RIES reliability evaluation method and device, electronic equipment and storage medium

Abstract

The application provides a RIES reliability evaluation method and device, electronic equipment and storage medium, relates to the technical field of artificial intelligence machine learning, and the method comprises the steps that the RIES is partitioned, and the homogeneous nodes in the RIES are equivalent, a RIES equivalent node model is constructed; at a moment, a target function is constructed to determine the optimal load shedding amount, the RIES is subjected to load shedding, the unavailability rate of each device in the RIES at the moment is determined, if the unavailability rate of each device in the RIES at the moment meets the corresponding forced unavailability rate, the RIES reliability index EANS is calculated, if the coefficient of variation of EANS is less than the coefficient of variation threshold value, the RIES reliability index EANS is output, a first training set and a second training set are constructed, input into a machine learning model, and the reliability evaluation result of the RIES is output. The patent improves the efficiency and accuracy of RIES reliability evaluation by simplifying the model, optimizing the load shedding, combining the model and data driving.

Description

Technical Field

[0001] This application relates to the technical field of artificial intelligence and machine learning, and in particular to a RIES reliability assessment method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rise of the concepts of Energy Internet and Integrated Energy System (IES), Regional Integrated Energy System (RIES), as an important physical carrier for multi-energy joint dispatch, has become a key link in the energy transition process. RIES integrates various energy conversion and storage devices to achieve coordinated optimization among different energy systems, and its reliability assessment is crucial for ensuring the energy stability of the system region.

[0003] However, reliability assessment of RIES faces numerous challenges. First, RIES incorporates multiple energy configurations, leading to complex multi-energy coupling. Second, equipment aging further complicates the assessment. Current research primarily focuses on multi-energy coupling modeling, multi-electrode load forecasting, and planning optimization, but often neglects component aging effects. Furthermore, most existing reliability assessment methods are model-driven, resulting in low computational efficiency and weak dynamic adaptability. While a few studies have proposed data-driven methods, these methods have shortcomings in data quality and cross-energy flow coupling.

[0004] In view of this, how to reduce the coupling of RIES, reduce the difficulty of reliability assessment due to equipment aging, improve computing efficiency and dynamic adaptability, and improve the accuracy of reliability assessment have become technical problems that urgently need to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a RIES reliability assessment method, apparatus, electronic device and storage medium to solve the above problems.

[0006] In a first aspect, embodiments of this application provide a method for assessing the reliability of an energy supply system (RIES). The method is applied to assess the reliability of an RIES, which includes energy supply equipment and energy transmission equipment. The method includes: The RIES are partitioned, and homogeneous nodes in the RIES are equivalent to construct an equivalent node model of RIES. Extract At this moment And construct an objective function, and based on the objective function, determine the optimal load shedding amount for each node in the RIES equivalent node model, wherein, —No. During the second sampling Failure time of such devices —No. During the second sampling Repair time for this type of equipment, among which, The time is always within the preset total sampling time; Based on the optimal load shedding amount, load shedding is performed on the RIES, and power flow calculations are conducted on the RIES to determine... The unavailability rate of each device in the RIES at the given time, if At any given time, if the unavailability rate of each device in the RIES meets the corresponding forced unavailability rate, then the RIES reliability index EANS is calculated. If the coefficient of variation of the EANS is less than the coefficient of variation threshold, then the RIES reliability index EANS is output. The forced unavailability rate of each device in the RIES is based on... The failure time and repair time at any given moment are determined; Constructing the first training set Second training set The data is then input into a machine learning model, which outputs the reliability assessment results of the RIES. in, , —Load level, —The equipment's unavailability rate at the load level; , —The RIES reliability index EANS corresponding to the equipment's unavailability.

[0007] One possible approach is that the energy supply equipment includes: gas-fired boiler energy supply sub-equipment, combined heat and power sub-equipment, and photovoltaic power generation equipment, and the energy transmission equipment includes: electrical energy transmission sub-equipment and natural gas / heat energy transmission sub-equipment; The load shedding is performed on the RIES based on the optimal load shedding amount, and power flow calculation is performed on the RIES to determine... In the steps of determining the unavailability of each device in the RIES at the given time: The unavailability rate of the gas-fired boiler power supply sub-equipment is calculated as follows: ; — The availability rate of gas-fired boiler power supply sub-equipment at all times; —Unavailability rate of the foundation of the gas-fired boiler power supply sub-equipment under rated operating conditions; —Load sensitivity coefficient of gas-fired boiler power supply sub-equipment Aging Influencing Factors of Gas-fired Boiler Power Supply Sub-equipment —Real-time load rate and rated load rate of the gas boiler power supply sub-equipment, respectively. —These are the base time and current time for the gas-fired boiler power supply sub-equipment. The unavailability rate of the cogeneration sub-equipment: ; ; — The unavailability of cogeneration equipment at all times —Unavailability rate of foundations for cogeneration sub-equipment under rated operating conditions; —The adjustment of output power of cogeneration sub-equipment caused by changes in load demand; —Aging-related factors affecting cogeneration equipment; —Weibull distribution parameters; , —Low load threshold and heavy load threshold of heat load rate of cogeneration equipment; — The heat load rate of the cogeneration equipment at all times; , —Low load threshold and heavy load threshold of electrical load rate of cogeneration sub-equipment; — The electrical load rate of the cogeneration equipment at all times; The unavailability rate of the photovoltaic power generation equipment is calculated in the following way: ; — The availability rate of photovoltaic power generation equipment at any given time; —Maximum unavailability of photovoltaic power generation electronic equipment under heavy load; —Basic unavailability rate of photovoltaic power generation equipment under rated operating conditions; —Maximum unavailability of photovoltaic power generation electronic equipment under low load; —Low load threshold for photovoltaic power generation devices; —Heavy load threshold for photovoltaic power generation equipment; — The load rate of photovoltaic power generation equipment at all times; —Minimum load rate of photovoltaic power generation equipment —Maximum load factor of photovoltaic power generation equipment; The unavailability rate of the power transmission sub-equipment is calculated in the following manner: ; ; — The basic unavailability of the power transmission sub-equipment at any given time; —Shape parameters of the power transmission sub-equipment; —Expected lifespan of power transmission sub-equipment; — The availability rate of power transmission sub-equipment at any given time; —Parameters to be estimated for the power transmission sub-equipment; —Load rate of power transmission sub-equipment; The unavailability of the natural gas / heat transmission sub-equipment is calculated as follows: ; —Unavailability of natural gas / heat pipelines considering aging effects; —Infrastructure unavailability of natural gas / heat pipelines —Service life of natural gas / heat pipelines; —Weibull distribution function; The constraints for power flow calculation are as follows: ; —Decision variables; —Power system node voltage phase angle —No. Load shedding amount of each natural gas system node; —No. Load shedding amount of each heat transfer system node; —No. Load shedding at each power system node; —Power output from power supply equipment; —Heating equipment output; —Natural gas pipeline flow rate; —Natural gas pipeline pressure; —Temperature of thermal system nodes.

