Island micro-grid composite energy storage optimal configuration method and device

Abstract

The invention provides an island micro-grid composite energy storage optimal configuration method and device, and the method comprises the steps: building an island micro-grid simulation model containing multiple types of impact loads based on the actual operation data of an island micro-grid containing multiple types of impact loads, and carrying out the simulation analysis, and obtaining a simulation result; constructing an island micro-grid composite energy storage optimal configuration model containing multiple types of impact loads; based on the simulation result, solving the island micro-grid composite energy storage optimal configuration model to obtain a target configuration result; and carrying out effect evaluation on the target configuration result to obtain an evaluation result, and carrying out island microgrid composite energy storage optimization configuration based on the evaluation result. According to the method, the influence of the impact load on the operation of the micro-grid is effectively considered, the reliability of power supply of the island micro-grid containing multiple types of impact loads can be effectively improved, and a technical basis and a practical method are provided for the operation and control of the island micro-grid containing multiple types of impact loads; implementation is easy, and arrangement is convenient.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to an isolated island microgrid composite energy storage optimization configuration method and device. Background Art

[0002] Energy storage devices are an indispensable part of the safe and stable operation of isolated island microgrids. They can effectively smooth out the fluctuations of impact loads and reduce the impact of impact loads on microgrids.

[0003] In recent years, researchers have proposed a number of optimization configuration methods for microgrid energy storage capacity. However, existing research ignores the impact of multiple types of impact loads on the life of energy storage media. When energy storage devices are impacted by instantaneous impact currents, their capacity decay rate and life will be accelerated, which has certain limitations in application effect. Therefore, an effective solution is urgently needed to solve the above problems. Summary of the invention

[0004] The present invention provides an isolated microgrid composite energy storage optimization configuration method and device, which are used to solve the defect of low optimization configuration effect of microgrid energy storage capacity in the prior art.

[0005] The present invention provides an island microgrid composite energy storage optimization configuration method, comprising the following steps: Based on the actual operation data of the isolated microgrid with multiple types of impact loads, a simulation model of the isolated microgrid with multiple types of impact loads was built and simulation analysis was performed to obtain simulation results. Construct a composite energy storage optimization configuration model for isolated microgrids with multiple types of impact loads; Based on the simulation results, the optimal configuration model of the isolated microgrid composite energy storage is solved and the target configuration result is obtained; The target configuration results are evaluated to obtain the evaluation results, and the island microgrid composite energy storage optimization configuration is performed based on the evaluation results.

[0006] According to an isolated microgrid composite energy storage optimization configuration method provided by the present invention, an isolated microgrid composite energy storage optimization configuration model containing multiple types of impact loads is constructed, including: Based on the data types contained in the isolated microgrid with multiple types of impact loads, the objective function and constraint conditions are constructed, and the objective function and constraint conditions constitute the composite energy storage optimization configuration model of the isolated microgrid with multiple types of impact loads; The objective functions include the minimum node voltage deviation function, the minimum frequency offset standard deviation function and the minimum power fluctuation penalty function; The constraints include power balance constraint, unit power constraint, ramp constraint, energy storage constraint, steady-state frequency deviation constraint and maximum frequency change rate constraint.

[0007] According to an island microgrid composite energy storage optimization configuration method provided by the present invention, a node voltage deviation minimum function is constructed based on a voltage reference value of each node in the island microgrid, an upper limit of a voltage amplitude, a lower limit of a voltage amplitude, and an actual value of a node voltage; The frequency offset standard deviation minimum function is constructed based on the actual frequency value and the reference frequency value at each moment; The power fluctuation penalty minimum function is constructed based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at the set time, as well as the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at the moment before the set time. The set time is an arbitrary time.

[0008] According to an island microgrid composite energy storage optimization configuration method provided by the present invention, the power balance constraint is constructed based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a set time, as well as the charging power and discharging power of the composite energy storage; The power constraints of the units are constructed based on the active power of photovoltaic power generation, wind power generation and diesel engine at the set time, as well as the maximum power generation of photovoltaic power generation, the maximum power generation of wind turbine and the maximum power generation of diesel generator; The climbing constraint is constructed based on the climbing rate, the diesel engine active power at the set time, and the diesel engine active power at the moment before the set time; The energy storage constraint is constructed based on setting the charging power and discharging power of the energy storage device at the set time, and setting the maximum charging power, maximum discharging power, minimum value of the energy storage device capacity and maximum value of the energy storage device capacity of the energy storage device; The steady-state frequency deviation constraint is constructed based on the steady-state frequency deviation, frequency modulation dead zone and steady-state frequency deviation limit; The maximum frequency change rate constraint is built based on the maximum frequency change rate and the frequency change rate limit.

[0009] According to an island microgrid composite energy storage optimization configuration method provided by the present invention, based on the actual operation data of the island microgrid containing multiple types of impact loads, a simulation model of the island microgrid containing multiple types of impact loads is built, including: Obtain actual operating data of isolated microgrids with multiple types of impact loads; Based on the actual operation data of the isolated microgrid with multi-type impact loads, a multi-type impact load model based on digital-analog hybrid drive is constructed; A multi-type impact load model is adopted to build an island microgrid simulation model containing multi-type impact loads.

[0010] According to an island microgrid composite energy storage optimization configuration method provided by the present invention, based on the actual operation data of the island microgrid containing multiple types of impact loads, a multi-type impact load model based on digital-analog hybrid drive is constructed, including: From the actual operation data of the isolated microgrid containing multiple types of impact loads, the first time series data when the isolated microgrid containing multiple types of impact loads has a short circuit fault in different scenarios, and the second time series data when the operating point changes due to the change of the operation mode of the isolated microgrid in different scenarios are collected; Obtaining the instantaneous value of voltage, instantaneous value of current, active power and reactive power at the point where the impact load is connected to the grid from the first time series data and the second time series data; Select the instantaneous value of voltage, active power and reactive power as input, select the instantaneous value of current as label, and construct the data set; A deep learning method combining recurrent gate units and attention mechanism is used to construct an impact load equivalent model; Based on the data set, the shock load equivalent model is trained to obtain multiple types of shock load models.

[0011] According to an island microgrid composite energy storage optimization configuration method provided by the present invention, the target configuration result is evaluated to obtain an evaluation result, including: Construct composite energy storage optimization configuration effect evaluation indicators, which include frequency qualification rate, voltage qualification rate, load loss rate, node voltage deviation, frequency offset standard deviation and power fluctuation; A Monte Carlo algorithm is used to generate at least one operation scenario corresponding to an island microgrid containing multiple types of impact loads; An island microgrid simulation model with multiple types of impact loads is used to simulate the operation scenarios and generate simulation results for each operation scenario; According to the simulation results of each operation scenario, the composite energy storage optimization configuration effect evaluation index of each operation scenario is calculated respectively to obtain the index value corresponding to each operation scenario; According to the indicator values ​​corresponding to each operating scenario, the entropy weight-better solution distance method is used to evaluate the effect of the target configuration results.

