Fault self-healing control method and system for distributed power supply access power distribution network

Abstract

The invention discloses a fault self-healing control method and system for a distributed power supply access power distribution network, and the method comprises the steps: collecting the operation data of each node of the power distribution network, and carrying out the preprocessing; and analyzing the preprocessed data, determining an evaluation target, and determining a key evaluation index according to the evaluation target. And calculating an index value of each key evaluation index, and performing quantification to obtain a comprehensive score. And carrying out grade division on the bearing capacity according to the value range of the comprehensive score to obtain a bearing capacity grade interval, and determining the bearing capacity grade of the comprehensive evaluation score. And constructing a power distribution network bearing capacity evaluation model, outputting a power distribution network bearing capacity grade, making a fault self-healing control scheme, and realizing rapid fault self-healing control. According to the method, the bearing capacity grade of the power distribution network is optimized and applied to model prediction, the more accurate bearing capacity grade of the fault occurrence area can be effectively predicted, and the execution priority of the self-healing control scheme is determined according to the bearing capacity grade so as to balance resource utilization and fault processing effects.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution network fault self-healing, and in particular to a fault self-healing control method and system for accessing a distributed power source to a power distribution network. Background Art

[0002] With the transformation of the global energy structure and the enhancement of environmental protection awareness, the application of distributed generation (DG) in distribution networks is becoming more and more extensive. Distributed generation mainly includes renewable energy generation forms such as solar photovoltaic, wind power generation, small hydropower generation, biomass power generation, etc., which have become an effective way to alleviate energy crisis, reduce environmental pollution and improve energy efficiency with their clean, efficient and flexible characteristics.

[0003] However, the access of distributed power sources also brings new challenges to the safe and stable operation of the distribution network. The traditional distribution network is a centralized, one-way power transmission system, while the access of distributed power sources makes the distribution network a complex multi-power, multi-directional power network. This change not only changes the power flow distribution and voltage level of the distribution network, but also increases the risk of failure of the distribution network. Once a failure occurs, how to quickly and accurately locate the fault point, isolate the fault area, and restore power supply to the non-fault area has become an important issue facing the self-healing control of distribution network faults.

[0004] Traditional distribution network fault self-healing control methods mainly rely on manual inspections and centralized fault handling systems. These methods have great limitations in fault location, isolation and power restoration, and cannot meet the requirements of high efficiency, real-time and accuracy of fault self-healing control in distribution networks after the access of distributed power sources. Therefore, studying the fault self-healing control method of distributed power sources connected to distribution networks is of great significance for improving the safe and stable operation level of distribution networks, reducing fault losses and improving power supply reliability. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: how to comprehensively consider various external factors that the distribution network may face and the timeliness of the response strategy during the fault self-healing repair process, quickly execute the fault self-healing control plan, and thus realize the emergency repair of distribution network faults.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a fault self-healing control method for a distributed power source connected to a distribution network, comprising: collecting operating data of each node of the distribution network and performing pre-processing.

[0008] Analyze the preprocessed data, determine the evaluation objectives, and determine the key evaluation indicators based on the evaluation objectives.

[0009] Calculate the index value of each key evaluation indicator and quantify it to obtain a comprehensive score.

[0010] The bearing capacity levels are divided according to the value range of the comprehensive score to obtain the bearing capacity level intervals, and the bearing capacity level of the comprehensive evaluation score is determined.

[0011] Construct a distribution network carrying capacity assessment model, output the distribution network carrying capacity level, formulate a fault self-healing control plan, and realize rapid fault self-healing control.

[0012] As a preferred solution of the fault self-healing control method for distributed power sources connected to a distribution network described in the present invention, the pre-processing of collecting the operating data of each node of the distribution network includes determining the nodes of the distribution network that need to collect operating data, and the nodes include power access points, load nodes, important branch nodes, and monitoring points of equipment.

[0013] Equip collection equipment at the collection point to accurately collect the node's operating data, including voltage, current, power factor, active power, and reactive power.

[0014] Preprocessing includes removing outliers and filling missing values ​​to ensure the accuracy and reliability of the data.

[0015] As a preferred solution of the fault self-healing control method for the access of distributed power sources to the distribution network described in the present invention, wherein: the pre-processed data is analyzed to determine the evaluation target, and the key evaluation indicators are determined according to the evaluation target, including in-depth analysis of the acquired operating data to understand the operating status of the distribution network and the impact of the distributed power sources, and according to the actual situation of the distribution network, the evaluation target is determined to enhance the self-recovery capability of the distribution network in the face of various faults or abnormal situations after the distributed power sources are connected.

[0016] First, a multi-level evaluation system is constructed. The multi-level evaluation system has a three-layer structure, including the target layer, the performance layer and the indicator layer. The evaluation target is used as the target layer. The performance layer includes safety, economy and flexibility. Safety includes voltage deviation index, voltage qualification rate and voltage stability index under weather influence. Economy includes reactive power compensation qualification rate, average line loss rate, power generation efficiency index under weather influence and energy utilization rate under grid control strategy. Flexibility includes net load fluctuation rate, proportion of new energy power generation, implementation rate of weather adaptive scheduling strategy and power access capability under grid control strategy.

[0017] As a preferred solution of the fault self-healing control method for the distributed power supply connected to the distribution network of the present invention, wherein: the calculation of the index value of each key evaluation index and the quantification to obtain a comprehensive score include calculating the voltage stability index under the influence of weather, the step includes calculating the voltage fluctuation amplitude according to the actual voltage, the rated voltage, and the voltage threshold, expressed as:

[0018]

[0019] Among them, B i Represents the voltage fluctuation amplitude of the ith node in the distribution network, V i Represents the actual voltage of the ith node in the distribution network, V ir represents the rated voltage of the ith node in the distribution network, and Y represents the voltage threshold of the distribution network.

[0020] Get the voltage fluctuation duration T of each node in the distribution network i and the node weight ω of each node in the distribution network i . Obtain the weather impact coefficient of the distribution network.

[0021] The voltage stability index under weather influence is calculated based on the voltage fluctuation amplitude, voltage fluctuation duration, node weight, and weather influence coefficient, and is expressed as:

[0022]

[0023] Among them, D i represents the voltage stability index under weather conditions, N represents the total number of nodes, i represents the i-th node, and F i represents the voltage fluctuation amplitude of the ith node in the distribution network, ω i represents the node weight of the ith node in the distribution network, W i Represents the weather impact coefficient of the i-th node in the distribution network.

