Method and system for improving distribution network resilience based on coordinated dispatch of energy storage output

Abstract

The present invention discloses a method and system for improving the resilience of a distribution network based on energy storage output collaborative scheduling, the method comprising: judging whether to trigger an energy storage capacity reduction warning according to the current energy storage capacity; judging whether to trigger an energy storage capacity shortage warning according to the obtained power change prediction curve; performing dynamic planning based on at least the current energy storage capacity and the power change prediction curve to obtain a short-term energy storage scheduling strategy; performing a flow calculation on the distribution network operation status data based on the short-term energy storage scheduling strategy to obtain a distribution network node voltage distribution result, and obtaining an energy storage voltage regulation effective capacity according to the distribution network node voltage distribution result; performing a power shortage calculation on the reactive compensation device operation strategy to obtain a reactive compensation circuit power shortage value; and when the distribution network is not in a power balance state, improving the resilience of the distribution network by executing a load shedding instruction. The present invention can effectively improve the resilience of the distribution network in an extreme low temperature environment.

Description

Technical Field

[0001] The present invention relates to the field of power system operation and control technology, and in particular to a method and system for improving the resilience of a distribution network based on coordinated dispatch of energy storage output. Background Art

[0002] In extremely low temperature environments, the coordinated operation of distributed energy storage and distributed power sources in distribution networks faces significant challenges. The charging and discharging capacity of energy storage units weakens as the temperature drops sharply, which directly affects their voltage regulation and power balancing capabilities. This causes energy storage units such as batteries to be unable to maintain normal output voltage when providing the same load, resulting in voltage instability. At the same time, they may not be able to meet power demand under high load conditions, exacerbating the imbalance between supply and demand in the distribution network. The output characteristics of distributed power sources are also more volatile and intermittent due to low temperatures, further increasing the difficulty of voltage regulation and power balancing. Therefore, the dynamic balance between distributed energy storage and distributed power sources becomes complex and fragile, and the distribution network recovery process may encounter problems such as voltage recovery lag and power oscillation, which seriously affect the stable operation of the distribution network.

[0003] There are few studies in the prior art on the coupling mechanism of voltage regulation and power balance when the energy storage capacity decreases under extreme low temperatures. Therefore, it is necessary to propose a new method to coordinate distributed energy storage and distributed power sources to improve the adaptability and recovery capabilities of the distribution network and ensure its safe and stable operation under extreme low temperature environments. Summary of the invention

[0004] The present invention aims to solve the technical problem of imbalance in voltage regulation and power balance capabilities when distributed energy storage and distributed power sources are operating in coordination in distribution networks under extreme low temperature environments. In order to solve the above technical problems, the present invention provides a method and system for improving the resilience of distribution networks based on coordinated scheduling of energy storage output.

[0005] In a first aspect, an embodiment of the present invention provides a method for improving the resilience of a distribution network based on coordinated dispatch of energy storage output, comprising:

[0006] Acquire real-time temperature data of the energy storage unit in the distribution network, obtain the current energy storage capacity of the energy storage unit by mapping based on the real-time temperature data, and determine whether to trigger an energy storage capacity reduction warning according to the current energy storage capacity;

[0007] Power prediction is performed based on the real-time output data of the new energy distributed power source in the distribution network, and judging whether to trigger an energy storage capacity shortage warning according to the obtained power change prediction curve;

[0008] Under the condition that an energy storage capacity decrease warning is triggered and an energy storage capacity insufficient warning is triggered, dynamic planning is performed based at least on the current energy storage capacity and the power change prediction curve to obtain a short-term energy storage scheduling strategy;

[0009] Based on the short-term energy storage scheduling strategy, the distribution network operation status data is subjected to power flow calculation to obtain the distribution network node voltage distribution result, the over-limit nodes are identified according to the distribution network node voltage distribution result, and the identified over-limit nodes are subjected to sensitivity analysis to obtain the effective capacity of energy storage voltage regulation, wherein the distribution network operation status data includes node injection power, branch power flow, node voltage data and line impedance data;

[0010] With the goal of minimizing the voltage deviation of the distribution network nodes, the effective capacity of the energy storage voltage regulation and the reactive compensation device in the distribution network are collaboratively planned to obtain the reactive compensation device operation strategy, and the power shortage of the reactive compensation device operation strategy is calculated to obtain the power shortage value of the reactive compensation circuit, wherein the reactive compensation device operation strategy includes the switching order of the reactive compensation device and the reactive compensation gear capacity configuration strategy;

[0011] Based on the power shortage value of the reactive compensation circuit, it is judged whether the distribution network is in a power balance state, and when the distribution network is not in a power balance state, the recovery capacity of the distribution network is improved by executing a load shedding instruction.

[0012] Preferably, after judging whether the distribution network is in a power balance state based on the power shortage value of the reactive compensation circuit, and improving the restoration capacity of the distribution network by executing a load shedding instruction when the distribution network is not in a power balance state, the method further includes:

[0013] The energy storage capacity is predicted based on the operating status data of the energy storage unit to obtain the energy storage capacity recovery rate, and the charging and discharging power of the energy storage unit is optimized according to the energy storage capacity recovery rate to obtain the energy storage charging power upper limit value and the energy storage discharging power upper limit value, wherein the energy storage unit operating status data includes the energy storage unit shell temperature data, the energy storage unit ambient temperature data and the energy storage unit voltage and current data.

[0014] Preferably, the acquiring of real-time temperature data of an energy storage unit in the distribution network, obtaining the current energy storage capacity of the energy storage unit by mapping based on the real-time temperature data, and determining whether to trigger an energy storage capacity reduction warning according to the current energy storage capacity, includes:

[0015] Perform distributed temperature collection on energy storage units in the distribution network to obtain real-time temperature data, wherein the real-time temperature data is a temperature dot matrix data group;

[0016] Performing weighted processing on each temperature value in the temperature dot matrix data group based on a distance weight to obtain a standardized temperature value of the energy storage unit;

[0017] Mapping the standardized temperature value based on a temperature-capacity correspondence curve to obtain a current energy storage capacity of the energy storage unit, wherein the temperature-capacity correspondence curve is a fitting curve between temperature and energy storage capacity;

[0018] Performing deviation calculation on the current energy storage capacity based on moving average to obtain current energy storage capacity deviation data;

[0019] Calculating a temperature change rate based on the temperature dot matrix data group, and determining whether the temperature change rate exceeds a temperature drop threshold;

[0020] If the temperature change rate exceeds the temperature drop threshold, it is determined whether the current energy storage capacity deviation data and the temperature change rate correspond to the same time period. If so, an energy storage capacity drop warning is triggered.

