Intelligent circuit breaker isolation system and method for intelligent grid-connected cabinet

Abstract

The present invention relates to the technical field of intelligent grid-connected cabinets, and discloses an intelligent circuit breaker isolation system and method for intelligent grid-connected cabinets, the system comprising a circuit breaker isolation module, a monitoring module, a fault prediction module, and a load transfer module; wherein: the circuit breaker isolation module is used to perform fault isolation on the fault line and the risk line in the intelligent grid-connected cabinet; the monitoring module is used to collect the circuit parameters of the intelligent grid-connected cabinet in real time and perform feature extraction on the circuit parameters; the fault prediction module performs fault prediction based on the circuit parameters and identifies the risk line in the intelligent grid-connected cabinet; the load transfer module is used to automatically generate a load transfer plan after the fault line and the risk line are isolated. The present invention solves the deficiencies of traditional grid-connected cabinets in fault detection and isolation, load transfer, etc., and improves the intelligent level of power grid operation.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent grid-connected cabinets, and in particular to an intelligent circuit breaker isolation system and method for intelligent grid-connected cabinets. Background Art

[0002] Distributed power generation systems (such as photovoltaic power generation, wind power generation, etc.) are usually connected to the public power grid through grid cabinets, thereby realizing centralized management and dispatching of electricity. At present, intelligent grid cabinets have been widely used in various distributed energy projects, and their main functions include power conversion, metering, protection, monitoring, etc. A variety of electrical components are integrated inside the grid cabinet, such as circuit breakers, relays, mutual inductors, communication modules, etc. Through the coordinated work of these components, the quality control and safety management of the output power of distributed power sources are realized. With the advancement of Internet of Things technology, grid cabinets have begun to have functions such as data collection and remote monitoring, further improving the level of intelligence in grid operation.

[0003] Although grid-connected cabinets have made significant technological progress, the following problems still exist: When facing grid faults, existing grid-connected cabinets can cut off the power supply through built-in protection devices to prevent the accident from expanding, but there is still much room for improvement in fault detection accuracy and response speed. In particular, for some hidden faults (such as insulation aging, poor contact, etc.), existing detection methods are often difficult to detect in time, resulting in long-term hidden faults and eventually causing larger-scale grid accidents. When a part of the power grid fails, how to quickly adjust the grid structure and reasonably transfer the load in the affected area to the healthy grid branch is an urgent task. The current load transfer mechanism mostly relies on preset transfer paths and manual operations. This method is not only time-consuming, but also difficult to achieve optimal configuration in a complex network environment, often resulting in some areas being without power for a long time, affecting users' normal power consumption.

[0004] For example, a Chinese patent with authorization announcement number CN208257385U discloses an energy storage grid-connected circuit and a grid-connected distribution cabinet, the circuit includes a distribution line drawn from a busbar and connected to a battery pack, a circuit breaker, a transformer, a rectifier, and a switch cabinet are arranged in sequence between the distribution line and the battery pack, a mutual inductor is also arranged between the circuit breaker and the transformer, a protection circuit for monitoring overcurrent and overvoltage of the distribution line is connected to the mutual inductor, the protection circuit includes an overvoltage relay connected in parallel with the mutual inductor, the overvoltage relay contacts are connected to a normally open contact, and an LED and a buzzer are connected in series on the normally open contact circuit; the mutual inductor cooperates with the protection circuit to timely monitor abnormalities in the distribution line and cut off the line in time, thereby protecting the power system; the invention has the advantages of real-time monitoring of the shock caused by the grid connection of the energy storage system and timely handling of circuit faults, but the problem raised by the background technology still exists: it is impossible to quickly adjust the grid structure and reasonably transfer the load of the affected area to the healthy grid branch.

[0005] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention

[0006] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide an intelligent circuit breaker isolation system and method for an intelligent grid-connected cabinet, so as to solve the deficiencies of traditional grid-connected cabinets in fault detection and isolation, load transfer, etc., and improve the intelligence level of grid operation.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] On the one hand, the present invention provides an intelligent circuit breaker and isolation system for an intelligent grid-connected cabinet, comprising a circuit breaker and isolation module, a monitoring module, a fault prediction module, and a load transfer module; wherein:

[0009] The circuit breaker isolation module is used to isolate fault lines and risk lines in the intelligent grid cabinet;

[0010] The monitoring module is used to collect circuit parameters of the intelligent grid-connected cabinet in real time and perform feature extraction on the circuit parameters;

[0011] The fault prediction module performs fault prediction based on the circuit parameters and identifies risky lines in the intelligent grid-connected cabinet;

[0012] The load transfer module is used to automatically generate a load transfer plan after isolating the faulty lines and risky lines.

