Power supply and generation regulation and control method based on light-storage integrated new energy microgrid

Abstract

The invention relates to the technical field of power supply and generation of micro-grids, and provides a power supply and generation regulation and control method based on an optical storage and utilization integrated new energy micro-grid, which comprises the following steps of: acquiring initial real-time operation data of the new energy micro-grid, preprocessing the initial real-time operation data to obtain real-time operation data, and storing the real-time operation data in a database; based on the photovoltaic power generation prediction model, the real-time photovoltaic power generation data and the real-time meteorological data, predicting the photovoltaic power generation capacity change trend of the new energy microgrid, and based on the load demand prediction model and the real-time load data, predicting the load demand change trend of the new energy microgrid. Performing harmonic analysis on the new energy microgrid based on the voltage and current waveform data to obtain a total harmonic distortion rate; generating a multi-target scheduling scheme based on a multi-target optimization algorithm, the real-time operation data and the prediction data; and performing priority management on the system load of the new energy micro-grid based on the multi-target scheduling scheme, and regulating and controlling the power supply and generation strategy of the new energy micro-grid. According to the invention, comprehensive optimization regulation and control of photovoltaic power generation, energy storage, load requirements and harmonic distortion of the new energy micro-grid are realized, and integration of light, storage and utilization of the new energy micro-grid is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply and generation of microgrids, and in particular to a power supply and generation control method based on a photovoltaic storage and utilization integrated new energy microgrid. Background Art

[0002] Microgrids can operate in two different modes: island mode and grid-connected mode. In the traditional control mode, although the system can run relatively smoothly and maintain stable output, there will be large system disturbances when the microgrid is off the grid. In addition, the power generation of renewable energy is volatile, and the load is time-varying. Therefore, a high total harmonic distortion rate will be generated in the system. A large amount of harmonics will damage the components in the system, and at the same time, the output voltage and current waveforms will be distorted and cannot be adjusted to the rated output, which seriously affects the power quality in the system.

[0003] The existing technology generally optimizes and adjusts the charging and discharging of the energy storage system in the microgrid to achieve precise control and optimization of the charging and discharging of the energy storage in the new energy microgrid. However, due to the volatility of new energy generation, when the load is high, the system is in a high voltage state, which will produce a high total harmonic distortion rate. The existing charging and discharging control method has a slow response speed and cannot effectively reduce the total harmonic distortion rate. Summary of the invention

[0004] In view of this, the present invention proposes a power supply and generation control method based on an integrated photovoltaic, energy storage and use new energy microgrid. By acquiring and preprocessing real-time operation data, photovoltaic power generation and load demand are predicted using a photovoltaic power generation prediction model and a load demand prediction model, and harmonic analysis is performed on current and voltage data. A scheduling plan is generated using a multi-objective optimization algorithm, and the state of the new energy microgrid is monitored in real time to control the power supply and generation strategy. The method realizes the comprehensive optimization control of photovoltaic power generation, energy storage, load demand and harmonic distortion of the new energy microgrid, as well as the photovoltaic, energy storage and use integration of the new energy microgrid, which solves the problems of power generation volatility, load time-varying and harmonic distortion in the new energy microgrid.

[0005] The technical solution of the present invention is implemented as follows: The present invention provides a power supply and generation control method based on an integrated photovoltaic storage and utilization new energy microgrid, comprising the following steps: S1, obtaining initial real-time operation data of the new energy microgrid, preprocessing the initial real-time operation data to obtain real-time operation data, wherein the real-time operation data includes voltage and current waveform data, real-time photovoltaic power generation data, real-time meteorological data and real-time load data; S2, based on the photovoltaic power generation prediction model, real-time photovoltaic power generation data and real-time meteorological data, predict the change trend of photovoltaic power generation of the new energy microgrid, based on the load demand prediction model and real-time load data, predict the change trend of load demand of the new energy microgrid, and perform harmonic analysis on the new energy microgrid based on the voltage and current waveform data to obtain the total harmonic distortion rate; S3, generating a multi-objective scheduling scheme based on a multi-objective optimization algorithm, real-time operation data and forecast data, wherein the forecast data includes a photovoltaic power generation change trend, a load demand change trend and a total harmonic distortion rate, and the optimization targets of the multi-objective scheduling scheme include a photovoltaic power generation change trend, an energy storage power value, a load demand change trend and a total harmonic distortion rate; S4, real-time monitoring of the current energy storage value, current photovoltaic power generation, current load output and current total harmonic distortion rate of the new energy microgrid, and adjusting the power supply and generation strategy of the new energy microgrid based on the multi-objective scheduling scheme, current energy storage value, current photovoltaic power generation, current load output and current total harmonic distortion rate.

[0006] On the basis of the above technical solution, preferably, step S1 includes: Preprocessing the initial real-time operation data, wherein the preprocessing includes data cleaning, outlier removal, data formatting and data standardization; The data cleaning includes filling missing values ​​using polynomial interpolation; The removing of outliers includes identifying outliers using the interquartile range method; The data formatting includes converting different formats of date and time into a unified format, converting different measurement units into a unified measurement unit, and converting all text data into a unified character encoding format; The data standardization includes converting the data using Z-score standardization.

[0007] On the basis of the above technical solution, preferably, the construction process of the photovoltaic power generation prediction model is: Acquire historical photovoltaic power generation data and historical meteorological data, and clean the historical photovoltaic power generation data and historical meteorological data to process missing values ​​and abnormal values; The seasonal variation coefficient is extracted by time series decomposition method, and the unit root test is performed on the difference between the historical photovoltaic power generation data and the seasonal variation coefficient. When the sequence of the difference is non-stationary, the historical photovoltaic power generation data and the seasonal variation coefficient are differentially processed to obtain the photovoltaic power generation difference component, and the sequence autocorrelation function diagram and partial autocorrelation function diagram of the photovoltaic power generation difference component are plotted. According to the characteristics of the sequence autocorrelation function diagram and the partial autocorrelation function diagram, the initial autoregressive term order set and the initial moving average term order set are determined; Determine an initial photovoltaic power generation prediction model, the calculation formula of the initial photovoltaic power generation prediction model is: ; in, is the autoregressive part, a is the order of the initial autoregressive term, B is the backward shift operator, is the difference operator, c is the initial difference processing order, for t Photovoltaic power generation at time 0, is the seasonal variation coefficient, d is the difference intercept term, is the meteorological data coefficient vector, for t The meteorological data vector at time 0, is the moving average part, b is the order of the initial moving average term, for t White noise error term at time 0; Different combinations of initial autoregressive terms, initial moving average terms and initial difference processing orders are selected, and the initial photovoltaic power generation prediction models under different combinations are compared through the information criterion algorithm for preliminary screening. The initial photovoltaic power generation prediction model after preliminary screening is evaluated to obtain a photovoltaic power generation prediction model.