[0024] The step of calculating the power generation efficiency index under weather influence includes obtaining the actual power generation measured under current weather conditions, the ideal power generation under ideal weather conditions, and the weather influence index of the distribution network.

[0025] The power generation efficiency index under weather influence is calculated based on the actual power generation measured under current weather conditions, the ideal power generation under ideal weather conditions, and the weather influence index of the distribution network, which is expressed as:

[0026]

[0027] Among them, F represents the power generation efficiency index of the distribution network under the influence of weather, AG represents the actual power generation measured under current weather conditions, TG represents the ideal power generation under ideal weather conditions, and WI represents the weather impact index of the distribution network.

[0028] The steps for calculating the energy utilization rate under the grid-connected control strategy include obtaining the total power consumption of the distribution network, the energy type factor of the distributed power source, the energy conversion efficiency of the distributed power source, and the energy loss rate of the distributed power source.

[0029] According to the actual power generation, total power consumption of the distribution network, energy type factor, energy conversion efficiency, and energy loss rate measured under current weather conditions, the energy utilization rate under the grid-connected control strategy is calculated:

[0030]

[0031] Where I' represents the energy utilization rate under the grid-connected control strategy, T e Indicates the total power consumption of the distribution network, E f Represents the energy type factor of distributed generation, C E Represents the energy conversion efficiency of distributed power generation, E L Represents the energy loss rate of distributed generation.

[0032] As a preferred scheme of the fault self-healing control method for distributed power sources connected to a distribution network described in the present invention, wherein: the carrying capacity level is divided according to the value range of the comprehensive score to obtain the carrying capacity level interval, and the carrying capacity level of the comprehensive evaluation score is determined, including defining the value range of the comprehensive evaluation score as {A, B, C, ..., K}, and assigning the maximum and minimum values ​​of the value range according to the actual data of the distribution network.

[0033] The comprehensive score is calculated by summing up the voltage fluctuation amplitude, voltage stability index, power generation efficiency index and energy utilization rate, and is expressed as:

[0034]

[0035] Among them, S total represents the comprehensive carrying capacity score, T represents the evaluation time period, N represents the total number of nodes in the distribution network, and B i represents the voltage fluctuation amplitude of the ith node, D i represents the voltage stability index of the ith node, F i Represents the power generation efficiency index of the i-th node, I' i represents the energy utilization rate of the i-th node, W i represents the weather influence coefficient of the i-th node, T i represents the voltage fluctuation duration of the ith node, ω i represents the weight of the i-th node, and α represents a constant parameter that adjusts the nonlinear relationship between voltage fluctuation and voltage stability.

[0036] The value range {A, B, C, ..., K} is divided into several bearing capacity level intervals and bearing capacity levels, and the bearing capacity level intervals include a first bearing capacity level interval, a second bearing capacity level interval, a third bearing capacity level interval, and a fourth bearing capacity level interval.

[0037] The bearing capacity level of the first bearing capacity level interval is greater than the bearing capacity level of the second bearing capacity level interval, the bearing capacity level of the second bearing capacity level interval is greater than the bearing capacity level of the third bearing capacity level interval, and the bearing capacity level of the third bearing capacity level interval is greater than the bearing capacity level of the fourth bearing capacity level interval.

[0038] The value range [I, K] represents the first bearing capacity interval, indicating that the distribution network has a high bearing capacity level.

[0039] The value range [F, H] represents the second carrying capacity interval, indicating that the distribution network has a higher carrying capacity level.

[0040] The value range [C, E] represents the third bearing capacity interval, indicating that the distribution network has a medium bearing capacity level.

[0041] The value range [A, B] represents the fourth bearing capacity interval, indicating that the distribution network has a low bearing capacity level.

[0042] The upper limit K of the first bearing capacity level interval is expressed as:

[0043]

[0044] The upper limit I of the first bearing capacity level interval is expressed as:

[0045]

[0046] The upper limit H of the second bearing capacity level interval is expressed as:

[0047]

[0048] The lower limit F of the second bearing capacity grade interval is expressed as:

[0049]

[0050] The upper limit E of the third bearing capacity level interval is expressed as:

[0051]

[0052] The lower limit C of the third bearing capacity level interval is expressed as:

[0053]

[0054] The upper limit B of the fourth bearing capacity level interval is expressed as:

[0055]

[0056] The lower limit A' of the fourth bearing capacity level interval is expressed as:

[0057]

[0058] Where x represents the instantaneous value of the scoring function Stotal at time t, T represents the duration of the entire evaluation, Indicates the maximum score. Indicates the minimum score.

[0059] Compare the current comprehensive evaluation score with the bearing capacity grade range to determine the bearing capacity grade of the current comprehensive evaluation score.

[0060] As a preferred solution of the fault self-healing control method for distributed power sources connected to a distribution network described in the present invention, wherein: the construction of a distribution network carrying capacity assessment model and the output of the distribution network carrying capacity level include taking the indicator values, comprehensive evaluation scores and carrying capacity levels of key evaluation indicators as training sets, training the distribution network carrying capacity assessment model, and obtaining a trained distribution network carrying capacity assessment model.

[0061] In order to accurately evaluate the carrying capacity of the distributed power sources connected to the distribution network and fully allocate and use the connected distributed power sources, this embodiment uses a distribution network carrying capacity evaluation model to evaluate the distribution network carrying capacity.

[0062] The distribution network carrying capacity assessment model also includes the objective function expressed as:

[0063] L=L1+L2+L3+L4+L5+L6

[0064]

[0065]

[0066]

[0067] Among them, L represents the objective function, L1 represents the voltage stability objective item, L2 represents the power generation efficiency objective item, L3 represents the scheduling strategy implementation objective item, L4 represents the energy utilization objective item, L5 represents the power supply access capability objective item, and L6 represents the basic objective item. Represents the average value of the voltage stability index, Represents the average value of the power generation efficiency index, C i represents the implementation rate of weather adaptive scheduling strategy, I' i represents the energy utilization rate under the grid-connected control strategy, J irepresents the power access capability value under the grid-connected control strategy, N represents the total number of nodes, i represents the i-th node, represents the weight of the voltage stability objective item, represents the weight of the power generation efficiency objective item, Represents the weight of the scheduling strategy implementation target item, represents the weight of the energy utilization target item, Indicates the weight of the power access capability objective item. i，t represents the distributed generation power of the ith node at time t. T represents a complete scheduling cycle.

