A multi-time scale hybrid energy storage capacity configuration method, system and storage medium

Abstract

The application relates to the technical field of data mining application, and discloses a multi-time-scale hybrid energy storage capacity configuration method and system and a storage medium. The method comprises the following steps: collecting data according to a wind power plant construction state and preprocessing to obtain standard wind power output power data; obtaining local power grid load curve or dispatching demand data, calculating a difference value to generate an energy storage reference power curve; splitting the power signal by using an SGMD decomposition algorithm, identifying multi-time-scale power waves to generate feature data; setting constraints based on the feature data, optimizing the energy storage capacity configuration by using an immune hybrid particle swarm algorithm; performing full life cycle simulation on the optimization result, verifying the effect and compliance and evaluating the economy to determine the best scheme. The application solves the problems of poor adaptability and insufficient economy of the existing energy storage configuration through multi-time-scale decomposition and closed-loop optimization, and improves the wind power grid stability and configuration economy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data mining application, and particularly relates to a multi-time scale hybrid energy storage capacity configuration method and system and a storage medium. BACKGROUND

[0002] With the increasing proportion of wind power in the energy structure, the output power of wind power is affected by natural factors such as wind speed and wind direction, and presents multi-time scale random fluctuations such as seconds, minutes, hours, weeks and above. If the fluctuations are directly connected to the power grid, it is easy to cause imbalance between supply and demand of the power grid, damage the stability of the power grid frequency, reduce the power supply quality, and even cause equipment failure and grid operation risk. Therefore, it is necessary to configure an energy storage system to smooth fluctuations and adapt to the demand of the power grid, and reasonable energy storage capacity configuration is a core prerequisite for ensuring efficient operation of the energy storage system.

[0003] The existing energy storage capacity configuration technology has many defects and cannot meet the high precision and economic demand of wind power grid connection. On the one hand, the traditional method is mostly based on single time scale analysis of power fluctuations, and does not develop adaptive solutions for the characteristics of different time scale fluctuations, such as only focusing on minute-level fluctuation smoothing, but ignoring second-level high-frequency impact or week-level low-frequency peak regulation demand, resulting in that the configuration result cannot comprehensively respond to multi-scenario fluctuations, affecting the stability of the power grid operation. On the other hand, the existing technology often takes meeting the grid connection standard as the only goal, and does not fully consider the whole life cycle economy, which is easy to cause problems such as high initial investment, out-of-control operation and maintenance cost, or insufficient income coverage, and the algorithm used in the optimization process mostly has local optimal trap, which cannot balance functionality and economy, and it is difficult to output a globally optimal configuration scheme. In addition, some methods do not establish a precise mapping between fluctuation characteristics and energy storage response, and the consideration of constraints such as energy storage charging and discharging power and state of charge in the configuration process is not comprehensive enough, which further reduces the practicality and reliability of the configuration scheme.

[0004] In view of the above defects, the present application proposes to identify fluctuation characteristics through multi-time scale power decomposition, conduct multi-objective optimization combined with an immune hybrid particle swarm algorithm, and form a technical route of "characteristic identification-optimization configuration-simulation verification" through whole life cycle simulation verification, so as to realize energy storage capacity configuration considering multi-scale fluctuation smoothing, grid compliance and economy. SUMMARY

[0005] The present application relates to the technical field of data mining application, and discloses a multi-time scale hybrid energy storage capacity configuration method and system and a storage medium. Through multi-time scale decomposition and closed-loop optimization, the present application solves the problems of poor adaptability and insufficient economy of the existing energy storage configuration, and improves the stability of wind power grid connection and the economy of configuration.

[0006] In a first aspect, the application provides a multi-time scale hybrid energy storage capacity configuration method, which comprises:

[0007] In step S101, data is collected according to the construction state of the wind farm, and the collected data is preprocessed to obtain standard wind power output data.

[0008] In step S102, the load curve or grid dispatch demand data of the local grid is obtained, the difference between the standard wind power output data and the load curve or grid dispatch demand data is calculated, and a reference power curve of the energy storage system is generated.

[0009] In step S103, the SGMD decomposition algorithm is used to decompose the standard wind power output data into multiple frequency components, and based on the frequency components, power fluctuations of different time scales such as seconds, minutes, hours, days, weeks, and above weeks are identified, and multi-time scale fluctuation characteristic data is generated.

[0010] In step S104, based on the multi-time scale fluctuation characteristic data, the response time constraint of the energy storage is set, and the immune hybrid particle swarm algorithm is used to optimize the capacity configuration of each energy storage device to preferentially meet the wind power grid connection national standard and the reference power curve fluctuation requirement, secondly maximize the economic benefit, and follow the energy storage charging and discharging power constraint, energy storage capacity constraint, state of charge constraint and response time constraint.

[0011] In step S105, the optimized energy storage capacity configuration is simulated for annual full life cycle to verify its effect on suppressing load fluctuations, meeting peak shaving demand and complying with wind power grid connection national standards at different time scales, and to evaluate the economy to determine the best energy storage capacity configuration scheme.

[0012] Optionally, the step S101 comprises:

[0013] The construction state of the wind farm is determined, and the construction state comprises a built state and a proposed state.

[0014] If it is in the built state, the actual output power data generated during the operation of the wind farm is directly collected, the actual output power data is cleaned, smoothed and processed for abnormal values to obtain the standard wind power output data.

[0015] If it is in the proposed state, local wind resource data and bid wind turbine model data are collected, and based on the local wind resource data and bid wind turbine model data, the wind power output is fitted through the LSTM algorithm to obtain the standard wind power output data of the proposed wind farm.

[0016] Optionally, the step S102 comprises:

[0017] calculating a difference between the standard wind power output data and the load curve data or the grid dispatch demand data at each time point;

[0018] integrating the difference in time sequence to form the reference power curve, wherein the reference power curve is used to reflect the power gap between the wind power output and the grid load or dispatch demand; the load curve data includes daily periodic fluctuation data and seasonal fluctuation data, the daily periodic fluctuation data reflects the load change in different time periods within a day, and the seasonal fluctuation data reflects the overall level difference of the load in different seasons.

[0019] Optionally, the step S103 comprises:

[0020] Taking the standard wind power output as the decomposition object, ensure that the time dimension matches the subsequent multi-time scale identification demand, covering time span of seconds, minutes, hours, days, weeks and above weeks;

[0021] Using the SGMD decomposition algorithm to decompose the standard wind power output, the single power signal is split into multiple sub-signals with different frequency characteristics, and each sub-signal corresponds to a power component with different fluctuation frequency;

[0022] Based on the frequency characteristics of each sub-signal, the corresponding time scale fluctuation characteristics are determined, wherein the high-frequency sub-signal corresponds to the second-level power fluctuation, the medium-high-frequency sub-signal corresponds to the minute-level power fluctuation, the medium-low-frequency sub-signal corresponds to the hour-level and day-level power fluctuation, and the low-frequency sub-signal corresponds to the week-level and above-week-level power fluctuation, and the amplitude, duration and period parameters of each time scale fluctuation are extracted synchronously;

[0023] Integrating the identified time scale fluctuation characteristics to generate the multi-time scale fluctuation characteristic data.

[0024] Optionally, the synchronous extraction of the amplitude, duration and period parameters of each time scale fluctuation comprises:

[0025] Taking each time scale corresponding sub-signal as the extraction object, first determine the power reference value corresponding to each sub-signal, the power reference value takes the average power value of the corresponding sub-signal in the complete fluctuation period;

[0026] Calculate the absolute value of the difference between the sub-signal power peak value and the power reference value as the amplitude of the corresponding time scale fluctuation;

[0027] Monitoring the complete time interval of the sub-signal power from the first deviation from the power reference value to the regression of the power reference value, and the time interval length is the duration of the corresponding time scale fluctuation;

[0028] For each sub-signal, the time points of the two consecutive power peaks or the two consecutive power valleys are identified, the time difference between the two adjacent peaks or the two adjacent valleys is calculated, and the average of the multiple calculation results is taken as the period parameter of the corresponding time scale fluctuation;

[0029] After the amplitude, duration and period parameters are extracted, each parameter is compared with the historical fluctuation parameter under the corresponding time scale. If the amplitude deviation exceeds the first preset value, or the duration deviation exceeds the second preset value, or the period deviation exceeds the third preset value, the sub-signal decomposition result is rechecked and the parameters are extracted again to ensure that the extracted parameters meet the actual characteristics of the corresponding time scale fluctuation.