[0008] One possible approach is the extraction At this moment In the step of constructing an objective function and determining the optimal load shedding amount for each node in the RIES equivalent node model based on the objective function, the objective function used is as follows: ; —Total sampling time; —The total number of power system nodes in the RIES equivalent node model; —No. Load shedding at each power system node; —High calorific value of natural gas; —The total number of nodes in the natural gas system in the RIES equivalent node model; —No. Load shedding amount of each natural gas system node; —The total number of nodes in the heat transfer system in the RIES equivalent node model; —No. Load shedding amount of each heat transfer system node.

[0009] One possible approach is to determine the forced unavailability rate for each device in the RIES as follows: ; —The failure time of the q-th type of equipment during the s-th sampling; —Repair time of the qth type of equipment during the sth sampling; —Equipment type —Gas-fired boiler power supply sub-equipment —Cogeneration equipment; — Photovoltaic power generation equipment —Power transmission sub-equipment; —Natural gas / heat transmission sub-equipment; The RIES reliability index EANS is calculated using the following method: ; —RIES reliability metrics; —Expected value of power shortage; —Expected natural gas supply shortage; —Expected value of heat energy shortage; in, ; —The total number of power system nodes in the RIES equivalent node model; —Time required for load resection; —No. Load shedding at each power system node; —Total sampling time; ; —High calorific value of natural gas; —The total number of nodes in the natural gas system in the RIES equivalent node model; —No. Load shedding amount of each natural gas system node; ; —The total number of nodes in the heat transfer system in the RIES equivalent node model; —No. Load shedding amount of each heat transfer system node; The coefficient of variation threshold is determined as follows: ; —Coefficient of variation of the RIES reliability index EANS; —Standard deviation of EANS; —The mean of EANS.

[0010] One possible approach is to construct the first training set. Second training set The steps of inputting the data into a machine learning model and outputting the reliability assessment results of the RIES include: The first dataset is determined, and the first dataset is the first training set. Second training set Out-of-bag dataset; The first dataset is input into the random forest model, and the first error is calculated. The first error includes the error of inputting the optimal dataset of the first dataset into each decision tree in the random forest model. The unavailability rates in the first dataset are rearranged to construct a second dataset. The second dataset is then input into a random forest model to calculate a second error. The second error includes the error of inputting the optimal dataset of the second dataset into each decision tree in the random forest model. The importance of at least some of the devices in the RIES is determined based on the first error and the second error, and the target device is selected based on the importance. An optimal dataset is constructed based on the importance, and the optimal dataset is input into the XGBoost regression model to output the reliability evaluation results of the RIES.

[0011] One possible approach is to construct an optimal dataset based on the importance, and then input this optimal dataset into the XGBoost regression model to output the reliability assessment results of the RIES. The constraints of the XGBoost regression model are as follows: ; ; —The i-th sample of the input data; —The t-th decision tree; —The sum of t decision tree predictions for the i-th sample; —The predicted value of the i-th sample; —The actual value of the i-th sample; —Gradient boosting algorithm, representing the actual value Compared with the predicted value The degree of deviation; —Regularization term.

[0012] One possible approach is to determine the importance of at least some of the devices in the RIES based on the first error and the second error, and in the step of selecting a target device based on the importance, calculate the importance of any device in the RIES as follows: ; —The importance of any device; —The number of decision trees; —Features in the second dataset Enter to the number The error of each decision tree; — Input the first dataset into the... The error of each decision tree.