[0012] According to an island microgrid composite energy storage optimization configuration method provided by the present invention, the frequency qualification rate is determined based on the actual operating inertia of the system and the lower limit of the inertia safety domain; The voltage qualification rate is determined based on the number of set nodes and the total number of nodes in the isolated island microgrid, so the set node is the node whose actual value of the node voltage is within the set range, and the set range is determined based on the voltage amplitude upper limit and voltage amplitude lower limit of the node; The load loss rate is determined based on the load loss amount and discharge power of the energy storage system at each moment; The node voltage deviation is determined based on the voltage reference value of each node in the island microgrid, the upper limit of the voltage amplitude, the lower limit of the voltage amplitude and the actual value of the node voltage; The frequency offset standard deviation is determined based on the actual frequency value and the reference frequency value at each moment; The power fluctuation is determined based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a set moment, and the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a moment before the set moment.

[0013] According to an island microgrid composite energy storage optimization configuration method provided by the present invention, according to the indicator values ​​corresponding to each operation scenario, the entropy weight-better solution distance method is used to evaluate the effect of the target configuration result, including: Construct the initialization decision matrix, very large indicators and very small indicators; The entropy weight method is used to calculate the weight of the indicator value corresponding to each operating scenario; The superior and inferior solution distance method is used to evaluate the effect based on the weight of each indicator value.

[0014] According to an island microgrid composite energy storage optimization configuration method provided by the present invention, the superior and inferior solution distance method is used to evaluate the effect based on the weight of each indicator value, including: Construct a standardized matrix; The weights based on the values ​​of each indicator are brought into the standardized matrix, and the good-bad solution distance method is used to obtain the positive ideal solution and negative ideal solution corresponding to each operating scenario. For each operation scenario, based on the positive ideal solution and the negative ideal solution corresponding to the operation scenario, the positive ideal point distance and the negative ideal point distance of the operation scenario are calculated, and based on the positive ideal point distance and the negative ideal point distance of the operation scenario, the relative fit of the operation scenario is calculated; The effect is evaluated based on the relative fit of each operating scenario.

[0015] The present invention also provides an island microgrid composite energy storage optimization configuration device, comprising the following modules: The simulation module is configured to build a simulation model of an isolated microgrid containing multiple types of impact loads and perform simulation analysis based on actual operation data of the isolated microgrid containing multiple types of impact loads to obtain simulation results; A building module is configured to build an island microgrid composite energy storage optimization configuration model containing multiple types of impact loads; A solution module is configured to solve the island microgrid composite energy storage optimization configuration model based on the simulation results to obtain a target configuration result; The evaluation module is configured to evaluate the effect of the target configuration result, obtain the evaluation result, and perform the optimal configuration of the isolated island microgrid composite energy storage based on the evaluation result.

[0016] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, any of the above-mentioned methods for optimizing the configuration of composite energy storage in an isolated microgrid is implemented.

[0017] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for optimizing the configuration of composite energy storage in an isolated microgrid is implemented as described above.

[0018] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for optimizing the configuration of composite energy storage in an isolated microgrid.

[0019] The method and device for optimizing the configuration of composite energy storage for an isolated microgrid provided by the present invention builds a simulation model of an isolated microgrid containing multiple types of impact loads based on the actual operation data of the isolated microgrid containing multiple types of impact loads and performs simulation analysis to obtain simulation results; constructs an optimized configuration model of composite energy storage for an isolated microgrid containing multiple types of impact loads; solves the optimized configuration model of composite energy storage for an isolated microgrid based on the simulation results to obtain target configuration results; performs an effect evaluation on the target configuration results to obtain evaluation results, and optimizes the configuration of composite energy storage for an isolated microgrid based on the evaluation results. By effectively considering the impact of impact loads on the operation of the microgrid in the optimized configuration model of composite energy storage for an isolated microgrid containing multiple types of impact loads, the reliability of power supply for an isolated microgrid containing multiple types of impact loads can be effectively improved, and a technical basis and a practical method can be provided for the operation and control of an isolated microgrid containing multiple types of impact loads; and the optimized configuration method for composite energy storage for an isolated microgrid provided by the present invention is easy to implement and convenient to arrange. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is one of the flow diagrams of the isolated island microgrid composite energy storage optimization configuration method provided by the present invention.

[0022] Figure 2 This is the second flow chart of the isolated island microgrid composite energy storage optimization configuration method provided by the present invention.

[0023] Figure 3It is a structural schematic diagram of the isolated island microgrid composite energy storage optimization configuration device provided by the present invention.

[0024] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Combine the following Figure 1-Figure 4 Describe the island microgrid composite energy storage optimization configuration method and device of the present invention. In order to facilitate a clearer understanding of the technical solutions of the embodiments of the present application, some technical contents related to the embodiments of the present application are first introduced.

[0027] MATLAB is a mathematical software used in data analysis, wireless communications, deep learning, image processing and computer vision, signal processing, quantitative finance and risk management, robotics, control systems and other fields.

[0028] Simulink is a visual simulation tool in MATLAB. Simulink is a block diagram environment for multi-domain simulation and model-based design. It supports system design, simulation, automatic code generation, and continuous testing and verification of embedded systems. Simulink provides a graphical editor, a customizable block library, and a solver to model and simulate dynamic systems.

[0029] Island microgrids usually have the characteristics of small inertia, insufficient damping and weak anti-interference ability. The impact load is highly periodic and non-periodic, and its value changes greatly in an instant, which will produce large harmonic current and power fluctuations. The impact on the power grid is mainly to cause frequency drop and node voltage fluctuations. In severe cases, it will cause system frequency oscillation and voltage flicker, and then the power supply reliability will decrease, destroying the stability of the microgrid. In the microgrid, the impact is usually a certain degree of active and reactive impact caused by the access of motors or capacitive loads. In addition, due to the nonlinear characteristics of the impact load, when there are multiple impact loads in the microgrid, the impact range of the impact load on the island microgrid is more difficult to estimate intuitively. It is necessary to minimize the negative impact of the impact load on the microgrid. As a buffer device, the energy storage system can reduce the impact caused by the grid connection of distributed energy and the stable operation of the island microgrid caused by the impact load. Therefore, in order to reduce the impact of multiple types of impact loads on the island microgrid, it is of great significance to optimize the selection and configuration of energy storage.

[0030] Energy storage devices are an indispensable part of the safe and stable operation of isolated microgrids. They can effectively smooth out the fluctuations of impact loads and reduce the impact of impact loads on microgrids. In recent years, researchers have proposed many methods for optimizing the configuration of microgrid energy storage capacity. However, these methods still have some problems. Most technologies do not consider the impact of impact loads on isolated microgrid equipment. The impact of energy storage devices on instantaneous impact currents will accelerate their capacity decay rate and life. Existing studies have ignored the impact of multiple types of impact loads on the life of energy storage media. Existing technologies basically do not consider the impact of the dynamic characteristics of impact loads on microgrids, including voltage, frequency and power fluctuations, etc., and cannot well meet the supporting role of energy storage in microgrid scheduling and operation. Therefore, there are certain limitations in application effects.

