Distributed energy access power distribution network fault diagnosis method and system

Abstract

The invention discloses a distributed energy access power distribution network fault diagnosis method and system, and relates to the technical field of power distribution network fault diagnosis, and the method comprises the steps: collecting gas fuel aspect data and renewable energy aspect data; judging whether the gas fuel aspect data meets a first threshold condition or not; judging whether the renewable energy aspect data meets a second threshold condition or not; and inputting the monitoring data obtained in the two aspects as sample set data into the improved sand dune cat optimization model to obtain optimized parameters, and performing fault diagnosis on the power distribution network based on the optimized parameters. Power distribution network fault diagnosis is determined by considering the influence of energy access in two aspects of gas fuel and renewable energy on the power distribution network, and whether power distribution network faults occur or not is determined by monitoring comparison between state parameters in the operation process of the power distribution network and a set threshold value. According to the method, the monitoring and calculation process is simple, the diagnosis efficiency is high, and the diagnosis result is comprehensive.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network fault diagnosis, and in particular to a distribution network fault diagnosis method and system for accessing distributed energy sources. Background Art

[0002] Distributed energy refers to an energy comprehensive utilization system distributed at the user end. Primary energy is mainly gas fuel, supplemented by renewable energy, and all available resources are utilized. Large-scale access to distributed energy will have a certain impact on the distribution network, including voltage fluctuations, power imbalance, harmonic pollution, etc. Chinese invention patent CN117031197A discloses a method for diagnosing faults in a distribution network of distributed renewable energy: obtaining basic information of each wind turbine corresponding to the target distribution network through real-time monitoring, and analyzing to obtain the fault risk coefficient of each wind turbine corresponding to the distribution network, and then diagnosing the fault of each wind turbine corresponding to the distribution network; obtaining the terminal current of each branch cable corresponding to each monitoring segment, and analyzing it to obtain the fault risk coefficient of each branch cable corresponding to the monitoring segment of the target distribution network, so as to diagnose the fault of each monitoring point; obtaining the temperature of each sub-segment of the main line, and calculating the operating fault risk coefficient of each sub-segment for fault diagnosis. It can be seen that the patent does not propose to diagnose distribution network faults by monitoring gas fuels in distributed energy. In addition, the fault risk coefficient is calculated when monitoring the renewable energy trunk lines and branches of the distribution network, which does not take into account the factors of the natural environment, making the results too inaccurate. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is: how to solve the problem of monitoring gas fuel in distributed energy that is not proposed in the existing methods.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a method for diagnosing faults in a distribution network with distributed energy access, comprising: collecting gas fuel data and renewable energy data; judging whether the gas fuel data meets a first threshold condition; judging whether the renewable energy data meets a second threshold condition; using the monitoring data obtained from the two aspects as sample set data, inputting them into an improved sand cat optimization model to obtain optimized parameters, and performing fault diagnosis on the distribution network based on the optimized parameters.

[0006] As a preferred scheme of the distribution network fault diagnosis method for distributed energy access described in the present invention, the data on gas fuel includes monitoring the amount of air and flue gas for fuel combustion and the temperature of fuel combustion; the data on renewable energy includes light radiation, temperature and wind speed.

[0007] As a preferred solution of the method for diagnosing faults in a distribution network of distributed energy access according to the present invention, the monitoring of the air volume and flue gas volume of fuel combustion includes setting an air volume threshold and a flue gas volume threshold, which are expressed as:

[0008] Q n =nλ 1 +0.00124g×nλ 1

[0009] V n =λ 2 +β+0.00124g×nλ 1

[0010] Among them, Q n To monitor the amount of air in the fuel, n is the excess air coefficient, λ 1 is the set air volume threshold; V n To monitor the flue gas volume of the fuel, λ 2 is the set flue gas volume threshold, β is the excess oxygen content, and 0.00124g is the moisture content in the air; the first threshold condition includes the air volume threshold, the flue gas volume threshold and the temperature change.