[0030] Optionally, the step S104 comprises:

[0031] Based on the multi-time scale fluctuation characteristic data, M particles are generated by logical mapping, the particles are matrices containing the capacities and powers of each energy storage device, and an initial antibody is generated, the initial antibody corresponds to the reference power of high-frequency or low-frequency compensation power and energy storage action respectively;

[0032] Based on the main target of meeting the national standard for wind power grid connection and the secondary target of maximizing economic benefits, combined with the allowed maximum fluctuation after smoothing, the time vector and the full life cycle cost formula, the operation and maintenance discounted present value, the fitness of each particle is calculated;

[0033] Through the concentration selection mechanism, N particles with required fitness are selected from the M particles, combined with the newly generated N particles by logical mapping, a population containing M+N particles is formed, and the algorithm is prevented from falling into local optimum;

[0034] According to the particle fitness, the position and speed of the particle are updated, the capacity, power parameters and optimization direction of each energy storage device are adjusted, and the local optimal solution and the global optimal solution are updated synchronously;

[0035] If the maximum number of iterations is reached or the global optimal position is obtained, the iteration is stopped and the optimal capacity configuration result of each energy storage device is output, if not, the fitness calculation step is returned to continue iteration;

[0036] The entire configuration process needs to follow the energy storage charging and discharging power constraint, the energy storage capacity constraint, the state of charge constraint and the response time constraint.

[0037] Optionally, the step S105 comprises:

[0038] Based on the optimal capacity configuration result, a simulation model covering the full life cycle of the energy storage system is constructed, the model input includes the multi-time scale fluctuation characteristic data, the reference power curve, and the charging and discharging efficiency and life attenuation parameters of the energy storage device;

[0039] The functionality is verified by annual simulation, and the compliance is verified by comparing the smoothed power curve of the energy storage obtained by simulation with the wind power grid connection national standard to confirm whether it meets the grid connection requirements.

[0040] The cost of the optimal capacity configuration result in the whole life cycle is calculated, including initial investment cost, operation and maintenance cost, energy storage replacement cost and energy storage disposal cost, while the peak shaving income, policy operation subsidy and other incomes are calculated to determine the whole life cycle economic benefit of the optimal capacity configuration result.

[0041] The simulation verification results and economic evaluation data based on the optimal capacity configuration result are compared, and the scheme that meets the peak shaving demand, conforms to the grid connection national standard and has the optimal economic benefit is selected as the best energy storage capacity configuration scheme.

[0042] In the second aspect, the application provides a multi-time scale hybrid energy storage capacity configuration system, which comprises:

[0043] The data acquisition and preprocessing module is used for acquiring data according to the construction state of the wind farm, cleaning, smoothing and outlier processing the actual output power data of the built wind farm, fitting the power based on the wind resource and wind turbine model data of the proposed wind farm using the LSTM algorithm to obtain standard wind power output power data;

[0044] The difference calculation module is used for obtaining the local grid load curve or dispatching demand data, calculating the difference between the standard wind power output power data and the data, and integrating the difference according to the time sequence to generate the reference power curve of the energy storage system;

[0045] The power decomposition module is used for decomposing the standard wind power output power data into multiple frequency components using the SGMD decomposition algorithm, identifying multi-time scale power fluctuations based on the frequency components, synchronously extracting fluctuation parameters and integrating to generate multi-time scale fluctuation feature data;

[0046] The capacity configuration optimization module is used for setting the energy storage response time constraint based on the fluctuation feature data, optimizing the energy storage capacity using the immune mixed particle swarm algorithm, preferentially meeting the grid connection standard and the reference power curve requirement, secondly maximizing the economic benefit, and complying with the relevant constraints;

[0047] The simulation verification module is used for annual whole life cycle simulation of the optimized energy storage capacity configuration, verifying the multi-time scale fluctuation suppression effect and grid connection compliance, and evaluating the economic efficiency to determine the best energy storage capacity configuration scheme.

[0048] In a third aspect, the present application provides a multi-time scale hybrid energy storage capacity configuration device, comprising a memory and at least one processor, the memory storing instructions; the at least one processor invoking the instructions in the memory to enable the multi-time scale hybrid energy storage capacity configuration device to perform the multi-time scale hybrid energy storage capacity configuration method described above.

[0049] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to perform the multi-time scale hybrid energy storage capacity configuration method described above.

[0050] The present application proposes a multi-time scale hybrid energy storage capacity configuration method, system and storage medium, which is suitable for capacity configuration design of wind farm grid-connected supporting energy storage system, and can solve the problems of poor adaptability of existing energy storage configuration to multi-time scale fluctuations, insufficient accuracy of wind power output prediction, difficulty in balancing economy and functionality, and lack of effective verification mechanism. Compared with the prior art, the beneficial effects of the technical solution of the present application are at least as follows:

[0051] First, precise adaptation of multi-time scale is realized. The SGMD decomposition algorithm is used to split the wind power output into different frequency components, identify power fluctuations of multiple time scales from seconds, minutes to weeks and above, and configure energy storage capacity accordingly, so as to comprehensively suppress load fluctuations of each scale and ensure the operation stability of the power grid under different working conditions, avoiding the defect that single time scale configuration cannot cope with multi-scenario fluctuations.

[0052] Second, the reliability of wind power output data is improved. The actual power data of the existing wind farm is preprocessed, and the power of the proposed wind farm is fitted by using a deep learning algorithm (such as LSTM), so as to ensure that the standard wind power output data accurately reflects the actual situation and provides a reliable data basis for subsequent energy storage configuration, solving the problem of insufficient data accuracy affecting the configuration effect in the prior art.

[0053] Third, functionality and economy are optimized. The primary goal is to meet the national standard for wind power grid connection, and the secondary goal is to maximize economic benefits. The immune hybrid particle swarm algorithm is used to optimize the energy storage capacity, while considering constraints such as charging and discharging power and state of charge, to avoid problems such as high initial investment and uncontrolled operation and maintenance costs, and to achieve a balance between the functionality and economy of the energy storage system.

[0054] Fourth, the long-term effectiveness of the configuration scheme is ensured. The energy storage configuration scheme is verified through annual life cycle simulation, which verifies the effectiveness of multi-time scale fluctuation suppression, peak shaving demand, grid connection compliance, and life cycle economic benefits, ensuring that the scheme meets the standard in long-term operation, and solving the problem of lack of effective verification leading to insufficient practicality of the scheme in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0056] Figure 1 A flow chart of a multi-time scale hybrid energy storage capacity configuration method of the present application;

[0057] Figure 2 A structure diagram of a multi-time scale hybrid energy storage capacity configuration system of the present application;

[0058] Figure 3 A structure diagram of a multi-time scale hybrid energy storage capacity configuration device of the present application. DETAILED DESCRIPTION

[0059] The embodiments of the present application provide a multi-time scale hybrid energy storage capacity configuration method, system and storage medium. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variation thereof is intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0060] The present application relates to the technical field of data mining application, and discloses a multi-time scale hybrid energy storage capacity configuration method, system and storage medium. The method comprises the following steps: collecting data according to a wind farm construction state and preprocessing to obtain standard wind power output power data; obtaining local power grid load curve or dispatching demand data, calculating a difference to generate an energy storage reference power curve; splitting the power signal by using an SGMD decomposition algorithm, identifying multi-time scale power waves to generate feature data; setting constraints based on the feature data, and optimizing energy storage capacity configuration by using an immune hybrid particle swarm algorithm; performing full life cycle simulation on the optimization result, verifying the effect and compliance and evaluating the economy to determine the best scheme. The present application solves the problems of poor adaptability and insufficient economy of existing energy storage configuration through multi-time scale decomposition and closed-loop optimization, and improves the wind power grid stability and configuration economy.