[0031] Figure 1 This is one of the flow diagrams of the isolated island microgrid composite energy storage optimization configuration method provided by the present invention, such as Figure 1 As shown, the method includes steps 101-104.

[0032] Step 101: Based on actual operation data of an isolated island microgrid containing multiple types of impact loads, a simulation model of an isolated island microgrid containing multiple types of impact loads is constructed and simulation analysis is performed to obtain simulation results.

[0033] Specifically, the actual operation data of the microgrid containing multiple types of impact loads includes: sampling data of impact loads of the isolated microgrid, wind, light, load, motor load, capacitor load and diesel generator operation data, etc. Composite energy storage includes: at least two of supercapacitors, superconducting energy storage, batteries and flywheel energy storage, etc.

[0034] In practical applications, the actual operation data of the isolated island microgrid containing multiple types of impact loads can be obtained. Then, based on the actual operation data of the isolated island microgrid containing multiple types of impact loads, a simulation model of the isolated island microgrid is built based on MATLAB or Simulink, and simulation analysis is performed based on the isolated island microgrid simulation model to obtain simulation results.

[0035] Step 102: Construct an island microgrid composite energy storage optimization configuration model containing multiple types of impact loads.

[0036] In practical applications, in order to effectively reduce the impact of uncertainty on the actual operation of the system and alleviate the burden of the power grid to smooth power fluctuations, when constructing an optimal configuration model for composite energy storage of an isolated microgrid, the impact of multiple types of impact loads on the life of the energy storage medium is considered. Therefore, an optimal configuration model for composite energy storage of an isolated microgrid with multiple types of impact loads is constructed.

[0037] Step 103: Based on the simulation results, the island microgrid composite energy storage optimization configuration model is solved to obtain the target configuration result.

[0038] In practical applications, the simulation results can be input into the isolated island microgrid composite energy storage optimization configuration model, and the isolated island microgrid composite energy storage optimization configuration model can be solved to obtain the target configuration results.

[0039] Step 104: Evaluate the effect of the target configuration result to obtain an evaluation result, and perform optimal configuration of the island microgrid composite energy storage based on the evaluation result.

[0040] In practical applications, on the basis of obtaining the target configuration results, the effect of the target configuration results is further evaluated, and the optimal configuration whose effect evaluation meets the optimization requirements is found from the target configuration results, and then the composite energy storage of the isolated microgrid is configured.

[0041] The method and device for optimizing the configuration of composite energy storage for an isolated microgrid provided by the present invention effectively consider the influence of impact loads on the operation of the microgrid in a composite energy storage optimization configuration model for an isolated microgrid containing multiple types of impact loads, thereby effectively improving the reliability of power supply for the isolated microgrid containing multiple types of impact loads, and providing a technical basis and a practical method for the operation and control of the isolated microgrid containing multiple types of impact loads; and the method for optimizing the configuration of composite energy storage for an isolated microgrid provided by the present invention is easy to implement and convenient to arrange.

[0042] In one or more optional embodiments of the present invention, a composite energy storage optimization configuration model of an isolated microgrid containing multiple types of impact loads is constructed, including: Based on the data types contained in the isolated microgrid with multiple types of impact loads, the objective function and constraints are constructed. The objective function and constraints constitute the composite energy storage optimization configuration model of the isolated microgrid with multiple types of impact loads.

[0043] Specifically, the objective functions include a node voltage deviation minimum function, a frequency offset standard deviation minimum function, and a power fluctuation penalty minimum function.

[0044] Specifically, the constraints include power balance constraints, unit power constraints, ramp constraints, energy storage constraints, steady-state frequency deviation constraints, and maximum frequency change rate constraints.

[0045] In practical applications, the composite energy storage optimization configuration model for isolated microgrids with multi-type impact loads mainly includes two parts: objective function and constraints.

[0046] The objective function needs to construct three functions, namely the node voltage deviation minimum function, the frequency offset standard deviation minimum function and the power fluctuation penalty minimum function.

[0047] The constraints mainly include five constraints: power balance constraint, unit power constraint, ramp constraint, energy storage constraint, steady-state frequency deviation constraint and maximum frequency change rate constraint.

[0048] The embodiment provided by the present invention can ensure the comprehensiveness and accuracy of the composite energy storage optimization configuration model of the isolated microgrid containing multiple types of impact loads through the minimum function of node voltage deviation, the minimum function of frequency offset standard deviation and the minimum function of power fluctuation penalty, as well as power balance constraints, unit power constraints, climbing constraints, energy storage constraints, steady-state frequency deviation constraints and maximum frequency change rate constraints. And in the optimization objectives of the composite energy storage optimization configuration model of the isolated microgrid containing multiple types of impact loads, the optimization objectives of minimum node voltage deviation, minimum frequency offset standard deviation and minimum power fluctuation penalty are considered. This method effectively considers the impact of impact loads on the operation of the microgrid, can effectively improve the reliability of power supply of the isolated microgrid containing multiple types of impact loads, and provides a technical basis and practical method for the operation and control of the isolated microgrid containing multiple types of impact loads.

[0049] In one or more optional embodiments of the present invention, the node voltage deviation minimum function is constructed based on the voltage reference value, the upper limit of the voltage amplitude, the lower limit of the voltage amplitude and the actual value of the node voltage of each node in the isolated island microgrid.

[0050] Specifically, the node voltage deviation minimum function for: in, represents the node voltage deviation, Representation Node Voltage reference value, Representation Node The upper limit of the voltage amplitude, Representation Node The lower limit of the voltage amplitude, is the actual value of the node voltage, is the number of nodes in the island microgrid.

[0051] In one or more optional embodiments of the present invention, a frequency offset standard deviation minimum function is constructed based on the actual frequency value and the reference frequency value at each moment.

[0052] Specifically, the frequency offset standard deviation minimum function for: in, For the The actual value of the frequency at a moment, f base The base frequency is 50Hz. is the number of moments taken.

[0053] In one or more optional embodiments of the present invention, the power fluctuation penalty minimum function is constructed based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a set moment, as well as the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a moment before the set moment, and the set moment is any moment.

[0054] Specifically, the power fluctuation penalty minimum function for: in, for The active power of photovoltaic power generation at the moment, for The wind power generation active power at the moment, for The diesel engine active power at the time, for The load active power at the moment, for The active power of photovoltaic power generation at the moment, for The wind power generation active power at the moment, for The diesel engine active power at the time, for The load active power at the moment.

[0055] In one or more optional embodiments of the present invention, the power balance constraint is constructed based on the active power of photovoltaic power generation, wind power generation, diesel engine active power and load active power at a set time, as well as the charging power and discharging power of the composite energy storage.

[0056] Specifically, the power balance constraint is: in, is the charging power of the composite energy storage, is the discharge power of the composite energy storage.

[0057] In one or more optional embodiments of the present invention, the unit power constraint is constructed based on the photovoltaic power generation active power, wind power generation active power and diesel engine active power at a set time, as well as the maximum photovoltaic power generation, the maximum wind turbine power generation and the maximum diesel generator power generation.

[0058] Specifically, the unit power constraint is: In the formula, is the maximum photovoltaic power generation power, is the maximum power generation of the wind turbine, It is the maximum power generation of the diesel generator.