[0013] Secondly, embodiments of this application provide a RIES reliability assessment apparatus for assessing the reliability of RIES, wherein the RIES includes: an energy supply device and an energy transmission device, and the method includes: Partitioning module: used to partition the RIES and convert homogeneous nodes in the RIES into equivalent nodes to construct an equivalent node model of the RIES; Calculation module: used for extraction At this moment And construct an objective function, and based on the objective function, determine the optimal load shedding amount for each node in the RIES equivalent node model, wherein, —No. During the second sampling Failure time of such devices —No. During the second sampling Repair time for this type of equipment, among which, The time is always within the preset total sampling time; Load shedding module: used to perform load shedding on the RIES based on the optimal load shedding amount, and to perform power flow calculations on the RIES to determine... The unavailability rate of each device in the RIES at the given time, if At any given time, if the unavailability rate of each device in the RIES meets the corresponding forced unavailability rate, then the RIES reliability index EANS is calculated. If the coefficient of variation of the EANS is less than the coefficient of variation threshold, then the RIES reliability index EANS is output. The forced unavailability rate of each device in the RIES is based on... The failure time and repair time at any given moment are determined; Output module: used to build the first training set Second training set The data is then input into a machine learning model, which outputs the reliability assessment results of the RIES. in, , —Load level, —The equipment's unavailability rate at the load level; , —The RIES reliability index EANS corresponding to the equipment's unavailability.

[0014] Thirdly, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method described in the first aspect.

[0015] Fourthly, this application provides a computer-readable medium having a processor-executable program code that causes the processor to perform the method described in the first aspect.

[0016] This application has at least the following beneficial effects: 1. Reduced complexity of multi-energy coupling: This method simplifies the complexity of multi-energy coupling by constructing an equivalent node model of RIES. This innovation effectively solves the problem of inefficiency in existing methods when dealing with multiple energy configurations, improving the accuracy and efficiency of reliability assessment.

[0017] 2. Fully Considering Equipment Aging Effects: This method specifically considers the aging effects of components during the evaluation process, overcoming the shortcomings of existing research in this area. This measure allows for a more accurate assessment of the impact of equipment aging on system reliability, thereby improving the comprehensiveness and accuracy of the evaluation.

[0018] 3. Improved computational efficiency and dynamic adaptability: This method combines the advantages of model-driven and data-driven approaches, improving both computational efficiency and dynamic adaptability. Compared to existing model-driven methods, this significantly enhances computational efficiency and flexibility, enabling better adaptation to changing energy demands and the environment.

[0019] 4. Accuracy of Reliability Assessment: This method, by combining model-driven and data-driven approaches, reduces the assessment process's dependence on data. This characteristic allows the method to maintain high assessment accuracy even when data quality is unstable or data is insufficient.

[0020] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application are realized and obtained through the structures particularly pointed out in the description, claims, and drawings.

[0021] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 A flowchart of a RIES reliability assessment method provided in this application embodiment; Figure 2 A flowchart of another RIES reliability assessment method provided in the embodiments of this application; Figure 3 A structural diagram of a RIES reliability assessment device provided in this application embodiment; Figure 4 A RIES topology diagram illustrated in an exemplary embodiment provided in this application; Figure 5 A diagram illustrating the RIES equivalent node model as provided in an exemplary embodiment of this application; Figure 6 A RIES importance ranking diagram illustrated in an exemplary embodiment provided in this application; Figure 7 The electronic device structure diagram provided in this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] Currently, with the rise of the Energy Internet and Integrated Energy Systems (IES), Regional Integrated Energy Systems (RIES), as an important physical carrier for multi-energy joint dispatch, have become a key link in the energy transition process. RIES achieves coordinated optimization between different energy systems by integrating various energy conversion and storage devices, and its reliability assessment is crucial for ensuring the energy stability of the system region.

[0026] However, reliability assessment of RIES faces numerous challenges. First, RIES incorporates multiple energy configurations, leading to complex multi-energy coupling. Second, equipment aging further complicates the assessment. Current research primarily focuses on multi-energy coupling modeling, multi-electrode load forecasting, and planning optimization, but often neglects component aging effects. Furthermore, most existing reliability assessment methods are model-driven, resulting in low computational efficiency and weak dynamic adaptability. While a few studies have proposed data-driven methods, these methods have shortcomings in data quality and cross-energy flow coupling.

[0027] In view of this, how to reduce the coupling of RIES, reduce the difficulty of reliability assessment due to equipment aging, improve computing efficiency and dynamic adaptability, and improve the accuracy of reliability assessment have become technical problems that urgently need to be solved by those skilled in the art.

[0028] Based on this, embodiments of this application provide a RIES reliability assessment method, apparatus, electronic device, and storage medium to solve the aforementioned technical problems.

[0029] To facilitate understanding of this embodiment, a detailed description of the RIES reliability assessment method disclosed in this application embodiment will be provided first. First, a RIES reliability assessment method provided in the embodiments of this application will be described: Reference Figure 1 This application provides a method for evaluating the reliability of RIES, which includes the following steps. This method is applied to evaluate the reliability of RIES, which includes: energy supply equipment and energy transmission equipment.

[0030] The energy supply equipment is responsible for converting the input energy into forms such as electricity and heat that can be directly used or transmitted. In one specific embodiment of this application, this part mainly includes the following three sub-devices operating in coordination: 1. Photovoltaic power generation equipment: used to convert solar energy into electrical energy. Its output is directly connected to the power transmission sub-equipment as a clean power source for the system.

[0031] 2. Combined heat and power (CHP) equipment: Specifically refers to gas turbine or internal combustion engine generator sets that use natural gas as fuel.

[0032] 3. Gas-fired boiler power supply sub-equipment: Uses natural gas as fuel to produce heat energy (hot water or steam). Its heat energy output end is connected to the heat network section of the natural gas / heat energy transmission sub-equipment, serving as a basic heat source, backup, or peak-shaving heat source. Energy transmission equipment is responsible for connecting energy supply equipment and end users (loads), and for realizing the distribution and allocation of different forms of energy within the network, specifically including: Power transmission sub-equipment: This specifically includes distribution transformers, switchgear, protection devices, and power cables in the power distribution network. It is used to receive and transmit electrical energy from photovoltaic power generation equipment and combined heat and power (CHP) sub-equipment, and distribute it to various power loads within the region.