[0068] The constraints include voltage constraints, power flow constraints, power generation and load balance conditions, scheduling strategy implementation constraints, energy utilization constraints, and power supply access capacity constraints.

[0069] The voltage constraint is expressed as:

[0070] V min ≤V i ≤V max

[0071] Among them, V i represents the voltage of the ith node, V min Indicates the minimum voltage, V max Indicates the maximum voltage.

[0072] The power flow constraint is expressed as:

[0073] P min，j ≤P max，j

[0074] Among them, P min，j represents the power flow of the jth line, P max，j represents the maximum allowed power flow of the jth line.

[0075] The generation and load balance constraints are expressed as:

[0076]

[0077] Among them, P g represents the power output of generator g, Σ g∈G P g represents the sum of the power output of all generators, P d represents the power demand of load d, Σ d∈M P d represents the sum of the power requirements of all loads, P loss represents the system power loss, G represents the engine set, and M represents the load set.

[0078] The scheduling strategy implementation constraints are expressed as:

[0079] C≥C min

[0080] Among them, C min Indicates the minimum implementation rate of the weather adaptive scheduling strategy.

[0081] The energy utilization constraint is expressed as:

[0082] I≥I min

[0083] Among them, I min It represents the minimum value of energy utilization under the grid-connected control strategy.

[0084] The power access capability constraint is expressed as:

[0085] J≥J min

[0086] Among them, J min Indicates the minimum value of the power access capability under the grid-connected control strategy.

[0087] The distribution network data to be predicted is input into the trained distribution network carrying capacity assessment model, and the distribution network carrying capacity level is output.

[0088] As a preferred scheme of the fault self-healing control method for connecting distributed power sources to a distribution network described in the present invention, wherein: the formulation of a fault self-healing control scheme to achieve rapid fault self-healing control includes, according to the priority of the predicted distribution network carrying capacity level, preferentially executing the self-healing control scheme for the area where the current fault is located.

[0089] For faults in the first load-bearing level range, rapid fault location and isolation are carried out, power supply to non-faulty areas is automatically restored, and the system operating status is monitored and optimized.

[0090] For faults in the second load-bearing level range, strengthen monitoring of the fault area, prevent the spread of faults, respond quickly and isolate the faults, reduce the scope of power outages, coordinate control of adjacent areas, and ensure stable power supply.

[0091] For faults in the third load-bearing level range, activate the emergency plan, including the preparation of backup power supplies and temporary lines, give priority to restoring power supply to critical loads, assess the impact of the fault, and formulate a recovery plan.

[0092] For faults in the fourth load-bearing level range, the emergency response mechanism is immediately activated, including coordination with external resources, rapid assessment of losses, ensuring personnel safety, formulating post-disaster reconstruction plans, and optimizing system structure.

[0093] A fault self-healing control and management system for distributed power sources connected to a distribution network, characterized in that it includes a data collection module for collecting operating data of each node of the distribution network and performing pre-processing.

[0094] The analysis module analyzes the preprocessed data, determines the evaluation objectives, and determines the key evaluation indicators based on the evaluation objectives.

[0095] The calculation module calculates the index value of each key evaluation index and quantifies it to obtain a comprehensive score. The bearing capacity level is divided according to the value range of the comprehensive score to obtain the bearing capacity level interval and determine the bearing capacity level of the comprehensive evaluation score.

[0096] Build a model module, construct a distribution network carrying capacity assessment model, output the distribution network carrying capacity level, formulate a fault self-healing control plan, and realize rapid fault self-healing control.

[0097] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0098] A computer-readable storage medium stores a computer program, which implements the steps of the method described above when executed by a processor.

[0099] Beneficial effects of the present invention: The present invention adds the voltage stability index under the influence of weather, the power generation efficiency index under the influence of weather, the implementation rate of the weather adaptive scheduling strategy, the energy utilization rate under the grid-connected control strategy, and the power supply access capacity under the grid-connected control strategy, and calculates the index values ​​to finally obtain a comprehensive score. The carrying capacity level of the distribution network is optimized according to the comprehensive score and applied to model prediction. It can effectively predict the carrying capacity level of the fault-occurring area more accurately, and determine the execution priority of the self-healing control scheme according to the carrying capacity level to balance resource utilization and fault handling effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0101] Figure 1 The first embodiment of the present invention provides a method and system for controlling a fault self-healing of a distributed power source connected to a distribution network. DETAILED DESCRIPTION

[0102] In order to make the above-mentioned purposes, 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 drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0103] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a fault self-healing control method for a distributed power source connected to a distribution network, comprising:

[0104] S1: Collect the operating data of each node in the distribution network and perform preprocessing.

[0105] Determine the nodes in the distribution network that need to collect operating data, including power access points, load nodes, important branch nodes, and equipment monitoring points.

[0106] Equip collection equipment at the collection point to accurately collect the node's operating data, including voltage, current, power factor, active power, and reactive power.

[0107] Preprocessing includes removing outliers and filling missing values ​​to ensure the accuracy and reliability of the data.

[0108] S2: Analyze the preprocessed data, determine the evaluation objectives, and determine the key evaluation indicators based on the evaluation objectives.

[0109] Through in-depth analysis of the acquired operating data, we can understand the operating status of the distribution network and the impact of distributed power sources. According to the actual situation of the distribution network, the evaluation goal is to enhance the self-recovery ability of the distribution network in the face of various faults or abnormal situations after the distributed power sources are connected.

[0110] First, a multi-level evaluation system is constructed. The multi-level evaluation system has a three-layer structure, including the target layer, the performance layer and the indicator layer. The evaluation target is used as the target layer. The performance layer includes safety, economy and flexibility. Safety includes voltage deviation index, voltage qualification rate and voltage stability index under weather influence. Economy includes reactive power compensation qualification rate, average line loss rate, power generation efficiency index under weather influence and energy utilization rate under grid control strategy. Flexibility includes net load fluctuation rate, proportion of new energy power generation, implementation rate of weather adaptive scheduling strategy and power access capability under grid control strategy.

[0111] It should be noted that this embodiment first constructs a multi-level evaluation system, which includes a three-layer structure, namely a target layer, a performance layer and an indicator layer. The evaluation target is used as the target layer. The performance layer includes safety, economy, and flexibility. Safety includes voltage offset index and voltage qualification rate. Economy includes reactive power compensation qualification rate and average line loss rate. Flexibility includes net load fluctuation rate and new energy power generation proportion. The above is the prior art. This embodiment adds weather-related indicators to the indicator layer of the prior art, as well as indicators related to the grid connection strategy.