[0013] As a preferred solution of the intelligent circuit breaker isolation system for intelligent grid-connected cabinets described in the present invention, wherein: the monitoring module includes a data acquisition unit and a data processing unit;

[0014] The data acquisition unit is used to collect circuit parameters of the intelligent grid-connected cabinet; the circuit parameters include current data, voltage data, temperature data, power data, and frequency data of each grid-connected branch;

[0015] The data processing unit is used to clean the circuit parameters of the intelligent grid-connected cabinet, and calculate the characteristic factor of each grid-connected branch based on the circuit parameters after data cleaning;

[0016] The characteristic factors of each grid-connected branch include average current, average voltage, power factor, distortion, average temperature, and peak factor; the characteristic factors are calculated once every sampling period of a fixed length, and each characteristic factor of each grid-connected branch calculated in each sampling period is sorted into a corresponding time series.

[0017] As a preferred solution of the intelligent circuit breaker isolation system for the intelligent grid-connected cabinet described in the present invention, wherein: the average current of any grid-connected branch is the average value of the current in a sampling period; the average voltage of any grid-connected branch is the average value of the voltage in a sampling period; the power factor of any grid-connected branch is the ratio of active power to apparent power in a sampling period; the average temperature of any grid-connected branch is the average value of the temperature at all cable joints of the grid-connected branch in a sampling period; the peak factor of any grid-connected branch is the ratio of peak current to average current in a sampling period; the calculation formula of the distortion of any grid-connected branch is as follows:

[0018] ;

[0019] in, Indicates the degree of distortion within any sampling period; Indicates the amplitude of the fundamental wave; Represents the amplitude of the i-th harmonic.

[0020] As a preferred solution of the intelligent circuit breaker and isolation system for intelligent grid-connected cabinets of the present invention, the circuit breaker and isolation module comprises a circuit breaker unit and a control switch unit; wherein the circuit breaker unit is used to automatically detect circuit faults and disconnect the faulty circuit; the control switch unit is used to isolate the faulty line and the risky line;

[0021] The circuit breaker unit is configured with a circuit breaker. When the current of the circuit configured with the circuit breaker exceeds the current threshold of the circuit breaker or the temperature of the circuit breaker exceeds the temperature threshold, the circuit breaker automatically cuts off the circuit and sends fault isolation information to the control switch unit; the control switch unit parses the fault isolation information, obtains the grid-connected branch corresponding to the faulty circuit, and cuts off the grid-connected branch through the switch.

[0022] As a preferred solution of the intelligent circuit breaker isolation system for intelligent grid-connected cabinets described in the present invention, the fault prediction module includes a prediction model unit and an isolation control unit; wherein:

[0023] The prediction model unit is configured with a fault prediction model for calculating the failure probability of each grid-connected branch; the fault prediction model is any one of a recurrent neural network, a long short-term memory network, and a gated recurrent unit, the input of which is the time series of each characteristic factor of each grid-connected branch, and the output is the failure probability of each grid-connected branch; the isolation control unit is configured with a failure probability threshold of the grid-connected branch; the isolation control unit marks any grid-connected branch whose failure probability is higher than the failure probability threshold as a risk line, and sends risk line information to the control switch unit, the control switch unit parses the risk line information, obtains the risk line, and cuts off the risk line by controlling the switch; the isolation control unit is also configured with a threshold range for each characteristic factor, and when any characteristic factor of any grid-connected branch exceeds the corresponding threshold range, it is marked as a risk line.

[0024] As a preferred solution of the intelligent circuit breaker isolation system for intelligent grid-connected cabinets described in the present invention, the fault prediction module further includes a frequency monitoring unit for monitoring the grid frequency; after each frequency detection cycle, N grid frequency values ​​are collected at a fixed sampling interval, and the frequency fluctuation index of the grid is calculated, and the formula is as follows:

[0025] ;

[0026] Where r represents the frequency fluctuation index of the power grid in any frequency detection cycle; Indicates the maximum frequency value of the power grid during the frequency detection cycle; Indicates the minimum frequency value of the power grid during the frequency detection cycle; express The corresponding time point; express The corresponding time point; represents the jth frequency value of the power grid in the frequency detection cycle; is the standard frequency of the power grid; , All are weight coefficients;

[0027] The frequency monitoring unit is configured with a fault risk adjustment strategy, which is as follows: the frequency monitoring unit is configured with a normal threshold of the frequency fluctuation index; if the frequency fluctuation index of any frequency detection cycle is higher than the normal threshold, the frequency monitoring unit sends frequency abnormality information to the isolation control unit; after receiving the frequency abnormality information, the isolation control unit reduces the threshold range of each characteristic factor.