[0033] Natural gas / heat transmission sub-equipment: It is responsible for supplying fuel natural gas to the cogeneration sub-equipment and the gas boiler power supply sub-equipment, and for collecting and transmitting waste heat from the cogeneration sub-equipment and heat energy from the gas boiler power supply sub-equipment, and distributing them to various heat loads in the region.

[0034] The embodiments provided in this application specifically include the following steps: S1: Partition the RIES and convert homogeneous nodes in the RIES into equivalent nodes to construct an equivalent node model of the RIES.

[0035] One possible design is to use the definition of nodes in network graph theory to equate the upstream energy supply systems such as distribution networks and gas distribution networks in the system to nodes with infinite capacity, the main pipelines and branch pipelines with the same fault to the same node, and the energy coupling equipment to a node, and connect it to the equivalent node topology in its original way.

[0036] Specifically, each node is a load point, and the main pipelines and branch pipelines with the same fault and the load point are equivalent to the same node.

[0037] S2: Extraction At this moment And construct an objective function, and determine the optimal load shedding amount for each node in the RIES equivalent node model based on the objective function.

[0038] Specifically, in the embodiments provided in this application, the sequential Monte Carlo state duration sampling method is used to sample the state of each equivalent node and energy coupling device within a specified time domain.

[0039] As a preferred embodiment, extraction At this moment ), Indicates the first During the second sampling Failure time of such devices Indicates the first During the second sampling Repair time for this type of equipment.

[0040] S3: Based on the optimal load shedding amount, load shedding is performed on the RIES, and power flow calculation is performed on the RIES to determine... The unavailability rate of each device in the RIES at the given time.

[0041] Specifically, if At any given time, if the unavailability rate of each device in the RIES meets the corresponding forced unavailability rate, then the RIES reliability index EANS is calculated. If the coefficient of variation of the EANS is less than the coefficient of variation threshold, then the RIES reliability index EANS is output.

[0042] Specifically, after load shedding of RIES, for each device in RIES, the unavailability rate of the device is first calculated. If the unavailability rate of the device meets the mandatory unavailability rate of the device, the RIES reliability index EANS is calculated.

[0043] To determine whether the RIES reliability index EANS has converged, the coefficient of variation is used as the basis. If the coefficient of variation of the RIES reliability index EANS is less than the coefficient of variation threshold, it indicates that the RIES reliability index EANS has converged.

[0044] It should be noted that the forced unavailability rate of each device in the RIES is based on The failure time and repair time are determined at any given moment.

[0045] As one possible design, the forced unavailability rate for each device in the RIES is determined in the following way: ; —The failure time of the q-th type of equipment during the s-th sampling; —Repair time of the qth type of equipment during the sth sampling; —Equipment type —Gas-fired boiler power supply sub-equipment —Cogeneration equipment; — Photovoltaic power generation equipment —Power transmission sub-equipment; —Natural gas / heat transmission sub-equipment.

[0046] In the embodiments provided in this application, the reliability assessment model's evaluation system consists of the expected power shortage value EENS, the expected natural gas shortage value EGNS, the expected heat shortage value ETNS, and the expected shortage value EANS for all energy sources. Specifically, the RIES reliability index EANS is calculated using the following method: ; —RIES reliability metrics; —Expected value of power shortage; —Expected natural gas supply shortage; —Expected value of heat energy shortage; in, ; —The total number of power system nodes in the RIES equivalent node model; —Time required for load resection; —No. Load shedding amount at each power system node; —Total sampling time; ; —High calorific value of natural gas; —The total number of nodes in the natural gas system in the RIES equivalent node model; —No. Load shedding amount for each natural gas system node; ; —The total number of nodes in the heat transfer system in the RIES equivalent node model; —No. Load shedding amount of each heat transfer system node.

[0047] Using the above method, the reliability index of each device in the RIES can be calculated after the load is removed.

[0048] Once the reliability metrics are obtained, the coefficient of variation of the RIES reliability metric EANS is determined using the following method. ; —Coefficient of variation of the RIES reliability index EANS; —Standard deviation of EANS; —The mean of EANS.

[0049] It should be noted that the coefficient of variation threshold represents the maximum permissible value of the coefficient of variation for the RIES reliability index EANS.

[0050] For power flow calculation, those skilled in the art can select their own constraints, which are not limited here.

[0051] S4: Constructing the first training set Second training set The data is then input into a machine learning model, which outputs the reliability assessment results of the RIES.

[0052] It should be noted that, in the embodiments provided in this application, , Represents load level, This represents the unavailability rate of equipment under a given load level; , The RIES reliability index EANS represents the equipment's reliability at the unavailability level.

[0053] Here, when the load on RIES changes, the corresponding reliability index EANS can be quickly output.

[0054] This application has at least the following beneficial effects: 1. Reduced complexity of multi-energy coupling: This method simplifies the complexity of multi-energy coupling by constructing an equivalent node model of RIES. This innovation effectively solves the problem of inefficiency in existing methods when dealing with multiple energy configurations, improving the accuracy and efficiency of reliability assessment.

[0055] 2. Fully Considering Equipment Aging Effects: This method specifically considers the aging effects of components during the evaluation process, overcoming the shortcomings of existing research in this area. This measure allows for a more accurate assessment of the impact of equipment aging on system reliability, thereby improving the comprehensiveness and accuracy of the evaluation.