[0112] Furthermore, the weather-related indicators are as follows: the voltage stability index under weather influence is added to safety, the power generation efficiency index under weather influence and energy utilization rate under grid-connected control strategy are added to economy, and the implementation rate of weather-adaptive dispatch strategy and power access capacity under grid-connected control strategy are added to flexibility.

[0113] Based on data analysis and evaluation objectives, the key evaluation indicators that can be determined are:

[0114] Voltage stability index under weather influence: used to evaluate the stability and fluctuation of distribution network voltage under different weather conditions. Power generation efficiency index under weather influence: used to evaluate the power generation efficiency of distributed power sources under different weather conditions. Weather adaptability dispatch strategy implementation rate: used to evaluate the adaptability of distribution network dispatch strategy to weather changes. Energy utilization rate under grid-connected control strategy: used to evaluate the efficiency of energy utilization of distribution network under grid-connected control strategy. Power supply access capability under grid-connected control strategy: used to evaluate the access capability of distribution network to distributed power sources under grid-connected control strategy.

[0115] S3: Calculate the index value of each key evaluation indicator and quantify it to obtain a comprehensive score.

[0116] The voltage stability index under the influence of weather is calculated. The steps include calculating the voltage fluctuation amplitude according to the actual voltage, the rated voltage, and the voltage threshold, which is expressed as:

[0117]

[0118] Among them, B i Represents the voltage fluctuation amplitude of the ith node in the distribution network, V i Represents the actual voltage of the ith node in the distribution network, V ir represents the rated voltage of the ith node in the distribution network, and Y represents the voltage threshold of the distribution network.

[0119] Get the voltage fluctuation duration T of each node in the distribution network i and the node weight ω of each node in the distribution network i . Obtain the weather impact coefficient of the distribution network.

[0120] The voltage stability index under weather influence is calculated based on the voltage fluctuation amplitude, voltage fluctuation duration, node weight, and weather influence coefficient, and is expressed as:

[0121]

[0122] Among them, D i represents the voltage stability index under weather conditions, N represents the total number of nodes, i represents the i-th node, and F i represents the voltage fluctuation amplitude of the ith node in the distribution network, ω i represents the node weight of the ith node in the distribution network, W i Represents the weather impact coefficient of the i-th node in the distribution network.

[0123] It should be noted that the node weight is determined according to the importance of the node in the network. In the power system, the importance of a node depends on factors such as the capacity of the generator or load connected to it, the geographical location of the node, and the connectivity with other key nodes. In this embodiment, a higher node weight is assigned to an important node, and a lower node weight is assigned to an ordinary node.

[0124] Furthermore, an important node refers to a node that makes a significant contribution to the calculation of the voltage stability index under the influence of weather. When the voltage fluctuation amplitude of the current node of the distribution network is relatively large, it makes a significant contribution to the calculation of the voltage stability index under the influence of weather, and the current node is regarded as an important node and is given a higher node weight. Alternatively, if the voltage fluctuation duration of the current node is relatively long, it is an important node and is given a higher node weight. Alternatively, the current node operates under adverse weather conditions (strong winds, low temperatures), and makes a significant contribution to the calculation of the voltage stability index under the influence of weather. It is an important node and can be given a larger node weight.

[0125] The step of calculating the power generation efficiency index under weather influence includes obtaining the actual power generation measured under current weather conditions, the ideal power generation under ideal weather conditions, and the weather influence index of the distribution network.

[0126] The power generation efficiency index under weather influence is calculated based on the actual power generation measured under current weather conditions, the ideal power generation under ideal weather conditions, and the weather influence index of the distribution network, which is expressed as:

[0127]

[0128] Among them, F represents the power generation efficiency index of the distribution network under the influence of weather, AG represents the actual power generation measured under current weather conditions, TG represents the ideal power generation under ideal weather conditions, and WI represents the weather impact index of the distribution network.

[0129] It should be noted that ideal weather conditions refer to the weather conditions that are most favorable to the operation of the distribution network, for example, moderate wind speed, sufficient sunlight, etc. Ideal power generation refers to the maximum power generation that the distribution network can achieve under ideal weather conditions.

[0130] The steps for calculating the energy utilization rate under the grid-connected control strategy include obtaining the total power consumption of the distribution network, the energy type factor of the distributed power source, the energy conversion efficiency of the distributed power source, and the energy loss rate of the distributed power source.

[0131] It should be noted that the energy type factor of distributed power generation is a quantitative expression of the relative value or weight of different energy types in energy utilization. To this end, it is necessary to determine the main evaluation factors that affect the weight of energy types, including environmental impact, environmental sustainability, technological maturity, and cost-effectiveness. For each evaluation factor, collect real-time data of different energy types, and assign a weight to each factor based on the importance and priority of the evaluation factor. Multiply the real-time data by the weight to obtain the score of each energy type under each evaluation factor, and sum the weighted scores under all evaluation factors to obtain the energy type factor value.

[0132] According to the actual power generation, total power consumption of the distribution network, energy type factor, energy conversion efficiency, and energy loss rate measured under current weather conditions, the energy utilization rate under the grid-connected control strategy is calculated:

[0133]

[0134] Where I' represents the energy utilization rate under the grid-connected control strategy, T e Indicates the total power consumption of the distribution network, E f Represents the energy type factor of distributed generation, C E Represents the energy conversion efficiency of distributed power generation, E L Represents the energy loss rate of distributed generation.

[0135] It should be noted that in the calculation formula of the energy utilization rate under the grid-connected control strategy, the actual power generation AG measured under the current weather conditions is the same as the actual power generation measured by the distribution network.

[0136] S4: Divide the bearing capacity level according to the value range of the comprehensive score to obtain the bearing capacity level interval, and determine the bearing capacity level of the comprehensive evaluation score.

[0137] The value range of the combined evaluation score is defined as {A, B, C, ..., K}, and the maximum and minimum values ​​of the value range are assigned according to the actual data of the distribution network.

[0138] The comprehensive score is calculated by summing up the voltage fluctuation amplitude, voltage stability index, power generation efficiency index and energy utilization rate, and is expressed as:

[0139]

[0140] Among them, S total represents the comprehensive carrying capacity score, T represents the evaluation time period, N represents the total number of nodes in the distribution network, and B i represents the voltage fluctuation amplitude of the ith node, D i represents the voltage stability index of the ith node, F i Represents the power generation efficiency index of the i-th node, I' i represents the energy utilization rate of the i-th node, W i represents the weather influence coefficient of the i-th node, T i represents the voltage fluctuation duration of the ith node, ω i represents the weight of the i-th node, and α represents a constant parameter that adjusts the nonlinear relationship between voltage fluctuation and voltage stability.