[0061] For ease of understanding, the specific process of the embodiments of this application is described below. Please refer to [link / reference]. Figure 1 One embodiment of a multi-timescale hybrid energy storage capacity configuration method in this application includes:

[0062] Step S101: Collect data based on the construction status of the wind farm, preprocess the collected data, and obtain standard wind power output data.

[0063] In one specific embodiment, the process of performing step S101 may specifically include the following steps:

[0064] Determine the construction status of the wind farm, which includes both completed and planned status;

[0065] If the wind farm is already built, the actual output power data generated during its operation is directly collected. The actual output power data is then cleaned, smoothed, and outlier-handled to obtain the standard wind power output power data.

[0066] If the project is in the planning stage, local wind resource data and wind turbine model data from the tender are collected. Based on the local wind resource data and wind turbine model data from the tender, the wind power output power is fitted using the LSTM algorithm to obtain the standard wind power output power data of the proposed wind farm.

[0067] Specifically, for wind farms already in operation, it is necessary to collect actual output power data generated during their operation. The collection period should cover at least one year to include power variation characteristics under different seasons and weather conditions. The data collection frequency must meet the needs of subsequent multi-timescale analysis, reaching at least the second-level sampling rate. The collected actual output power data may contain abnormal jump values ​​due to sensor failures, zero or missing values ​​due to equipment maintenance shutdowns, and high-frequency noise caused by grid fluctuations. These data need to be processed. During data cleaning, abnormal fluctuation values ​​exceeding the rated power range of wind turbines are removed by setting a power threshold range. For zero values ​​generated during shutdowns, the shutdown period needs to be confirmed in conjunction with maintenance records before being marked or removed. For missing data values, linear interpolation or imputation using the mean of adjacent time periods is used to complete the data. Smoothing is performed using a moving average method with a 30-second sliding window to filter the cleaned data, reducing the impact of high-frequency noise on subsequent analysis. Outlier handling also requires identifying data points that deviate from the data mean by more than three times the standard deviation using the 3σ principle to further ensure data accuracy. After the above processing, standard wind power output power data is obtained, which can directly reflect the actual power output characteristics of the built wind farms.

[0068] For the proposed state of the wind farm, the local wind resource data and the tendered wind turbine model data need to be collected. The local wind resource data includes at least five years of wind speed, wind direction, air density and other data. The collection sites need to be distributed in multiple wind towers in the wind farm planning area to ensure that the data can represent the wind resource distribution of the entire wind farm. The tendered wind turbine model data includes technical parameters such as rated power, cut-in wind speed, cut-out wind speed, rated wind speed, and power curve. These parameters are provided by the wind turbine manufacturer and need to meet relevant industry standards. The wind speed data in the collected local wind resource data is associated with the power curve in the wind turbine model data. With wind speed as the input variable, the power curve is corrected by combining the air density. The theoretical power output corresponding to different wind speeds is calculated. The processed wind speed data and theoretical power output data are then input into the LSTM algorithm model as training samples. The LSTM algorithm constructs a neural network structure with input layer, hidden layer and output layer, and uses the gating unit (input gate, forget gate and output gate) to capture the long-time dependence between wind speed and power output. During the model training process, the wind speed-power data of an actual similar wind farm is used as the validation set. By adjusting the learning rate, the number of hidden layer neurons, the number of iterations and other parameters of the model, the mean square error of the predicted power and the actual power is minimized. After the model converges, the predicted wind speed data of the proposed wind farm for the next year is input into the trained LSTM model, and the standard wind power output data of the proposed wind farm is fitted. This data can predict the power output characteristics of the proposed wind farm in advance.

[0069] In step S102, the load curve or grid dispatch demand data of the local grid is obtained, and the difference between the standard wind power output data and the load curve or grid dispatch demand data is calculated to generate a reference power curve for the energy storage system.

[0070] In a specific embodiment, the process of step S102 can specifically include the following steps:

[0071] The difference between the standard wind power output data and the load curve data or the grid dispatch demand data is calculated at each time point;

[0072] The difference is integrated in time sequence to form the reference power curve, wherein the reference power curve is used to reflect the power gap between wind power output and grid load or dispatch demand; the load curve data includes daily periodic fluctuation data and seasonal fluctuation data, the daily periodic fluctuation data reflects the load change at different time periods within a day, and the seasonal fluctuation data reflects the overall level difference of load in different seasons.

[0073] Specifically, to obtain the load curve of the local power grid or the grid dispatching demand data, the local power grid dispatching center database needs to be connected. The load curve data needs to cover at least one year period and contain daily 24-hour load values. The data sampling interval needs to be consistent with the standard wind power output power data to ensure time dimension matching. The grid dispatching demand data needs to contain the power acceptance upper limit of the grid for wind power grid connection at different time periods, the peak shaving demand threshold and other parameters, which need to comply with the local grid operation regulations and national standards for wind power grid connection. In the load curve data, the daily periodic fluctuation data reflects the load changes at different time periods within a day, such as the load peaks at 8-10 am and 18-22 pm on weekdays due to industrial production and increased residential electricity consumption, and the load valleys at 2-6 am. The seasonal fluctuation data reflects the overall load level differences in different seasons, such as higher overall load level in summer due to air conditioning and refrigeration and in winter due to heating demand, which needs to be classified and extracted and labeled with time dimension information.

[0074] When calculating the difference between the standard wind power output power data and the load curve data or the grid dispatching demand data at each time, the timestamp is used as the matching basis. The standard wind power output power value at the same time is subtracted from the load value in the load curve data (or the power acceptance upper limit value in the grid dispatching demand data). If the standard wind power output power value is greater than the load value (or the power acceptance upper limit value), the difference is positive, representing excess wind power output, which needs to be stored in the energy storage system. If the standard wind power output power value is less than the load value (or the power acceptance upper limit value), the difference is negative, representing insufficient wind power output, which needs to be discharged by the energy storage system to supplement the power gap. If they are equal, the difference is zero, and the energy storage system does not need to act. Each set of time data needs to be verified one by one during the calculation process to avoid calculation errors caused by timestamp misplacement. For time points with abnormal difference (such as absolute value exceeding the maximum fluctuation range of the same period), it is necessary to check whether the standard wind power output power data and the load / dispaching data at the corresponding time are abnormal, and to recalculate after excluding data collection or transmission errors.

[0075] When integrating the difference by time sequence, the difference calculated at each time is arranged in sequence according to time sequence to form a continuous difference sequence, and then the sequence is converted into a reference power curve through a data visualization tool. The horizontal axis of the reference power curve is time (accurate to the same unit as the data sampling interval), and the vertical axis is power difference. Each point on the curve corresponds to the power gap or surplus at a specific time, which can directly reflect the dynamic balance relationship between wind power output and grid load / dispaching demand.

[0076] Step S103, decompose the standard wind power output data by using the SGMD decomposition algorithm, split into multiple frequency components, identify power fluctuations of different time scales of seconds, minutes, hours, days, weeks and above weeks based on the frequency components, and generate multi-time scale fluctuation feature data.

[0077] In a specific embodiment, the process of step S103 can specifically include the following steps:

[0078] Taking the standard wind power output as the decomposition object ensures that its time dimension matches the subsequent multi-time scale identification requirements, covering the time span of seconds, minutes, hours, days, weeks and above weeks;

[0079] The SGMD decomposition algorithm is used to decompose the standard wind power output signal, and the single power signal is split into multiple sub-signals with different frequency characteristics, each sub-signal corresponding to a power component of different fluctuation frequency;

[0080] Based on the frequency characteristics of each sub-signal, the corresponding time scale fluctuation feature is determined, wherein the high-frequency sub-signal corresponds to the second-level power fluctuation, the medium-high-frequency sub-signal corresponds to the minute-level power fluctuation, the medium-low-frequency sub-signal corresponds to the hour-level and day-level power fluctuation, and the low-frequency sub-signal corresponds to the week-level and above-week-level power fluctuation. The amplitude, duration and period parameters of each time scale fluctuation are extracted synchronously;

[0081] Integrate the identified time scale fluctuation features to generate the multi-time scale fluctuation feature data.