[0028] As a preferred solution of the intelligent circuit breaker isolation system for intelligent grid-connected cabinets described in the present invention, wherein: the load transfer module includes a load information unit and a transfer strategy unit; wherein the load information unit is used to obtain load information corresponding to the load to be transferred; the transfer strategy unit formulates a load transfer plan based on the load information;

[0029] The load information unit records the load information of each load, including load priority and load amount; after fault isolation, the control switch unit sends isolation information to the load information unit, and the load information unit queries the load information of all grid-connected branches that have undergone fault isolation based on the isolation information and transmits it to the transfer strategy unit.

[0030] As a preferred solution of the intelligent circuit breaker isolation system for intelligent grid-connected cabinets of the present invention, the method for the transfer strategy unit to formulate a load transfer plan based on load information is as follows:

[0031] S100: Calculate the remaining power supply of each distributed power generation device and calculate the total remaining power supply;

[0032] S200: Number the loads corresponding to the loads to be transferred in descending order of priority and construct a list to be transferred; the kth row in the list to be transferred includes the load with the kth priority and the number and load amount corresponding to the load;

[0033] S300: setting the first load in the list to be transferred as the current load and removing it from the list to be transferred;

[0034] S400: Determine whether the current load is not greater than the total remaining power supply. If so, proceed to step S500; if not, return to step S300;

[0035] S500: allocating a transfer plan for the current load;

[0036] S600: updating the remaining power supply of each distributed generation device and the total remaining power supply based on the transfer plan for the current load distribution;

[0037] S700: Repeat steps S300 to S600 until the list of loads to be transferred is empty, save the transfer plan for each load distribution, and obtain the load transfer plan.

[0038] As a preferred solution of the intelligent circuit breaker and isolation system for the intelligent grid-connected cabinet described in the present invention, the method for distributing the current load transfer scheme is as follows: randomly select a distributed power generation device whose remaining power supply is not less than the load of the current load for load transfer to the current load; if the remaining power supply of all distributed power generation devices is less than the load of the current load, the current load is load cut to obtain m load sub-loads; select m distributed power generation devices to transfer load to the m load sub-loads respectively.

[0039] As a preferred solution of the intelligent circuit breaker isolation system for intelligent grid-connected cabinets described in the present invention, the method in which the transfer strategy unit formulates a load transfer plan based on load information also includes: repeatedly executing steps S300 to S700 to obtain M load transfer plans; calculating the objective function of each load transfer plan, and transmitting the load transfer plan with the largest objective function to the control switch unit; the calculation formula of the objective function of any load transfer plan is as follows:

[0040] ;

[0041] Where T represents the objective function; Q represents the total load transferred in the load transfer scheme; Indicates the total number of load shedding in the load transfer scheme; is the weight coefficient.

[0042] In a second aspect, the present invention provides an intelligent circuit breaker isolation method for an intelligent grid-connected cabinet, comprising the following steps:

[0043] S1: Collecting circuit parameters of the intelligent grid-connected cabinet and extracting features of the circuit parameters to obtain characteristic factors of each grid-connected branch;

[0044] S2: Perform fault prediction and characteristic factor detection based on the circuit parameters to identify risky lines in the smart grid cabinet;

[0045] S3: Isolate the risk line fault by controlling the switch;

[0046] S4: Obtain load information corresponding to the load to be transferred after fault isolation, and formulate a load transfer plan based on the load information.

[0047] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0048] By combining the circuit breaker isolation module with the monitoring module, the present invention can monitor key parameters such as current, voltage, and temperature in the grid-connected cabinet in real time, and respond immediately when an abnormal situation is detected, automatically cut off the fault circuit, effectively prevent the spread of the fault, and ensure the safety of the power grid. By using the fault prediction model, combined with historical data and real-time monitoring data, the present invention can identify potential risk lines in advance and achieve forward-looking early warning of faults. This helps operation and maintenance personnel take timely measures to eliminate hidden dangers, reduce unplanned downtime, and improve the reliability of power grid operation.

[0049] The load transfer module provided by the present invention can automatically calculate the optimal load transfer scheme according to the load information to ensure that the power supply in the non-fault area is not affected. Through reasonable load distribution, not only the utilization rate of power grid resources is improved, but also the impact caused by frequent load switching is reduced, and the service life of the equipment is extended. Taking into account the remaining power supply capacity of the distributed power generation device and the priority of each load, the dynamic allocation of power resources is realized, the needs of important loads are met to the greatest extent, while avoiding power waste and promoting the economic operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0051] Figure 1 A schematic diagram of the structure of an intelligent circuit breaker and isolation system for an intelligent grid-connected cabinet provided by the present invention;

[0052] Figure 2 A flow chart of an intelligent circuit breaker and isolation method for an intelligent grid-connected cabinet provided by the present invention;

[0053] Figure 3 A flow chart of a method for formulating a load transfer plan based on load information provided by the present invention. DETAILED DESCRIPTION