[0059] In one or more optional embodiments of the present invention, the climbing constraint is constructed based on the climbing rate, the active power of the diesel engine at a set time, and the active power of the diesel engine at a time before the set time.

[0060] Specifically, the climbing constraint is: in, is the climbing rate.

[0061] In one or more optional embodiments of the present invention, the energy storage constraint is constructed based on setting the charging power and discharging power of the energy storage device at a set time, as well as setting the maximum charging power, maximum discharging power, minimum value of the energy storage device capacity and maximum value of the energy storage device capacity.

[0062] Specifically, the energy storage constraint is: in, For the Energy storage device Charging power at all times, For the Energy storage device Discharge power at all times, For the Maximum charging power of each energy storage device, For the The maximum discharge power of each energy storage device is For the The minimum capacity of an energy storage device, For the The capacity of the energy storage device, For the The maximum capacity of an energy storage device.

[0063] In one or more optional embodiments of the present invention, the steady-state frequency deviation constraint is constructed based on the steady-state frequency deviation, the frequency modulation dead zone and the steady-state frequency deviation limit.

[0064] Specifically, the steady-state frequency deviation constraint is: in, is the steady-state frequency deviation, is the FM dead zone, is the steady-state frequency deviation limit.

[0065] In one or more optional embodiments of the present invention, the maximum frequency change rate constraint is constructed based on the maximum frequency change rate and the frequency change rate limit.

[0066] Specifically, the maximum frequency change rate constraint is: in, is the maximum frequency change rate, is the frequency change rate limit.

[0067] In one or more optional embodiments of the present invention, the target configuration result is evaluated to obtain an evaluation result, including: Construct evaluation indicators for composite energy storage optimization configuration effects; A Monte Carlo algorithm is used to generate at least one operation scenario corresponding to an island microgrid containing multiple types of impact loads; An island microgrid simulation model with multiple types of impact loads is used to simulate the operation scenarios and generate simulation results for each operation scenario; According to the simulation results of each operation scenario, the composite energy storage optimization configuration effect evaluation index of each operation scenario is calculated respectively to obtain the index value corresponding to each operation scenario; According to the indicator values ​​corresponding to each operating scenario, the entropy weight-better solution distance method is used to evaluate the effect of the target configuration results.

[0068] Specifically, the evaluation indicators for the composite energy storage optimization configuration effect include frequency qualification rate, voltage qualification rate, load loss rate, node voltage deviation, frequency offset standard deviation and power fluctuation.

[0069] In practical applications, the effect of the target configuration results is evaluated, that is, the effect of the composite energy storage optimization configuration is evaluated: the composite energy storage optimization configuration effect evaluation index can be constructed first; then the Monte Carlo algorithm is used to generate the island microgrid operation scenario with multiple types of impact loads; further, for the generated island microgrid operation scenario with multiple types of impact loads, the island microgrid simulation model with multiple types of impact loads based on MATLAB / Simulink is used for simulation; according to the simulation results, the composite energy storage optimization configuration effect evaluation index of each scenario is calculated; then the entropy weight-superiority and inferiority solution distance (TOPSIS) method is used to evaluate the composite energy storage optimization configuration effect. In this way, the accuracy of the evaluation can be guaranteed and the efficiency of the optimization configuration can be improved.

[0070] In one or more optional embodiments of the present invention, the frequency qualification rate is determined based on the actual operating inertia of the system and the lower limit of the inertia safety domain.

[0071] Specifically, the frequency qualification rate for: in, Represents the actual operating inertia of the system, Represents the lower limit of the inertia safety region.

[0072] In one or more optional embodiments of the present invention, the voltage qualification rate is determined based on the number of set nodes and the total number of nodes in the isolated island microgrid, so the set node is a node whose actual value of the node voltage is within a set range, and the set range is determined based on the voltage amplitude upper limit and the voltage amplitude lower limit of the node.

[0073] Specifically, the voltage qualification rate for: in, Represents a collection of nodes; is the total number of nodes; For Node The voltage For Node The upper voltage limit, For Node The voltage lower limit, Nodes representing qualified voltage quality .

[0074] In one or more optional embodiments of the present invention, the load loss rate is determined based on the load loss amount and discharge power of the energy storage system at each moment.

[0075] Specifically, the load loss rate for: in, for The system load loss at the moment, represent The discharge power of the energy storage system at a certain moment, and T represents the number of moments.

[0076] In one or more optional embodiments of the present invention, the node voltage deviation is determined based on a voltage reference value, an upper limit of a voltage amplitude, a lower limit of a voltage amplitude and an actual value of a node voltage of each node in the island microgrid.

[0077] Specifically, the node voltage deviation for: in, represents the node voltage deviation, Representation Node Voltage reference value, Representation Node The upper limit of the voltage amplitude, Representation Node The lower limit of the voltage amplitude, is the actual value of the node voltage, is the number of nodes in the island microgrid.

[0078] In one or more optional embodiments of the present invention, the frequency offset standard deviation is determined based on the actual frequency value and the reference frequency value at each moment.

[0079] Specifically, the frequency offset standard deviation for: in, For the The actual value of the frequency at a moment, f base The base frequency is 50Hz. is the number of moments taken.

[0080] In one or more optional embodiments of the present invention, the power fluctuation is determined based on the active power of photovoltaic power generation, the active power of wind power generation, the active power of diesel engine and the active power of load at a set moment, as well as the active power of photovoltaic power generation, the active power of wind power generation, the active power of diesel engine and the active power of load at a moment before the set moment.

[0081] Specifically, power fluctuations for: in, for The active power of photovoltaic power generation at the moment, for The wind power generation active power at the moment, for The diesel engine active power at the time, for The load active power at the moment, for The active power of photovoltaic power generation at the moment, for The wind power generation active power at the moment, for The diesel engine active power at the time, for The load active power at the moment.

[0082] In one or more optional embodiments of the present invention, according to the indicator values ​​corresponding to each operation scenario, an entropy weight-good and bad solution distance method is used to evaluate the effect of the target configuration result, including: Construct the initialization decision matrix, very large indicators and very small indicators; The entropy weight method is used to calculate the weight of the indicator value corresponding to each operating scenario; The superior and inferior solution distance method is used to evaluate the effect based on the weight of each indicator value.

[0083] In practical applications, when the entropy weight-better solution distance method is used to evaluate the effect of the target configuration results, it is necessary to first initialize the decision matrix construction and normalize it, that is, to construct the initialization decision matrix, the extremely large index and the extremely small index.

[0084] Specifically, construct the initialization decision matrix, with Candidate evaluation scenarios (running scenarios), evaluation indicators, Indicates The first scene to be evaluated The evaluation index value is given by The scenarios to be evaluated, The judgment matrix composed of evaluation indicators, that is, the initialization decision matrix .

[0085] The forward calculation formula includes extremely large indicators and very small indicators , among which, the extremely large index for ; Very small indicator for .