[0056] 3. Improved computational efficiency and dynamic adaptability: This method combines the advantages of model-driven and data-driven approaches, improving both computational efficiency and dynamic adaptability. Compared to existing model-driven methods, this significantly enhances computational efficiency and flexibility, enabling it to better adapt to changing energy demands and the environment.

[0057] 4. Accuracy of Reliability Assessment: This method, by combining model-driven and data-driven approaches, reduces the assessment process's dependence on data. This characteristic allows the method to maintain high assessment accuracy even when data quality is unstable or data is insufficient.

[0058] The following will explain how unavailability is calculated: In light of the foregoing, in the embodiments provided in this application, it is necessary to calculate the unavailability rate of each device in the RIES. One possible approach is... The unavailability rate of the gas-fired boiler power supply sub-equipment is calculated as follows: ; — The availability rate of gas-fired boiler power supply sub-equipment at all times; —Unavailability rate of the foundation of the gas-fired boiler power supply sub-equipment under rated operating conditions; —Load sensitivity coefficient of gas-fired boiler power supply sub-equipment Aging Influencing Factors of Gas-fired Boiler Power Supply Sub-equipment —Real-time load rate and rated load rate of the gas boiler power supply sub-equipment, respectively. —These are the base time and current time for the gas-fired boiler power supply sub-equipment. The unavailability rate of the cogeneration sub-equipment: ; ; — The unavailability of cogeneration equipment at all times —Unavailability rate of foundations for cogeneration sub-equipment under rated operating conditions; —The adjustment of output power of cogeneration sub-equipment caused by changes in load demand; —Aging-related factors affecting cogeneration equipment; —Weibull distribution parameters; , —Low load threshold and heavy load threshold of heat load rate of cogeneration equipment; — The heat load rate of the cogeneration equipment at all times; , —Low load threshold and heavy load threshold of electrical load rate of cogeneration sub-equipment; — The electrical load rate of the cogeneration equipment at all times; The unavailability rate of the photovoltaic power generation equipment is calculated in the following way: ; — The availability rate of photovoltaic power generation equipment at any given time; —Maximum unavailability of photovoltaic power generation electronic equipment under heavy load; —Basic unavailability rate of photovoltaic power generation equipment under rated operating conditions; —Maximum unavailability of photovoltaic power generation electronic equipment under low load; —Low load threshold for photovoltaic power generation devices; —Heavy load threshold for photovoltaic power generation equipment; — The load rate of photovoltaic power generation equipment at all times; —Minimum load rate of photovoltaic power generation equipment —Maximum load factor of photovoltaic power generation equipment; The unavailability rate of the power transmission sub-equipment is calculated in the following manner: ; ; — The basic unavailability of the power transmission sub-equipment at any given time; —Shape parameters of the power transmission sub-equipment; —Expected lifespan of power transmission sub-equipment; — The availability rate of power transmission sub-equipment at any given time; —Parameters to be estimated for the power transmission sub-equipment; —Load rate of power transmission sub-equipment; The unavailability of the natural gas / heat transmission sub-equipment is calculated as follows: ; —Unavailability of natural gas / heat pipelines considering aging effects; —Infrastructure unavailability of natural gas / heat pipelines —Service life of natural gas / heat pipelines; —Weibull distribution function; To calculate the load on each node after load shedding, the following constraints are used in the power flow calculation: ; —Decision variables; —Power system node voltage phase angle —No. Load shedding amount for each natural gas system node; —No. Load shedding amount of each heat transfer system node; —No. Load shedding amount at each power system node; —Power output from the power supply equipment; —Heating equipment output; —Natural gas pipeline flow rate; —Natural gas pipeline pressure; —Temperature of thermal system nodes.

[0059] Furthermore, as mentioned above, in the embodiments provided in this application, it is necessary to determine the optimal load shedding amount for the RIES equivalent node model. To determine the optimal load shedding amount, the objective function is constructed as follows: ; —Total sampling time; —The total number of power system nodes in the RIES equivalent node model; —No. Load shedding amount at each power system node; —High calorific value of natural gas; —The total number of nodes in the natural gas system in the RIES equivalent node model; —No. Load shedding amount for each natural gas system node; —The total number of nodes in the heat transfer system in the RIES equivalent node model; —No. Load shedding amount of each heat transfer system node.

[0060] The training process for this application will be described below: To reduce the dimensionality of the data and further reduce the computational load, we use a random forest model to reduce the data dimensionality.

[0061] Reference Figure 2 In the aforementioned S4: Constructing the first training set Second training set The steps of inputting the data into a machine learning model and outputting the reliability assessment results of the RIES specifically include: S401: Determine the first dataset.

[0062] The first dataset is the first training set. Second training set The out-of-bag dataset.

[0063] S402: Input the first dataset into the random forest model and calculate the first error.

[0064] The first error includes: the error of inputting the optimal dataset of the first dataset into each decision tree in the random forest model; Specifically, it should be noted that the first dataset is an Out-of-Bag (OOB) dataset, used to calculate the error of each decision tree in the random forest. (i.e., the first error), here, Representing the A decision tree.

[0065] S403: Rearrange the unavailability rates in the first dataset to construct a second dataset, and input the second dataset into the random forest model to calculate the second error.

[0066] The second error includes the error of inputting the optimal dataset of the second dataset into each decision tree in the random forest model.

[0067] S404: Determine the importance of at least some of the devices in the RIES based on the first error and the second error, and select the target device based on the importance.

[0068] Here, the target device refers to the device that has a significant impact on the reliability of RIES. The importance of any device in the RIES is calculated as follows: ; —The importance of any device; —The number of decision trees; —Features in the second dataset Enter to the number The error of each decision tree; — Input the first dataset into the... The error of each decision tree.