[0008] Based on the above technical solution, preferably, the process of constructing the load demand prediction model includes: Acquire initial historical load data and initial historical meteorological data, and perform normalization processing on the initial historical load data and the initial historical meteorological data to obtain historical load data and historical meteorological data; The time series characteristics of historical load data are captured through long short-term memory units, and the initial load demand forecasting model is established in combination with historical meteorological data; The model parameters of the initial load demand forecasting model are updated by an adaptive optimization algorithm until the loss function converges, thereby obtaining a trained load demand forecasting model; The calculation formula of the adaptive optimization algorithm is: ; ; in, For the initial load demand prediction model t Model parameters at time 1, For the initial load demand prediction model t Model parameters at time 1-1, For the initial load demand prediction modelt Adaptive learning rate at 1 moment, is the parameter gradient of the loss function, , , , The initial load demand prediction model is t The weight matrix of the forget gate, input gate, candidate memory unit, and output gate at time 1, , , , The initial load demand prediction model is t The bias of the forget gate, input gate, candidate memory unit, and output gate at time 1; The calculation formula of the loss function is: ; in, For the t The loss function for 2 iterations, N is the total number of samples, For the i The actual value of the load demand, For the i The load demand forecast value, is the regularization coefficient, is the regularization term, For the t Model parameters of the initial load demand prediction model at 2 iterations.

[0009] On the basis of the above technical solution, preferably, the calculation formula of the load demand prediction model is: ; ; ; ; ; ; ; in, for t The load demand forecast value at the time, is the weight matrix of the output layer of the long short-term memory unit, is the bias of the output layer of the LSTM unit, For long short-term memory units t The hidden state of the moment, , , , They are respectively the forget gate, input gate, candidate memory unit, and output gate. t The activation value at the moment, is the current state of the memory unit, for Sigmoid Activation function, , , , are the weight matrices of the forget gate, input gate, candidate memory unit, and output gate, respectively. , , , They are the biases of the forget gate, input gate, candidate memory unit, and output gate, respectively. is the hyperbolic tangent activation function, For long short-term memory units t -1 moment of hidden state, is the historical load data, For historical meteorological data, For candidate memory cells t -1 activation value at the moment.

[0010] Based on the above technical solution, preferably, step S2 includes: The photovoltaic power generation prediction model is used to obtain the photovoltaic power generation at each moment in the future period at preset time intervals, and a curve of the photovoltaic power generation changing with time is drawn, and the trend of photovoltaic power generation changes is obtained by fitting; the load demand prediction model is used to obtain the load demand at each moment in the future period at preset time intervals, and a curve of the load demand changing with time is drawn, and the trend of load demand changes is obtained by fitting.

[0011] On the basis of the above technical solution, preferably, step S2 further includes: The harmonic analysis of the new energy microgrid is performed through the voltage and current waveform data, and the voltage and current waveform data are fast Fourier transformed to convert the voltage and current waveform data into the frequency domain to obtain the fundamental effective value and the harmonic component effective value of the voltage and current waveform data. The total harmonic distortion rate is calculated according to the fundamental effective value and the harmonic component effective value: ; in, THD is the total harmonic distortion rate, V 1 is the effective value of the fundamental wave, V 2 is the effective value of the second harmonic component, V 3 is the effective value of the third harmonic component, V n for n Effective value of subharmonic components.

[0012] On the basis of the above technical solution, preferably, step S3 includes: The objective function of the multi-objective optimization algorithm is: ; ; in, is the objective function of the multi-objective optimization algorithm, , , , are the weight coefficients of the target sub-functions of photovoltaic power generation change trend, energy storage capacity value, load demand change trend and total harmonic distortion rate, respectively. is the target sub-function of the photovoltaic power generation change trend, is the load demand change trend objective sub-function, is the target sub-function of energy storage capacity value, is the total harmonic distortion target subfunction, X is the solution of the objective function, , , , They are the photovoltaic power generation change trend, energy storage capacity value, load demand change trend and total harmonic distortion rate corresponding to the solution of the objective function; The constraints of the multi-objective optimization algorithm are: ; in, for t Photovoltaic power generation of new energy microgrid at 3 moments, for t The power supply of the new energy microgrid at 3 moments, for t System load demand of new energy microgrid at 3 moments, for t The power generation capacity of the new energy microgrid at 3 moments, for t The power imbalance at time 3, for t 3 moments of energy storage capacity, is the minimum power supply value of the new energy microgrid, is the maximum power generation value of the new energy microgrid, for t Total harmonic distortion rate of the new energy microgrid at 3 moments, is the total harmonic distortion threshold.