[0086] Then, the entropy weight method is used to calculate the weight of the composite energy storage optimization configuration effect evaluation index, that is, the weight of the index value corresponding to each operating scenario is calculated: for each composite energy storage optimization configuration effect evaluation index (hereinafter referred to as the index) of each evaluation scenario, the standardized evaluation weight, entropy value and difference coefficient of the index of the evaluation scenario are calculated; based on the standardized evaluation weight, entropy value and difference coefficient of the index, the weight of the composite energy storage optimization configuration effect evaluation index of the index is calculated.

[0087] Specifically, the steps include: Calculate the Select the evaluation scenario Standardized evaluation weights of indicators : ; Calculate the The entropy value of the index : , where , when the evaluation weight hour, ; Determine The coefficient of variation of the index : ; Determine the weight of evaluation indicators for composite energy storage optimization configuration effect : .

[0088] After determining the weights of the indicator values ​​corresponding to each operating scenario, the superior and inferior solution distance method can be used to evaluate the effect.

[0089] In one or more optional embodiments of the present invention, a superior-inferior solution distance method is used to perform effect evaluation based on the weight of each indicator value, including: Construct a standardized matrix; The weights based on the values ​​of each indicator are brought into the standardized matrix, and the good-bad solution distance method is used to obtain the positive ideal solution and negative ideal solution corresponding to each operating scenario. For each operation scenario, based on the positive ideal solution and the negative ideal solution corresponding to the operation scenario, the positive ideal point distance and the negative ideal point distance of the operation scenario are calculated, and based on the positive ideal point distance and the negative ideal point distance of the operation scenario, the relative fit of the operation scenario is calculated; The effect is evaluated based on the relative fit of each operating scenario.

[0090] In practical applications, we first construct a standardized matrix . Standardized matrix The expression is: ,in, Represents a standardized matrix Middle Line Elements of a column. Indicates Line The index of the column.

[0091] Then, obtain the positive and negative ideal solutions.

[0092] Specifically, the positive ideal solution The expression is , negative ideal solution The expression is .

[0093] in, The element is the optimal value in the indicator, is the worst value among the indicators, is a benefit-based indicator set (the larger the indicator, the better), It is a cost-type indicator set (the smaller the indicator, the better).

[0094] Next, calculate the positive ideal point distance of each scene to be evaluated Distance to negative ideal point .

[0095] Specifically, the positive ideal point distance The expression is ; Negative ideal point distance The expression is .

[0096] Furthermore, the relative fit of each scene to be evaluated is calculated Finally, sort the scenarios to be evaluated according to their relative closeness, the larger the value, the better, and find the optimal solution.

[0097] Specifically, the relative fit The expression is .

[0098] In one or more optional embodiments of the present invention, based on actual operation data of an isolated island microgrid containing multiple types of impact loads, a simulation model of an isolated island microgrid containing multiple types of impact loads is constructed, including: Obtain actual operating data of isolated microgrids with multiple types of impact loads; Based on the actual operation data of the isolated microgrid with multi-type impact loads, a multi-type impact load model based on digital-analog hybrid drive is constructed; A multi-type impact load model is adopted to build an island microgrid simulation model containing multi-type impact loads.

[0099] In practical applications, the actual operation data of the isolated microgrid containing multiple types of impact loads can be obtained, such as the sampling data of the impact load of the isolated microgrid, wind, light, load, motor load, capacitor load and diesel generator operation data. Then, based on the multiple types of impact loads driven by digital-analog hybrid in the actual operation data obtained, a multiple types of impact load model based on digital-analog hybrid drive is established. Furthermore, the constructed multiple types of impact load model based on digital-analog hybrid drive is used to build and simulate the isolated microgrid containing multiple types of impact loads based on MATLAB / simulink, and the voltage, current, system frequency, active power and reactive power of each node of the isolated microgrid are obtained according to the simulation results. In this way, the construction efficiency and accuracy of the simulation model of the isolated microgrid containing multiple types of impact loads can be improved.

[0100] The embodiment provided by the present invention constructs a multi-type impact load model based on digital-analog hybrid drive, which makes up for the fact that the existing modeling method cannot adapt to the impact of operating point changes on the dynamic / static operating characteristics of the isolated island microgrid, and has strong engineering practicality.

[0101] In one or more optional embodiments of the present invention, based on actual operation data of an island microgrid containing multiple types of impact loads, a multi-type impact load model based on digital-analog hybrid drive is constructed, including: From the actual operation data of the isolated microgrid containing multiple types of impact loads, the first time series data when the isolated microgrid containing multiple types of impact loads has a short circuit fault in different scenarios, and the second time series data when the operating point changes due to the change of the operation mode of the isolated microgrid in different scenarios are collected; Obtaining the instantaneous value of voltage, instantaneous value of current, active power and reactive power at the point where the impact load is connected to the grid from the first time series data and the second time series data; Select the instantaneous value of voltage, active power and reactive power as input, select the instantaneous value of current as label, and construct the data set; A deep learning method combining recurrent gate units and attention mechanism is used to construct an impact load equivalent model; Based on the data set, the shock load equivalent model is trained to obtain multiple types of shock load models.

[0102] In practical applications, the first time series data when a short circuit fault occurs in different scenarios of an island microgrid containing multiple types of impact loads and the second time series data when the operating point changes due to changes in the operating mode are collected from the actual operation data.

[0103] Then, the instantaneous voltage value and the instantaneous current value at the impact load grid connection are obtained from the first time series data and the second time series data. If necessary, the instantaneous voltage value in the three-phase abc coordinate system can be converted into Two-dimensional data in coordinate system and , convert the instantaneous current value in the three-phase abc coordinate system into Two-dimensional data in coordinate system and And obtain the active power of the impact load grid connection from the first time series data and the second time series data and reactive power .

[0104] Furthermore, select As the input vector of the deep learning model, select As the output vector (label) of the deep learning model, thus constructing a deep learning-based dataset; Afterwards, a deep learning method combining the Gated Recurrent Unit (GRU) and the attention mechanism was used to construct the shock load equivalent model. Finally, the dataset was input into the constructed shock load equivalent model based on the combination of GRU and attention and trained to obtain the optimal model, that is, the multi-type shock load model based on digital-analog hybrid drive.

[0105] In one or more optional embodiments of the present invention, based on the simulation results, the island microgrid composite energy storage optimization configuration model is solved to obtain the target configuration result, including: The simulation results are input into the optimal configuration model of composite energy storage for isolated island microgrid, and the particle swarm evolution algorithm is used to solve the optimal configuration model of composite energy storage for isolated island microgrid to obtain the target configuration results.

[0106] Specifically, the particle swarm is randomly initialized, mainly the random particle swarm parameters, the position and speed of each particle; then the fitness of each particle is evaluated, and the first The individual optimal solution corresponding to the minimum fitness value of the particle searched so far is in the individual optimal solution set In the process, the global optimal solution corresponding to the minimum fitness value of the entire particle swarm in the search process so far is liberated from the global optimal solution set Then according to and , update the position and speed of the particle, update the individual historical optimal fitness value and position of each particle, and update the historical optimal fitness value and position of the population; then determine whether the constraints in the island microgrid composite energy storage optimization configuration model for multi-type impact loads are met. If so, the search stops and the optimal configuration result is output. Otherwise, return according to and , the steps of updating the position and speed of the particles, updating the individual historical optimal fitness value and position of each particle, and updating the historical optimal fitness value and position of the population continue to be executed.