[0054] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0055] Example 1

[0056] This embodiment introduces an intelligent circuit breaker isolation system for an intelligent grid-connected cabinet. Figure 1 The system includes a circuit breaker isolation module, a monitoring module, a fault prediction module, and a load transfer module; wherein:

[0057] The circuit breaker isolation module is used to isolate fault lines and risk lines in the intelligent grid cabinet;

[0058] The circuit breaker isolation module includes a circuit breaker unit and a control switch unit; wherein the circuit breaker unit is used to automatically detect circuit faults and disconnect the faulty circuit; the control switch unit is used to isolate the faulty line and the risky line;

[0059] The circuit breaker unit is configured with a circuit breaker. When the current of the circuit configured with the circuit breaker exceeds the current threshold of the circuit breaker or the temperature of the circuit breaker exceeds the temperature threshold, the circuit breaker automatically cuts off the circuit and sends fault isolation information to the control switch unit; the control switch unit parses the fault isolation information, obtains the grid-connected branch corresponding to the faulty circuit, and cuts off the grid-connected branch through the switch.

[0060] The grid-connected branch refers to the line and a series of equipment from the output end of the distributed energy generation device (such as photovoltaic arrays, wind turbines, etc.) to the connection point with the public power grid or user load. The equipment on this path usually includes but is not limited to inverters, circuit breakers, electric meters, monitoring equipment, etc.

[0061] The circuit breaker includes a thermal release and an electromagnetic release; wherein the thermal release uses a bimetallic strip. When the current is abnormal for a long time, the bimetallic strip deforms due to the temperature rise, triggering the tripping mechanism to disconnect the circuit;

[0062] The electromagnetic release uses the magnetic field generated by the current to drive the tripping mechanism. When the current reaches the current threshold, the magnetic field strength is sufficient to overcome the spring force or other resistance, causing the circuit breaker to cut off the circuit. In addition to the traditional temperature-triggered circuit breaker mechanism, the design of this circuit breaker also adds the function of current overload protection, enabling it to respond immediately when an abnormal situation is detected. For example, in the event of a short circuit, the electromagnetic release can respond immediately and disconnect the circuit breaker. This instant response function ensures that the circuit can be quickly cut off in the event of a fault, thereby minimizing the risk of equipment damage and safety accidents.

[0063] After the circuit breaker cuts off the circuit, the faulty line still needs to be physically isolated by the control switch to prevent the fault from spreading to other areas of the power grid. The control switch provides an obvious breakpoint so that maintenance personnel can intuitively see that the circuit has been cut off, thereby ensuring safety during maintenance. In addition to isolating the faulty line and the risky line, the control switch unit is also used to reconstruct the circuit network in the grid cabinet to implement the load transfer plan after the fault is isolated. After the fault area is isolated, the topology of the power grid can be changed by operating the control switch, and the load originally powered by the faulty area can be transferred to the healthy power grid branch. The load transfer plan aims to ensure that the power supply in the non-faulty area is not affected, and the load is transferred to other available power sources by adjusting the switch state in the power grid. The control switch unit implements the load transfer plan by adjusting the open and closed state of each control switch.

[0064] The monitoring module is used to collect circuit parameters of the intelligent grid-connected cabinet in real time and extract features of the circuit parameters; it includes a data acquisition unit and a data processing unit;

[0065] The data acquisition unit is used to collect circuit parameters of the intelligent grid-connected cabinet; the circuit parameters include current data, voltage data, temperature data, power data, and frequency data of each grid-connected branch;

[0066] The data processing unit is used to clean the circuit parameters of the intelligent grid-connected cabinet, and calculate the characteristic factor of each grid-connected branch based on the circuit parameters after data cleaning;

[0067] The characteristic factors of each grid-connected branch include average current, average voltage, power factor, distortion, average temperature, and peak factor; the characteristic factors are calculated once every fixed-length sampling period, and each characteristic factor of each grid-connected branch calculated in each sampling period is sorted into a corresponding time series; wherein, the average current of any grid-connected branch is the average value of the current in a sampling period; the change of current can reflect the change of branch load, and excessive current may cause overheating or overload, thereby causing a fault. The average voltage of any grid-connected branch is the average value of the voltage in a sampling period; voltage fluctuations or instability may cause equipment damage, so monitoring voltage can help discover potential problems. The power factor of any grid-connected branch is the ratio of active power to apparent power in a sampling period; apparent power is the product of current and voltage in the circuit, including active power and reactive power. The power data collected by the multi-function meter includes active power and apparent power of each grid-connected branch; low power factor means more reactive power, which will increase the burden on the power grid and may cause equipment efficiency to decrease. The average temperature of any grid-connected branch is the average temperature of all cable joints of the grid-connected branch within a sampling period; monitoring the temperature helps to detect overheating problems in a timely manner, and excessively high temperatures may cause thermal runaway. The peak factor of any grid-connected branch is the ratio of the peak current to the average current within a sampling period; different load characteristics will have different effects on the power grid, and the peak factor reflects the load characteristics of the grid-connected branch. Understanding the load characteristics helps to better manage grid resources. The calculation formula for the distortion of any grid-connected branch is as follows:

[0068] ;

[0069] in, Indicates the degree of distortion within any sampling period; Indicates the amplitude of the fundamental wave; Represents the amplitude of the ith harmonic; a multifunctional electric meter with harmonic analysis function is used to collect the frequency data, including the amplitude data of the fundamental wave and the harmonic; harmonics are frequency components other than the fundamental wave in alternating current, which will cause interference to the power grid and affect the power quality and the normal operation of the equipment.