[0013] On the basis of the above technical solution, preferably, step S3 further includes: Generate multiple groups of initial solutions through the objective function and constraint conditions of the multi-objective optimization algorithm, wherein the multiple groups of initial solutions satisfy the constraint conditions, and the multi-objective optimization algorithm minimizes the objective function based on the constraint conditions to screen out the optimal solution as the multi-objective scheduling solution; The steps of the multi-objective optimization algorithm include: Generate initial solution set , each solution in the initial solution set satisfies the constraints; For each solution in the initial solution set, calculate the objective function value corresponding to each solution, and select the optimal solution and the worst solution, wherein the objective function value corresponding to the optimal solution is the smallest, and the objective function value corresponding to the worst solution is the largest; Update each solution in the initial solution set. The calculation formula of the update process is: ; in, is the first j A solution, for The updated solution of is the optimal solution in the initial solution set, is the worst solution in the initial solution set, and is the optimal bias coefficient and the worst bias coefficient; Filter all update solutions based on the constraint conditions to obtain a first update solution set; Repeat the solution update until the preset number of iterations is reached; The optimal solution in the final updated solution set is output as a multi-objective scheduling scheme, wherein the multi-objective scheduling scheme includes a photovoltaic power generation control value, an energy storage power value control value, a load demand control value, and a total harmonic distortion rate control value.

[0014] Based on the above technical solution, preferably, step S4 includes: Based on the multi-objective scheduling scheme, the power supply and generation management of the new energy microgrid is carried out, and the power supply and generation strategy of the new energy microgrid is adjusted. The power supply and generation strategy includes the power supply and generation state, the photovoltaic power generation state, the system load state and the harmonic suppression state. The current energy storage power value of the new energy microgrid is compared with the energy storage power value control value to determine the power supply and generation state of the new energy microgrid; the current photovoltaic power generation of the new energy microgrid is compared with the photovoltaic power generation control value to determine the photovoltaic power generation state of the new energy microgrid; the current load output of the new energy microgrid is compared with the load demand control value to determine the system load state of the new energy microgrid; the current total harmonic distortion rate of the new energy microgrid is compared with the total harmonic distortion rate control value to determine the harmonic suppression state of the new energy microgrid. The power supply and generation control method based on the integrated photovoltaic storage and new energy microgrid of the present invention has the following beneficial effects compared with the prior art: (1) By acquiring and preprocessing real-time operation data, using photovoltaic power generation prediction models and load demand prediction models to predict photovoltaic power generation and load demand, and performing harmonic analysis on current and voltage data, a multi-objective optimization algorithm is used to generate a scheduling plan, monitor the state of the new energy microgrid in real time and adjust the power supply and generation strategy, thus achieving comprehensive optimization and regulation of photovoltaic power generation, energy storage, load demand and harmonic distortion of the new energy microgrid, and realizing the integration of photovoltaic storage and use of the new energy microgrid; (2) Taking seasonal factors into account through the photovoltaic power generation prediction model, a photovoltaic power generation prediction model was constructed using historical data and time series analysis methods to accurately predict the changing trend of photovoltaic power generation and improve the prediction accuracy of the system; (3) Through the load demand prediction model, the changing trend of load demand is accurately predicted, load management is optimized, and the reliability and efficiency of power supply are improved. The power quality is evaluated by using fast Fourier transform and harmonic distortion rate calculation, which serves as the basis for harmonic suppression and improves the power quality of new energy microgrids. (4) By adopting a multi-objective optimization algorithm, the overall optimization is carried out by comprehensively considering photovoltaic power generation, energy storage, load demand and harmonic distortion, and the power supply and generation strategy is monitored and dynamically adjusted, which enhances the adaptability and flexibility of the new energy microgrid and ensures the efficient operation of the new energy microgrid. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 The present invention is a flow chart of a power supply and generation control method based on a new energy microgrid with integrated photovoltaic storage. DETAILED DESCRIPTION

[0017] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0018] See also Figure 1The present invention provides a method for regulating power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization, comprising the following steps: S1, obtaining initial real-time operation data of the new energy microgrid, preprocessing the initial real-time operation data to obtain real-time operation data, wherein the real-time operation data includes voltage and current waveform data, real-time photovoltaic power generation data, real-time meteorological data and real-time load data; S2, based on the photovoltaic power generation prediction model, real-time photovoltaic power generation data and real-time meteorological data, predict the change trend of photovoltaic power generation of the new energy microgrid, based on the load demand prediction model and real-time load data, predict the change trend of load demand of the new energy microgrid, and perform harmonic analysis on the new energy microgrid based on the voltage and current waveform data to obtain the total harmonic distortion rate; S3, generating a multi-objective scheduling scheme based on a multi-objective optimization algorithm, real-time operation data and forecast data, wherein the forecast data includes a photovoltaic power generation change trend, a load demand change trend and a total harmonic distortion rate, and the optimization targets of the multi-objective scheduling scheme include a photovoltaic power generation change trend, an energy storage power value, a load demand change trend and a total harmonic distortion rate; S4, real-time monitoring of the current energy storage value, current photovoltaic power generation, current load output and current total harmonic distortion rate of the new energy microgrid, and adjusting the power supply and generation strategy of the new energy microgrid based on the multi-objective scheduling scheme, current energy storage value, current photovoltaic power generation, current load output and current total harmonic distortion rate.

[0019] Specifically, this embodiment proposes a power supply and generation control method based on an integrated photovoltaic, energy storage and utilization new energy microgrid. By acquiring and preprocessing real-time operation data, photovoltaic power generation and load demand are predicted using a photovoltaic power generation prediction model and a load demand prediction model, and harmonic analysis is performed on current and voltage data. A scheduling plan is generated using a multi-objective optimization algorithm, and the state of the new energy microgrid is monitored in real time and the power supply and generation strategy is regulated. This realizes the comprehensive optimization and regulation of photovoltaic power generation, energy storage, load demand and harmonic distortion of the new energy microgrid, as well as the photovoltaic, energy storage and utilization integration of the new energy microgrid.

[0020] Step S1 includes: Preprocessing the initial real-time operation data, wherein the preprocessing includes data cleaning, outlier removal, data formatting and data standardization; The data cleaning includes filling missing values ​​using polynomial interpolation; The removing of outliers includes identifying outliers using the interquartile range method; The data formatting includes converting different formats of date and time into a unified format, converting different measurement units into a unified measurement unit, and converting all text data into a unified character encoding format; The data standardization includes converting the data using Z-score standardization.

