchronization anomaly coefficient and the data packet loss rate in the power system based on the preset communication anomaly formula.

5. The power transformation path analysis method based on shadow carbon price according to claim 1 is characterized in that: The power supply abnormality coefficient, the equipment overload coefficient and the communication abnormality coefficient are used to construct a power supply fault model based on a neural network to generate a power supply fault coefficient. The specific steps are as follows: Obtaining historical power supply abnormality coefficients, historical equipment overload coefficients, and historical communication abnormality coefficients, performing data cleaning on the historical power supply abnormality coefficients, historical equipment overload coefficients, and historical communication abnormality coefficients, processing missing values, and performing data standardization; The preprocessed data is divided into training set and test set. Based on the neural network initialization model, the training set is used as the input layer and the first hidden layer is added. The parameters are automatically adjusted and weighted. Taking the power supply fault as the output layer, constructing a power supply fault model, and using the test set to train and evaluate the power supply fault model to obtain a trained power supply fault model; The newly acquired power supply anomaly coefficient, equipment overload coefficient and communication anomaly coefficient are input into the trained power supply fault model to generate a power supply fault coefficient.

6. The power transformation path analysis method based on shadow carbon price according to claim 1 is characterized in that: The specific steps of obtaining the power supply failure coefficient of each node area, drawing a power supply-failure curve, judging the area where the failure occurs during the power transformation process based on the power supply-failure curve and performing priority processing are as follows: Obtain the power supply failure coefficient of each node area, use the power supply failure coefficient of each node area as the ordinate and each node area as the abscissa to draw a power supply-failure curve graph; Obtaining a plurality of historical power supply stability coefficients to calculate an average value, and using the average value as a reference threshold value of a power supply-fault curve graph; Marking the node areas on the power supply-fault curve graph that exceed the reference threshold of the power supply-fault curve graph, and obtaining a priority power supply fault troubleshooting table in a downward gradient order; According to the priority power supply fault troubleshooting table, maintenance personnel are notified of areas with serious power supply faults in priority, and fault troubleshooting and repairs are carried out in serious node areas in a timely manner to ensure the stability of work during the power transformation process.

7. The power transformation path analysis method based on shadow carbon price according to claim 2 is characterized in that: The specific calculation formula of the abnormal coefficient of the energy storage device is as follows: The specific calculation formula of the power supply abnormality coefficient is as follows: In the formula, is the power supply anomaly coefficient, is the abnormal noise data of the i-th working period, is the load abnormality data of the i-th working period, where i=1,2,3,...,R, R is an integer, N is the node area, is the abnormal coefficient of energy storage equipment, is the remaining battery capacity, is the rated capacity of the battery, is the charging current, is the discharge current, is the actual temperature of the energy storage device, Rated temperature for energy storage equipment.

8. The power transformation path analysis method based on shadow carbon price according to claim 3 is characterized in that: The specific calculation formula of the equipment overload coefficient is as follows: In the formula, Y is the equipment overload factor, is the line temperature rise abnormality coefficient, d is the conductor material coefficient, is the insulation rate of the wire material, is the current carrying capacity, is the response time of the protection device, is the overload factor of the transformer, is the overload factor of the transformer, is the aging rate of the protection device.

9. The method for analyzing power transformation paths based on shadow carbon prices according to claim 4 is characterized in that: The communication anomaly coefficient is specifically calculated as follows: In the formula, is the communication anomaly coefficient, bi is the data frame length, is the transmission rate, m is the channel length, ms is the propagation rate of electromagnetic waves, is the clock synchronization anomaly coefficient, is the data packet loss rate.

10. A system using the power transformation path analysis method based on shadow carbon price according to any one of claims 1 to 9, characterized in that: It includes power supply status data acquisition module, power supply fault model construction module, and power supply fault coefficient processing module. There are links between modules: A power supply status data acquisition module is used to divide the path in the power transformation process into multiple node areas, obtain the power supply status data of each area, and extract the power supply abnormality coefficient, equipment overload coefficient and communication abnormality coefficient from the power supply status data; A power supply fault model building module, used to build a power supply fault model based on a neural network using the power supply abnormality coefficient, the equipment overload coefficient and the communication abnormality coefficient to generate a power supply fault coefficient; The power supply fault coefficient processing module is used to obtain the power supply fault coefficient of each node area, draw a power supply-fault curve diagram, and judge the areas where faults occur during the power transformation process based on the power supply-fault curve diagram and perform priority processing.

Images