[0070] The fault prediction module performs fault prediction based on the circuit parameters and identifies risky lines in the intelligent grid-connected cabinet; it includes a prediction model unit and an isolation control unit; wherein:

[0071] The prediction model unit is configured with a fault prediction model for calculating the fault probability of each grid-connected branch; the fault prediction model is any one of a recurrent neural network, a long short-term memory network, and a gated recurrent unit, the input of which is the time series of each characteristic factor of each grid-connected branch, and the output is the fault probability of each grid-connected branch; the isolation control unit is configured with a fault probability threshold of the grid-connected branch, any grid-connected branch with a fault probability higher than the fault probability threshold is marked as a risk line, and the risk line information is sent to the control switch unit, the control switch unit parses the risk line information, obtains the risk line, and cuts off the risk line by controlling the switch; the isolation control unit is also configured with a threshold range for each characteristic factor, and when any characteristic factor of any grid-connected branch exceeds the corresponding threshold range, it is marked as a risk line.

[0072] The fault prediction model includes an input layer, a circulation layer, a dense layer, and an output layer; wherein the input layer is used to receive input data, i.e., the time series of each characteristic factor of each grid-connected branch; the input layer defines the format requirements of the input data, including the number of samples, the time step, and the number of features, wherein the number of samples is the number of grid-connected branches, the time step is the time series length of any characteristic factor, and the number of features is the number of types of characteristic factors; the circulation layer is used to extract the time series features of the input data; in this process, the circulation layer retains the characteristic information of each time step, thereby capturing the time dependency in the time series; the dense layer is used to further extract the high-level features of the input data; the dense layer is used to further extract the high-level features of the input data from the time series features extracted by the circulation layer. These layers increase the expressive power of the model through nonlinear activation functions (such as ReLU, tanh, etc.); the feature dimension can be reduced through the processing of the dense layer, thereby reducing the complexity of the model; the output layer is used to calculate the output of the model, i.e., the fault probability of each grid-connected branch; the activation function is used to map the output of each neuron to between 0 and 1, indicating the fault probability of each grid-connected branch. For each branch, the probability value output by the model indicates the possibility of failure of the branch in a certain period of time in the future. This probability value is a real number between 0 and 1. The larger the value, the higher the possibility of failure. Define the structure of the fault prediction model through deep learning frameworks such as TensorFlow and PyTorch, collect historical data and train the model, use cross-validation to evaluate model performance and find the optimal hyperparameter combination through grid search, random search and other methods, and introduce regularization techniques such as dropout to prevent overfitting. Deploy the trained fault prediction model and continuously monitor its performance. If necessary, adjust and optimize the model based on feedback.

[0073] The fault prediction module also includes a frequency monitoring unit for monitoring the power grid frequency; after each frequency detection cycle, N power grid frequency values ​​are collected at a fixed sampling interval, where N is a positive integer, and the frequency fluctuation index of the power grid is calculated, and the formula is as follows:

[0074] ;

[0075] Where r represents the frequency fluctuation index of the power grid in any frequency detection cycle; Indicates the maximum frequency value of the power grid during the frequency detection cycle; Indicates the minimum frequency value of the power grid during the frequency detection cycle; express The corresponding time point; express The corresponding time point; represents the jth frequency value of the power grid in the frequency detection cycle; is the standard frequency of the power grid, which is set by technicians in this field based on experience, such as 50 Hz; , They are all weight coefficients, which are set by technicians in this field based on actual needs;

[0076] The dimension is ignored in the calculation process of the frequency fluctuation index of the above power grid; the first summation item reflects the speed of the power grid frequency change, and the second summation item represents the average level of the power grid frequency fluctuation; the weighted sum of the two items can comprehensively reflect the stability of the power grid frequency. The frequency of the power grid should be stable at a constant value (such as the standard frequency of my country's power grid is 50Hz). If the power grid frequency fluctuates abnormally, it may be caused by a sudden change in load or a power grid failure.