[0082] Specifically, the time dimension integrity of the standard wind power output is first verified to ensure that its time span covers seconds, minutes, hours, days, weeks and above weeks, and the data sampling frequency matches the requirements of each time scale identification, wherein the second-level data sampling interval is not greater than 1 second, the minute-level data sampling interval is not greater than 1 minute, and the hour-level to week-level and above data sampling can be calculated by aggregation based on the preprocessed data of the previous time scale, for example, the hour-level data is obtained by summing and averaging the minute-level preprocessed data, to ensure the comprehensiveness and accuracy of subsequent multi-time scale fluctuation identification.

[0083] The SGMD decomposition algorithm is used to decompose the standard wind power output signal. The SGMD decomposition algorithm is based on the theory of multi-scale geometric analysis. The core logic is to construct an adaptive basis function to split the single power signal into multiple sub-signals in order from high to low frequency. The process follows the energy conservation principle of signal decomposition, that is, the total energy of all sub-signals after decomposition is equal to the energy of the original standard wind power output signal. In the specific decomposition process, the standard wind power output signal is first initialized. The decomposition layer number and error threshold are set. The decomposition layer number is determined according to the number of time scales to be identified (in this embodiment, it is set to 5 layers, corresponding to seconds, minutes, hours, days, weeks and above). The error threshold is set to 5% of the energy of the original signal. Then through iterative calculation, the high-frequency component in the current signal is extracted as a sub-signal each time, and the remaining signal is used as the input of the next iteration, until the iteration number reaches the set decomposition layer number or the energy of the remaining signal is less than the error threshold. Finally, five sub-signals with different frequency characteristics are obtained, each corresponding to a power component with different fluctuation frequency.

[0084] Based on the frequency characteristics of each sub-signal, the corresponding time scale fluctuation characteristics are determined. The center frequency of each sub-signal is calculated by a spectrum analysis tool. The sub-signal with a center frequency greater than 1 Hz is a high-frequency sub-signal, corresponding to a second-level power fluctuation (such as a power fluctuation caused by instantaneous airflow changes of wind turbine blades). The sub-signal with a center frequency between 0.0167 Hz and 1 Hz is a medium-high frequency sub-signal, corresponding to a minute-level power fluctuation (such as a power fluctuation caused by short-time gusts). The sub-signal with a center frequency between 2.778×10⁻ 4 Hz and 0.0167 Hz is a medium-low frequency sub-signal, corresponding to an hour-level and day-level power fluctuation (such as a power fluctuation caused by diurnal wind speed changes and day-night temperature differences). The sub-signal with a center frequency less than 2.778×10⁻ 4 Hz is a low-frequency sub-signal, corresponding to a week-level and above-week-level power fluctuation (such as a power fluctuation caused by weekly weather changes and seasonal alternations).

[0085] The average power value in a complete fluctuation cycle of the sub-signal is taken as a power reference value, and the absolute value of the difference between the power peak value and the reference value is taken as the fluctuation amplitude; the time interval from the first deviation of the power from the reference value to the return to the reference value is monitored to obtain the duration; the time points of the two consecutive peaks or valleys are identified, the time difference is calculated, and the average value is taken as the period parameter. After extraction, the parameters are compared with the historical data of the corresponding time scale. If the amplitude deviation exceeds 10%-30% (threshold values are different for each time scale), the duration deviation exceeds 20%, or the period deviation exceeds 15%, the decomposition result is rechecked and the parameters are extracted again to ensure that the parameters meet the actual fluctuation characteristics. Finally, the fluctuation characteristics of each time scale (including sub-signal frequency range, fluctuation amplitude, duration, and period parameter) are integrated in order of time scale from small to large to generate multi-time scale fluctuation characteristic data, which provides data support for the optimization of energy storage capacity configuration in step S104.

[0086] In a specific embodiment, the step of synchronously extracting the amplitude, duration, and period parameter of the fluctuation of each time scale can specifically include the following steps:

[0087] Taking the sub-signal corresponding to each time scale as the extraction object, first determine the power reference value corresponding to each sub-signal, which takes the average power value of the corresponding sub-signal in a complete fluctuation cycle;

[0088] Calculate the absolute value of the difference between the power peak value of the sub-signal and the power reference value as the amplitude of the fluctuation of the corresponding time scale;

[0089] Monitor the complete time interval from the first deviation of the sub-signal power from the power reference value to the return to the power reference value, and the duration of the time interval is the duration of the fluctuation of the corresponding time scale;

[0090] For each sub-signal, identify the time points of the two consecutive power peaks or the two consecutive power valleys, calculate the time difference between the two adjacent peaks or the two adjacent valleys, and take the average value of multiple calculation results as the period parameter of the fluctuation of the corresponding time scale;

[0091] After the amplitude, duration, and period parameter are extracted, compare each parameter with the historical fluctuation parameter under the corresponding time scale. If the amplitude deviation exceeds the first preset value, or the duration deviation exceeds the second preset value, or the period deviation exceeds the third preset value, recheck the sub-signal decomposition result and extract the parameters again to ensure that the extracted parameters meet the actual characteristics of the fluctuation of the corresponding time scale.

[0092] Specifically, when synchronously extracting the amplitude, duration, and period parameter of the fluctuation of each time scale, taking the sub-signal corresponding to each time scale as the extraction object, first determine the power reference value corresponding to each sub-signal, which takes the average power value of the corresponding sub-signal in a complete fluctuation cycle, and the calculation formula is wherein This is a power reference value (unit: kW). The complete fluctuation period of the sub-signal (unit: s). For the sub-signal at time t The power value (unit: kW) is obtained by integration to obtain the average power level within the period, ensuring that the reference value can reflect the overall power characteristics of the sub-signal.

[0093] The absolute value of the difference between the peak power of the sub-signal and the power reference value is calculated as the amplitude of the fluctuation on the corresponding time scale. The calculation formula is as follows: ,in Fluctuation amplitude (unit: kW) The peak power (in kW) of the sub-signal within its fluctuation period is derived based on the definition of fluctuation amplitude in physics. Taking a high-frequency sub-signal corresponding to a second-level power fluctuation as an example, if within a certain period... ,but That is, the fluctuation range is 80kW on a second-level scale.

[0094] The monitoring sub-signal power is used to track the complete time interval from the first deviation from the power reference value to the return to the power reference value. The duration of this time interval is the duration of the fluctuation on the corresponding time scale. The time of the first deviation is recorded using a timestamp. With the moment of return The formula for calculating the duration is: ,in Duration (in seconds). This is a timestamp (unit: seconds), directly reflecting the duration of power fluctuations. For example, for mid-to-high frequency sub-signals corresponding to minute-level power fluctuations, the first deviation from the reference value occurs at [time missing]. The regression baseline time is ,but That is, the duration of minute-level fluctuations is 120 seconds.

[0095] For each sub-signal, identify the time points of two consecutive power peaks or two consecutive power troughs, calculate the time difference between two adjacent peaks or two adjacent troughs, and take the average of multiple calculations as the period parameter of the corresponding time scale fluctuation. The calculation formula is as follows: ,in The average period (unit: s). The number of peaks or valleys identified. For the first i The timestamps of each peak or trough (in seconds) are averaged through multiple sampling to reduce random errors. Taking the low-to-medium frequency sub-signal corresponding to daily power fluctuations as an example, five consecutive peak timestamps were identified as follows: The time differences are respectively The daily fluctuation period is 86400s.