[0021] Preferably, the power forecasting is performed based on the real-time output data of the new energy distributed power source in the distribution network, and judging whether to trigger the energy storage capacity insufficient warning according to the obtained power change prediction curve, including:

[0022] Collecting real-time output data of the new energy distributed power source in the distribution network, and converting the real-time output data to obtain real-time power data;

[0023] Performing time synchronization on the real-time power data based on a sampling period to obtain power time series data;

[0024] Based on the power time series data, power prediction is performed through a recursive neural network to obtain a power change prediction curve, wherein the power change prediction curve corresponds to a first fluctuation interval of power change;

[0025] Calculating the energy storage capacity usage data of the preset time window of the energy storage unit based on moving average to obtain an energy storage capacity change curve, wherein the energy storage capacity change curve corresponds to a second fluctuation range of energy storage capacity change;

[0026] The fluctuation interval difference between the power change prediction curve and the energy storage capacity change curve is calculated based on the first fluctuation interval and the second fluctuation interval, and it is determined whether the fluctuation interval difference exceeds the nominal capacity threshold of the energy storage unit. If so, an energy storage capacity insufficient warning is triggered.

[0027] Preferably, under the condition that the energy storage capacity decrease warning is triggered and the energy storage capacity insufficient warning is triggered, dynamic planning is performed at least based on the current energy storage capacity and the power change prediction curve to obtain a short-term energy storage scheduling strategy, including:

[0028] Obtaining load power data of a load management device in the distribution network and power prediction data corresponding to the power change prediction curve;

[0029] Constructing an operation status data set based on the current energy storage capacity, load power data and power prediction data;

[0030] Dynamic programming is performed based on the operating status data set to obtain a short-term energy storage scheduling strategy, wherein the short-term energy storage scheduling strategy includes a charging and discharging power adjustment instruction of the energy storage unit in each sub-period.

[0031] Preferably, the method of performing power flow calculation on the distribution network operation status data based on the short-term energy storage scheduling strategy to obtain a distribution network node voltage distribution result, identifying the over-limit nodes according to the distribution network node voltage distribution result, and performing sensitivity analysis on the identified over-limit nodes to obtain the effective capacity of energy storage voltage regulation includes:

[0032] Based on the short-term energy storage scheduling strategy, the Newton-Raphson algorithm is used to iteratively calculate the power flow of the distribution network operation status data until the convergence condition is reached to obtain the voltage distribution result of the distribution network node;

[0033] Determine whether each node voltage in the distribution network node voltage distribution result is within the distribution network voltage limit interval, and if not, identify the node corresponding to the node voltage as an out-of-limit node;

[0034] Perform energy storage power disturbance on each of the above-mentioned crossing nodes, and calculate the sensitivity coefficient corresponding to the above-mentioned crossing node based on the obtained node voltage change, wherein the sensitivity coefficient is calculated using the following formula:

[0035]

[0036] in, represents the sensitivity coefficient, represents the node voltage change, Represents the energy storage power disturbance;

[0037] The power required for voltage regulation of the energy storage unit corresponding to the out-of-limit node is calculated based on the sensitivity coefficient, and the power required for voltage regulation of the energy storage unit is characterized as the effective capacity of energy storage voltage regulation.

[0038] Preferably, the method aims to minimize the voltage deviation of the distribution network nodes, coordinates the effective capacity of the energy storage voltage regulation and the reactive compensation device in the distribution network to obtain an operation strategy of the reactive compensation device, and performs power shortage calculation on the operation strategy of the reactive compensation device to obtain a power shortage value of the reactive compensation circuit, including:

[0039] With the goal of minimizing the voltage deviation of the distribution network nodes, a genetic algorithm is used to coordinately plan the effective capacity of the energy storage voltage regulation and the reactive compensation capacity of the reactive compensation device to obtain a multidimensional configuration table, wherein the multidimensional configuration table includes the energy storage voltage regulation gear, the number of reactive compensation groups and the reactive compensation gear capacity value;

[0040] Determine the switching order of reactive compensation devices based on the multidimensional configuration table, set the reactive compensation gear capacity configuration strategy according to the multiple ratio relationship, and construct the reactive compensation device operation strategy according to the switching order of reactive compensation devices and the reactive compensation gear capacity configuration strategy;

[0041] The power deficit of the reactive power compensation device operation strategy is calculated based on a deep neural network to obtain a power deficit value of the reactive power compensation circuit.

[0042] Preferably, judging whether the distribution network is in a power balance state based on the power shortage value of the reactive compensation circuit, and improving the recovery of the distribution network by executing a load shedding instruction when the distribution network is not in a power balance state, comprises:

[0043] Determine whether the power shortage value of the reactive power compensation circuit exceeds the sum of the effective capacity of the energy storage voltage regulation and the reactive power compensation capacity of the reactive power compensation device, and if so, determine that the distribution network is not in a power balance state;

[0044] When the distribution network is not in a power balance state, a load shedding control table is obtained by performing load classification through a deep neural network based on load characteristic data of a load management device in the distribution network, and a load shedding instruction is generated according to the load shedding control table, wherein the load characteristic data includes a load circuit voltage level and a user type;

[0045] The load shedding instruction is executed to improve the restoration capacity of the distribution network.

[0046] Preferably, the energy storage capacity is predicted based on the energy storage unit operation status data to obtain the energy storage capacity recovery rate, and the charging and discharging power of the energy storage unit is optimized according to the energy storage capacity recovery rate to obtain the energy storage charging power upper limit value and the energy storage discharging power upper limit value, including:

[0047] Based on the operation status data of the energy storage unit, the energy storage capacity is predicted through the long short-term memory network to obtain the energy storage capacity recovery rate;

[0048] The temperature correction coefficient corresponding to the energy storage capacity recovery rate is calculated based on the energy storage unit ambient temperature data by support vector regression, wherein the temperature correction coefficient is calculated using the following formula:

[0049]

[0050] in, represents the temperature correction factor, represents the temperature sensitivity coefficient, Indicates the actual ambient temperature of the energy storage unit. Indicates the reference ambient temperature of the energy storage unit;

[0051] An upper limit value of energy storage charging power and an upper limit value of energy storage discharging power of the energy storage unit are determined based on the temperature correction coefficient.