[0077] The frequency monitoring unit is configured with a fault risk adjustment strategy, which is as follows: the frequency monitoring unit is configured with a normal threshold of the frequency fluctuation index; if the frequency fluctuation index of any frequency detection cycle is higher than the normal threshold, the frequency monitoring unit sends frequency abnormality information to the isolation control unit; after receiving the frequency abnormality information, the isolation control unit reduces the threshold range of each characteristic factor. For example, based on the interval endpoint or the interval midpoint of the threshold range of each characteristic factor, the threshold range is reduced by 30%;

[0078] The grid-connected cabinet centrally regulates distributed power generation energy and inputs it into the grid to supply power to user loads. During this process, if some grid-connected branches have abnormal current or voltage, it may cause grid frequency fluctuations and affect grid stability. If the fault prediction module fails to identify the risk line at this time, it cannot exclude the grid-connected branch that makes the grid frequency unstable. Therefore, it is necessary to reduce the threshold range of each characteristic factor at this time to improve the sensitivity of risk route identification.

[0079] The load transfer module is used to automatically generate a load transfer plan after isolating the faulty lines and risky lines.

[0080] The load transfer module includes a load information unit and a transfer strategy unit; wherein the load information unit is used to obtain load information corresponding to the load to be transferred; and the transfer strategy unit formulates a load transfer plan based on the load information;

[0081] The load information unit records the load information of each load, including load priority and load quantity; wherein the load priority indicates the importance of each load, and is usually used to determine which loads should be given priority when the power supply is limited; the load quantity indicates the amount of electric energy required by each load, and can be used to calculate the power demand. After the fault is isolated, the control switch unit sends the isolation information to the load information unit, and the load information unit queries the load information of all grid-connected branches that have undergone fault isolation based on the isolation information and transmits it to the transfer strategy unit; the method for the transfer strategy unit to formulate a load transfer plan based on the load information is referred to Figure 3 , as follows:

[0082] S100: Calculate the remaining power supply of each distributed power generation device at present, and calculate the total remaining power supply; the remaining power supply is the difference between the power generation and the load load; wherein the load load is the total load of all loads being powered by the distributed power generation device; the total remaining power supply is the sum of the remaining power supplies of all distributed power generation devices;

[0083] S200: Number the loads corresponding to the loads to be transferred in descending order of priority and construct a list to be transferred; the kth row in the list to be transferred includes the load with the kth priority and the number and load amount corresponding to the load;

[0084] S300: setting the first load in the list to be transferred as the current load and removing it from the list to be transferred;

[0085] S400: Determine whether the current load is not greater than the total remaining power supply. If so, proceed to step S500; if not, return to step S300;

[0086] S500: Distribute the current load transfer plan; the method is as follows:

[0087] Randomly select a distributed generation device whose remaining power supply is not less than the load of the current load to transfer the load to the current load; if the remaining power supply of all distributed generation devices is less than the load of the current load, the current load is load-cut to obtain m load sub-loads, where m is a positive integer; select m distributed generation devices to transfer the load to the m load sub-loads respectively;

[0088] S600: Based on the current load distribution transfer scheme, the remaining power supply of each distributed power generation device and the total remaining power supply are updated; the method subtracts the load that the distributed power generation device is responsible for transferring in the current distribution transfer scheme from the remaining power supply of any distributed power generation device before the current distribution transfer scheme, as the updated value of the remaining power supply; subtracts the current load from the total remaining power supply before the current distribution transfer scheme, as the updated value of the total remaining power supply;

[0089] S700: repeating steps S300 to S600 until the list of loads to be transferred is empty, saving the transfer plan for each load distribution, and obtaining the load transfer plan;

[0090] Repeat steps S300 to S700 to obtain M load transfer schemes, where M is a positive integer; calculate the objective function of each load transfer scheme, and transmit the load transfer scheme with the largest objective function to the control switch unit; the calculation formula of the objective function of any load transfer scheme is as follows:

[0091] ;

[0092] Wherein, T represents the objective function; Q represents the total load transferred in the load transfer scheme, that is, the sum of the loads of all loads assigned to the transfer scheme; It indicates the total number of load shedding in the load transfer scheme, that is, the total number of load sub-loads; is a weight coefficient, which is set by technicians in this field based on actual needs. Based on the above objective function, the selected load transfer scheme takes into account both maximizing the total amount of load transfer and suppressing the number of load cutting; maximizing load transfer can make full use of available power resources, avoid waste, improve the economic benefits of the power system, and reduce unnecessary expenses; frequent load cutting may bring shocks to the power grid, increase equipment wear and failure risks, and by suppressing the number of cuttings, this shock can be reduced, which helps to extend equipment life and improve system stability.