[0107] Combine the following Figure 2 The isolated island microgrid composite energy storage optimization configuration method provided by the present invention is further explained.

[0108] Figure 2 This is the second flow chart of the isolated island microgrid composite energy storage optimization configuration method provided by the present invention, such as Figure 2 As shown, the method includes steps 201-206.

[0109] Step 201: Acquire actual operation data of an island microgrid containing multiple types of impact loads.

[0110] The actual operation data of the microgrid containing multiple types of impact loads include: sampling data of impact loads of isolated microgrids, wind, light, load, motor load, capacitor load and diesel generator operation data, etc.

[0111] Step 202: Modeling of multiple types of impact load models based on digital-analog hybrid drive.

[0112] (1) Collect the time series data when short circuit faults occur in different scenarios of isolated microgrids with multiple types of impact loads and the time series data when the operating point changes due to changes in the operating mode; Obtain the instantaneous values ​​of voltage and current at the point where the impact load is connected to the grid; (3) Obtain active power and reactive power at the point where the impact load is connected to the grid; (4) Select active power, reactive power and instantaneous voltage as the input vectors of the deep learning model, and select the instantaneous value of current as the output vector of the deep learning model, so as to construct a data set based on deep learning; (5) A deep learning method combining GRU and attention is used to construct an impact load equivalent model; (6) Input the data set of step (4) into the impact load equivalent model based on the combination of GRU and attention constructed in step (5) and train it to obtain the optimal model.

[0113] Step 203: Build an island microgrid simulation model containing multiple types of impact loads based on MATLAB / Simulink and perform simulation analysis.

[0114] A multi-type impact load model based on digital-analog hybrid drive is adopted to build and simulate an island microgrid simulation with multi-type impact loads based on MATLAB / Simulink. According to the simulation results, the voltage, current, system frequency, active power and reactive power of each node in the island microgrid are obtained.

[0115] Step 204: Construct an island microgrid composite energy storage optimization configuration model containing multiple types of impact loads.

[0116] Based on the data types contained in the isolated microgrid with multiple types of impact loads, the objective function and constraint conditions are constructed, and the objective function and constraint conditions constitute the composite energy storage optimization configuration model of the isolated microgrid with multiple types of impact loads; The objective functions include the minimum node voltage deviation function, the minimum frequency offset standard deviation function and the minimum power fluctuation penalty function; The constraints include power balance constraint, unit power constraint, ramp constraint, energy storage constraint, steady-state frequency deviation constraint and maximum frequency change rate constraint.

[0117] Step 205: Solve the composite energy storage optimization configuration model of the isolated microgrid containing multiple types of impact loads.

[0118] The particle swarm evolution algorithm is used to solve the composite energy storage optimal configuration model of isolated microgrids with multi-type impact loads.

[0119] Step 206: Evaluate the effect of composite energy storage optimization configuration.

[0120] Construct an evaluation index for the effect of composite energy storage optimization configuration; use the Monte Carlo algorithm to generate an island microgrid operation scenario with multiple types of impact loads; use the MATLAB / Simulink-based island microgrid simulation model with multiple types of impact loads to simulate the generated island microgrid operation scenario with multiple types of impact loads; calculate the evaluation index of the composite energy storage optimization configuration effect for each scenario based on the simulation results; use the entropy weight-TOPSIS method to evaluate the effect of composite energy storage optimization configuration.

[0121] The isolated microgrid composite energy storage optimization configuration method provided by the present invention constructs a multi-type impact load model based on digital-analog hybrid drive, which makes up for the fact that the existing modeling method cannot adapt to the impact of operating point changes on the dynamic / static operating characteristics of the isolated microgrid, and has strong engineering practicality; in the optimization objectives of the isolated microgrid composite energy storage optimization configuration model containing multi-type impact loads, the optimization objectives of minimum node voltage deviation, minimum frequency offset standard deviation, and minimum power fluctuation penalty are considered, which effectively considers the impact of impact loads on the operation of the microgrid, can effectively improve the reliability of power supply of the isolated microgrid containing multi-type impact loads, and provide a technical basis and practical method for the operation and control of the isolated microgrid containing multi-type impact loads; and the isolated microgrid composite energy storage optimization configuration method provided by the present invention is easy to implement and convenient to arrange.

[0122] The following is a description of the isolated island microgrid composite energy storage optimization configuration device provided by the present invention. The isolated island microgrid composite energy storage optimization configuration device described below and the isolated island microgrid composite energy storage optimization configuration method described above can be referenced to each other.

[0123] Figure 3 Schematic diagram of the structure of the isolated island microgrid composite energy storage optimization configuration device provided by the present invention. Figure 3 As shown, including: The simulation module 301 is configured to build a simulation model of an isolated microgrid containing multiple types of impact loads and perform simulation analysis based on actual operation data of the isolated microgrid containing multiple types of impact loads to obtain simulation results; A construction module 302 is configured to construct an island microgrid composite energy storage optimization configuration model containing multiple types of impact loads; The solution module 303 is configured to solve the island microgrid composite energy storage optimization configuration model based on the simulation results to obtain the target configuration result; The evaluation module 304 is configured to evaluate the effect of the target configuration result, obtain the evaluation result, and perform the optimal configuration of the island microgrid composite energy storage based on the evaluation result.

[0124] Optionally, the construction module 302 is further configured to: Based on the data types contained in the isolated microgrid with multiple types of impact loads, the objective function and constraint conditions are constructed, and the objective function and constraint conditions constitute the composite energy storage optimization configuration model of the isolated microgrid with multiple types of impact loads; The objective functions include the minimum node voltage deviation function, the minimum frequency offset standard deviation function and the minimum power fluctuation penalty function; The constraints include power balance constraint, unit power constraint, ramp constraint, energy storage constraint, steady-state frequency deviation constraint and maximum frequency change rate constraint.

[0125] Optionally, the node voltage deviation minimum function is constructed based on the voltage reference value of each node in the isolated island microgrid, the upper limit of the voltage amplitude, the lower limit of the voltage amplitude and the actual value of the node voltage; The frequency offset standard deviation minimum function is constructed based on the actual frequency value and the reference frequency value at each moment; The power fluctuation penalty minimum function is constructed based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at the set time, as well as the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at the moment before the set time. The set time is an arbitrary time.

[0126] Optionally, the power balance constraint is constructed based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a set time, as well as the charging power and discharging power of the composite energy storage; The power constraints of the units are constructed based on the active power of photovoltaic power generation, wind power generation and diesel engine at the set time, as well as the maximum power generation of photovoltaic power generation, the maximum power generation of wind turbine and the maximum power generation of diesel generator; The climbing constraint is constructed based on the climbing rate, the diesel engine active power at the set time, and the diesel engine active power at the moment before the set time; The energy storage constraint is constructed based on setting the charging power and discharging power of the energy storage device at the set time, and setting the maximum charging power, maximum discharging power, minimum value of the energy storage device capacity and maximum value of the energy storage device capacity of the energy storage device; The steady-state frequency deviation constraint is constructed based on the steady-state frequency deviation, frequency modulation dead zone and steady-state frequency deviation limit; The maximum frequency change rate constraint is built based on the maximum frequency change rate and the frequency change rate limit.