[0011] As a preferred solution of the method for diagnosing faults in a distribution network connected to distributed energy resources of the present invention, the temperature of the fuel combustion includes judging the temperature change by monitoring the temperature value. When the temperature value is greater than the temperature change, it indicates that a fault has occurred, which is expressed as:

[0012]

[0013] Where ΔT is the temperature change, Q lcv is the received low calorific value of the fuel, Q phof is the physical heat of fuel, Q aph is the physical heat of air, Q lj is the heat absorbed by the cracking of combustion products under high temperature conditions, c py is the average specific heat capacity of flue gas.

[0014] As a preferred solution of the method for diagnosing faults in a distribution network of distributed energy access according to the present invention, the monitoring data of renewable energy includes monitoring the output power corresponding to the illumination G and the output power of the wind turbine generator; the output power corresponding to the illumination G is expressed as:

[0015]

[0016] Among them, P op is the output power corresponding to the illumination G, P max is the maximum output power under standard conditions, G is the incident radiation, G maxis the maximum irradiance under standard conditions, k is the temperature coefficient corresponding to the standard irradiance, T c is the array temperature, T r is the reference temperature.

[0017] As a preferred solution of the method for diagnosing faults in a distribution network to which distributed energy is connected according to the present invention, the output power of the wind turbine generator is expressed as:

[0018]

[0019]

[0020]

[0021] Among them, P W is the output power of the wind turbine, a, b, c are wind speed influence coefficients, V is wind speed, P R is the rated power, V in is the cut-in wind speed, V out is the cut-out wind speed, V 0 is the rated wind speed; the second threshold condition includes setting a light output power threshold and a wind turbine output power threshold, calculating the output power corresponding to the light G by monitoring the light radiance and temperature, judging whether the output power corresponding to the light G meets the set light output power threshold, calculating the output power of the wind turbine by monitoring the wind speed, judging whether the output power of the wind turbine meets the set threshold, and determining whether the distribution network is faulty.

[0022] As a preferred solution of the distribution network fault diagnosis method for distributed energy access described in the present invention, the improved dune cat optimization model includes setting initial parameters and initializing the population, using the refraction reverse learning strategy to optimize the population position and calculate the fitness value of each dune cat, using the roulette algorithm to select a random angle for each dune cat, and judging the value of the parameter R. If |R|>1, the dune cat group is converted to the search stage, if |R|≤1, the dune cat group is converted to the attack and utilization stage, calculating the position update, judging whether the algorithm has reached the maximum number of iterations, if the maximum number of iterations is reached, looping and outputting the optimal value and the optimal solution, otherwise continue to search for the best.

[0023] Another object of the present invention is to provide a system for a distribution network fault diagnosis method for distributed energy access, which can solve the distribution network fault diagnosis problem for distributed energy access by constructing a distribution network fault diagnosis system for distributed energy access.

[0024] To solve the above technical problems, the present invention provides the following technical solutions: a distribution network fault diagnosis system for distributed energy access, comprising a data acquisition module, a first threshold condition judgment module, a second threshold condition judgment module and a distribution network fault diagnosis module; the data acquisition module is used to collect gas fuel data and renewable energy data; the first threshold condition judgment module is used to judge whether the gas fuel data meets the first threshold condition; the second threshold condition judgment module is used to judge whether the renewable energy data meets the second threshold condition; the distribution network fault diagnosis module is used to use the monitoring data obtained from the two aspects as sample set data, input it into the improved sand cat optimization model, obtain optimized parameters, and perform fault diagnosis on the distribution network based on the optimized parameters.

[0025] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the distribution network fault diagnosis method for distributed energy access as described above are implemented.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the distribution network fault diagnosis method for distributed energy access as described above.