[0069] S405: Construct an optimal dataset based on the importance, input the optimal dataset into the XGBoost regression model, and output the reliability evaluation results of the RIES.

[0070] Once the target devices are identified, components / devices that have a significant impact on the reliability of RIES can be screened out, while components / devices that have a minor impact on the reliability of RIES can be eliminated. This reduces the dimensionality of the features and the amount of computation.

[0071] As one possible implementation, the constraints of the XGBoost regression model are as follows: ; ; —The i-th sample of the input data; —The t-th decision tree; —The sum of t decision tree predictions for the i-th sample; —The predicted value of the i-th sample; —The actual value of the i-th sample; —Gradient boosting algorithm, representing the actual value Compared with the predicted value The degree of deviation; —Regularization term.

[0072] Building upon the aforementioned embodiments, to further improve the accuracy of the regression model, cross-validation can be employed. Specifically, the first and second training sets are divided into 10 parts, 9 parts are randomly selected as the training set to build the prediction model, and the remaining part is used as the test set to verify the model's accuracy. The optimal regression model is then selected. This allows for the assessment of RIES reliability as the RIES load level changes.

[0073] To evaluate the predictive accuracy of the regression model, the coefficient of determination is as follows: ; in, For the first The target value of the experimental data, For the first Predicted values ​​of the test data This is the mean of all true values ​​in the test set.

[0074] Reference Figure 3 Based on the foregoing embodiments, this application provides a RIES reliability assessment device for assessing the reliability of RIES, wherein the RIES includes: energy supply equipment and energy transmission equipment, including: Partitioning module: used to partition the RIES and convert homogeneous nodes in the RIES into equivalent nodes to construct an equivalent node model of the RIES; Calculation module: used for extraction At this moment And construct an objective function, and based on the objective function, determine the optimal load shedding amount for each node in the RIES equivalent node model, wherein, —No. During the second sampling Failure time of such devices —No. During the second sampling Repair time for this type of equipment, among which, The time is always within the preset total sampling time; Load shedding module: used to perform load shedding on the RIES based on the optimal load shedding amount, and to perform power flow calculations on the RIES to determine... The unavailability rate of each device in the RIES at the given time, if At any given time, if the unavailability rate of each device in the RIES meets the corresponding forced unavailability rate, then the RIES reliability index EANS is calculated. If the coefficient of variation of the EANS is less than the coefficient of variation threshold, then the RIES reliability index EANS is output. The forced unavailability rate of each device in the RIES is based on... The failure time and repair time at any given moment are determined; Output module: used to build the first training set Second training set The data is then input into a machine learning model, which outputs the reliability assessment results of the RIES. in, , —Load level, —The equipment's unavailability rate at the load level; , —The RIES reliability index EANS corresponding to the equipment's unavailability.

[0075] The following is a specific example: Reference Figure 4 Taking a regional integrated energy system as an example, this system consists of a 33-node distribution network, a 12-node gas distribution network, and a 32-node heat distribution network. By establishing its equivalent node model, the complex relationships between components within the RIES are simplified, reducing the system's complexity and conforming to engineering practice. The RIES equivalent node model is as follows: Figure 5 As shown.

[0076] All components in this area are initially set to normal operating condition, and the components in the simulation belong to a time-varying probability model. 6000 electrical, gas, and heat load samples and component unavailability rate samples are randomly generated, and the simulation is performed according to... Figure 1 The process shown uses the sequential Monte Carlo method to calculate the reliability index of RIES for each sample, and the reliability index results are shown in Table 1.

[0077] Table 1 Reliability Index Results

[0078] The results show that the system is affected by the failure rate of units such as GB (gas boiler power supply sub-equipment), CHP (cogeneration sub-equipment), and PV (photovoltaic power generation equipment), resulting in a higher expected value for overall gas supply shortage than for power supply shortage. The thermal reliability of the system is similar to that of electrical reliability, and the simulation results are consistent with the actual operating conditions.

[0079] At the same time, the electrical, heat, and gas load samples and the unavailability rate of each component are used as... The RIES reliability index and component unavailability rate calculated from the above samples are used as the dataset. 750 samples were obtained with a statistical time step of 1 hour. Each sample group used different component and load point parameters as unique feature values. All feature values ​​were sorted using Randomized Randomized (RF) to calculate the ranking of reliability indices. The top 10 feature values ​​were selected as the key components affecting system reliability. Figure 6 The top 10 characteristics among the three reliability indices are presented. The results show that N21 and N28 of the distribution network, N11 and N1 of the gas distribution network, and N1 and N4 of the heating network have the greatest impact on EENS, EGNS, and ETNS, respectively. This can improve the accuracy of RIES reliability assessment and facilitate the development of reasonable operation and scheduling schemes.

[0080] Simulation results show that the reliability assessment model of this application has a high accuracy. Based on the prior training on historical system data, it can quickly assess and analyze the system reliability when the load level changes at the load point, causing the component failure rate to change. The entire regression training process takes 45.73 seconds, which is a significant improvement in calculation speed compared to the time taken by the traditional model-driven method.

[0081] The device provided in this application embodiment has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0082] In all the examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limitations; therefore, other examples of exemplary embodiments may have different values.

[0083] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0084] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0085] Figure 7 A block diagram is shown that is suitable for implementing embodiments of the present application. Figure 7 The electronic device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0086] like Figure 7 As shown, the electronic device is represented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors 410, memory 430, and communication bus 440 connecting different system components (including memory 430 and processing unit 410).