[0141] It should be noted that the mutual influence of multiple factors such as voltage fluctuation, voltage stability, power generation efficiency and energy utilization is ensured through the combination of exponential function, logarithmic function, sinusoidal function and fraction, and the comprehensive carrying capacity in the whole dispatching cycle is evaluated through integration operation.

[0142] The value range {A, B, C, ..., K} is divided into several bearing capacity level intervals and bearing capacity levels, and the bearing capacity level intervals include a first bearing capacity level interval, a second bearing capacity level interval, a third bearing capacity level interval, and a fourth bearing capacity level interval.

[0143] The bearing capacity level of the first bearing capacity level interval is greater than the bearing capacity level of the second bearing capacity level interval, the bearing capacity level of the second bearing capacity level interval is greater than the bearing capacity level of the third bearing capacity level interval, and the bearing capacity level of the third bearing capacity level interval is greater than the bearing capacity level of the fourth bearing capacity level interval.

[0144] The value range [I, K] represents the first bearing capacity interval, indicating that the distribution network has a high bearing capacity level.

[0145] The value range [F, H] represents the second carrying capacity interval, indicating that the distribution network has a higher carrying capacity level.

[0146] The value range [C, E] represents the third bearing capacity interval, indicating that the distribution network has a medium bearing capacity level.

[0147] The value range [A, B] represents the fourth bearing capacity interval, indicating that the distribution network has a low bearing capacity level.

[0148] The upper limit K of the first bearing capacity level interval is expressed as:

[0149]

[0150] The upper limit I of the first bearing capacity level interval is expressed as:

[0151]

[0152] The upper limit H of the second bearing capacity level interval is expressed as:

[0153]

[0154] The lower limit F of the second bearing capacity grade interval is expressed as:

[0155]

[0156] The upper limit E of the third bearing capacity level interval is expressed as:

[0157]

[0158] The lower limit C of the third bearing capacity level interval is expressed as:

[0159]

[0160] The upper limit B of the fourth bearing capacity level interval is expressed as:

[0161]

[0162] The lower limit A' of the fourth bearing capacity level interval is expressed as:

[0163]

[0164] Where x represents the instantaneous value of the scoring function Stotal at time t, T represents the duration of the entire evaluation, Indicates the maximum score. Indicates the minimum score.

[0165] Compare the current comprehensive evaluation score with the bearing capacity grade range to determine the bearing capacity grade of the current comprehensive evaluation score.

[0166] S5: Construct a distribution network carrying capacity assessment model, output the distribution network carrying capacity level, formulate a fault self-healing control plan, and realize rapid fault self-healing control.

[0167] The index values, comprehensive evaluation scores and carrying capacity levels of key evaluation indicators are used as training sets to train the distribution network carrying capacity assessment model, and a trained distribution network carrying capacity assessment model is obtained.

[0168] In order to accurately evaluate the carrying capacity of the distributed power sources connected to the distribution network and fully allocate and use the connected distributed power sources, this embodiment uses a distribution network carrying capacity evaluation model to evaluate the distribution network carrying capacity.

[0169] The distribution network carrying capacity assessment model also includes the objective function expressed as:

[0170] L=L1+L2+L3+L4+L5+L6

[0171]

[0172]

[0173]

[0174] Among them, L represents the objective function, L1 represents the voltage stability objective item, L2 represents the power generation efficiency objective item, L3 represents the scheduling strategy implementation objective item, L4 represents the energy utilization objective item, L5 represents the power supply access capability objective item, and L6 represents the basic objective item. Represents the average value of the voltage stability index, Represents the average value of the power generation efficiency index, C i represents the implementation rate of the weather adaptive dispatch strategy, I'i represents the energy utilization rate under the grid-connected control strategy, J i represents the power access capability value under the grid-connected control strategy, N represents the total number of nodes, i represents the i-th node, represents the weight of the voltage stability objective item, represents the weight of the power generation efficiency objective item, Represents the weight of the scheduling strategy implementation target item, represents the weight of the energy utilization target item, represents the weight of the power access capability target item. Ci,t represents the distributed power of the ith node at time t. T represents a complete scheduling cycle.

[0175] It should be noted that the objective function and constraints play a core role in the capacity level prediction model. By integrating key performance indicators such as voltage stability, generation efficiency, dispatch strategy implementation, energy utilization and power access capability, the model provides a comprehensive system performance evaluation. The introduction of weight coefficients allows balancing according to the priority of different indicators, while voltage and power flow constraints ensure the safe operation of the power system and prevent overload and voltage anomalies. Generation and load balance constraints ensure the precise match between supply and demand and improve energy efficiency. Dispatch strategy implementation constraints enhance the adaptability and flexibility of the system, while risk management reduces the impact of uncertainty on system stability through constraints. In addition, the model provides strong decision support for grid operators and planners to help them evaluate the impact of different strategies. The flexibility and adaptability of the model allow it to be adjusted according to different operating environments and strategic goals. At the same time, its prediction ability provides an important reference for long-term planning and short-term operation of the power grid, supporting the sustainable development and environmental protection goals of the power system.

[0176] The constraints include voltage constraints, power flow constraints, power generation and load balance conditions, scheduling strategy implementation constraints, energy utilization constraints, and power supply access capacity constraints.

[0177] The voltage constraint is expressed as:

[0178] V min ≤V i ≤V max

[0179] Among them, V i represents the voltage of the ith node, V min Indicates the minimum voltage, V max Indicates the maximum voltage.

[0180] The power flow constraint is expressed as:

[0181] P min，j ≤P max，j

[0182] Among them, P min，j represents the power flow of the jth line, P max，j represents the maximum allowed power flow of the jth line.

[0183] The generation and load balance constraints are expressed as:

[0184]

[0185] Among them, P g represents the power output of generator g, Σ g∈G P grepresents the sum of the power output of all generators, P d represents the power demand of load d, Σ d∈M P d represents the sum of the power requirements of all loads, P loss represents the system power loss, G represents the engine set, and M represents the load set.

[0186] The scheduling strategy implementation constraints are expressed as:

[0187] C≥C min

[0188] Among them, C min Indicates the minimum implementation rate of the weather adaptive scheduling strategy.

[0189] The energy utilization constraint is expressed as:

[0190] I≥I min

[0191] Among them, I min It represents the minimum value of energy utilization under the grid-connected control strategy.