[0021] Specifically, step S1 of this embodiment improves the quality and reliability of data through preprocessing steps such as data cleaning and outlier removal. The polynomial interpolation method can fill missing values ​​to maintain the continuity of data, and the quartile range method can effectively eliminate unreasonable data points to provide a reliable data basis.

[0022] The data formatting step ensures that data from different sources and formats can be processed uniformly. Standardizing date and time, units of measurement, and character encoding can eliminate processing errors caused by inconsistent data formats and improve the accuracy and efficiency of data processing.

[0023] Z-score standardization is used to transform the data so that data of different scales and units can be compared and analyzed under the same standard. The dimension effect is eliminated so that each feature has the same weight in the model.

[0024] The preprocessing operation in step S1 of this embodiment lays a solid data foundation for the subsequent prediction and optimization steps, which is a crucial step in the entire new energy microgrid power supply and generation control method and can improve stability and reliability.

[0025] The construction process of the photovoltaic power generation prediction model is as follows: Acquire historical photovoltaic power generation data and historical meteorological data, and clean the historical photovoltaic power generation data and historical meteorological data to process missing values ​​and abnormal values; The seasonal variation coefficient is extracted by time series decomposition method, and the unit root test is performed on the difference between the historical photovoltaic power generation data and the seasonal variation coefficient. When the sequence of the difference is non-stationary, the historical photovoltaic power generation data and the seasonal variation coefficient are differentially processed to obtain the photovoltaic power generation difference component, and the sequence autocorrelation function diagram and partial autocorrelation function diagram of the photovoltaic power generation difference component are plotted. According to the characteristics of the sequence autocorrelation function diagram and the partial autocorrelation function diagram, the initial autoregressive term order set and the initial moving average term order set are determined; Determine an initial photovoltaic power generation prediction model, the calculation formula of the initial photovoltaic power generation prediction model is: ; in, is the autoregressive part, a is the order of the initial autoregressive term, B is the backward shift operator, is the difference operator, c is the initial difference processing order, for t Photovoltaic power generation at time 0, is the seasonal variation coefficient, d is the difference intercept term, is the meteorological data coefficient vector, for t The meteorological data vector at time 0, is the moving average part, b is the order of the initial moving average term, for t White noise error term at time 0; Different combinations of initial autoregressive terms, initial moving average terms and initial difference processing orders are selected, and the initial photovoltaic power generation prediction models under different combinations are compared through the information criterion algorithm for preliminary screening. The initial photovoltaic power generation prediction model after preliminary screening is evaluated to obtain a photovoltaic power generation prediction model.

[0026] Specifically, the construction process of the photovoltaic power generation prediction model of this embodiment includes extracting the seasonal variation coefficient by the time series decomposition method. The time series decomposition method decomposes the time series into trend components, seasonal components and random components. The specific process of this step is: Calculate the moving average to smooth the data, remove seasonality and random fluctuations, and obtain the trend component: ; in, for w The trend component of the moment, M is the moving window length, For the moment w - l Historical photovoltaic power generation; Calculate the average value in each seasonal cycle, subtract the trend component from the historical photovoltaic power generation data, obtain the seasonal component and the random component, average the seasonal component and the random component to obtain the seasonal variation coefficient: ; in, is the seasonal variation coefficient, for w The historical PV power generation at the time instant, NN is the total number of seasons in the time series of the historical PV power generation data; The construction process of the photovoltaic power generation prediction model in this embodiment also includes: performing a unit root test on the difference between the historical photovoltaic power generation data and the seasonal variation coefficient. The unit root test is used to detect whether the time series is stable. In this embodiment, the ADF test is used. The specific process of this step is: Assumptions: Null hypothesis H 0: The time series has a unit root, indicating that the series is non-stationary; Alternative hypothesis H1: There is no unit root in the time series, indicating that the series is stable; Build ADF Test the model: ; in, for t The difference between the historical photovoltaic power generation data at 4 moments and the seasonal variation coefficient, for t 4-1 The difference between the historical photovoltaic power generation data and the seasonal variation coefficient at time 1, and They are and The difference, is a constant term, for t 4. The time trend term at moment 4, is the coefficient of the time series to be tested, is the lag term coefficient, for t The error term at 4 moments, p is the lag order; According to the ADF The test model calculates the test statistic and compares it with the critical value. If the test statistic is less than the critical value, the null hypothesis is rejected and the sequence is considered to be stationary. If the test statistic is not less than the critical value, the null hypothesis is not rejected and the sequence is considered to be non-stationary.

[0027] The sequence autocorrelation function diagram and the partial autocorrelation function diagram of the photovoltaic power generation difference component are drawn, and the initial autoregressive term order set and the initial moving average term order set are determined according to the characteristics of the sequence autocorrelation function diagram and the partial autocorrelation function diagram, wherein the initial autoregressive term order set and the initial moving average term order set are respectively determined by the truncation of the autocorrelation function diagram and the partial autocorrelation function diagram.

[0028] In the initial photovoltaic power generation prediction model of this embodiment, the autoregressive part Used to express the relationship between the current photovoltaic power generation and its past value; differential processing part Used to make t Photovoltaic power generation at time 0 and seasonal variation coefficient Become stable and introduce seasonal variation coefficient Used to capture seasonal fluctuations in PV power generation; t Weather data vector at time 0 Including various meteorological factors that may affect photovoltaic power generation, such as temperature and light intensity; meteorological data coefficient vector Used to indicate the impact on photovoltaic power generation; moving average part Used to smooth random fluctuations in time series of historical photovoltaic data; t White noise error term at time 0 It is used to represent the random error not captured in the initial photovoltaic power generation prediction model; the difference intercept term d Used to compensate for errors in differential processing.

[0029] The initial photovoltaic power generation prediction model of this embodiment combines the ideas of autoregression and moving average. The historical dependence of photovoltaic power generation is captured by the autoregression part, the non-stationarity is eliminated by differential processing, the external influencing factors are captured by seasonal variation coefficients and meteorological data, and the random fluctuations are smoothed by the moving average part, and finally the prediction of future photovoltaic power generation is obtained. This initial photovoltaic power generation prediction model aims to comprehensively consider the intrinsic characteristics of the time series and the external influencing factors to improve the accuracy of the prediction.