[0027] The beneficial effects of the present invention are as follows: the distribution network fault diagnosis method for distributed energy access provided by the present invention considers the impact of both gas fuel and renewable energy energy access on the distribution network to determine the distribution network fault diagnosis, sets thresholds under standard conditions based on the characteristics of gas fuel and renewable energy, and determines whether a distribution network fault occurs by comparing the state parameters during the operation of the distribution network with the set thresholds. The monitoring and calculation process of this method is relatively simple, which makes the diagnosis efficiency relatively high, and the diagnosis results are relatively comprehensive. The existing methods do not propose the monitoring of gas fuel in distributed energy, but the present invention proposes monitoring in this aspect, which makes the monitoring more comprehensive and makes the monitored data more accurate while considering natural environmental factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0029] Figure 1 A flow chart of a method for diagnosing faults in a distribution network to which distributed energy resources are connected, provided as a first embodiment of the present invention.

[0030] Figure 2A diagram of a refracted reverse learning mechanism for a method for diagnosing faults in a distribution network with distributed energy access provided in the first embodiment of the present invention.

[0031] Figure 3 A structural diagram of a distribution network fault diagnosis system for access of distributed energy resources provided in a second embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0033] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0034] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a distribution network fault diagnosis method for distributed energy access, including: collecting gas fuel data and renewable energy data; judging whether the gas fuel data meets a first threshold condition; judging whether the renewable energy data meets a second threshold condition; based on the monitoring data obtained from the two aspects as sample set data, inputting them into the improved sand cat optimization model to obtain optimized parameters, and diagnosing the distribution network faults based on the optimized parameters.

[0035] S1. Collect data on gas fuels and renewable energy.

[0036] Gas fuel data includes monitoring of the amount of air and smoke for fuel combustion and the temperature of fuel combustion.

[0037] Renewable energy data include solar radiation, temperature and wind speed.

[0038] S2. Determine whether the gas fuel data meets a first threshold condition.

[0039] S2.1. Air volume and flue gas volume: In practical applications, gas fuels mainly monitor natural gas, coke oven gas, blast furnace gas, generator gas, converter gas and biogas, monitor the air volume and flue gas volume generated during fuel combustion, and set air volume thresholds and flue gas volume thresholds:

[0040] Q n =nλ 1 +0.00124g×nλ 1

[0041] Vn =λ 2 +β+0.00124g×nλ 1

[0042] Where: Q n To monitor the amount of air in the fuel, n is the excess air coefficient, λ 1 is the set air volume threshold; V n To monitor the flue gas volume of the fuel, λ 2 is the set flue gas volume threshold, β is the excess oxygen volume, and 0.00124g is the moisture content in the air.

[0043] S2.2, fuel combustion temperature: high temperature will be generated during fuel combustion. The temperature change is judged by monitoring the temperature value. When the temperature value is greater than the temperature change, it indicates a fault:

[0044]

[0045] Where ΔT is the temperature change, Q lcv is the received low calorific value of the fuel, Q phof is the physical heat of fuel, Q aph is the physical heat of air, Q lj is the heat absorbed by the cracking of combustion products under high temperature conditions, c py is the average specific heat capacity of flue gas.

[0046] The first threshold condition includes an air volume threshold, a smoke volume threshold, and a combustion temperature change threshold.

[0047] S3. Determine whether the renewable energy data meets the second threshold condition.

[0048] Renewable energy here studies photovoltaic and wind power generation, and the conditions monitored here take into account changing weather factors and electricity demand.

[0049] S3.1. Photovoltaic power generation:

[0050]

[0051] Among them, P op is the output power corresponding to the illumination G, P max is the maximum output power under standard conditions, G is the incident radiation, G max is the maximum irradiance under standard conditions, k is the temperature coefficient corresponding to the standard irradiance, T c is the array temperature, T r is the reference temperature.

[0052] S3.2. Wind power generation:

[0053]

[0054]

[0055]

[0056] Among them, P W is the output power of the wind turbine, a, b, c are wind speed influence coefficients, V is wind speed, P R is the rated power, V in is the cut-in wind speed, V out is the cut-out wind speed, V 0 is the rated wind speed.