[0093] Example 2

[0094] Based on the same inventive concept as in Example 1, refer to Figure 2 This embodiment introduces an intelligent circuit breaker isolation method for an intelligent grid-connected cabinet, comprising the following steps:

[0095] S1: Collecting circuit parameters of the intelligent grid-connected cabinet and extracting features of the circuit parameters to obtain characteristic factors of each grid-connected branch; the collected circuit parameters include current data, voltage data, temperature data, power data, and frequency data of each grid-connected branch; the characteristic factors extracted based on these circuit parameters include average current, average voltage, power factor, distortion, average temperature, and peak factor;

[0096] S2: Perform fault prediction and characteristic factor detection based on the circuit parameters to identify risk lines in the intelligent grid-connected cabinet; calculate the fault probability of each grid-connected branch based on the fault prediction model, and the grid-connected branch with a fault probability higher than the fault probability threshold is a risk line; any grid-connected branch with a characteristic factor exceeding the corresponding threshold range is also a risk line;

[0097] S3: Isolate the risk line fault by controlling the switch;

[0098] S4: Obtain the load information corresponding to the load to be transferred after the fault is isolated, and formulate a load transfer plan based on the load information; the load information includes load priority and load amount; the formulated load transfer plan maximizes the total load transfer amount and suppresses the number of load cutting times under the premise of considering the priority, so as to make full use of available power resources and ensure the stability of the system.

[0099] The specific functional implementation of each of the above steps refers to the relevant content of the intelligent circuit breaker isolation system for the intelligent grid-connected cabinet described in Example 1, and will not be repeated here.

[0100] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose and scope of protection of the present invention, which are all within the protection of the present invention.

Claims

1. An intelligent circuit breaker isolation system for an intelligent grid-connected cabinet, characterized in that: It includes circuit breaker isolation module, monitoring module, fault prediction module and load transfer module; among which: The circuit breaker isolation module is used to isolate fault lines and risk lines in the intelligent grid cabinet; The monitoring module is used to collect circuit parameters of the intelligent grid-connected cabinet in real time and perform feature extraction on the circuit parameters; The fault prediction module performs fault prediction based on the circuit parameters and identifies risky lines in the intelligent grid-connected cabinet; The fault prediction module includes a prediction model unit and an isolation control unit; wherein: The prediction model unit is configured with a fault prediction model for calculating the fault probability of each grid-connected branch; the fault prediction model is any one of a recurrent neural network, a long short-term memory network, and a gated recurrent unit, the input of which is the time series of each characteristic factor of each grid-connected branch, and the output is the fault probability of each grid-connected branch; the isolation control unit is configured with a fault probability threshold of the grid-connected branch; the isolation control unit marks any grid-connected branch whose fault probability is higher than the fault probability threshold as a risk line, and sends risk line information to the control switch unit, the control switch unit parses the risk line information, obtains the risk line, and cuts off the risk line by controlling the switch; the isolation control unit is also configured with a threshold range of each characteristic factor, and when any characteristic factor of any grid-connected branch exceeds the corresponding threshold range, it is marked as a risk line; The fault prediction module also includes a frequency monitoring unit for monitoring the power grid frequency; after each frequency detection cycle, N power grid frequency values ​​are collected at a fixed sampling interval, and the frequency fluctuation index of the power grid is calculated, and the formula is as follows: ； Where r represents the frequency fluctuation index of the power grid in any frequency detection cycle; Indicates the maximum frequency value of the power grid during the frequency detection cycle; Indicates the minimum frequency value of the power grid during the frequency detection cycle; express The corresponding time point; express The corresponding time point; represents the jth frequency value of the power grid in the frequency detection cycle; is the standard frequency of the power grid; , All are weight coefficients; The frequency monitoring unit is configured with a fault risk adjustment strategy, which is as follows: the frequency monitoring unit is configured with a normal threshold of the frequency fluctuation index; if the frequency fluctuation index of any frequency detection cycle is higher than the normal threshold, the frequency monitoring unit sends frequency abnormality information to the isolation control unit; after receiving the frequency abnormality information, the isolation control unit reduces the threshold range of each characteristic factor; The load transfer module is used to automatically generate a load transfer plan after isolating the faulty lines and risky lines.

2. The intelligent circuit breaker isolation system for an intelligent grid-connected cabinet according to claim 1, characterized in that: The monitoring module includes a data acquisition unit and a data processing unit; The data acquisition unit is used to collect circuit parameters of the intelligent grid-connected cabinet; the circuit parameters include current data, voltage data, temperature data, power data, and frequency data of each grid-connected branch; The data processing unit is used to clean the circuit parameters of the intelligent grid-connected cabinet, and calculate the characteristic factor of each grid-connected branch based on the circuit parameters after data cleaning; The characteristic factors of each grid-connected branch include average current, average voltage, power factor, distortion, average temperature, and peak factor; the characteristic factors are calculated once every sampling period of a fixed length, and each characteristic factor of each grid-connected branch calculated in each sampling period is sorted into a corresponding time series.