[0030] In this embodiment, AIC The information criterion algorithm compares the initial photovoltaic power generation prediction models under different combinations for preliminary screening. AIC The calculation formula of the information criterion algorithm is: ; in, AIC for AIC The evaluation value of the information criterion algorithm, k for AIC The number of parameters of the model evaluated by the information criterion algorithm, in this embodiment AIC The parameters of the model evaluated by the information criterion algorithm include the initial autoregressive term order and the initial moving average term order, so k The value is 2. is the maximum likelihood estimate of the initial photovoltaic power generation prediction model under different combinations of the initial autoregressive term order and the initial moving average term order. AIC The minimum corresponding initial autoregressive term order and initial moving average term order are taken as the final autoregressive term order and moving average term order, thereby obtaining the final photovoltaic power generation prediction model.

[0031] In a specific embodiment, the final autoregressive term order and moving average term order can be 3 and 1, that is, a Finally, we get 3. b Finally, 1 is taken. Considering that photovoltaic power generation data is usually affected by factors such as weather and season, there is short-term non-stationarity. The first-order difference can effectively remove this short-term non-stationarity and make the sequence more stable. Therefore c Finally, take 1.

[0032] The construction process of the load demand prediction model includes: Acquire initial historical load data and initial historical meteorological data, and perform normalization processing on the initial historical load data and the initial historical meteorological data to obtain historical load data and historical meteorological data; The time series characteristics of historical load data are captured through long short-term memory units, and the initial load demand forecasting model is established in combination with historical meteorological data; The model parameters of the initial load demand forecasting model are updated by an adaptive optimization algorithm until the loss function converges, thereby obtaining a trained load demand forecasting model; The calculation formula of the adaptive optimization algorithm is: ; ; in, For the initial load demand prediction model t Model parameters at time 1, For the initial load demand prediction model t Model parameters at time 1-1, For the initial load demand prediction model t Adaptive learning rate at 1 moment, is the parameter gradient of the loss function, , , , The initial load demand prediction model is t The weight matrix of the forget gate, input gate, candidate memory unit, and output gate at time 1, , , , The initial load demand prediction model is t The bias of the forget gate, input gate, candidate memory unit, and output gate at time 1; The calculation formula of the loss function is: ; in, For the t The loss function for 2 iterations, N is the total number of samples, For the i The actual value of the load demand, For the i The load demand forecast value, is the regularization coefficient, is the regularization term, For the t Model parameters of the initial load demand prediction model at 2 iterations.

[0033] Specifically, in a new energy microgrid, accurate prediction of load demand is crucial for optimal scheduling of power resources. The load demand prediction model of this embodiment uses an adaptive optimization algorithm to update model parameters. Since the time series data contained in the historical load data of the new energy microgrid is relatively complex, parameter gradients are introduced. By calculating the gradient of the loss function with respect to the parameters, the model parameters are updated in the direction of reducing losses in each iteration. The adaptive learning rate optimization algorithm can quickly adjust the learning rate and improve the convergence speed of the model, so that the model can respond to changes in load demand in a timely manner. Through rapid convergence, the new energy microgrid can more efficiently perform energy scheduling and load management, and maximize the utilization rate of photovoltaic power generation. In a new energy microgrid, load data may be affected by many factors (such as weather, seasonal changes, etc.), resulting in data complexity and uncertainty. The regularization term limits the complexity of the model and prevents overfitting, thereby improving the generalization ability of the model under different conditions. The load demand forecasting model of this embodiment is improved from the mean square error loss function, which is used to measure the difference between the predicted value and the actual value. By introducing the regularization term ,Prevent overfitting of the load demand forecasting model and improve the generalization ability of the model by penalizing excessively large parameter values.

[0034] The calculation formula of the load demand prediction model is: ; ; ; ; ; ; ; in, for t The load demand forecast value at the time, is the weight matrix of the output layer of the long short-term memory unit, is the bias of the output layer of the LSTM unit, For long short-term memory units t The hidden state of the moment, , , , They are respectively the forget gate, input gate, candidate memory unit, and output gate. t The activation value at the moment, is the current state of the memory unit, for Sigmoid Activation function, , , , are the weight matrices of the forget gate, input gate, candidate memory unit, and output gate, respectively. , , , They are the biases of the forget gate, input gate, candidate memory unit, and output gate, respectively. is the hyperbolic tangent activation function, For long short-term memory units t -1 moment of hidden state, is the historical load data, For historical meteorological data, For candidate memory cells t -1 activation value at the moment.

[0035] Specifically, the load demand forecasting model of this embodiment is improved based on the long short-term memory network model, and the load demand forecasting model includes an input layer, a long short-term memory network layer, a fully connected layer, and an output layer, and the input layer, the long short-term memory network layer, the fully connected layer, and the output layer are connected in sequence; The input layer is used to receive two input features, namely, initial historical load data and initial historical meteorological data, and preprocess the initial historical load data and the initial historical meteorological data; The long short-term memory network layer includes 64 neurons, which are used to capture the long-term dependencies in the time series data of the historical load data. The long short-term memory network layer includes a forget gate, an input gate, an output gate, a memory unit update, and a hidden state. The forget gate is used to determine the unimportant part of the historical load data and forget it. The input gate is used to determine the new information that needs to be written into the historical load data. The memory unit update is used to update the state of the current memory unit. The output gate is used to determine what information needs to be output from the historical load data. The fully connected layer includes 32 neurons, which are used to further process the features extracted by the long short-term memory network layer and generate nonlinear combinations of features; The output layer includes 1 neuron, which is used to output the load demand forecast value at the future moment.

[0036] Step S2 includes: The photovoltaic power generation prediction model is used to obtain the photovoltaic power generation at each moment in the future period at preset time intervals, and a curve of the photovoltaic power generation changing with time is drawn, and the trend of photovoltaic power generation changes is obtained by fitting; the load demand prediction model is used to obtain the load demand at each moment in the future period at preset time intervals, and a curve of the load demand changing with time is drawn, and the trend of load demand changes is obtained by fitting.