[0087] Communication bus 440 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) buses, Micro Channel Architecture (MAC) buses, Enhanced ISA buses, Video Electronics Standards Association (VESA) local buses, and Peripheral Component Interconnect (PCI) buses.

[0088] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0089] Memory 430 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 430 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0090] A program / utility having a set (at least one) of program modules can be stored in memory 430. Such program modules include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules typically perform the functions and / or methods described in the embodiments of this application.

[0091] Processor 410 executes various functional applications and data processing by running programs stored in memory 430, such as implementing embodiments of this application. Figure 1 The RIES reliability assessment method provided in the illustrated embodiment.

[0092] This application provides a non-transitory computer-readable storage medium that stores computer instructions, which cause the computer to execute embodiments of this application. Figure 1 The RIES reliability assessment method provided in the illustrated embodiment.

[0093] The aforementioned computer-readable storage medium may be any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0094] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0095] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0096] Computer program code for performing the operations of the embodiments of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0097] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0098] In the description of the embodiments of this application, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments of this application. In the embodiments of this application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in the embodiments of this application, as well as the features of different embodiments or examples.

[0099] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of embodiments of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0100] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0101] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0102] It should be noted that the terminals involved in the embodiments of this application may include, but are not limited to, personal computers (PCs), personal digital assistants (PDAs), wireless handheld devices, tablet computers, mobile phones, MP3 players, MP4 players, etc.

[0103] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0104] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0105] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present application should be included within the scope of protection of the present application.

Claims

1. A method for assessing the reliability of RIES, characterized in that, The method is applied to assess the reliability of RIES, which includes: energy supply equipment and energy transmission equipment, and the method includes: The RIES are partitioned, and homogeneous nodes in the RIES are equivalent to construct an equivalent node model of RIES. Extract At this moment And construct an objective function, and based on the objective function, determine the optimal load shedding amount for each node in the RIES equivalent node model, wherein, —No. During the second sampling Failure time of such devices —No. During the second sampling Repair time for this type of equipment, among which, The time is always within the preset total sampling time; Based on the optimal load shedding amount, load shedding is performed on the RIES, and power flow calculations are conducted on the RIES to determine... The unavailability rate of each device in the RIES at the given time, if At any given time, if the unavailability rate of each device in the RIES meets the corresponding forced unavailability rate, then the RIES reliability index EANS is calculated. If the coefficient of variation of the EANS is less than the coefficient of variation threshold, then the RIES reliability index EANS is output. The forced unavailability rate of each device in the RIES is based on... The failure time and repair time at any given moment are determined; Constructing the first training set Second training set The data is then input into a machine learning model, which outputs the reliability assessment results of the RIES. in, , —Load level, —The equipment's unavailability rate at the load level; , —The RIES reliability index EANS corresponding to the equipment's unavailability.

2. The method according to claim 1, characterized in that, The energy supply equipment includes: gas boiler power supply sub-equipment, combined heat and power sub-equipment, and photovoltaic power generation equipment; the energy transmission equipment includes: electrical energy transmission sub-equipment and natural gas / heat energy transmission sub-equipment. The load shedding is performed on the RIES based on the optimal load shedding amount, and power flow calculation is performed on the RIES to determine... In the steps of determining the unavailability of each device in the RIES at the given time: The unavailability rate of the gas-fired boiler power supply sub-equipment is calculated as follows: ; — The availability rate of gas-fired boiler power supply sub-equipment at all times; —Unavailability rate of the foundation of the gas-fired boiler power supply sub-equipment under rated operating conditions; —Load sensitivity coefficient of gas-fired boiler power supply sub-equipment Aging Influencing Factors of Gas-fired Boiler Power Supply Sub-equipment —Real-time load rate and rated load rate of the gas boiler power supply sub-equipment, respectively. —These are the base time and current time for the gas-fired boiler power supply sub-equipment. The unavailability rate of the cogeneration sub-equipment: ; ; — The unavailability of cogeneration equipment at all times —Unavailability rate of foundations for cogeneration sub-equipment under rated operating conditions; —The adjustment of output power of cogeneration sub-equipment caused by changes in load demand; —Aging-related factors affecting cogeneration equipment; —Weibull distribution parameters; , —Low load threshold and heavy load threshold of heat load rate of cogeneration equipment; — The heat load rate of the cogeneration equipment at all times; , —Low load threshold and heavy load threshold of electrical load rate of cogeneration sub-equipment; — The electrical load rate of the cogeneration equipment at all times; The unavailability rate of the photovoltaic power generation equipment is calculated in the following way: ; — The availability rate of photovoltaic power generation equipment at any given time; —Maximum unavailability of photovoltaic power generation electronic equipment under heavy load; —Basic unavailability rate of photovoltaic power generation equipment under rated operating conditions; —Maximum unavailability of photovoltaic power generation electronic equipment under low load; —Low load threshold for photovoltaic power generation devices; —Heavy load threshold for photovoltaic power generation equipment; — The load rate of photovoltaic power generation equipment at all times; —Minimum load rate of photovoltaic power generation equipment —Maximum load factor of photovoltaic power generation equipment; The unavailability rate of the power transmission sub-equipment is calculated in the following manner: ; ; — The basic unavailability of the power transmission sub-equipment at any given time; —Shape parameters of the power transmission sub-equipment; —Expected lifespan of power transmission sub-equipment; — The availability rate of power transmission sub-equipment at any given time; —Parameters to be estimated for the power transmission sub-equipment; —Load rate of power transmission sub-equipment; The unavailability of the natural gas / heat transmission sub-equipment is calculated as follows: ; —Unavailability of natural gas / heat pipelines considering aging effects; —Infrastructure unavailability of natural gas / heat pipelines —Service life of natural gas / heat pipelines; —Weibull distribution function; The constraints for power flow calculation are as follows: ; —Decision variables; —Power system node voltage phase angle —No. Load shedding amount of each natural gas system node; —No. Load shedding amount of each heat transfer system node; —No. Load shedding at each power system node; —Power output from power supply equipment; —Heating equipment output; —Natural gas pipeline flow rate; —Natural gas pipeline pressure; —Temperature of thermal system nodes.