[0057] The second threshold condition includes setting a light output power threshold and a wind turbine generator output power threshold.

[0058] Based on the photovoltaic power generation output power and wind power generation output power set above, whether the output power meets the set threshold is determined by monitoring the light radiation; whether the output power meets the set threshold is determined by monitoring the wind speed, so as to determine the distribution network fault.

[0059] The above judgment process does not set a judgment order. The judgment can be set to be performed simultaneously or one after another. It can be set according to the monitoring conditions and needs.

[0060] S4. The monitoring data obtained from the two aspects are used as sample set data and input into the improved SandCat optimization model to obtain optimized parameters, and the distribution network fault diagnosis is performed based on the optimized parameters.

[0061] The sand cat swarm optimization algorithm consists of two phases: searching for prey and attacking prey, and there is also a mechanism to achieve a balance between the two phases.

[0062] Searching for prey: During the prey search phase, the sand cat will look for the best prey within its search range and move towards the prey's location. The position is updated as follows:

[0063] x c，t+1 = r(x b,t+1 -lx c,t+1 )

[0064] Among them, x c is the initial position of the SandCat algorithm, x bc is the optimal individual of the tth generation, r is the sensitivity of the sand dune cat, r = r G l, l is a random number between 0 and 1, r G As the iteration process decreases linearly from 2 to 0, it ensures that the component is close to the prey without losing, r G =s M -s Mt / T,s M is the auditory characteristic of the sand cat, its value is set to 2, and T is the maximum number of iterations.

[0065] Attacking prey: In this stage, each sand dune cat approaches the hunting position along different circular directions in space at random angles. The position update formula is:

[0066]

[0067] Among them, P is the random distance, θ is the random angle, P rand Is a random number.

[0068] In the SandCat algorithm, the balance between the search and exploitation phases is determined by the parameter R, R = 2r G P rand -r G , if |R|>1, the sand cat enters the search phase, and the next position can be a random position between the prey and the current position, and a global search is performed. If |R|≤1, the sand cat will enter the attack and exploitation phase and perform a local search.

[0069] Since the population diversity of the DuneCat algorithm is insufficient and it is easy to fall into the local optimum during the optimization stage, the refraction reverse learning mechanism is used here to enrich the population diversity and improve the quality of the initial solution of the population. Figure 2 shown.

[0070] Let the scaling factor The refractive index of the above figure is derived and extended to the high-dimensional space of the SandCat algorithm to obtain the reverse solution formula of refraction as follows:

[0071]

[0072] Where: x z For x t+1 The reverse solution of refraction, a j is the upper limit of the search space, b j The lower bound of the search space.

[0073] In the sand cat swarm optimization algorithm, the sensitivity r of the sand cat is G The parameter R is adjusted to balance the global search and local development capabilities of the algorithm. The sensitivity formula of the original sand cat swarm algorithm changes linearly with the number of iterations. Therefore, the formula is improved here to make it converge nonlinearly with the number of iterations. The improved sensitivity formula is as follows:

[0074]

[0075] It can be seen from the above formula that the improved sensitivity decays at a faster rate in the early stage and converges to the search range of the optimal solution. In the later stage, the decay speed slows down, the amplitude change decreases, the local search is enhanced, and the convergence accuracy of the algorithm is improved.

[0076] According to the above optimization of the SandCat algorithm, the specific improved algorithm flow is as follows:

[0077] S4.1. Set initial parameters and initialize the population.

[0078] S4.2. Use the refraction reverse learning strategy to optimize the population position and calculate the fitness value of each sand dune cat.

[0079] S4.3. Use the roulette wheel algorithm to select a random angle for each sand dune cat.

[0080] S4.4. Determine the value of parameter R.

[0081] S4.5. If |R|>1, the sand dune cat group switches to the search phase and updates its position according to the above calculation formula.

[0082] S4.6. If |R|≤1, the sand cat group switches to the attack and exploitation phase and calculates the position update.