[0096] After the amplitude, duration and period parameters are extracted, the parameters are compared with the historical fluctuation parameters under the corresponding time scale. If the amplitude deviation exceeds the first preset value (10%, 15%, 20%, 25%, 30% for seconds, minutes, hours, days, weeks and above, respectively), or the duration deviation exceeds the second preset value (20% for each time scale), or the period deviation exceeds the third preset value (15% for each time scale), the sub-signal decomposition result is rechecked and the parameters are extracted again to ensure that the extracted parameters meet the actual characteristics of the fluctuation under the corresponding time scale. The identified fluctuation characteristics of each time scale (including the frequency range, fluctuation amplitude, duration, period parameters of the corresponding sub-signal) are integrated and arranged in order from small to large according to the time scale to generate multi-time scale fluctuation characteristic data. This data needs to include the unique identifier of each time scale, the corresponding sub-signal number and the values of each fluctuation parameter, providing data support for subsequent energy storage capacity configuration optimization.

[0097] In step S104, based on the multi-time scale fluctuation characteristic data, the response time constraint of energy storage is set, and the immune mixed particle swarm algorithm is used to optimize the capacity configuration of each energy storage device to preferentially meet the wind power grid connection national standard and the reference power curve fluctuation requirement, secondly maximize the economic benefit, and comply with the energy storage charging and discharging power constraint, the energy storage capacity constraint, the state of charge constraint and the response time constraint.

[0098] In a specific embodiment, the process of step S104 can specifically include the following steps:

[0099] Based on the multi-time scale fluctuation characteristic data, M particles containing the capacity and power of each energy storage device are generated by logical mapping, and an initial antibody is also generated, which corresponds to the high-frequency or low-frequency compensation power and the reference power of the energy storage action respectively;

[0100] Based on the main target of meeting the wind power grid connection national standard and the secondary target of maximizing economic benefit, combined with the maximum fluctuation allowed after smoothing, the time vector and the full life cycle cost formula, the operation and maintenance present value is calculated to calculate the fitness of each particle;

[0101] Through the concentration selection mechanism, N particles with fitness meeting the requirements are selected from the M particles, combined with the newly generated N particles by logical mapping, a population containing M+N particles is formed to avoid the algorithm falling into local optimum;

[0102] According to the particle fitness, the position and speed of the particle are updated, the capacity, power parameters and optimization direction of each energy storage device are adjusted, and the local optimal solution and the global optimal solution are updated synchronously;

[0103] If the maximum number of iterations is reached or the global optimal position is obtained, stop the iteration and output the optimal capacity configuration result of each energy storage device, if not, return to the fitness calculation step to continue iteration;

[0104] The entire configuration process needs to follow the energy storage charge and discharge power constraints, energy storage capacity constraints, state of charge constraints, and response time constraints.

[0105] Specifically, first, the energy storage response time constraints are set based on the multi-time scale fluctuation feature data generated in step S103, wherein the energy storage response time constraint corresponding to the second-level power fluctuation is not more than 0.5 seconds, the minute-level is not more than 30 seconds, the hour-level is not more than 1 hour, and the day-level and above is not more than 12 hours, ensuring that the energy storage device action speed is adapted to the change rate of different time scale fluctuations.

[0106] When the immune mixed particle swarm algorithm is used to configure the capacity of each energy storage device, M particles are first generated by logical mapping, wherein the value of M is determined according to the type of energy storage device. If three types of devices, flywheel energy storage, lithium battery energy storage, and compressed air energy storage, are configured, M is set to 30, and the particle is a 6-row 30-column matrix. Each row corresponds to the capacity (unit: kWh) and power (unit: kW) parameters of the three types of energy storage devices, respectively, i.e., the elements in the matrix are flywheel energy storage capacity, flywheel energy storage power, lithium battery energy storage capacity, lithium battery energy storage power, compressed air energy storage capacity, and compressed air energy storage power. At the same time, the initial antibody is generated, the number of initial antibodies is consistent with the number of particles, and each antibody corresponds to the high-frequency compensation power (adapted to the second-level and minute-level fluctuations), the low-frequency compensation power (adapted to the hour-level and above fluctuations), and the energy storage action reference power. The reference power is based on the reference power curve generated in step S102, and the average value of the absolute value of the power gap in each period is taken.

[0107] The fitness function needs to reflect the main target of meeting the national standard for wind power grid connection and the secondary target of maximizing economic benefits. The fitness function is constructed as formula (1):

[0108] (1)

[0109] wherein, F is the particle fitness value, α is the main target weight (value 0.8), β is the secondary target weight (value 0.2), and α+β=1 to ensure that the weight distribution is reasonable; is the main target function value, reflecting the degree of satisfaction of the energy storage configuration scheme with the national standard for wind power grid connection; is the secondary target function value, reflecting the economic benefit level of the energy storage configuration scheme.

[0110] For the main target function According to the reference wind power grid connection and other national standards, the fluctuation of the energy storage reference power curve after energy storage smoothing meets the requirements of grid connection, combined with the specific provisions of "wind power grid connection power fluctuation within 1 minute not more than 10% of the rated power, within 1 hour not more than 15% of the rated power" in "GB / T 19963.1-2021 Technical Regulation for Access of Wind Farms to Power Systems", as shown in formula (2):

[0111] (2)

[0112] Wherein, Δ P P is the degree of fluctuation after smoothing, if the 1-minute fluctuation after smoothing is ≤10% and the 1-hour fluctuation is ≤15%, then ΔP=0, =100; if the 1-minute fluctuation exceeds the standard by 1% or the 1-hour fluctuation exceeds the standard by 1%, then ΔP increases by 1, and γ is the penalty coefficient (value 5), which indicates that every 1% exceeding the standard, deduct 5 points, the minimum =0.

[0113] In specific calculation, the energy storage configuration scheme corresponding to the particle is substituted into the reference power curve generated in step S102 to simulate the energy storage charging and discharging process to smooth the power curve, for example, the 1-minute power fluctuation of a particle configuration scheme after smoothing is 8% (≤10%), and the 1-hour power fluctuation is 12% (≤15%), then Δ P P=0, =100; if another particle configuration scheme after smoothing has a 1-minute power fluctuation of 12% (exceeding the standard by 2%) and a 1-hour power fluctuation of 16% (exceeding the standard by 1%), then Δ P P=2+1=3, =100-5×3=85.

[0114] The secondary objective function is calculated according to the life cycle cost and benefit model, which clearly shows that the life cycle cost includes initial investment cost, operation and maintenance cost, replacement cost, and disposal cost, and the benefit includes peak regulation benefit and policy operation subsidy. First, calculate the net benefit (NPV) of the life cycle, and then normalize the net benefit to value, as shown in formula (3):

[0115] (3)

[0116] Wherein, NPV is the net benefit of the particle corresponding configuration scheme, NPV=life cycle benefit-life cycle cost; is the minimum net benefit among all particles, is the maximum net benefit among all particles, and NPV is mapped to 0-100 by linear normalization The normalization process ensures that net gains of different magnitudes can be converted into fitness scores of a uniform dimension, facilitating comparisons between particles.

[0117] The calculation of total life-cycle benefits is as follows:

[0118] Peak shaving revenue = peak shaving power × peak shaving price × annual peak shaving duration × lifespan. For example, if the peak shaving power is 200kW, the peak shaving price is 0.5 yuan / kWh, the annual peak shaving duration is 3000h, and the lifespan is 20 years, the peak shaving revenue = 200 × 0.5 × 3000 × 20 = 6,000,000 yuan.

[0119] Policy subsidy = annual subsidy amount × lifespan. For example, if the annual subsidy is 100,000 yuan, the total subsidy over 20 years = 100,000 × 20 = 2,000,000 yuan.

[0120] Therefore, the total life-cycle revenue = 6,000,000 + 2,000,000 = 8,000,000 yuan.