[0192] The power access capability constraint is expressed as:

[0193] J≥J min

[0194] Among them, J min Indicates the minimum value of the power access capability under the grid-connected control strategy.

[0195] The distribution network data to be predicted is input into the trained distribution network carrying capacity assessment model, and the distribution network carrying capacity level is output.

[0196] According to the priority of the predicted distribution network carrying capacity level, the self-healing control scheme is preferentially executed for the area where the current fault is located.

[0197] For faults in the first load-bearing level range, rapid fault location and isolation are carried out, power supply to non-faulty areas is automatically restored, and the system operating status is monitored and optimized.

[0198] For faults in the second load-bearing level range, strengthen monitoring of the fault area, prevent the spread of faults, respond quickly and isolate the faults, reduce the scope of power outages, coordinate control of adjacent areas, and ensure stable power supply.

[0199] For faults in the third load-bearing level range, activate the emergency plan, including the preparation of backup power supplies and temporary lines, give priority to restoring power supply to critical loads, assess the impact of the fault, and formulate a recovery plan.

[0200] For faults in the fourth load-bearing level range, the emergency response mechanism is immediately activated, including coordination with external resources, rapid assessment of losses, ensuring personnel safety, formulating post-disaster reconstruction plans, and optimizing system structure.

[0201] It should be noted that all imaginary numbers such as weight coefficients and adjustment parameters in this embodiment are obtained through experiments and set by professionals, and can be modified according to actual conditions in specific applications.

[0202] The above embodiments also include a fault self-healing control system for a distributed power source connected to a distribution network, specifically:

[0203] The data collection module collects the operating data of each node in the distribution network and performs pre-processing.

[0204] The analysis module analyzes the preprocessed data, determines the evaluation objectives, and determines the key evaluation indicators based on the evaluation objectives.

[0205] The calculation module calculates the index value of each key evaluation index and quantifies it to obtain a comprehensive score. The bearing capacity level is divided according to the value range of the comprehensive score to obtain the bearing capacity level interval and determine the bearing capacity level of the comprehensive evaluation score.

[0206] Build a model module, construct a distribution network carrying capacity assessment model, output the distribution network carrying capacity level, formulate a fault self-healing control plan, and realize rapid fault self-healing control.

[0207] The computer device may be a server. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data cluster data of the power monitoring system. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection.

[0208] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0209] Embodiment 2, an embodiment of the present invention, provides a fault self-healing control method and system for a distributed power source connected to a distribution network. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0210] In order to verify the effectiveness of the fault self-healing control method for distributed power access to the distribution network proposed in this invention, a comparative experiment was conducted with the existing technical means of fault-free self-healing control system. The experimental scenario selected a small distribution network with distributed power access, which contains 8 nodes, including 2 distributed power access points, 3 load nodes, 2 important branch nodes and 1 equipment monitoring point.

[0211] The implementation steps of our invention are:

[0212] Data collection and preprocessing: High-precision power monitoring equipment is deployed at each node to collect data such as voltage, current, power factor, reactive power, etc. in real time. In the preprocessing stage, the unreasonable abnormal data is first filtered out, and the missing data is filled by linear interpolation method to ensure the accuracy and reliability of the data.

[0213] Determination of evaluation objectives and key indicators: Based on the actual operating status of the distribution network, the self-recovery capability of the power grid in the event of a fault was determined as the evaluation objective, and then key indicators such as voltage stability index, power generation efficiency under weather influence, and energy utilization rate under the grid-connected control strategy were selected.

[0214] Index value calculation and comprehensive scoring: The key index values ​​of each node were calculated, such as the voltage stability index under weather influence based on the voltage fluctuation amplitude and duration, and the power generation efficiency was calculated based on the actual power generation and weather impact index. The comprehensive score of each node was obtained by integrating various indicators through integration and summation methods.

[0215] Carrying capacity classification and model construction: The comprehensive score is divided into four levels, the highest level is the IK interval, and the lowest level is the AB interval. Using these data, a distribution network carrying capacity assessment model is constructed and the carrying capacity level is output.

[0216] Development and implementation of fault self-healing control schemes: According to different load-bearing capacity levels, faults in high-load-bearing capacity areas are handled first, achieving rapid fault location, isolation and power restoration, while monitoring system stability.

[0217] Existing technical implementation steps:

[0218] Data collection and preprocessing: The monitoring equipment used in the prior art has low accuracy, resulting in large errors in the collected data. In addition, the prior art only fills in missing data through simple average values, and the accuracy of the data cannot be fully guaranteed.

[0219] Fault handling method: The existing technology uses traditional manual handling, which cannot locate the fault point in time, and the power supply restoration speed is slow, which easily leads to large-scale power outages. In addition, the existing technology does not consider the impact of weather factors on power generation efficiency and voltage stability, and lacks a comprehensive assessment of the operating status of the power grid.

[0220] By comparing the above steps, the prior art cannot provide the capability of automatic and self-healing control, while the present invention realizes rapid recovery of faults and optimization of system stability through an intelligent control method.

[0221] The experimental results are shown in Table 1.

[0222]

[0223] From the table data, we can see that the voltage fluctuation amplitudes of the prior art at nodes 1 and 2 are 18V and 22V respectively, with large fluctuations, and the voltage stability indexes are 0.65 and 0.60 respectively. However, the present invention optimizes the control of voltage fluctuations, controls the fluctuation amplitude between 10V-12V, and improves the voltage stability index to 0.83-0.88. It can be seen that the present invention effectively reduces voltage fluctuations and enhances the voltage stability of the system, especially under severe weather conditions. The present invention can significantly improve the safety of the distribution network.

[0224] The power generation efficiency and energy utilization rate of the existing technology under the influence of weather are poor, fluctuating between 70% and 76% and 63% and 68% respectively, showing sensitivity to weather changes. The present invention, by introducing a weather-adaptive scheduling strategy, increases the power generation efficiency to 85% to 90%, while the energy utilization rate is also increased to 80% to 85%. This result shows that the present invention is significantly superior to the existing technology in terms of resource utilization.

[0225] According to the load-bearing capacity classification results, the node load-bearing capacity level of the prior art is C, indicating that the system has a low load-bearing capacity and is easily affected by failures. However, the present invention improves the node load-bearing capacity level to A or B by improving the comprehensive score, indicating that the system has a higher load-bearing capacity and fault resistance. In particular, the present invention can maintain stable operation when the load fluctuates greatly.