3. The method according to claim 2, characterized in that, The extraction At this moment In the step of constructing an objective function and determining the optimal load shedding amount for each node in the RIES equivalent node model based on the objective function, the objective function used is as follows: ; —Total sampling time; —The total number of power system nodes in the RIES equivalent node model; —No. Load shedding at each power system node; —High calorific value of natural gas; —The total number of nodes in the natural gas system in the RIES equivalent node model; —No. Load shedding amount of each natural gas system node; —The total number of nodes in the heat transfer system in the RIES equivalent node model; —No. Load shedding amount of each heat transfer system node.

4. The method according to claim 3, characterized in that, The forced unavailability rate for each device in the RIES is determined in the following way: ; —The failure time of the q-th type of equipment during the s-th sampling; —Repair time of the qth type of equipment during the sth sampling; —Equipment type —Gas-fired boiler power supply sub-equipment —Cogeneration equipment; — Photovoltaic power generation equipment —Power transmission sub-equipment; —Natural gas / heat transmission sub-equipment; The RIES reliability index EANS is calculated using the following method: ; —RIES reliability metrics; —Expected value of power shortage; —Expected natural gas supply shortage; —Expected value of heat energy shortage; in, ; —The total number of power system nodes in the RIES equivalent node model; —Time required for load resection; —No. Load shedding at each power system node; —Total sampling time; ; —High calorific value of natural gas; —The total number of nodes in the natural gas system in the RIES equivalent node model; —No. Load shedding amount of each natural gas system node; ; —The total number of nodes in the heat transfer system in the RIES equivalent node model; —No. Load shedding amount of each heat transfer system node; The coefficient of variation threshold is determined as follows: ; —Coefficient of variation of the RIES reliability index EANS; —Standard deviation of EANS; —The mean of EANS.

5. The method according to any one of claims 1 to 4, characterized in that, Constructing the first training set Second training set The steps of inputting the data into a machine learning model and outputting the reliability assessment results of the RIES include: The first dataset is determined, and the first dataset is the first training set. Second training set Out-of-bag dataset; The first dataset is input into the random forest model, and the first error is calculated. The first error includes the error of inputting the optimal dataset of the first dataset into each decision tree in the random forest model. The unavailability rates in the first dataset are rearranged to construct a second dataset. The second dataset is then input into a random forest model to calculate a second error. The second error includes the error of inputting the optimal dataset of the second dataset into each decision tree in the random forest model. The importance of at least some of the devices in the RIES is determined based on the first error and the second error, and the target device is selected based on the importance. An optimal dataset is constructed based on the importance, and the optimal dataset is input into the XGBoost regression model to output the reliability evaluation results of the RIES.

6. The method according to claim 5, characterized in that, The steps of constructing an optimal dataset based on the importance, inputting the optimal dataset into the XGBoost regression model, and outputting the reliability assessment results of the RIES are as follows: The constraints of the XGBoost regression model are as follows: ; ; —The i-th sample of the input data; —The t-th decision tree; —The sum of t decision tree predictions for the i-th sample; —The predicted value of the i-th sample; —The actual value of the i-th sample; —Gradient boosting algorithm, representing the actual value Compared with the predicted value The degree of deviation; —Regularization term.

7. The method according to claim 5, characterized in that, In the step of determining the importance of at least some devices in the RIES based on the first error and the second error, and selecting a target device based on the importance, the importance of any device in the RIES is calculated in the following manner: ; —The importance of any device; —The number of decision trees; —Features in the second dataset Enter to the number The error of each decision tree; — Input the first dataset into the... The error of each decision tree.

8. A RIES reliability assessment device, characterized in that, This is used for evaluating the reliability of RIES, which include: energy supply equipment and energy transmission equipment, including: Partitioning module: used to partition the RIES and convert homogeneous nodes in the RIES into equivalent nodes to construct an equivalent node model of the RIES; Calculation module: used for extraction At this moment And construct an objective function, and based on the objective function, determine the optimal load shedding amount for each node in the RIES equivalent node model, wherein, —No. During the second sampling Failure time of such devices —No. During the second sampling Repair time for this type of equipment, among which, The time is always within the preset total sampling time; Load shedding module: used to perform load shedding on the RIES based on the optimal load shedding amount, and to perform power flow calculations on the RIES to determine... The unavailability rate of each device in the RIES at the given time, if At any given time, if the unavailability rate of each device in the RIES meets the corresponding forced unavailability rate, then the RIES reliability index EANS is calculated. If the coefficient of variation of the EANS is less than the coefficient of variation threshold, then the RIES reliability index EANS is output. The forced unavailability rate of each device in the RIES is based on... The failure time and repair time at any given moment are determined; Output module: used to build the first training set Second training set The data is then input into a machine learning model, which outputs the reliability assessment results of the RIES. in, , —Load level, —The equipment's unavailability rate at the load level; , —The RIES reliability index EANS corresponding to the equipment's unavailability.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 7.

10. A computer-readable medium having processor-executable capability, characterized in that, The program code causes the processor to perform the method according to any one of claims 1 to 7.

Images