[0052] In a second aspect, an embodiment of the present invention provides a distribution network resilience enhancement system based on energy storage output coordinated scheduling, comprising:

[0053] A capacity reduction warning judgment module is used to obtain real-time temperature data of the energy storage unit in the distribution network, obtain the current energy storage capacity of the energy storage unit by mapping based on the real-time temperature data, and determine whether to trigger the energy storage capacity reduction warning according to the current energy storage capacity;

[0054] A capacity shortage warning judgment module is used to perform power prediction based on the real-time output data of the new energy distributed power source in the distribution network, and determine whether to trigger the energy storage capacity shortage warning according to the obtained power change prediction curve;

[0055] A dynamic planning module, for performing dynamic planning based on at least the current energy storage capacity and the power change prediction curve to obtain a short-term energy storage scheduling strategy under the conditions of triggering an energy storage capacity reduction warning and triggering an energy storage capacity shortage warning;

[0056] The energy storage voltage regulation effective capacity determination module is used to perform power flow calculation on the distribution network operation status data based on the short-term energy storage scheduling strategy to obtain the distribution network node voltage distribution result, identify the over-limit nodes according to the distribution network node voltage distribution result, and perform sensitivity analysis on the identified over-limit nodes to obtain the energy storage voltage regulation effective capacity, wherein the distribution network operation status data includes node injection power, branch power flow, node voltage data and line impedance data;

[0057] A power shortage calculation module is used to coordinately plan the effective capacity of the energy storage voltage regulation and the reactive compensation device in the distribution network to obtain a reactive compensation device operation strategy with the goal of minimizing the voltage deviation of the distribution network nodes, and to perform power shortage calculation on the reactive compensation device operation strategy to obtain a reactive compensation circuit power shortage value, wherein the reactive compensation device operation strategy includes a reactive compensation device switching sequence and a reactive compensation gear capacity configuration strategy;

[0058] The resilience enhancement module is used to determine whether the distribution network is in a power balance state based on the power shortage value of the reactive compensation circuit, and when the distribution network is not in a power balance state, enhance the resilience of the distribution network by executing a load shedding instruction.

[0059] Compared with the prior art, the method and system for improving the resilience of a distribution network based on coordinated dispatch of energy storage output in the embodiment of the present invention have the following beneficial effects: by acquiring the real-time temperature of the energy storage unit and combining it with the temperature-capacity correspondence curve, the dynamic evaluation capability of the energy storage capacity can be improved; when the energy storage capacity decreases and the risk of new energy fluctuations increases, dynamic programming can be used to optimize the coordinated dispatch strategy of energy storage charging and discharging and new energy output; power flow calculation is performed in combination with the distribution network operation status data, and sensitivity analysis is used to determine the effective capacity of energy storage voltage regulation, and reactive power regulation is performed in coordination with the reactive compensation device, which helps to improve the voltage quality and reactive power management capability of the distribution network; and the recovery capability of the distribution network in an extreme low temperature environment can be effectively improved by executing the load shedding instruction. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of a method for improving the resilience of a distribution network based on coordinated dispatch of energy storage output according to an embodiment of the present invention;

[0061] Figure 2 It is another flow chart of a method for improving the resilience of a distribution network based on coordinated dispatch of energy storage output according to an embodiment of the present invention;

[0062] Figure 3 It is a structural schematic diagram of a distribution network resilience enhancement system based on energy storage output coordinated scheduling according to an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0064] In the description of the present invention, it should be understood that the terms "first" and "second" etc. are used in the present invention to distinguish different objects rather than to describe a specific order.

[0065] like Figure 1 As shown, an embodiment of the present invention provides a method for improving the resilience of a distribution network based on coordinated dispatch of energy storage output, comprising the steps of:

[0066] S1. Acquire the real-time temperature data of the energy storage unit in the distribution network, map the current energy storage capacity of the energy storage unit based on the real-time temperature data, and determine whether to trigger an energy storage capacity reduction warning based on the current energy storage capacity;

[0067] Specifically, step S1 includes:

[0068] 1) Perform distributed temperature collection on energy storage units in the distribution network to obtain real-time temperature data;

[0069] Distributed temperature collection is performed on the energy storage unit. Multiple temperature sampling points are evenly distributed on the surface of the energy storage unit. Each temperature sampling point is equipped with a temperature sensor to form a temperature monitoring dot matrix to achieve full coverage monitoring of the surface temperature of the energy storage unit. At the same time, the collected real-time temperature data is stored in the data collection distributed database in the form of a temperature dot matrix data group. In this embodiment, the spacing between adjacent temperature sampling points is 5 cm, the sampling frequency of each temperature sensor is once per second, the temperature measurement range is between -40 degrees and 80 degrees, and the measurement accuracy reaches 0.1 degrees.

[0070] 2) Perform weighted processing on each temperature value in the temperature dot matrix data group based on the distance weight to obtain the standardized temperature value of the energy storage unit;

[0071] In the distance weight calculation, the weight coefficient of the temperature value of the corresponding temperature sampling point is determined according to the distance between the temperature sampling point and the center point of the energy storage unit. The closer the distance, the greater the weight coefficient. In this embodiment, the weight coefficient is between 0 and 1. When the distance is 0, the weight coefficient is 1, and when the distance is 25 cm, the weight coefficient is 0.2. By analogy, the weight coefficient of the temperature value of each temperature sampling point is obtained. Each temperature value is weighted to obtain the standardized temperature value of the energy storage unit.

[0072] 3) Map the standardized temperature value based on the temperature-capacity correspondence curve to obtain the current energy storage capacity of the energy storage unit;

[0073] The temperature-capacity correspondence curve is a fitting curve between temperature and energy storage capacity, which is obtained by fitting and analyzing the capacity characteristics of the energy storage unit under different temperature conditions, and realizes the accurate mapping of energy storage capacity and temperature change. In this embodiment, within the range of -20 degrees to 60 degrees, the energy storage capacity value of a temperature point is recorded every 5 degrees to form a temperature-capacity correspondence curve. The standardized temperature value is mapped to obtain the current energy storage capacity of the energy storage unit.

[0074] 4) Calculate the deviation of the current energy storage capacity based on the moving average to obtain the current energy storage capacity deviation data;

[0075] The current energy storage capacity is compared with the historical capacity data within a fixed time interval, and the current energy storage capacity deviation data is obtained by using a moving average calculation formula. In this embodiment, the moving average calculation adopts a 10-minute time window, that is, the fixed time interval is 10 minutes, and the capacity data in the time window is averaged, and the obtained average capacity is compared with the current energy storage capacity to obtain the current energy storage capacity deviation data.

[0076] It should be noted that after determining the current energy storage capacity deviation data, it is also determined whether the current energy storage capacity deviation data exceeds the energy storage capacity fluctuation threshold. If so, the capacity is marked abnormal and the current energy storage capacity deviation data is recorded for subsequent application. In this embodiment, the energy storage capacity fluctuation threshold is 15% of the nominal capacity.