[0226] In summary, the present invention not only improves the stability and security of the power grid through an intelligent fault self-healing control method, but also greatly improves the power generation efficiency and resource utilization, showing significant innovation and advantages. In practical applications, the present invention can effectively solve the defects in the prior art and provide a more reliable distribution network fault handling solution.

[0227] 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 fault self-healing control method for a distributed power source connected to a distribution network, characterized in that: include: Collect the operating data of each node in the distribution network and perform pre-processing; Analyze the preprocessed data, determine the evaluation objectives, and determine the key evaluation indicators based on the evaluation objectives; Calculate the index value of each key evaluation indicator and quantify it to obtain a comprehensive score; The bearing capacity level is divided according to the value range of the comprehensive score to obtain the bearing capacity level interval, and the bearing capacity level of the comprehensive evaluation score is determined; Construct a distribution network carrying capacity assessment model, output the distribution network carrying capacity level, formulate a fault self-healing control plan, and realize rapid fault self-healing control.

2. The fault self-healing control method for distributed power supply access to a distribution network according to claim 1, characterized in that: The collecting of the operation data of each node of the distribution network and the preprocessing include determining the nodes of the distribution network from which the operation data needs to be collected, the nodes including power access points, load nodes, important branch nodes, and monitoring points of equipment; Equip collection equipment at the collection point to accurately collect the operation data of the node, including voltage, current, power factor, active power, and reactive power; Preprocessing includes removing outliers and filling missing values ​​to ensure the accuracy and reliability of the data.

3. The fault self-healing control method for connecting a distributed power source to a distribution network as claimed in claim 2, characterized in that: The analysis of the pre-processed data to determine the evaluation target and the determination of the key evaluation indicators according to the evaluation target include: conducting in-depth analysis of the acquired operation data to understand the operation status of the distribution network and the impact of the distributed power source, and determining the evaluation target to enhance the self-recovery capability of the distribution network in the face of various faults or abnormal situations after the distributed power source is connected according to the actual situation of the distribution network; First, a multi-level evaluation system is constructed. The multi-level evaluation system has a three-layer structure, including a target layer, a performance layer and an indicator layer. The evaluation target is taken as the target layer, and the performance layer includes safety, economy and flexibility. Safety includes voltage deviation index, voltage qualification rate and voltage stability index under weather influence; economy includes reactive power compensation qualification rate, average line loss rate, power generation efficiency index under weather influence and energy utilization rate under grid-connected control strategy; flexibility includes net load fluctuation rate, proportion of new energy power generation, implementation rate of weather adaptive dispatching strategy and power supply access capability under grid-connected control strategy.

4. The fault self-healing control method for connecting a distributed power source to a distribution network as claimed in claim 3, characterized in that: The calculation of the index value of each key evaluation index and quantification to obtain a comprehensive score includes calculating the voltage stability index under the influence of weather, and the steps include calculating the voltage fluctuation amplitude according to the actual voltage, the rated voltage, and the voltage threshold, which is expressed as: Among them, B i Represents the voltage fluctuation amplitude of the ith node in the distribution network, V i Represents the actual voltage of the ith node in the distribution network, V ir represents the rated voltage of the ith node of the distribution network, and Y represents the voltage threshold of the distribution network; Get the voltage fluctuation duration T of each node in the distribution network i and the node weight ω of each node in the distribution network i ; Obtain the weather impact coefficient of the distribution network; The voltage stability index under weather influence is calculated based on the voltage fluctuation amplitude, voltage fluctuation duration, node weight, and weather influence coefficient, and is expressed as: Among them, D i represents the voltage stability index under weather conditions, N represents the total number of nodes, i represents the i-th node, and F i represents the voltage fluctuation amplitude of the ith node in the distribution network, ω i represents the node weight of the ith node in the distribution network, W i represents the weather impact coefficient of the ith node in the distribution network; The step of calculating the power generation efficiency index under weather influence includes obtaining the actual power generation measured under current weather conditions, the ideal power generation under ideal weather conditions, and the weather influence index of the distribution network; The power generation efficiency index under weather influence is calculated based on the actual power generation measured under current weather conditions, the ideal power generation under ideal weather conditions, and the weather influence index of the distribution network, which is expressed as: Among them, F represents the power generation efficiency index of the distribution network under the influence of weather, AG represents the actual power generation measured under current weather conditions, TG represents the ideal power generation under ideal weather conditions, and WI represents the weather influence index of the distribution network; The steps of calculating the energy utilization rate under the grid-connected control strategy include obtaining the total power consumption of the distribution network, the energy type factor of the distributed power source, the energy conversion efficiency of the distributed power source, and the energy loss rate of the distributed power source; According to the actual power generation, total power consumption of the distribution network, energy type factor, energy conversion efficiency, and energy loss rate measured under current weather conditions, the energy utilization rate under the grid-connected control strategy is calculated: Where I' represents the energy utilization rate under the grid-connected control strategy, T e Indicates the total power consumption of the distribution network, E f Represents the energy type factor of distributed generation, C E Represents the energy conversion efficiency of distributed power generation, E L Represents the energy loss rate of distributed generation.