[0083] S4.7 determines whether the algorithm has reached the maximum number of iterations. If so, it loops and outputs the optimal value and optimal solution. Otherwise, it jumps back to step S4.2 to continue optimizing.

[0084] Finally, the monitoring data obtained based on the above two aspects are used as sample set data and input into the improved SandCat optimization model to obtain the optimized parameters, and then the distribution network fault diagnosis is carried out based on the optimized parameters.

[0085] Example 2, reference Figure 3 , which is the second embodiment of the present invention, is different from the previous embodiment in that it provides a distribution network fault diagnosis system for distributed energy access, including: a data acquisition module 100, a first threshold condition judgment module 200, a second threshold condition judgment module 300 and a distribution network fault diagnosis module 400.

[0086] The data collection module 100 is used to collect data on gas fuel and renewable energy.

[0087] The first threshold condition judgment module 200 is used to judge whether the gas fuel data meets the first threshold condition.

[0088] The second threshold condition judgment module 300 is used to judge whether the renewable energy data meets the second threshold condition.

[0089] The distribution network fault diagnosis module 400 is used to input the monitoring data obtained from the two aspects as sample set data into the improved sand cat optimization model to obtain optimized parameters, and perform fault diagnosis on the distribution network based on the optimized parameters.

[0090] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0091] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0092] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0093] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0094] Embodiment 3 is the third embodiment of the present invention. It is different from the first two embodiments in that it is used to verify the technical effects adopted in the present invention so as to verify the real effects of the method.

[0095] For the unoptimized SVM, set the default parameters or select a fixed set of parameters based on experience, such as penalty parameter C = 1.0, kernel function is Gaussian kernel function (rbf), kernel function parameter γ = 0.5; use the above-mentioned sand cat swarm optimization algorithm to optimize C and γ, and apply the optimized parameter combination C and γ to the SVM model.

[0096] For the unoptimized model and the optimized model, predictions are made on the test set respectively.

[0097] Compute the performance metrics for the following models:

[0098] Accuracy: The ratio of correctly predicted samples to the total number of samples. The formula is:

[0099]

[0100] TP is the number of true positive examples, TN is the number of true negative examples, FP is the number of false positive examples, and FN is the number of false negative examples.

[0101] Recall rate: The proportion of true positive examples that are correctly predicted. For the positive class, the formula is:

[0102]

[0103] F1 value: An indicator that comprehensively considers accuracy and recall. The formula is:

[0104]

[0105]

[0106] The fault diagnosis data of distributed energy access is used as an indicator to obtain the data results after model optimization:

[0107] Monitoring dataset:

[0108] Unoptimized SVM: Accuracy: about 0.867; Recall: about 0.857 (may vary for each category, the average is taken here); F1 value: about 0.862.

[0109] After optimization, the accuracy of the SVM is about 0.933, the recall rate is about 0.929, and the F1 value is about 0.931.

[0110] By comparing the performance indicators, the optimized SVM has significant improvements in accuracy, recall and F1 value, which shows that the Sand Cat Swarm Algorithm can effectively find a more suitable parameter combination for SVM, thereby improving the classification performance of SVM.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for diagnosing faults in a distribution network with distributed energy access, characterized in that: include, Collect data on gas fuels and renewable energy; Determining whether the gas fuel data meets a first threshold condition; Determining whether the renewable energy data meets the second threshold condition; The monitoring data obtained from the two aspects are used as sample set data and input into the improved SandCat optimization model to obtain the optimized parameters. The distribution network fault diagnosis is then carried out based on the optimized parameters.

2. The method for diagnosing faults in a distribution network with distributed energy access as claimed in claim 1, characterized in that: The gas fuel data include monitoring the amount of air and smoke for fuel combustion and the temperature of fuel combustion; The renewable energy data include solar radiation, temperature and wind speed.