[0127] Optionally, the simulation module 301 is further configured to: Obtain actual operating data of isolated microgrids with multiple types of impact loads; Based on the actual operation data of the isolated microgrid with multi-type impact loads, a multi-type impact load model based on digital-analog hybrid drive is constructed; A multi-type impact load model is adopted to build an island microgrid simulation model containing multi-type impact loads.

[0128] Optionally, the simulation module 301 is further configured to: From the actual operation data of the isolated microgrid containing multiple types of impact loads, the first time series data when the isolated microgrid containing multiple types of impact loads has a short circuit fault in different scenarios, and the second time series data when the operating point changes due to the change of the operation mode of the isolated microgrid in different scenarios are collected; Obtaining the instantaneous value of voltage, instantaneous value of current, active power and reactive power at the point where the impact load is connected to the grid from the first time series data and the second time series data; Select the instantaneous value of voltage, active power and reactive power as input, select the instantaneous value of current as label, and construct the data set; A deep learning method combining recurrent gate units and attention mechanism is used to construct an impact load equivalent model; Based on the data set, the shock load equivalent model is trained to obtain multiple types of shock load models.

[0129] Optionally, the evaluation module 304 is further configured to: Construct composite energy storage optimization configuration effect evaluation indicators, which include frequency qualification rate, voltage qualification rate, load loss rate, node voltage deviation, frequency offset standard deviation and power fluctuation; A Monte Carlo algorithm is used to generate at least one operation scenario corresponding to an island microgrid containing multiple types of impact loads; An island microgrid simulation model with multiple types of impact loads is used to simulate the operation scenarios and generate simulation results for each operation scenario; According to the simulation results of each operation scenario, the composite energy storage optimization configuration effect evaluation index of each operation scenario is calculated respectively to obtain the index value corresponding to each operation scenario; According to the indicator values ​​corresponding to each operating scenario, the entropy weight-better solution distance method is used to evaluate the effect of the target configuration results.

[0130] Optionally, the frequency qualification rate is determined based on the actual operating inertia of the system and the lower limit of the inertia safety domain; The voltage qualification rate is determined based on the number of set nodes and the total number of nodes in the isolated island microgrid, so the set node is the node whose actual value of the node voltage is within the set range, and the set range is determined based on the voltage amplitude upper limit and voltage amplitude lower limit of the node; The load loss rate is determined based on the load loss amount and discharge power of the energy storage system at each moment; The node voltage deviation is determined based on the voltage reference value of each node in the island microgrid, the upper limit of the voltage amplitude, the lower limit of the voltage amplitude and the actual value of the node voltage; The frequency offset standard deviation is determined based on the actual frequency value and the reference frequency value at each moment; The power fluctuation is determined based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a set moment, and the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a moment before the set moment.

[0131] Optionally, the evaluation module 304 is further configured to: Construct the initialization decision matrix, very large indicators and very small indicators; The entropy weight method is used to calculate the weight of the indicator value corresponding to each operating scenario; The superior and inferior solution distance method is used to evaluate the effect based on the weight of each indicator value.

[0132] Optionally, the evaluation module 304 is further configured to: Construct a standardized matrix; The weights based on the values ​​of each indicator are brought into the standardized matrix, and the good-bad solution distance method is used to obtain the positive ideal solution and negative ideal solution corresponding to each operating scenario. For each operation scenario, based on the positive ideal solution and the negative ideal solution corresponding to the operation scenario, the positive ideal point distance and the negative ideal point distance of the operation scenario are calculated, and based on the positive ideal point distance and the negative ideal point distance of the operation scenario, the relative fit of the operation scenario is calculated; The effect is evaluated based on the relative fit of each operating scenario.

[0133] Figure 4 An example of a physical structure diagram of an electronic device is provided, and the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the isolated microgrid composite energy storage optimization configuration method, and the method includes: based on the actual operation data of the isolated microgrid containing multiple types of impact loads, building an isolated microgrid simulation model containing multiple types of impact loads and performing simulation analysis to obtain simulation results; constructing an isolated microgrid composite energy storage optimization configuration model containing multiple types of impact loads; based on the simulation results, solving the isolated microgrid composite energy storage optimization configuration model to obtain a target configuration result; evaluating the effect of the target configuration result to obtain an evaluation result, and performing the isolated microgrid composite energy storage optimization configuration based on the evaluation result.

[0134] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0135] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the isolated microgrid composite energy storage optimization configuration method provided by the above methods, the method including: based on the actual operation data of the isolated microgrid containing multiple types of impact loads, building an isolated microgrid simulation model containing multiple types of impact loads and performing simulation analysis to obtain simulation results; constructing an isolated microgrid composite energy storage optimization configuration model containing multiple types of impact loads; based on the simulation results, solving the isolated microgrid composite energy storage optimization configuration model to obtain a target configuration result; performing an effect evaluation on the target configuration result to obtain an evaluation result, and performing the isolated microgrid composite energy storage optimization configuration based on the evaluation result.

[0136] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the isolated microgrid composite energy storage optimization configuration method provided by the above-mentioned methods, the method comprising: based on actual operation data of the isolated microgrid containing multiple types of impact loads, building an isolated microgrid simulation model containing multiple types of impact loads and performing simulation analysis to obtain simulation results; constructing an isolated microgrid composite energy storage optimization configuration model containing multiple types of impact loads; based on the simulation results, solving the isolated microgrid composite energy storage optimization configuration model to obtain a target configuration result; performing an effect evaluation on the target configuration result to obtain an evaluation result, and performing the isolated microgrid composite energy storage optimization configuration based on the evaluation result.

[0137] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0139] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the configuration of composite energy storage in an isolated microgrid, characterized in that: include: Based on the actual operation data of the isolated microgrid with multiple types of impact loads, a simulation model of the isolated microgrid with multiple types of impact loads was built and simulation analysis was performed to obtain simulation results. Construct a composite energy storage optimization configuration model for isolated microgrids with multiple types of impact loads; Based on the simulation results, solving the island microgrid composite energy storage optimization configuration model to obtain the target configuration result; An effect evaluation is performed on the target configuration result to obtain an evaluation result, and an island microgrid composite energy storage optimization configuration is performed based on the evaluation result.

2. The isolated island microgrid composite energy storage optimization configuration method according to claim 1 is characterized in that: The construction of an island microgrid composite energy storage optimization configuration model containing multiple types of impact loads includes: Based on the data types contained in the isolated microgrid containing multiple types of impact loads, construct an objective function and constraint conditions, wherein the objective function and the constraint conditions constitute a composite energy storage optimization configuration model for the isolated microgrid containing multiple types of impact loads; The objective functions include a node voltage deviation minimum function, a frequency offset standard deviation minimum function, and a power fluctuation penalty minimum function; The constraints include power balance constraints, unit power constraints, ramp constraints, energy storage constraints, steady-state frequency deviation constraints and maximum frequency change rate constraints.