3. The intelligent circuit breaker isolation system for an intelligent grid-connected cabinet according to claim 2, characterized in that: The average current of any grid-connected branch is the average value of the current in a sampling period; the average voltage of any grid-connected branch is the average value of the voltage in a sampling period; The power factor of any grid-connected branch is the ratio of active power to apparent power within a sampling period; the average temperature of any grid-connected branch is the average temperature of all cable joints of the grid-connected branch within a sampling period; the peak factor of any grid-connected branch is the ratio of peak current to average current within a sampling period; the calculation formula of the distortion of any grid-connected branch is as follows: ； in, Indicates the degree of distortion within any sampling period; Indicates the amplitude of the fundamental wave; Represents the amplitude of the i-th harmonic.

4. The intelligent circuit breaker isolation system for an intelligent grid-connected cabinet according to claim 3, characterized in that: The circuit breaker isolation module includes a circuit breaker unit and a control switch unit; wherein the circuit breaker unit is used to automatically detect circuit faults and disconnect the faulty circuit; the control switch unit is used to isolate the faulty line and the risky line; The circuit breaker unit is configured with a circuit breaker. When the current of the circuit configured with the circuit breaker exceeds the current threshold of the circuit breaker or the temperature of the circuit breaker exceeds the temperature threshold, the circuit breaker automatically cuts off the circuit and sends fault isolation information to the control switch unit; the control switch unit parses the fault isolation information, obtains the grid-connected branch corresponding to the faulty circuit, and cuts off the grid-connected branch through the switch.

5. The intelligent circuit breaker and isolation system for an intelligent grid-connected cabinet according to claim 4, characterized in that: The load transfer module includes a load information unit and a transfer strategy unit; wherein the load information unit is used to obtain load information corresponding to the load to be transferred; and the transfer strategy unit formulates a load transfer plan based on the load information; The load information unit records the load information of each load, including load priority and load amount; after fault isolation, the control switch unit sends isolation information to the load information unit, and the load information unit queries the load information of all grid-connected branches that have undergone fault isolation based on the isolation information and transmits it to the transfer strategy unit.

6. The intelligent circuit breaker isolation system for an intelligent grid-connected cabinet according to claim 5, characterized in that: The method for the transfer strategy unit to formulate a load transfer plan based on load information is as follows: S100: Calculate the remaining power supply of each distributed power generation device and calculate the total remaining power supply; S200: Number the loads corresponding to the loads to be transferred in descending order of priority and construct a list to be transferred; the kth row in the list to be transferred includes the load with the kth priority and the number and load amount corresponding to the load; S300: setting the first load in the list to be transferred as the current load and removing it from the list to be transferred; S400: Determine whether the current load is not greater than the total remaining power supply. If so, proceed to step S500; if not, return to step S300; S500: allocating a transfer plan for the current load; S600: updating the remaining power supply of each distributed generation device and the total remaining power supply based on the transfer plan for the current load distribution; S700: Repeat steps S300 to S600 until the list of loads to be transferred is empty, save the transfer plan for each load distribution, and obtain the load transfer plan.

7. The intelligent circuit breaker and isolation system for an intelligent grid-connected cabinet according to claim 6, characterized in that: The method for distributing the transfer scheme for the current load is as follows: randomly select a distributed power generation device whose remaining power supply is not less than the load of the current load to transfer the load to the current load; if the remaining power supply of all distributed power generation devices is less than the load of the current load, load cutting is performed on the current load to obtain m load sub-loads; and m distributed power generation devices are selected to transfer the load to the m load sub-loads respectively.

8. The intelligent circuit breaker and isolation system for an intelligent grid-connected cabinet according to claim 7, characterized in that: The method for the transfer strategy unit to formulate a load transfer plan based on load information also includes: repeatedly executing steps S300 to S700 to obtain M load transfer plans; calculating the objective function of each load transfer plan, and transmitting the load transfer plan with the largest objective function to the control switch unit; the calculation formula of the objective function of any load transfer plan is as follows: ； Where T represents the objective function; Q represents the total load transferred in the load transfer scheme; Indicates the total number of load shedding in the load transfer scheme; is the weight coefficient.

9. An intelligent circuit breaker and isolation method for an intelligent power-connected cabinet, implemented based on the intelligent circuit breaker and isolation system for an intelligent power-connected cabinet according to any one of claims 1 to 8, characterized in that: The following steps are involved: S1: Collecting circuit parameters of the intelligent grid-connected cabinet and extracting features of the circuit parameters to obtain characteristic factors of each grid-connected branch; S2: Perform fault prediction and characteristic factor detection based on the circuit parameters to identify risky lines in the smart grid cabinet; S3: Isolate the risk line fault by controlling the switch; S4: Obtain load information corresponding to the load to be transferred after fault isolation, and formulate a load transfer plan based on the load information.

Images