[0077] 5) Calculate the temperature change rate based on the temperature dot matrix data group, and determine whether the temperature change rate exceeds the temperature drop threshold;

[0078] The temperature difference data of adjacent temperature sampling moments are extracted from the temperature dot matrix data group, and the temperature difference data is fitted by the support vector regressor to obtain the temperature change rate, and it is judged whether the temperature change rate exceeds the temperature drop threshold. The support vector regressor of this embodiment adopts the radial basis kernel function, and the training samples include the corresponding relationship data of temperature drop and capacity change, and the temperature drop threshold is 5 degrees per minute.

[0079] 6) If the temperature change rate exceeds the temperature drop threshold, it is determined whether the current energy storage capacity deviation data and the temperature change rate correspond to the same time period. If so, an energy storage capacity drop warning is triggered.

[0080] If the temperature change rate exceeds the temperature drop threshold, it is determined whether the current energy storage capacity deviation data and the temperature change rate correspond to the same time period. If so, it is marked that the capacity has an abnormal deviation and the abnormal capacity deviation is caused by a temperature drop, triggering an energy storage capacity decrease warning.

[0081] S2. Power forecasting is performed based on the real-time output data of the new energy distributed power sources in the distribution network, and judging whether to trigger an energy storage capacity shortage warning based on the obtained power change prediction curve;

[0082] Specifically, step S2 includes:

[0083] 1) Collect the real-time output data of the new energy distributed power source in the distribution network, and convert the real-time output data to obtain real-time power data;

[0084] The real-time output data of the new energy distributed power source in the distribution network is collected by power sensors. The unit of the real-time output data is kilowatt-hour. The real-time power data can be obtained by mathematical conversion of the real-time output data. The unit of the real-time power data is kilowatt. The objects of real-time output data collection in this embodiment include photovoltaic sub-arrays and wind turbines.

[0085] 2) Time synchronization of real-time power data based on the sampling period to obtain power time series data;

[0086] The real-time power data is synchronized based on the sampling period of the new energy distributed power source to obtain the power time series data. Considering that the new energy distributed power source in this embodiment includes a photovoltaic sub-array and a wind turbine group, the real-time power data is synchronized based on the sampling period of the photovoltaic sub-array and the wind turbine group to obtain the power time series data. Among them, considering that photovoltaic power generation is affected by changes in light intensity and the wind turbine group is affected by changes in wind speed, in order to ensure that the rapid change of power is captured, this embodiment sets the sampling period of photovoltaic power data to 5 seconds and the sampling period of wind turbine power data to 10 seconds.

[0087] 3) Power prediction is performed based on the power time series data through a recursive neural network to obtain a power change prediction curve;

[0088] The recursive neural network used in this embodiment is a long short-term memory network. The input layer uses a sliding window with a time window length of 30 minutes as the input sequence, the number of nodes in the hidden layer is 32, and the output layer obtains the power change prediction curve for the next two hours. The input data of the input layer includes power value, timestamp, light intensity and wind speed, and the power change prediction curve corresponds to the first fluctuation interval of power change.

[0089] 4) Calculate the energy storage capacity usage data of the preset time window of the energy storage unit based on the moving average to obtain the energy storage capacity change curve;

[0090] This embodiment collects the energy storage capacity usage data of the energy storage unit in a 60-second time window, records the voltage change from 400 volts to 350 volts and the charge and discharge current change from zero to 100 amperes during the charge and discharge process of the energy storage unit, and obtains the change trend of the energy storage capacity from the full capacity of 1000 kWh to 800 kWh through moving average calculation, that is, the energy storage capacity change curve. Among them, the energy storage capacity change curve corresponds to the second fluctuation range of the energy storage capacity change.

[0091] 5) Based on the first fluctuation range and the second fluctuation range, the fluctuation range difference between the power change prediction curve and the energy storage capacity change curve is calculated, and it is determined whether the fluctuation range difference exceeds the nominal capacity threshold of the energy storage unit. If so, an energy storage capacity insufficient warning is triggered.

[0092] In this embodiment, the nominal capacity threshold of the energy storage unit is 30% of the nominal capacity. The power change prediction curve shows that the first fluctuation range of the new energy distributed power source in the next two hours is 200 kW to 800 kW. The energy storage capacity change curve shows that the remaining available capacity of the energy storage unit is 300 kWh. Considering that the nominal capacity of the energy storage unit is 1000 kWh, the difference between the two exceeds 30% of the nominal capacity, that is, 300 kWh, triggering an early warning of insufficient energy storage capacity.

[0093] S3. Under the conditions that an energy storage capacity decrease warning is triggered and an energy storage capacity shortage warning is triggered, dynamic planning is performed based on at least the current energy storage capacity and the power change prediction curve to obtain a short-term energy storage scheduling strategy;

[0094] Specifically, step S3 includes:

[0095] 1) Obtain the load power data of the load management device in the distribution network and the power prediction data corresponding to the power change prediction curve;

[0096] The load power data of the load management device and the power prediction data corresponding to the power change prediction curve are obtained through the data collector.

[0097] 2) Build an operating status data set based on current energy storage capacity, load power data, and power forecast data;

[0098] Construct an operating status data set including current energy storage capacity, load power data and power forecast data.

[0099] 3) Perform dynamic programming based on the operating status data set to obtain a short-term energy storage scheduling strategy.

[0100] The operating status data set of this embodiment is the operating status data set of the 4-hour scheduling time period. Dynamic planning is performed based on the operating status data set, and the 4-hour scheduling time period is divided into 24 sub-periods at intervals of 10 minutes. The state transition data between adjacent sub-periods is obtained by recursive calculation, and a predictor including 12 input variables including 4 load power values, 4 energy storage capacity values ​​and 4 power prediction values ​​is established based on the random forest algorithm, and the power regulation direction and power regulation amplitude of each sub-period are output to form a power compensation sequence of the energy storage unit. The charging and discharging power adjustment instructions of the energy storage unit in each sub-period are extracted according to the power compensation sequence, that is, the short-term energy storage scheduling strategy. In other words, the short-term energy storage scheduling strategy includes the charging and discharging power adjustment instructions of the energy storage unit in each sub-period of the 4-hour scheduling time period. During the load peak period from 9:00 to 11:00, the energy storage unit adopts the discharge mode with a power setting value of 800 kilowatts; during the load valley period from 11:00 to 14:00, the energy storage unit adopts the charging mode with a power setting value of 600 kilowatts to achieve peak shaving and valley filling.