[0121] The life cycle cost is calculated as follows:

[0122] Initial investment cost: ,in For initial investment costs, The unit power investment cost The unit capacity investment cost For the configured energy storage rated power, This refers to the rated capacity of the configured energy storage. If using flywheel energy storage: =1000 yuan / kW =500 yuan / kWh, configuration =500kW =1000kWh, then the initial investment cost of the flywheel = 1000×500 + 500×1000 = 1,000,000 yuan; if lithium battery energy storage: The initial investment cost of lithium batteries Yuan; if compressed air is used for energy storage: Therefore, the initial investment cost of compressed air = 1000 × 400 + 300 × 1500 = 850,000 yuan; the total initial investment cost of the three types of equipment = 1,000,000 + 900,000 + 1,620,000 = 2,750,000 yuan.

[0123] The calculation of operation and maintenance costs is as follows:

[0124] Discounted present value of maintenance (NC) = Annual maintenance cost × ,in r Let 8% be the discount rate and T be the maintenance lifespan, set to 20 years. Then the discounted present value of maintenance = ≈981814 yuan;

[0125] The replacement cost is calculated as follows:

[0126] wherein is the replacement cost, is the unit capacity investment cost, is the configured energy storage rated capacity, if the lithium battery is replaced once every 5 years, and the physical energy storage does not need to be replaced for 20 years, then the lithium battery is replaced 3 times in 20 years, and the lithium battery replacement cost = 400 x 1500 x 3 = 1800000 yuan;

[0127] The disposal cost is calculated as follows:

[0128] The disposal cost = equipment residual value deduction, the total disposal cost of three types of equipment is 200000 yuan;

[0129] The life cycle cost = 2750000 + 9818147 + 1800000 + 200000 = 5731814 yuan.

[0130] According to the above, NPV = 8000000 - 5731814 = 2268186 yuan, if all particles are , yuan, then .

[0131] Substitute into the fitness function, we get , that is, the fitness value of the particle is .

[0132] Screen particles through the concentration selection mechanism, calculate the concentration of each particle (concentration = number of particles with a fitness difference of <5 from the particle / total number of particles), screen out N particles with a concentration <10% and a top 10 fitness (N = 10), and then generate 10 new particles from the logical mapping (parameter value range is 80%-120% of the existing particle parameters), forming a population of M+N = 40 particles. Update the particle position and velocity according to the particle fitness, the position update follows the classical particle swarm algorithm, and the velocity update introduces the antibody promotion and inhibition mechanism. For particles with a fitness ≥80, the velocity adjustment coefficient is set to 1.2 (promote closer to the optimal solution); for particles with a fitness <60, the velocity adjustment coefficient is set to 0.8 (suppress ineffective search), and the local optimal solution (particle historical highest fitness corresponding parameters) and global optimal solution (all particle historical highest fitness corresponding parameters) are updated synchronously. If the number of iterations reaches 100 or the global optimal solution does not change for 10 consecutive iterations, stop iteration and output the optimal capacity configuration result; if not, return to the fitness calculation step and continue iteration. The entire process must follow the constraint condition: the energy storage charging and discharging power constraint is , the energy storage capacity constraint is , the state of charge constraint is 20%≤SOC≤80%, and the response time constraint is implemented according to the foregoing.

[0133] Step S105, annual full life cycle simulation is performed on the optimized energy storage capacity configuration to verify the effect of suppressing load fluctuation, meeting peak shaving demand and the compliance with the wind power grid connection national standard at different time scales, and to evaluate the economy to determine the optimal energy storage capacity configuration scheme.

[0134] In an embodiment, the process of performing step S105 can specifically include the following steps:

[0135] Based on the optimal capacity configuration result, a simulation model covering the full life cycle of the energy storage system is constructed, and the model input includes the multi-time scale fluctuation characteristic data, the reference power curve, and the charging and discharging efficiency and life attenuation parameters of the energy storage device;

[0136] The functionality and compliance are verified through annual simulation, wherein the functionality is verified by detecting the effect of the optimal capacity configuration result on suppressing load fluctuation at the time scales of seconds, minutes, hours, days, weeks and above, and determining whether the grid peak shaving demand is met, and the compliance is verified by comparing the smoothed power curve of the energy storage obtained through simulation with the wind power grid connection national standard to confirm whether the grid connection requirement is met;

[0137] The cost of the optimal capacity configuration result in the full life cycle is calculated, including the initial investment cost, operation and maintenance cost, energy storage replacement cost and energy storage disposal cost, while the peak shaving income, policy operation subsidy and other incomes are calculated, and the full life cycle economic benefit of the optimal capacity configuration result is determined;

[0138] The simulation verification results and economic evaluation data based on the optimal capacity configuration result are compared, and the scheme that meets the peak shaving demand, conforms to the grid connection national standard and has the optimal economic benefit is selected as the optimal energy storage capacity configuration scheme.

[0139] Specifically, according to the optimal capacity configuration result, a simulation model covering the whole life cycle of the energy storage system is constructed, and the model input needs to be accurately matched with the multi-time scale analysis demand. Among them, the multi-time scale fluctuation characteristic data adopts the data set containing the fluctuation amplitude, duration and period parameters of seconds, minutes, hours, days, weeks and above generated in step S103, which is directly related to the fluctuation characteristics that the energy storage device needs to cope with under each time scale; the energy storage reference power curve uses the time series data generated in step S102 reflecting the power gap between wind power output and load / scheduling demand, which provides a benchmark basis for the energy storage charging and discharging action in the simulation; the charging and discharging efficiency and life attenuation parameters of the energy storage device are set in combination with common energy storage technology characteristics, such as flywheel energy storage charging and discharging efficiency 92%, annual life attenuation rate 0.5%, lithium battery energy storage charging and discharging efficiency 88%, annual life attenuation rate 3%, compressed air energy storage charging and discharging efficiency 75%, annual life attenuation rate 1%, to ensure that the model input data is consistent with the actual energy storage device operation characteristics, laying a foundation for simulation accuracy.

[0140] When verifying functionality and compliance through annual simulation, the simulation period is set to the benchmark life of 20 years of the energy storage system, and the simulation step is determined according to the sampling interval of each time scale fluctuation. The 1-second step is used for second-level fluctuations, the 1-minute step is used for minute-level fluctuations, the 1-hour step is used for hour-level fluctuations, and the corresponding time unit step is used for day-level and above, to ensure that the simulation process can accurately capture the dynamic changes of fluctuations at each scale. In the process of verifying functionality, the parameters such as capacity, power and response time of each energy storage device in the optimal capacity configuration scheme are substituted into the simulation model to simulate the energy storage charging and discharging action under different time scale fluctuations, such as second-level power fluctuation triggering flywheel energy storage to complete charging and discharging response within ≤0.5 seconds, and hour-level power fluctuation triggering lithium battery energy storage and compressed air energy storage to cooperate with charging and discharging. By monitoring the power curve of each time scale output by the simulation in real time, the amplitude and duration of the flattened power fluctuation are calculated. If the second-level fluctuation amplitude is ≤2%, the minute-level fluctuation is ≤5%, and the hour-level and above fluctuation is ≤10%, it is determined that the grid peak shaving demand is met. In the process of verifying compliance, the smoothed power curve of the energy storage obtained by simulation is compared with the provisions of "1-minute power fluctuation ≤10%, 1-hour power fluctuation ≤15%" in the national standard for wind power grid connection. If the fluctuations in all time periods of the curve meet the standard provisions, it is determined that the grid connection is compliant.