[0037] The harmonic analysis of the new energy microgrid is performed through the voltage and current waveform data, and the voltage and current waveform data are fast Fourier transformed to convert the voltage and current waveform data into the frequency domain to obtain the fundamental effective value and the harmonic component effective value of the voltage and current waveform data. The total harmonic distortion rate is calculated according to the fundamental effective value and the harmonic component effective value: ; in, THD is the total harmonic distortion rate, V 1 is the effective value of the fundamental wave, V 2 is the effective value of the second harmonic component, V 3 is the effective value of the third harmonic component, V n for n Effective value of subharmonic components.

[0038] Specifically, this embodiment can accurately predict the photovoltaic power generation and load demand in the future period through the photovoltaic power generation prediction model and the load demand prediction model.

[0039] The curves of photovoltaic power generation and load demand changing with time are drawn, and the changing trend is fitted. Based on the changing trend, the time-varying functions of photovoltaic power generation and load demand are fitted.

[0040] By performing harmonic analysis on voltage and current waveform data and calculating the total harmonic distortion rate, the power quality of the new energy microgrid can be effectively evaluated to ensure the stable operation of the power system and the safe use of equipment.

[0041] Use fast Fourier transform to convert time domain data to frequency domain to more deeply analyze harmonic problems in power systems. By identifying specific harmonic components, it helps to formulate targeted harmonic suppression strategies.

[0042] Real-time monitoring of the system is achieved by acquiring data and analyzing it at preset time intervals.

[0043] The changing trends of photovoltaic power generation and load demand, as well as the calculated total harmonic distortion rate, provide the necessary input characteristics for multi-objective optimization scheduling, thereby achieving precise scheduling and optimization control.

[0044] Through accurate prediction and real-time monitoring, potential supply-demand imbalances or power quality issues can be identified in advance, so that preventive measures can be taken to improve system stability.

[0045] Accurate prediction and analysis can help the system better balance supply and demand, improve the efficiency of renewable energy utilization, and reduce energy waste.

[0046] Harmonic analysis can not only evaluate power quality, but also serve as a fault diagnosis tool. Abnormal harmonic components can be used to indicate the existence of certain faults or abnormal conditions in the system.

[0047] Step S3 includes: The objective function of the multi-objective optimization algorithm is: ; ; in, is the objective function of the multi-objective optimization algorithm, , , , are the weight coefficients of the target sub-functions of photovoltaic power generation change trend, energy storage capacity value, load demand change trend and total harmonic distortion rate, respectively. is the target sub-function of the photovoltaic power generation change trend, is the load demand change trend objective sub-function, is the target sub-function of energy storage capacity value, is the total harmonic distortion target subfunction, X is the solution of the objective function, , , , They are the photovoltaic power generation change trend, energy storage capacity value, load demand change trend and total harmonic distortion rate corresponding to the solution of the objective function; The constraints of the multi-objective optimization algorithm are: ; in, for t Photovoltaic power generation of new energy microgrid at 3 moments, for t The power supply of the new energy microgrid at 3 moments, for t System load demand of new energy microgrid at 3 moments, for t The power generation capacity of the new energy microgrid at 3 moments, for t The power imbalance at time 3, for t 3 moments of energy storage capacity, is the minimum power supply value of the new energy microgrid, is the maximum power generation value of the new energy microgrid, for t Total harmonic distortion rate of the new energy microgrid at 3 moments, is the total harmonic distortion threshold.

[0048] Specifically, this embodiment realizes the comprehensive optimization of multiple key indicators of the new energy microgrid by setting a multi-objective function including the photovoltaic power generation change trend, energy storage power value, load demand change trend and total harmonic distortion rate; Use weight factor , , , Adjust the importance of PV power generation trend, energy storage value, load demand trend and total harmonic distortion rate according to actual needs, making the optimization process more flexible and adaptable to different operating scenarios and priorities; Through multi-objective optimization, the best balance can be found between improving photovoltaic power generation utilization, optimizing energy storage use, meeting load demand and controlling harmonic distortion to achieve the overall optimal operation of the system; The set constraints ensure that the system operates within a safe and reliable range. Specifically, the power balance constraint ensures the balance between supply and demand, the energy storage capacity constraint ensures the rational use of the energy storage system, and the total harmonic distortion rate constraint ensures the power quality; taking the total harmonic distortion rate as one of the optimization goals can improve the power quality of the system and reduce the adverse effects of harmonics on equipment.

[0049] Step S3 also includes: Generate multiple groups of initial solutions through the objective function and constraint conditions of the multi-objective optimization algorithm, wherein the multiple groups of initial solutions satisfy the constraint conditions, and the multi-objective optimization algorithm minimizes the objective function based on the constraint conditions to screen out the optimal solution as the multi-objective scheduling solution; The steps of the multi-objective optimization algorithm include: Generate initial solution set , each solution in the initial solution set satisfies the constraints; For each solution in the initial solution set, calculate the objective function value corresponding to each solution, and select the optimal solution and the worst solution, wherein the objective function value corresponding to the optimal solution is the smallest, and the objective function value corresponding to the worst solution is the largest; Update each solution in the initial solution set. The calculation formula of the update process is: ; in, is the first j A solution, for The updated solution of is the optimal solution in the initial solution set, is the worst solution in the initial solution set, and is the optimal bias coefficient and the worst bias coefficient; Filter all update solutions based on the constraint conditions to obtain a first update solution set; Repeat the solution update until the preset number of iterations is reached; The optimal solution in the final updated solution set is output as a multi-objective scheduling scheme, wherein the multi-objective scheduling scheme includes a photovoltaic power generation control value, an energy storage power value control value, a load demand control value, and a total harmonic distortion rate control value.