[0101] S4. Based on the short-term energy storage dispatching strategy, the power flow calculation is performed on the distribution network operation status data to obtain the distribution network node voltage distribution results, the over-limit nodes are identified according to the distribution network node voltage distribution results, and the sensitivity analysis is performed on the identified over-limit nodes to obtain the effective capacity of energy storage voltage regulation;

[0102] Specifically, step S4 includes:

[0103] 1) Based on the short-term energy storage scheduling strategy, the Newton-Raphson algorithm is used to iteratively calculate the power flow of the distribution network operation status data until the convergence condition is reached to obtain the voltage distribution results of the distribution network nodes;

[0104] The distribution network operation status data is obtained through the data collector. Specifically, the distribution network operation status data includes node injection power, branch power flow power, node voltage data and line impedance data. Based on the short-term energy storage scheduling strategy, the Newton-Raphson algorithm is used to iterate the power flow calculation of the distribution network operation status data until the convergence condition is reached to obtain the distribution network node voltage distribution result. Among them, the convergence condition of this embodiment is that the number of iterations reaches 10 times or the relative error of the node voltage between two adjacent iterations is less than 0.01.

[0105] 2) Determine whether the voltage of each node in the distribution network node voltage distribution result is within the distribution network voltage limit interval. If not, identify the node corresponding to the node voltage as an out-of-limit node;

[0106] In this embodiment, the voltage limit interval of the distribution network is 7% lower than the nominal voltage to 5% higher than the nominal voltage. When the node corresponding to the node voltage is identified as an over-limit node, each one thousandth of the node voltage exceeding the voltage limit interval of the distribution network is recorded as an over-limit unit.

[0107] 3) Perform energy storage power disturbance on each out-of-limit node, and calculate the sensitivity coefficient of the corresponding out-of-limit node based on the obtained node voltage change;

[0108] Energy storage power disturbance is injected into each out-of-limit node, and the sensitivity coefficient of the corresponding out-of-limit node is calculated by observing the node voltage change.

[0109] Specifically, the sensitivity coefficient is calculated using the following formula:

[0110]

[0111] in, represents the sensitivity coefficient, represents the node voltage change, Indicates the energy storage power disturbance. In this embodiment, the amplitude of the energy storage power disturbance is 1% of the rated power.

[0112] 4) The power required for voltage regulation of the energy storage unit corresponding to the over-limit node is calculated based on the sensitivity coefficient, and the power required for voltage regulation of the energy storage unit is represented as the effective capacity of energy storage voltage regulation.

[0113] The power required for voltage regulation of the energy storage unit corresponding to the over-limit node is calculated based on the sensitivity coefficient, and the energy storage charging and discharging capacity is judged by the charge state. In this embodiment, when the charge state is in the range of 20% to 80%, the rated power is maintained. When the charge state is lower than 20%, the discharge power is reduced to 30% of the rated power. When the charge state is higher than 80%, the charging power is reduced to 30% of the rated power.

[0114] It should be noted that after the power required for voltage regulation of the energy storage unit is represented as the effective capacity of energy storage voltage regulation, the over-limit nodes are sorted from high to low according to the number of over-limit units, and the power of the over-limit nodes is adjusted in sequence according to the sorting results.

[0115] S5. With the goal of minimizing the voltage deviation of the distribution network nodes, the effective capacity of the energy storage voltage regulation and the reactive compensation device in the distribution network are coordinated to obtain the reactive compensation device operation strategy, and the power shortage of the reactive compensation device operation strategy is calculated to obtain the power shortage value of the reactive compensation circuit;

[0116] Specifically, step S5 includes:

[0117] 1) With the goal of minimizing the voltage deviation of distribution network nodes, a genetic algorithm is used to coordinate the effective capacity of energy storage voltage regulation and the reactive compensation capacity of reactive compensation devices to obtain a multi-dimensional configuration table;

[0118] Through genetic algorithm, an optimizer with the minimum voltage deviation of distribution network nodes as the objective function is established, and the effective capacity of energy storage voltage regulation and reactive compensation capacity are coordinated and planned to generate a multidimensional configuration table including energy storage voltage regulation gear, number of reactive compensation groups and reactive compensation gear capacity value.

[0119] 2) Determine the switching order of reactive compensation devices based on the multidimensional configuration table, set the reactive compensation gear capacity configuration strategy according to the multiple ratio relationship, and construct the reactive compensation device operation strategy according to the switching order of reactive compensation devices and the reactive compensation gear capacity configuration strategy;

[0120] The switching order of the reactive compensation device is divided according to the multidimensional configuration table, and the reactive compensation gear capacity configuration strategy is set according to the multiple ratio relationship. In this embodiment, 6 reactive compensation gears are divided according to the reactive compensation gear capacity from small to large, and the switching rule is set to be less than 5% of the reactive compensation capacity between adjacent reactive compensation gears. The capacitor group and the reactor group are controlled by the principle of nearby switching, and a reactive compensation device operation plan including the switching order of the reactive compensation device and the reactive compensation gear capacity configuration strategy is generated.

[0121] 3) Based on the deep neural network, the power shortage of the reactive compensation device operation strategy is calculated to obtain the power shortage value of the reactive compensation circuit.

[0122] The real-time power data of each node in the reactive compensation circuit is collected, and the power shortage of the reactive compensation device operation strategy is calculated based on the real-time power data through a deep neural network to obtain the power shortage value of the reactive compensation circuit.

[0123] S6. Determine whether the distribution network is in a power balance state based on the power shortage value of the reactive power compensation circuit, and when the distribution network is not in a power balance state, improve the recovery capacity of the distribution network by executing a load shedding instruction.

[0124] Specifically, step S6 includes:

[0125] 1) Determine whether the power shortage value of the reactive power compensation circuit exceeds the sum of the effective capacity of the energy storage voltage regulation and the reactive power compensation capacity of the reactive power compensation device. If so, it is determined that the distribution network is not in a power balance state;

[0126] 2) When the distribution network is not in a power balance state, a load shedding control table is obtained by performing load classification based on the load characteristic data of the load management device in the distribution network through a deep neural network, and a load shedding instruction is generated according to the load shedding control table;

[0127] Based on the load characteristic data, the load is graded through a deep neural network to obtain a load priority identifier, and the load shedding control table is obtained according to the reactive compensation circuit power shortage value and the load priority identifier, thereby generating a load shedding instruction. Among them, the load characteristic data includes the load circuit voltage level and the user type. In this embodiment, the power supply load is divided into four levels, the first level is the important load, the second level is the industrial production load, the third level is the commercial load, and the fourth level is the ordinary civil load, with the priority increasing in sequence.

[0128] 3) Improve the resilience of the distribution network by executing load shedding instructions.