[0141] When calculating the economic benefits over the entire life cycle, cost and benefit calculations must be based on clear formulas and parameters. For cost accounting, the initial investment cost is calculated as "Initial Investment Cost = Unit Power Investment Cost × Rated Power + Unit Capacity Investment Cost × Rated Capacity". For example, a flywheel energy storage system with a rated power of 500kW and a rated capacity of 1000kWh, a unit power investment cost of 2000 yuan / kW, and a unit capacity investment cost of 500 yuan / kWh, has an initial investment cost of 2000 × 500 + 500 × 1000 = 1,500,000 yuan. Lithium battery energy storage and compressed air energy storage are calculated using the same formula and then summed. Operation and maintenance costs are calculated as "Discounted Value of Operation and Maintenance = Annual Operation and Maintenance Cost ×..." "Calculate the discount rate" r Take 8%, lifespan T Taking a 20-year period, the annual operation and maintenance cost is 100,000 yuan (total of the three types of equipment). Substituting into the formula, the present value of operation and maintenance is approximately 981,814 yuan. The replacement cost of energy storage is calculated as replacement cost = unit capacity investment cost × rated capacity × number of replacements. Lithium batteries are replaced once every 5 years, and physical energy storage does not need to be replaced for 20 years. Therefore, lithium batteries are replaced 3 times in 20 years. If the rated capacity of lithium batteries is 1500kWh and the unit capacity investment cost is 400 yuan / kWh, the replacement cost is 400 × 1500 × 3 = 1,800,000 yuan. The disposal cost is calculated according to the equipment residual value deduction rule, totaling 200,000 yuan for the three types of equipment. The total cost is the sum of the above costs. In terms of revenue calculation, peak shaving revenue is calculated as peak shaving revenue = peak shaving power × peak shaving price × annual peak shaving duration × lifespan. For example, if the annual peak shaving power is 200kW, the peak shaving price is 0.5 yuan / kWh, and the annual peak shaving duration is 3000h, then the peak shaving revenue over 20 years is 200 × 0.5 × 3000 × 20 = 6,000,000 yuan. Policy operation subsidies are calculated as policy subsidies = annual subsidy amount × lifespan. If the annual subsidy is 100,000 yuan, the total subsidy over 20 years is 2,000,000 yuan. The total revenue is the sum of peak shaving revenue and subsidies. The economic benefit over the entire life cycle = total revenue - total cost.

[0142] When comparing simulation verification results and economic evaluation data based on various optimal capacity configurations, at least three differentiated configuration schemes need to be generated. These may include adjusting the capacity ratio of flywheel energy storage and lithium battery energy storage, and the power parameters of compressed air energy storage. The simulation and calculation process described above is repeated for each scheme to obtain the functional compliance rate (peak-shaving demand satisfaction rate, grid connection compliance rate) and economic indicators (net life-cycle return, investment payback period) for each scheme. Based on the optimization logic of prioritizing compliance with national wind power grid connection standards and reference power curve fluctuation requirements, and then maximizing economic benefits, the scheme with a 100% functional compliance rate is selected first. Then, the scheme with the highest net life-cycle return among the compliant schemes is chosen as the optimal energy storage capacity configuration scheme.

[0143] The above describes a multi-time scale hybrid energy storage capacity configuration method in an embodiment of the application. The following describes a multi-time scale hybrid energy storage capacity configuration system 200 in an embodiment of the application. Please refer to Figure 2 An embodiment of the multi-time scale hybrid energy storage capacity configuration system 200 in the embodiment of the application includes:

[0144] The data acquisition and preprocessing module 201 is configured to acquire data according to the construction state of the wind farm, clean, smooth and process outliers of the actual output power data of the built wind farm, and fit the power based on the wind resource and wind turbine model data of the proposed wind farm using the LSTM algorithm to obtain standard wind power output data.

[0145] The difference calculation module 202 is configured to obtain the local grid load curve or dispatching demand data, calculate the difference between the standard wind power output data and the data, and integrate the difference according to the time sequence to generate a reference power curve of the energy storage system.

[0146] The power decomposition module 203 is configured to decompose the standard wind power output data into multiple frequency components using the SGMD decomposition algorithm, identify multi-time scale power fluctuations based on the frequency components, and simultaneously extract fluctuation parameters and integrate to generate multi-time scale fluctuation feature data.

[0147] The capacity configuration optimization module 204 is configured to set a response time constraint of the energy storage based on the fluctuation feature data, optimize the energy storage capacity using the immune hybrid particle swarm algorithm, preferentially meet the grid connection standards and reference power curve requirements, secondarily maximize economic benefits, and comply with relevant constraints.

[0148] The simulation verification module 205 is configured to perform annual full life cycle simulation on the optimized energy storage capacity configuration, verify the multi-time scale fluctuation suppression effect and grid connection compliance, evaluate the economic efficiency to determine the optimal energy storage capacity configuration scheme.

[0149] The above Figure 2 The following describes a multi-time scale hybrid energy storage capacity configuration device 300 in an embodiment of the application from the perspective of hardware processing.

[0150] Referring to Figure 3 The embodiment of the application further provides a multi-time scale hybrid energy storage capacity configuration device 300. The multi-time scale hybrid energy storage capacity configuration device can be a server, and the internal structure thereof can be as shown in Figure 3The multi-time scale hybrid energy storage capacity configuration device shown. The multi-time scale hybrid energy storage capacity configuration device includes a processor 302, a memory 303, a display screen 304, an input device 305, a network interface 306 and a database 307 connected through a system bus 301. Among them, the processor 302 of the computer design is used to provide computing and control ability. The memory 303 of the multi-time scale hybrid energy storage capacity configuration device includes a non-volatile storage medium 3031 and an internal memory 3032. The non-volatile storage medium 3031 stores an operating system and a computer program. The internal memory 3032 provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database 307 of the multi-time scale hybrid energy storage capacity configuration device is used to store the corresponding data in this embodiment. The network interface 306 of the multi-time scale hybrid energy storage capacity configuration device is used to communicate with the external terminal through the network connection. The computer program executed by the processor can realize the above method.

[0151] Those skilled in the art can understand that, Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the multi-time scale hybrid energy storage capacity configuration device to which the scheme of the present application is applied.

[0152] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium, and can also be a volatile computer readable storage medium, and the computer readable storage medium stores instructions, when the instructions run on the computer, make the computer execute the steps of the multi-time scale hybrid energy storage capacity configuration method.

[0153] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-mentioned system, system and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0154] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical scheme of the present application essentially or the part that contributes to the prior art or the whole or part of the technical scheme can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a multi-time scale hybrid energy storage capacity configuration device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and various media that can store program codes.

[0155] The above examples are only used to illustrate the technical solutions of the present application, but not to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A multi-time scale hybrid energy storage capacity configuration method, characterized in that, The method comprises the following steps: Step S101, collecting data according to the construction state of a wind farm, and preprocessing the collected data to obtain standard wind power output data; Step S102, obtaining a load curve or grid dispatch demand data of a local power grid, calculating the difference between the standard wind power output data and the load curve or grid dispatch demand data, and generating a reference power curve of an energy storage system; Step S103, decomposing the standard wind power output data by using an SGMD decomposition algorithm, splitting it into multiple frequency components, identifying power fluctuations of different time scales such as seconds, minutes, hours, days, and weeks or more based on the frequency components, and generating multi-time scale fluctuation feature data; Step S104, setting an energy storage response time constraint based on the multi-time scale fluctuation feature data, and optimizing the capacity configuration of each energy storage device by using an immune mixed particle swarm algorithm to preferentially meet the wind power grid connection national standard and the reference power curve fluctuation requirement, secondly maximize economic benefits, and follow the energy storage charging and discharging power constraint, energy storage capacity constraint, state of charge constraint, and response time constraint; the wind power grid connection national standard refers to that the wind power grid connection power fluctuation is not more than 10% of the rated power within 1 minute, and not more than 15% of the rated power within 1 hour; Step S105, simulating the annual life cycle of the optimized energy storage capacity configuration, verifying its effect of suppressing load fluctuations, meeting peak shaving demand, and meeting the wind power grid connection national standard at different time scales, and evaluating the economy to determine the best energy storage capacity configuration scheme; In the step S103, the standard wind power output is taken as the decomposition object to ensure that its time dimension matches the subsequent multi-time scale identification requirements and covers time spans of seconds, minutes, hours, days, and weeks or more; an SGMD decomposition algorithm is used to decompose the standard wind power output signal, splitting a single power signal into multiple sub-signals with different frequency characteristics, each sub-signal corresponding to a power component of different fluctuation frequency; the time scale fluctuation characteristics corresponding to each sub-signal are determined based on the frequency characteristics of the sub-signals, wherein high-frequency sub-signals correspond to second-level power fluctuations, medium-high-frequency sub-signals correspond to minute-level power fluctuations, medium-low-frequency sub-signals correspond to hour-level and day-level power fluctuations, and low-frequency sub-signals correspond to week-level or more power fluctuations; the amplitude, duration, and period parameters of each time scale fluctuation are extracted synchronously; and the identified time scale fluctuation characteristics are integrated to generate the multi-time scale fluctuation feature data. The step S105 comprises: based on the optimal capacity configuration result, constructing a simulation model covering the whole life cycle of the energy storage system, the optimal capacity configuration result being obtained by capacity configuration optimization of each energy storage device based on the immune mixed particle swarm algorithm, the model input containing the multi-time scale fluctuation characteristic data, the reference power curve, and the charging and discharging efficiency and life attenuation parameters of the energy storage device; verifying functionality and compliance through annual simulation, wherein the verification of functionality is to determine whether the optimal capacity configuration result meets the grid peak shaving demand by detecting the effect of the optimal capacity configuration result on load fluctuation at time scales of seconds, minutes, hours, days, and weeks or more, and the verification of compliance is to confirm whether the power curve after energy storage smoothing obtained through simulation meets the grid connection requirements by comparing the power curve after energy storage smoothing with the national standard for wind power grid connection; calculating the cost of the optimal capacity configuration result within the whole life cycle, including initial investment cost, operation and maintenance cost, energy storage replacement cost, and energy storage disposal cost, while calculating the peak shaving income and policy operation subsidy income to determine the whole life cycle economic benefit of the optimal capacity configuration result; comparing the simulation verification results and economic evaluation data of multiple schemes based on the optimal capacity configuration result to screen out the scheme that meets the peak shaving demand, meets the national grid connection standard, and has the optimal economic benefit as the best energy storage capacity configuration scheme.