5. The fault self-healing control method for connecting a distributed power source to a distribution network as claimed in claim 4, characterized in that: The carrying capacity level is divided according to the value range of the comprehensive score to obtain the carrying capacity level interval, and the carrying capacity level of the comprehensive evaluation score is determined, including defining the value range of the comprehensive evaluation score as {A, B, C, ..., K}, and assigning the maximum value and the minimum value of the value range according to the actual data of the distribution network; The comprehensive score is calculated by summing up the voltage fluctuation amplitude, voltage stability index, power generation efficiency index and energy utilization rate, and is expressed as: Among them, S total represents the comprehensive carrying capacity score, T represents the evaluation time period, N represents the total number of nodes in the distribution network, and B i represents the voltage fluctuation amplitude of the ith node, D i represents the voltage stability index of the ith node, F i Represents the power generation efficiency index of the i-th node, I' i represents the energy utilization rate of the i-th node, W i represents the weather influence coefficient of the ith node, T i represents the voltage fluctuation duration of the ith node, ω i represents the weight of the i-th node, α represents a constant parameter, which adjusts the nonlinear relationship between voltage fluctuation and voltage stability; Divide the value range {A, B, C, ..., K} into a plurality of bearing capacity level intervals and bearing capacity levels, wherein the bearing capacity level intervals include a first bearing capacity level interval, a second bearing capacity level interval, a third bearing capacity level interval, and a fourth bearing capacity level interval; The bearing capacity level of the first bearing capacity level interval is greater than the bearing capacity level of the second bearing capacity level interval, the bearing capacity level of the second bearing capacity level interval is greater than the bearing capacity level of the third bearing capacity level interval, and the bearing capacity level of the third bearing capacity level interval is greater than the bearing capacity level of the fourth bearing capacity level interval; The value range [I, K] represents the first carrying capacity interval, indicating that the distribution network has a high carrying capacity level; The value range [F, H] represents the second carrying capacity interval, indicating that the distribution network has a higher carrying capacity level; The value range [C, E] represents the third carrying capacity interval, indicating that the distribution network has a medium carrying capacity level; The value range [A, B] represents the fourth carrying capacity interval, indicating that the distribution network has a low carrying capacity level; The upper limit K of the first bearing capacity level interval is expressed as: The upper limit I of the first bearing capacity level interval is expressed as: The upper limit H of the second bearing capacity level interval is expressed as: The lower limit F of the second bearing capacity grade interval is expressed as: The upper limit E of the third bearing capacity level interval is expressed as: The lower limit C of the third bearing capacity level interval is expressed as: The upper limit B of the fourth bearing capacity level interval is expressed as: The lower limit A' of the fourth bearing capacity level interval is expressed as: Where x represents the instantaneous value of the scoring function Stotal at time t, T represents the duration of the entire evaluation, Indicates the maximum score. Indicates the minimum score; Compare the current comprehensive evaluation score with the bearing capacity grade range to determine the bearing capacity grade of the current comprehensive evaluation score.

6. The fault self-healing control method for connecting a distributed power source to a distribution network as claimed in claim 5, characterized in that: The constructing of the distribution network carrying capacity assessment model and outputting the distribution network carrying capacity level comprises taking the index value of the key evaluation index, the comprehensive evaluation score, and the carrying capacity level as a training set, training the distribution network carrying capacity assessment model, and obtaining a trained distribution network carrying capacity assessment model; In order to accurately evaluate the carrying capacity of the distributed power sources connected to the distribution network and fully allocate and use the connected distributed power sources, this embodiment uses the distribution network carrying capacity evaluation model to evaluate the distribution network carrying capacity; The distribution network carrying capacity assessment model also includes the objective function expressed as: L=L1+L2+L3+L4+L5+L6 Among them, L represents the objective function, L1 represents the voltage stability objective item, L2 represents the power generation efficiency objective item, L3 represents the dispatch strategy implementation objective item, L4 represents the energy utilization objective item, L5 represents the power supply access capability objective item, and L6 represents the basic objective item; Represents the average value of the voltage stability index, Represents the average value of the power generation efficiency index, C i represents the implementation rate of the weather adaptive dispatch strategy, I'i represents the energy utilization rate under the grid-connected control strategy, J i represents the power access capability value under the grid-connected control strategy, N represents the total number of nodes, i represents the i-th node, represents the weight of the voltage stability objective item, represents the weight of the power generation efficiency objective item, Represents the weight of the scheduling strategy implementation target item, represents the weight of the energy utilization target item, represents the weight of the power access capability target item; Ci,t represents the distributed power of the i-th node at time t; T represents a complete scheduling cycle; The constraints include voltage constraints, power flow constraints, power generation and load balance conditions, scheduling strategy implementation constraints, energy utilization constraints, and power access capacity constraints; The voltage constraint is expressed as: Vmi n ≤V i ≤Vma x Among them, V i Represents the voltage of the ith node, Vmi n Indicates the minimum voltage, Vma x Indicates the maximum voltage; The power flow constraint is expressed as: P min，j ≤P max，j Among them, P min，j represents the power flow of the jth line, P max，j represents the maximum allowed power flow of the jth line; The generation and load balance constraints are expressed as: Among them, P g represents the power output of generator g, Σ g∈G P g represents the sum of the power output of all generators, P d represents the power demand of load d, Σ d∈M P d represents the sum of the power requirements of all loads, P loss represents the system power loss, G represents the engine set, and M represents the load set; The scheduling strategy implementation constraints are expressed as: C≥C min Among them, C min It represents the minimum value of the implementation rate of the weather adaptive scheduling strategy; The energy utilization constraint is expressed as: I≥I min Among them, I min It represents the minimum value of energy utilization under the grid-connected control strategy; The power access capability constraint is expressed as: J≥J min Among them, J min Indicates the minimum value of the power access capability under the grid-connected control strategy; The distribution network data to be predicted is input into the trained distribution network carrying capacity assessment model, and the distribution network carrying capacity level is output.

7. The fault self-healing control method for connecting a distributed power source to a distribution network as claimed in claim 6, characterized in that: The formulating of the fault self-healing control scheme to realize the rapid fault self-healing control includes, according to the priority of the distribution network carrying capacity level obtained by prediction, preferentially executing the self-healing control scheme for the area where the current fault is located; For faults in the first load-carrying level interval, fast fault location and isolation are performed, power supply to non-faulty areas is automatically restored, and system operation status is monitored and optimized; For faults in the second load-carrying capacity level interval, strengthen fault area monitoring, prevent fault spread, quickly respond and isolate faults, reduce the scope of power outages, coordinate control of adjacent areas, and ensure stable power supply; For faults in the third load capacity level range, the emergency plan is activated, including the preparation of backup power supplies and temporary lines, priority is given to restoring power supply to critical loads, assessing the impact of the fault, and formulating a recovery plan; For faults in the fourth load-bearing level range, the emergency response mechanism is immediately activated, including coordination with external resources, rapid assessment of losses, ensuring personnel safety, formulating post-disaster reconstruction plans, and optimizing system structure.

8. A fault self-healing control system for a distributed power source connected to a distribution network using the method according to any one of claims 1 to 7, characterized in that: The data collection module collects the operating data of each node in the distribution network and performs pre-processing; The analysis module analyzes the preprocessed data, determines the evaluation objectives, and determines the key evaluation indicators based on the evaluation objectives; The calculation module calculates the index value of each key evaluation index and quantifies it to obtain a comprehensive score; divides the bearing capacity level according to the value range of the comprehensive score, obtains the bearing capacity level interval, and determines the bearing capacity level of the comprehensive evaluation score; Build a model module, construct a distribution network carrying capacity assessment model, output the distribution network carrying capacity level, formulate a fault self-healing control plan, and realize rapid fault self-healing control.

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 according to 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 according to any one of claims 1 to 7 are implemented.

Images