[0129] When the distribution network is not in a power balance state, the load shedding instruction is executed to improve the resilience of the distribution network. Specifically, the shedding starts from the load with the highest priority. In this embodiment, the shedding starts from the fourth-level ordinary civilian load, and the load capacity of each shedding does not exceed 50 kilowatts, and the shedding interval is not less than 1 second, thereby ensuring the stable improvement of the resilience of the distribution network.

[0130] In order to further improve the resilience of the distribution network, after step S6, as Figure 2 As shown, the steps include:

[0131] S7. Predict the energy storage capacity based on the operating status data of the energy storage unit to obtain the energy storage capacity recovery rate, and optimize the charging and discharging power of the energy storage unit according to the energy storage capacity recovery rate to obtain the energy storage charging power upper limit value and the energy storage discharging power upper limit value.

[0132] Specifically, step S7 includes:

[0133] 1) Based on the operating status data of the energy storage unit, the energy storage capacity is predicted through the long short-term memory network to obtain the energy storage capacity recovery rate;

[0134] The operating status data of the energy storage unit includes the shell temperature data of the energy storage unit, the ambient temperature data of the energy storage unit, and the voltage and current data of the energy storage unit. Based on the operating status data of the energy storage unit, the energy storage capacity recovery rate is obtained by sliding the long short-term memory network forward based on the time window. This embodiment uses a long short-term memory network to construct an energy storage capacity predictor with 64 hidden layer nodes. Based on a 15-minute time window sliding forward, the capacity change of the energy storage unit during the load power transmission process is predicted to generate the energy storage capacity recovery rate.

[0135] 2) Calculate the temperature correction coefficient corresponding to the energy storage capacity recovery rate through support vector regression based on the ambient temperature data of the energy storage unit;

[0136] Specifically, the temperature correction coefficient is calculated using the following formula:

[0137]

[0138] in, represents the temperature correction factor, represents the temperature sensitivity coefficient, Indicates the actual ambient temperature of the energy storage unit. Indicates the reference ambient temperature of the energy storage unit. In this embodiment, a support vector regressor using a radial basis kernel function is used to calculate the temperature correction coefficient corresponding to the energy storage capacity recovery rate.

[0139] 3) Determine the upper limit value of the energy storage charging power and the upper limit value of the energy storage discharging power of the energy storage unit based on the temperature correction coefficient.

[0140] The energy storage unit capacity recovery rate is corrected based on the temperature correction coefficient to obtain the energy storage unit capacity recovery correction rate. The upper limit value of energy storage charging power and the upper limit value of energy storage discharging power change with the energy storage power supply capacity recovery correction rate. In this embodiment, when the energy storage unit capacity recovery correction rate is higher than 0.4% per minute, the upper limit value of energy storage charging power maintains the rated power of 1000 kilowatts; when the energy storage unit capacity recovery correction rate is reduced to 0.2% per minute, the upper limit value of energy storage charging power is reduced to 500 kilowatts; when the energy storage unit capacity recovery correction rate is lower than 0.1% per minute, the upper limit value of energy storage charging power is reduced to 300 kilowatts. Further, when the energy storage unit capacity recovery correction rate is higher than 0.4% per minute, the upper limit value of energy storage discharge power is maintained at 800 kilowatts; when the energy storage unit capacity recovery correction rate is reduced to 0.2% per minute, the upper limit value of energy storage discharge power is reduced to 400 kilowatts; when the energy storage unit capacity recovery correction rate is lower than 0.1% per minute, the upper limit value of energy storage discharge power is reduced to 200 kilowatts.

[0141] The embodiment of the present invention provides a method for improving the resilience of a distribution network based on coordinated dispatch of energy storage output. By acquiring the real-time temperature of an energy storage unit and combining it with a temperature-capacity correspondence curve, the dynamic evaluation capability of the energy storage capacity can be improved. When the energy storage capacity decreases and the risk of new energy fluctuations increases, dynamic programming can be used to optimize the coordinated dispatch strategy of energy storage charging and discharging and new energy output. The power flow calculation is performed in combination with the distribution network operation status data, and sensitivity analysis is used to determine the effective capacity of energy storage voltage regulation. The reactive power is adjusted in coordination with a reactive compensation device, which helps to improve the voltage quality and reactive power management capability of the distribution network. The recovery capability of the distribution network in an extreme low temperature environment can be effectively improved by executing a load shedding instruction.

[0142] Based on the above-mentioned method for improving the resilience of distribution network based on coordinated dispatch of energy storage output, Figure 3 As shown, an embodiment of the present invention provides a distribution network resilience enhancement system based on energy storage output coordinated scheduling, including:

[0143] The capacity reduction warning judgment module 1 is used to obtain the real-time temperature data of the energy storage unit in the distribution network, obtain the current energy storage capacity of the energy storage unit based on the real-time temperature data, and judge whether to trigger the energy storage capacity reduction warning according to the current energy storage capacity;

[0144] The capacity shortage warning judgment module 2 is used to predict the power based on the real-time output data of the new energy distributed power source in the distribution network, and judge whether to trigger the energy storage capacity shortage warning according to the obtained power change prediction curve;

[0145] Dynamic planning module 3, used to perform dynamic planning based on at least the current energy storage capacity and power change prediction curve to obtain a short-term energy storage scheduling strategy under the conditions of triggering an energy storage capacity reduction warning and triggering an energy storage capacity shortage warning;

[0146] The energy storage voltage regulation effective capacity determination module 4 is used to perform power flow calculation on the distribution network operation status data based on the short-term energy storage scheduling strategy to obtain the distribution network node voltage distribution results, identify the over-limit nodes according to the distribution network node voltage distribution results, and perform sensitivity analysis on the identified over-limit nodes to obtain the energy storage voltage regulation effective capacity, wherein the distribution network operation status data includes node injection power, branch power flow, node voltage data and line impedance data;

[0147] The power shortage calculation module 5 is used to coordinately plan the effective capacity of energy storage voltage regulation and the reactive compensation device in the distribution network to obtain the reactive compensation device operation strategy with the goal of minimizing the voltage deviation of the distribution network node, and to calculate the power shortage of the reactive compensation device operation strategy to obtain the power shortage value of the reactive compensation circuit, wherein the reactive compensation device operation strategy includes the switching order of the reactive compensation device and the reactive compensation gear capacity configuration strategy;

[0148] The resilience enhancement module 6 is used to determine whether the distribution network is in a power balance state based on the power shortage value of the reactive compensation circuit, and when the distribution network is not in a power balance state, enhance the resilience of the distribution network by executing a load shedding instruction.