3. The method for diagnosing faults in a distribution network with distributed energy access as claimed in claim 2, characterized in that: The monitoring of the air volume and smoke volume of fuel combustion includes setting an air volume threshold and a smoke volume threshold, which are expressed as: Q n =nλ1+0.00124g×nλ1 V n =λ2+β+0.00124g×nλ1 Among them, Q n To monitor the amount of air in the fuel, n is the excess air coefficient, λ1 is the set air amount threshold; V n To monitor the smoke volume of the fuel, λ2 is the set smoke volume threshold, β is the excess oxygen volume, and 0.00124g is the moisture content in the air; The first threshold condition includes an air volume threshold, a smoke volume threshold and a temperature change.

4. The method for diagnosing faults in a distribution network with distributed energy access as claimed in claim 3, characterized in that: The temperature of fuel combustion includes judging the temperature change by monitoring the temperature value. When the temperature value is greater than the temperature change, it indicates that a fault has occurred, which is expressed as: Where ΔT is the temperature change, Q lcv is the received low calorific value of the fuel, Q phof is the physical heat of fuel, Q aph is the physical heat of air, Q lj is the heat absorbed by the cracking of combustion products under high temperature conditions, c py is the average specific heat capacity of flue gas.

5. The method for diagnosing faults in a distribution network with distributed energy access as claimed in claim 4, characterized in that: The monitoring of renewable energy data includes monitoring the output power corresponding to the illumination G and the output power of the wind turbine; The output power corresponding to the illumination G is expressed as, Among them, P op is the output power corresponding to the illumination G, P max is the maximum output power under standard conditions, G is the incident radiation, G max is the maximum irradiance under standard conditions, k is the temperature coefficient corresponding to the standard irradiance, T c is the array temperature, T r is the reference temperature.

6. The method for diagnosing faults in a distribution network with distributed energy access as claimed in claim 5, characterized in that: The output power of the wind turbine is expressed as, Among them, P W is the output power of the wind turbine, a, b, c are wind speed influence coefficients, V is wind speed, P R is the rated power, V in is the cut-in wind speed, V out is the cut-out wind speed, V0 is the rated wind speed; The second threshold condition includes setting a light output power threshold and a wind turbine output power threshold, calculating the output power corresponding to the light G by monitoring the light radiation and temperature, judging whether the output power corresponding to the light G meets the set light output power threshold, calculating the output power of the wind turbine by monitoring the wind speed, judging whether the output power of the wind turbine meets the set threshold, and determining whether the distribution network is faulty.

7. The method for diagnosing faults in a distribution network to which distributed energy is connected as claimed in claim 6, characterized in that: The improved sand cat optimization model includes setting initial parameters and initializing the population, using the refraction reverse learning strategy to optimize the population position and calculate the fitness value of each sand cat, using the roulette algorithm to select a random angle for each sand cat, judging the value of the parameter R, if |R|>1, the sand cat group is converted to the search stage, if |R|≤1, the sand cat group is converted to the attack and utilization stage, calculating the position update, judging whether the algorithm has reached the maximum number of iterations, if the maximum number of iterations is reached, looping and outputting the optimal value and the optimal solution, otherwise continue to search for the best.

8. A system using the method for diagnosing faults in a distribution network with distributed energy access as claimed in any one of claims 1 to 7, characterized in that: It comprises a data acquisition module (10000), a first threshold condition judgment module (200), a second threshold condition judgment module (300) and a distribution network fault diagnosis module (400); The data collection module (100) is used to collect data on gas fuel and data on renewable energy; The first threshold condition judgment module (200) is used to judge whether the gas fuel data meets the first threshold condition; The second threshold condition judgment module (300) is used to judge whether the renewable energy data meets the second threshold condition; The distribution network fault diagnosis module (400) is used to use the monitoring data obtained from the two aspects as sample set data, input them into the improved SandCat optimization model, obtain optimized parameters, and perform fault diagnosis on the distribution network based on the optimized parameters.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for diagnosing faults in a distribution network to which distributed energy resources are connected as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for diagnosing faults in a distribution network to which distributed energy resources are connected as described in any one of claims 1 to 7 are implemented.

Images