2. The method of claim 1, wherein, The step S101 comprises: judging the construction state of the wind farm, the construction state including the built state and the proposed state; if in the built state, directly collecting actual output power data generated in the operation process of the wind farm, performing cleaning, smoothing processing, and outlier processing on the actual output power data to obtain the standard wind power output power data; if in the proposed state, collecting local wind resource data and bid wind turbine model data, fitting wind power output based on the local wind resource data and the bid wind turbine model data through the LSTM algorithm to obtain the standard wind power output power data of the proposed wind farm.

3. The method of claim 1, wherein, The load curve data contains daily periodic fluctuation data and seasonal fluctuation data, the daily periodic fluctuation data reflecting load changes at different times within a day, and the seasonal fluctuation data reflecting overall level differences of load in different seasons, and the step S102 comprises: calculating the difference between the standard wind power output power data and the load curve data or the grid dispatching demand data at each time point; integrating the difference in time sequence to form the reference power curve, wherein the reference power curve is used to reflect the power gap between wind power output power and grid load or dispatching demand.

4. The method of claim 1, wherein, The step of synchronously extracting the amplitude, duration, and period parameters of fluctuations at each time scale comprises: taking each time scale corresponding sub-signal as the extraction object, first determining the power reference value corresponding to each sub-signal, the power reference value taking the average power value of the corresponding sub-signal within a complete fluctuation period; calculating the absolute value of the difference between the sub-signal power peak value and the power reference value as the amplitude of the fluctuation at the corresponding time scale; The complete time interval from the first deviation of the sub-signal power from the power reference value to the return to the power reference value is the duration of the corresponding time scale fluctuation; For each sub-signal, the time points of the two consecutive power peaks or the two consecutive power valleys are identified, the time difference between the two adjacent peaks or the two adjacent valleys is calculated, and the average of multiple calculation results is taken as the period parameter of the corresponding time scale fluctuation; After the amplitude, duration and period parameters are extracted, each parameter is compared with the historical fluctuation parameter under the corresponding time scale. If the amplitude deviation exceeds the first preset value, or the duration deviation exceeds the second preset value, or the period deviation exceeds the third preset value, the sub-signal decomposition result is rechecked and the parameters are extracted again to ensure that the extracted parameters meet the actual characteristics of the corresponding time scale fluctuation.

5. The method of claim 1, wherein, The step S104 comprises: Based on the multi-time scale fluctuation feature data, M particles are generated by logical mapping, and the particles are matrices containing the capacities and powers of each energy storage device; Based on the main target of meeting the national standard for wind power grid connection and the secondary target of maximizing economic benefits, combined with the allowed maximum fluctuation after smoothing, the time vector and the full life cycle cost formula, the operation and maintenance discounted present value, the fitness of each particle is calculated; N particles with required fitness are selected from the M particles through a concentration selection mechanism, combined with N newly generated particles by logical mapping, a population containing M+N particles is formed to avoid the algorithm falling into local optimum; The position and speed of the particles are updated according to the fitness of the particles, the capacity, power parameters and optimization direction of each energy storage device are adjusted, and the local optimal solution and the global optimal solution are updated synchronously; If the maximum iteration number is reached or the global optimal position is obtained, the iteration is stopped and the optimal capacity configuration result of each energy storage device is output, if not, the fitness calculation step is returned to continue iteration; The entire configuration process needs to follow the constraints of energy storage charging and discharging power, energy storage capacity, state of charge and response time.

6. A multi-time scale hybrid energy storage capacity configuration system, characterized in that, A multi-time scale hybrid energy storage capacity configuration system for implementing the multi-time scale hybrid energy storage capacity configuration method according to any one of claims 1-5, the multi-time scale hybrid energy storage capacity configuration system comprising: A data acquisition and preprocessing module, configured to acquire data according to the construction state of a wind farm, clean, smooth and process outliers of actual output power data of the built wind farm, acquire local wind resource data and bid wind turbine model data of the proposed wind farm, fit wind power output power based on the local wind resource data and the bid wind turbine model data through an LSTM algorithm, and obtain the standard wind power output power data of the proposed wind farm; A difference calculation module, configured to acquire local grid load curve or dispatching demand data, calculate the difference between the standard wind power output power data and the load curve or grid dispatching demand data, and integrate the difference according to time sequence to generate a reference power curve of the energy storage system; A difference calculation module, configured to acquire local grid load curve or dispatching demand data, calculate the difference between the standard wind power output power data and the load curve or grid dispatching demand data, and integrate the difference according to time sequence to generate a reference power curve of the energy storage system; The power decomposition module adopts an SGMD decomposition algorithm to perform signal decomposition on the standard wind power output power, splits a single power signal into multiple sub-signals with different frequency characteristics, and each sub-signal corresponds to a power component with different fluctuation frequencies; based on the frequency characteristics of each sub-signal, the corresponding time scale fluctuation characteristics are determined, and the amplitude, duration and period parameters of each time scale fluctuation are synchronously extracted; the identified time scale fluctuation characteristics are integrated to generate the multi-time scale fluctuation characteristic data; The capacity configuration optimization module is configured to set energy storage response time constraints based on the multi-time scale fluctuation characteristic data, and to perform capacity configuration optimization on each energy storage device using an immune mixed particle swarm algorithm to preferentially meet the wind power grid connection national standards and the reference power curve fluctuation requirements, secondly maximize economic benefits, and comply with the energy storage charging and discharging power constraints, energy storage capacity constraints, state of charge constraints and response time constraints; The simulation verification module is configured to perform annual full life cycle simulation on the optimized energy storage capacity configuration, verify the effect of suppressing load fluctuation, meeting peak shaving demand and the conformity of the wind power grid connection national standards at different time scales, and evaluate the economy to determine the best energy storage capacity configuration scheme.

7. A multi-time scale hybrid energy storage capacity configuration device, characterized by, The computer program is stored in the memory and can be run on the processor, and the processor implements the multi-time scale hybrid energy storage capacity configuration method of any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is stored in the memory and can be run on the processor, and the processor implements the multi-time scale hybrid energy storage capacity configuration method of any one of claims 1 to 5 when executing the computer program.

Images