[0149] It should be noted that each unit in the above-mentioned distribution network resilience enhancement system based on coordinated dispatch of energy storage output can be fully or partially implemented by software, hardware and a combination thereof. The above-mentioned units can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. For the specific definition of a distribution network resilience enhancement system based on coordinated dispatch of energy storage output, please refer to the above definition of a distribution network resilience enhancement method based on coordinated dispatch of energy storage output. The two have the same functions and effects, which will not be repeated here.

[0150] In summary, the embodiment of the present invention is a method and system for improving the resilience of a distribution network based on coordinated scheduling of energy storage output. By acquiring the real-time temperature of the energy storage unit and combining it with the temperature-capacity correspondence curve, the dynamic evaluation capability of the energy storage capacity can be improved; when the energy storage capacity decreases and the risk of new energy fluctuations increases, dynamic programming can be used to optimize the coordinated scheduling strategy of energy storage charging and discharging and new energy output; power flow calculation is performed in combination with the distribution network operation status data, and sensitivity analysis is used to determine the effective capacity of energy storage voltage regulation, and reactive power regulation is performed in coordination with the reactive compensation device, which helps to improve the voltage quality and reactive power management capability of the distribution network; by executing the load shedding instruction, the resilience of the distribution network in an extreme low temperature environment can be effectively improved.

[0151] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0152] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. A method for improving the resilience of a distribution network based on coordinated dispatch of energy storage output, characterized in that: include: Acquire real-time temperature data of the energy storage unit in the distribution network, obtain the current energy storage capacity of the energy storage unit by mapping based on the real-time temperature data, and determine whether to trigger an energy storage capacity reduction warning according to the current energy storage capacity; Power prediction is performed based on the real-time output data of the new energy distributed power source in the distribution network, and judging whether to trigger an energy storage capacity shortage warning according to the obtained power change prediction curve; Under the condition that an energy storage capacity decrease warning is triggered and an energy storage capacity insufficient warning is triggered, dynamic planning is performed based at least on the current energy storage capacity and the power change prediction curve to obtain a short-term energy storage scheduling strategy; Based on the short-term energy storage scheduling strategy, the distribution network operation status data is subjected to power flow calculation to obtain the distribution network node voltage distribution result, the over-limit nodes are identified according to the distribution network node voltage distribution result, and the identified over-limit nodes are subjected to sensitivity analysis to obtain the effective capacity of energy storage voltage regulation, wherein the distribution network operation status data includes node injection power, branch power flow, node voltage data and line impedance data; With the goal of minimizing the voltage deviation of the distribution network nodes, the effective capacity of the energy storage voltage regulation and the reactive compensation device in the distribution network are collaboratively planned to obtain the reactive compensation device operation strategy, and the power shortage of the reactive compensation device operation strategy is calculated to obtain the power shortage value of the reactive compensation circuit, wherein the reactive compensation device operation strategy includes the switching order of the reactive compensation device and the reactive compensation gear capacity configuration strategy; Whether the distribution network is in a power balance state is determined based on the power deficit value of the reactive compensation circuit, and when the distribution network is not in a power balance state, the restoration capacity of the distribution network is improved by executing a load shedding instruction.

2. The method for improving the resilience of a distribution network according to claim 1, characterized in that: After judging whether the distribution network is in a power balance state based on the power shortage value of the reactive compensation circuit, and improving the restoration capacity of the distribution network by executing a load shedding instruction when the distribution network is not in a power balance state, the method further includes: The energy storage capacity is predicted based on the operating status data of the energy storage unit to obtain the energy storage capacity recovery rate, and the charging and discharging power of the energy storage unit is optimized according to the energy storage capacity recovery rate to obtain the energy storage charging power upper limit value and the energy storage discharging power upper limit value, wherein the energy storage unit operating status data includes the energy storage unit shell temperature data, the energy storage unit ambient temperature data and the energy storage unit voltage and current data.

3. The method for improving the resilience of a distribution network according to claim 1, characterized in that: The acquiring real-time temperature data of the energy storage unit in the distribution network, mapping based on the real-time temperature data to obtain the current energy storage capacity of the energy storage unit, and judging whether to trigger the energy storage capacity reduction warning according to the current energy storage capacity, includes: Perform distributed temperature collection on energy storage units in the distribution network to obtain real-time temperature data, wherein the real-time temperature data is a temperature dot matrix data group; Performing weighted processing on each temperature value in the temperature dot matrix data group based on a distance weight to obtain a standardized temperature value of the energy storage unit; Mapping the standardized temperature value based on a temperature-capacity correspondence curve to obtain a current energy storage capacity of the energy storage unit, wherein the temperature-capacity correspondence curve is a fitting curve between temperature and energy storage capacity; Performing deviation calculation on the current energy storage capacity based on moving average to obtain current energy storage capacity deviation data; Calculating a temperature change rate based on the temperature dot matrix data group, and determining whether the temperature change rate exceeds a temperature drop threshold; If the temperature change rate exceeds the temperature drop threshold, it is determined whether the current energy storage capacity deviation data and the temperature change rate correspond to the same time period. If so, an energy storage capacity drop warning is triggered.

4. The method for improving the resilience of a distribution network according to claim 1, characterized in that: The power prediction is performed based on the real-time output data of the new energy distributed power source in the distribution network, and judging whether to trigger the energy storage capacity insufficient warning according to the obtained power change prediction curve, including: Collecting real-time output data of the new energy distributed power source in the distribution network, and converting the real-time output data to obtain real-time power data; Performing time synchronization on the real-time power data based on a sampling period to obtain power time series data; Based on the power time series data, power prediction is performed through a recursive neural network to obtain a power change prediction curve, wherein the power change prediction curve corresponds to a first fluctuation interval of power change; Calculating the energy storage capacity usage data of the preset time window of the energy storage unit based on moving average to obtain an energy storage capacity change curve, wherein the energy storage capacity change curve corresponds to a second fluctuation range of the energy storage capacity change; The fluctuation interval difference between the power change prediction curve and the energy storage capacity change curve is calculated based on the first fluctuation interval and the second fluctuation interval, and it is determined whether the fluctuation interval difference exceeds the nominal capacity threshold of the energy storage unit. If so, an energy storage capacity insufficient warning is triggered.

5. The method for improving the resilience of a distribution network according to claim 1, characterized in that: Under the condition that the energy storage capacity decrease warning is triggered and the energy storage capacity insufficient warning is triggered, dynamic planning is performed based on at least the current energy storage capacity and the power change prediction curve to obtain a short-term energy storage scheduling strategy, including: Obtaining load power data of a load management device in the distribution network and power prediction data corresponding to the power change prediction curve; Constructing an operation status data set based on the current energy storage capacity, load power data and power prediction data; Dynamic programming is performed based on the operating status data set to obtain a short-term energy storage scheduling strategy, wherein the short-term energy storage scheduling strategy includes a charging and discharging power adjustment instruction of the energy storage unit in each sub-period.