3. The method for optimizing the configuration of composite energy storage for isolated island microgrids according to claim 2, characterized in that: The node voltage deviation minimum function is constructed based on the voltage reference value of each node in the isolated island microgrid, the upper limit of the voltage amplitude, the lower limit of the voltage amplitude and the actual value of the node voltage; The frequency offset standard deviation minimum function is constructed based on the actual frequency value and the reference frequency value at each moment; The power fluctuation penalty minimum function is constructed based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a set time, and the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a moment before the set time, and the set time is any time; The power balance constraint is constructed based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at the set time, as well as the charging power and discharging power of the composite energy storage; The unit power constraint is constructed based on the photovoltaic power generation active power, wind power generation active power and diesel engine active power at the set time, as well as the photovoltaic maximum power generation, wind turbine maximum power generation and diesel generator maximum power generation; The climbing constraint is constructed based on the climbing rate, the active power of the diesel engine at the set time and the active power of the diesel engine at a moment before the set time; The energy storage constraint is constructed based on the charging power and discharging power of the energy storage device at the set time, as well as the maximum charging power, the maximum discharging power, the minimum value of the energy storage device capacity, and the maximum value of the energy storage device capacity of the set energy storage device; The steady-state frequency deviation constraint is constructed based on the steady-state frequency deviation, the frequency modulation dead zone and the steady-state frequency deviation limit; The maximum frequency change rate constraint is constructed based on the maximum frequency change rate and the frequency change rate limit.

4. The isolated island microgrid composite energy storage optimization configuration method according to claim 1 is characterized in that: The method of building an island microgrid simulation model containing multiple types of impact loads based on actual operation data of the island microgrid containing multiple types of impact loads includes: Obtain actual operating data of isolated microgrids with multiple types of impact loads; Based on the actual operation data of the isolated microgrid with multi-type impact loads, a multi-type impact load model based on digital-analog hybrid drive is constructed; The multi-type impact load model is adopted to build an island microgrid simulation model containing multi-type impact loads.

5. The isolated island microgrid composite energy storage optimization configuration method according to claim 4 is characterized in that: The multi-type impact load model based on digital-analog hybrid drive is constructed based on the actual operation data of the isolated island microgrid containing multi-type impact loads, including: From the actual operation data of the isolated microgrid based on the multi-type impact load, first time series data when a short circuit fault occurs in the isolated microgrid containing the multi-type impact load in different scenarios, and second time series data when the operating point changes due to changes in the operation mode of the isolated microgrid in different scenarios are collected; Obtaining the instantaneous value of voltage, instantaneous value of current, active power and reactive power at the point where the impact load is connected to the grid from the first time series data and the second time series data; Selecting the instantaneous value of voltage, the active power and the reactive power as input, selecting the instantaneous value of current as a label, and constructing a data set; A deep learning method combining recurrent gate units and attention mechanism is used to construct an impact load equivalent model; Based on the data set, the impact load equivalent model is trained to obtain a multi-type impact load model.

6. The method for optimizing the configuration of composite energy storage in an isolated microgrid according to any one of claims 1 to 5, characterized in that: The step of performing effect evaluation on the target configuration result to obtain an evaluation result includes: Constructing composite energy storage optimization configuration effect evaluation indicators, wherein the composite energy storage optimization configuration effect evaluation indicators include frequency qualification rate, voltage qualification rate, load loss rate, node voltage deviation, frequency offset standard deviation and power fluctuation; A Monte Carlo algorithm is used to generate at least one operation scenario corresponding to an island microgrid containing multiple types of impact loads; The operation scenarios are simulated using the island microgrid simulation model containing multiple types of impact loads to generate simulation results for each of the operation scenarios; According to the simulation results of each of the operation scenarios, respectively calculate the composite energy storage optimization configuration effect evaluation index of each of the operation scenarios to obtain the index value corresponding to each of the operation scenarios; According to the indicator values ​​corresponding to each of the operating scenarios, the entropy weight-good and bad solution distance method is used to evaluate the effect of the target configuration results.

7. The method for optimizing the configuration of composite energy storage for isolated island microgrids according to claim 6, characterized in that: The frequency qualification rate is determined based on the actual operating inertia of the system and the lower limit of the inertia safety domain; The voltage qualification rate is determined based on the number of set nodes and the number of all nodes in the isolated island microgrid, so the set node is a node whose actual value of the node voltage is within a set range, and the set range is determined based on the voltage amplitude upper limit and the voltage amplitude lower limit of the node; The load loss rate is determined based on the load loss amount and discharge power of the energy storage system at each moment; The node voltage deviation is determined based on a voltage reference value, an upper limit of a voltage amplitude, a lower limit of a voltage amplitude and an actual value of a node voltage of each node in the island microgrid; The frequency offset standard deviation is determined based on the actual frequency value and the reference frequency value at each moment; The power fluctuation is determined based on the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a set moment, and the photovoltaic power generation active power, wind power generation active power, diesel engine active power and load active power at a moment before the set moment.

8. The isolated island microgrid composite energy storage optimization configuration method according to claim 6 is characterized in that: According to the indicator values ​​corresponding to each of the operation scenarios, the entropy weight-better solution distance method is used to evaluate the effect of the target configuration result, including: Construct the initialization decision matrix, very large indicators and very small indicators; The entropy weight method is used to calculate the weight of the indicator value corresponding to each operating scenario; The superior and inferior solution distance method is adopted to evaluate the effect based on the weight of each indicator value.

9. The isolated island microgrid composite energy storage optimization configuration method according to claim 8 is characterized in that: The method of using the superior and inferior solution distance method to evaluate the effect based on the weight of each indicator value includes: Construct a standardized matrix; The weights based on the index values ​​are introduced into the standardized matrix, and the good-bad solution distance method is used to obtain the positive ideal solution and the negative ideal solution corresponding to each of the operating scenarios; For each of the operation scenarios, based on the positive ideal solution and the negative ideal solution corresponding to the operation scenario, the positive ideal point distance and the negative ideal point distance of the operation scenario are calculated, and based on the positive ideal point distance and the negative ideal point distance of the operation scenario, the relative fit of the operation scenario is calculated; The effect is evaluated based on the relative fit of each of the operating scenarios.

10. An island microgrid composite energy storage optimization configuration device, characterized in that: include: The simulation module is configured to build a simulation model of an isolated microgrid containing multiple types of impact loads and perform simulation analysis based on actual operation data of the isolated microgrid containing multiple types of impact loads to obtain simulation results; A building module is configured to build an island microgrid composite energy storage optimization configuration model containing multiple types of impact loads; A solution module is configured to solve the island microgrid composite energy storage optimization configuration model based on the simulation result to obtain a target configuration result; The evaluation module is configured to evaluate the effect of the target configuration result, obtain the evaluation result, and perform the optimal configuration of the isolated island microgrid composite energy storage based on the evaluation result.

Images