6. The method for improving the resilience of a distribution network according to claim 1, characterized in that: The method comprises: performing power flow calculation on the distribution network operation status data based on the short-term energy storage scheduling strategy to obtain the distribution network node voltage distribution result, identifying the over-limit nodes according to the distribution network node voltage distribution result, and performing sensitivity analysis on the identified over-limit nodes to obtain the effective capacity of energy storage voltage regulation, including: Based on the short-term energy storage scheduling strategy, the Newton-Raphson algorithm is used to iteratively calculate the power flow of the distribution network operation status data until the convergence condition is reached to obtain the voltage distribution result of the distribution network node; Determine whether each node voltage in the distribution network node voltage distribution result is within the distribution network voltage limit interval, and if not, identify the node corresponding to the node voltage as an out-of-limit node; Perform energy storage power disturbance on each of the above-mentioned crossing nodes, and calculate the sensitivity coefficient corresponding to the above-mentioned crossing node based on the obtained node voltage change, wherein the sensitivity coefficient is calculated using the following formula: in, represents the sensitivity coefficient, represents the node voltage change, Represents the energy storage power disturbance; The power required for voltage regulation of the energy storage unit corresponding to the out-of-limit node is calculated based on the sensitivity coefficient, and the power required for voltage regulation of the energy storage unit is characterized as the effective capacity of energy storage voltage regulation.

7. The method for improving the resilience of a distribution network according to claim 1, characterized in that: The method aims to minimize the voltage deviation of the distribution network nodes, coordinately plan the effective capacity of the energy storage voltage regulation and the reactive compensation device in the distribution network to obtain the reactive compensation device operation strategy, and calculate the power shortage of the reactive compensation device operation strategy to obtain the reactive compensation circuit power shortage value, including: With the goal of minimizing the voltage deviation of the distribution network nodes, a genetic algorithm is used to coordinately plan the effective capacity of the energy storage voltage regulation and the reactive compensation capacity of the reactive compensation device to obtain a multidimensional configuration table, wherein the multidimensional configuration table includes the energy storage voltage regulation gear, the number of reactive compensation groups and the reactive compensation gear capacity value; Determine the switching order of reactive compensation devices based on the multidimensional configuration table, set the reactive compensation gear capacity configuration strategy according to the multiple ratio relationship, and construct the reactive compensation device operation strategy according to the switching order of reactive compensation devices and the reactive compensation gear capacity configuration strategy; The power deficit of the reactive power compensation device operation strategy is calculated based on a deep neural network to obtain a power deficit value of the reactive power compensation circuit.

8. The method for improving the resilience of a distribution network according to claim 1, characterized in that: The method of judging whether the distribution network is in a power balance state based on the power shortage value of the reactive compensation circuit, and improving the recovery of the distribution network by executing a load shedding instruction when the distribution network is not in a power balance state, comprises: Determine whether the power shortage value of the reactive power compensation circuit exceeds the sum of the effective capacity of the energy storage voltage regulation and the reactive power compensation capacity of the reactive power compensation device, and if so, determine that the distribution network is not in a power balance state; When the distribution network is not in a power balance state, a load shedding control table is obtained by performing load classification through a deep neural network based on load characteristic data of a load management device in the distribution network, and a load shedding instruction is generated according to the load shedding control table, wherein the load characteristic data includes a load circuit voltage level and a user type; The load shedding instruction is executed to improve the restoration capacity of the distribution network.

9. The method for improving the resilience of a distribution network according to claim 2, characterized in that: The energy storage capacity is predicted based on the energy storage unit operation status data to obtain the energy storage capacity recovery rate, and the charging and discharging power of the energy storage unit is optimized according to the energy storage capacity recovery rate to obtain the energy storage charging power upper limit value and the energy storage discharging power upper limit value, including: Based on the operation status data of the energy storage unit, the energy storage capacity is predicted through the long short-term memory network to obtain the energy storage capacity recovery rate; The temperature correction coefficient corresponding to the energy storage capacity recovery rate is calculated based on the energy storage unit ambient temperature data by support vector regression, wherein the temperature correction coefficient is calculated using the following formula: in, represents the temperature correction factor, represents the temperature sensitivity coefficient, Indicates the actual ambient temperature of the energy storage unit. Indicates the reference ambient temperature of the energy storage unit; An upper limit value of energy storage charging power and an upper limit value of energy storage discharging power of the energy storage unit are determined based on the temperature correction coefficient.

10. A distribution network resilience enhancement system based on energy storage output coordinated dispatch, characterized in that: include: A capacity reduction warning judgment module is used to obtain real-time temperature data of the energy storage unit in the distribution network, obtain the current energy storage capacity of the energy storage unit by mapping based on the real-time temperature data, and determine whether to trigger the energy storage capacity reduction warning according to the current energy storage capacity; A capacity shortage warning judgment module is used to perform power prediction based on the real-time output data of the new energy distributed power source in the distribution network, and determine whether to trigger the energy storage capacity shortage warning according to the obtained power change prediction curve; A dynamic planning module, for performing dynamic planning based on at least the current energy storage capacity and the power change prediction curve to obtain a short-term energy storage scheduling strategy under the conditions of triggering an energy storage capacity reduction warning and triggering an energy storage capacity shortage warning; The energy storage voltage regulation effective capacity determination module is used to perform power flow calculation on the distribution network operation status data based on the short-term energy storage scheduling strategy to obtain the distribution network node voltage distribution result, identify the over-limit nodes according to the distribution network node voltage distribution result, and perform sensitivity analysis on the identified over-limit nodes to obtain the energy storage voltage regulation effective capacity, wherein the distribution network operation status data includes node injection power, branch power flow, node voltage data and line impedance data; A power shortage calculation module is used to coordinately plan the effective capacity of the energy storage voltage regulation and the reactive compensation device in the distribution network to obtain a reactive compensation device operation strategy with the goal of minimizing the voltage deviation of the distribution network nodes, and to perform power shortage calculation on the reactive compensation device operation strategy to obtain a reactive compensation circuit power shortage value, wherein the reactive compensation device operation strategy includes a reactive compensation device switching sequence and a reactive compensation gear capacity configuration strategy; The resilience enhancement module is used to determine whether the distribution network is in a power balance state based on the power shortage value of the reactive compensation circuit, and when the distribution network is not in a power balance state, enhance the resilience of the distribution network by executing a load shedding instruction.

Images