[0050] Specifically, in this embodiment, based on the global search of the Jaya algorithm, the Jaya algorithm is applied from single-objective optimization to the field of multi-objective optimization, a local search strategy is added, and an adaptive weight adjustment mechanism is introduced to dynamically adjust the weight according to the current performance of each objective; By generating multiple sets of initial solutions and optimizing them under constraints, the algorithm can explore multiple regions of the solution space, increasing the possibility of finding the global optimal solution and avoiding falling into the local optimum.

[0051] In the process of generating the initial solution and updating the solution, we always ensure that the solution satisfies the constraints, ensure that each step in the optimization process is carried out within the feasible solution space, and ensure the feasibility and practicality of the final solution.

[0052] This embodiment iteratively updates the solution set and dynamically adjusts the direction and amplitude of feasible solutions to gradually approach the optimal solution, thereby improving the convergence speed and accuracy. By introducing the optimal bias coefficient and the worst bias coefficient, the solution update strategy is improved, making the algorithm more directional and efficient during the search process.

[0053] The improved multi-objective optimization algorithm retains the simplicity and efficiency of the Jaya algorithm, enhances its applicability and performance in complex multi-objective problems, and realizes the optimal regulation of new energy microgrids.

[0054] Step S4 includes: Based on the multi-objective scheduling scheme, the power supply and generation management of the new energy microgrid is carried out, and the power supply and generation strategy of the new energy microgrid is adjusted. The power supply and generation strategy includes the power supply and generation state, the photovoltaic power generation state, the system load state and the harmonic suppression state. The current energy storage value of the new energy microgrid is compared with the energy storage value control value to determine the power supply and generation state of the new energy microgrid; the current photovoltaic power generation of the new energy microgrid is compared with the photovoltaic power generation control value to determine the photovoltaic power generation state of the new energy microgrid; the current load output of the new energy microgrid is compared with the load demand control value to determine the system load state of the new energy microgrid; the current total harmonic distortion rate of the new energy microgrid is compared with the total harmonic distortion rate control value to determine the harmonic suppression state of the new energy microgrid.

[0055] Specifically, step S4 of this embodiment achieves refined management of the new energy microgrid by comparing the current state with the control value. Each state (power supply, photovoltaic power generation, system load, harmonic suppression) can be monitored and adjusted separately to ensure that the system operates in the best state.

[0056] By real-time monitoring and adjustment of various parameters of the microgrid, it can quickly respond to changes in the external environment and internal demand, improve the dynamic adaptability of the system, regulate power supply and generation strategies, optimize the utilization of photovoltaic power generation and energy storage resources, reduce energy waste, and improve energy utilization efficiency.

[0057] By managing the harmonic suppression status, the harmonic distortion rate in the power grid is reduced, the power quality is improved, the stability and reliability of the system are enhanced, the load output is compared with the demand control value, the load management is optimized, and the load demand is effectively met while avoiding overload or waste of resources.

[0058] Specifically, the power supply strategy of this embodiment includes the following calculation formulas according to the power supply state, photovoltaic power generation state, system load state and harmonic suppression state: ; ; ; ; in, , , , They are power supply status, photovoltaic power generation status, system load status, and harmonic suppression status. , , , They are respectively the energy storage capacity control value, photovoltaic power generation control value, load demand control value, and total harmonic distortion rate control value. , , , They are the current energy storage value, current photovoltaic power generation, current load output, and current total harmonic distortion rate; It is the power supply status of the new energy microgrid. It is the power supply state that drives the new energy microgrid to supply power to the outside; It is the photovoltaic power generation state that improves the photovoltaic power generation efficiency of new energy microgrids. It is the photovoltaic power generation state that reduces the photovoltaic power generation efficiency of the new energy microgrid; It is the system load state that improves the load output of the new energy microgrid. It is the system load state that reduces the load output of the new energy microgrid; It is to maintain the harmonic suppression state of the total harmonic distortion rate of the new energy microgrid. It is the harmonic suppression state that reduces the total harmonic distortion rate of the new energy microgrid.

[0059] Through the power supply and generation status, photovoltaic power generation status, system load status and harmonic suppression status, this embodiment realizes the integration of photovoltaic storage and use of the new energy microgrid, and reasonably controls the power supply and power generation of the new energy microgrid.

[0060] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for regulating power supply and generation based on a new energy microgrid with integrated photovoltaic storage, characterized in that: The following steps are involved: S1, obtaining initial real-time operation data of the new energy microgrid, preprocessing the initial real-time operation data to obtain real-time operation data, wherein the real-time operation data includes voltage and current waveform data, real-time photovoltaic power generation data, real-time meteorological data and real-time load data; S2, based on the photovoltaic power generation prediction model, real-time photovoltaic power generation data and real-time meteorological data, predict the change trend of photovoltaic power generation of the new energy microgrid, based on the load demand prediction model and real-time load data, predict the change trend of load demand of the new energy microgrid, and perform harmonic analysis on the new energy microgrid based on the voltage and current waveform data to obtain the total harmonic distortion rate; S3, generating a multi-objective scheduling scheme based on a multi-objective optimization algorithm, real-time operation data and forecast data, wherein the forecast data includes a photovoltaic power generation change trend, a load demand change trend and a total harmonic distortion rate, and the optimization targets of the multi-objective scheduling scheme include a photovoltaic power generation change trend, an energy storage power value, a load demand change trend and a total harmonic distortion rate; S4, real-time monitoring of the current energy storage value, current photovoltaic power generation, current load output and current total harmonic distortion rate of the new energy microgrid, and adjusting the power supply and generation strategy of the new energy microgrid based on the multi-objective scheduling scheme, current energy storage value, current photovoltaic power generation, current load output and current total harmonic distortion rate.

2. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 1, characterized in that: Step S1 includes: Preprocessing the initial real-time operation data, wherein the preprocessing includes data cleaning, outlier removal, data formatting and data standardization; The data cleaning includes filling missing values ​​using polynomial interpolation; The removing of outliers includes identifying outliers using the interquartile range method; The data formatting includes converting different formats of date and time into a unified format, converting different measurement units into a unified measurement unit, and converting all text data into a unified character encoding format; The data standardization includes converting the data using Z-score standardization.

3. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 1, characterized in that: The construction process of the photovoltaic power generation prediction model is as follows: Acquire historical photovoltaic power generation data and historical meteorological data, and clean the historical photovoltaic power generation data and historical meteorological data to process missing values ​​and abnormal values; The seasonal variation coefficient is extracted by time series decomposition method, and the unit root test is performed on the difference between the historical photovoltaic power generation data and the seasonal variation coefficient. When the sequence of the difference is non-stationary, the historical photovoltaic power generation data and the seasonal variation coefficient are differentially processed to obtain the photovoltaic power generation difference component, and the sequence autocorrelation function diagram and partial autocorrelation function diagram of the photovoltaic power generation difference component are plotted. According to the characteristics of the sequence autocorrelation function diagram and the partial autocorrelation function diagram, the initial autoregressive term order set and the initial moving average term order set are determined; Determine an initial photovoltaic power generation prediction model, the calculation formula of the initial photovoltaic power generation prediction model is: ； in, is the autoregressive part, a is the order of the initial autoregressive term, B is the backward shift operator, is the difference operator, c is the initial difference processing order, for t Photovoltaic power generation at time 0, is the seasonal variation coefficient, d is the difference intercept term, is the meteorological data coefficient vector, for t The meteorological data vector at time 0, is the moving average part, b is the order of the initial moving average term, for t White noise error term at time 0; Different combinations of initial autoregressive terms, initial moving average terms and initial difference processing orders are selected, and the initial photovoltaic power generation prediction models under different combinations are compared through the information criterion algorithm for preliminary screening. The initial photovoltaic power generation prediction model after preliminary screening is evaluated to obtain a photovoltaic power generation prediction model.

4. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 3, characterized in that: The construction process of the load demand prediction model includes: Acquire initial historical load data and initial historical meteorological data, and perform normalization processing on the initial historical load data and the initial historical meteorological data to obtain historical load data and historical meteorological data; The time series characteristics of historical load data are captured through long short-term memory units, and the initial load demand forecasting model is established in combination with historical meteorological data; The model parameters of the initial load demand forecasting model are updated by an adaptive optimization algorithm until the loss function converges, thereby obtaining a trained load demand forecasting model; The calculation formula of the adaptive optimization algorithm is: ； ； in, For the initial load demand prediction model t Model parameters at time 1, For the initial load demand prediction model t Model parameters at time 1-1, For the initial load demand prediction model t Adaptive learning rate at 1 moment, is the parameter gradient of the loss function, , , , The initial load demand prediction model is t The weight matrix of the forget gate, input gate, candidate memory unit, and output gate at time 1, , , , The initial load demand prediction model is t The bias of the forget gate, input gate, candidate memory unit, and output gate at time 1; The calculation formula of the loss function is: ； in, For the t The loss function for 2 iterations, N is the total number of samples, For the i The actual value of the load demand, For the i The load demand forecast value, is the regularization coefficient, is the regularization term, For the t Model parameters of the initial load demand prediction model at 2 iterations.

5. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 4, characterized in that: The calculation formula of the load demand prediction model is: ； ； ； ； ； ； ； in, for t The load demand forecast value at the time, is the weight matrix of the output layer of the long short-term memory unit, is the bias of the output layer of the LSTM unit, For long short-term memory units t The hidden state of the moment, , , , They are respectively the forget gate, input gate, candidate memory unit, and output gate. t The activation value at the moment, is the current state of the memory unit, for Sigmoid Activation function, , , , are the weight matrices of the forget gate, input gate, candidate memory unit, and output gate, respectively. , , , They are the biases of the forget gate, input gate, candidate memory unit, and output gate, respectively. is the hyperbolic tangent activation function, For long short-term memory units t -1 moment of hidden state, is the historical load data, For historical meteorological data, For candidate memory cells t -1 activation value at the moment.

6. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 5, characterized in that: Step S2 includes: The photovoltaic power generation prediction model is used to obtain the photovoltaic power generation at each moment in the future period at preset time intervals, and a curve of the photovoltaic power generation changing with time is drawn, and the trend of photovoltaic power generation changes is obtained by fitting; the load demand prediction model is used to obtain the load demand at each moment in the future period at preset time intervals, and a curve of the load demand changing with time is drawn, and the trend of load demand changes is obtained by fitting.

7. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 6, characterized in that: Step S2 also includes: The harmonic analysis of the new energy microgrid is performed through the voltage and current waveform data, and the voltage and current waveform data are fast Fourier transformed to convert the voltage and current waveform data into the frequency domain to obtain the fundamental effective value and the harmonic component effective value of the voltage and current waveform data. The total harmonic distortion rate is calculated according to the fundamental effective value and the harmonic component effective value: ； in, THD is the total harmonic distortion rate, V 1 is the effective value of the fundamental wave, V 2 is the effective value of the second harmonic component, V 3 is the effective value of the third harmonic component, V n for n Effective value of subharmonic components.

8. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 7, characterized in that: Step S3 includes: The objective function of the multi-objective optimization algorithm is: ； ； in, is the objective function of the multi-objective optimization algorithm, , , , are the weight coefficients of the target sub-functions of photovoltaic power generation change trend, energy storage capacity value, load demand change trend and total harmonic distortion rate, respectively. is the target sub-function of the photovoltaic power generation change trend, is the load demand change trend objective sub-function, is the target sub-function of energy storage capacity value, is the total harmonic distortion target subfunction, X is the solution of the objective function, , , , They are the photovoltaic power generation change trend, energy storage capacity value, load demand change trend and total harmonic distortion rate corresponding to the solution of the objective function; The constraints of the multi-objective optimization algorithm are: ； in, for t Photovoltaic power generation of new energy microgrid at 3 moments, for t The power supply of the new energy microgrid at 3 moments, for t System load demand of new energy microgrid at 3 moments, for t The power generation capacity of the new energy microgrid at 3 moments, for t The power imbalance at time 3, for t 3 moments of energy storage capacity, is the minimum power supply value of the new energy microgrid, is the maximum power generation value of the new energy microgrid, for t Total harmonic distortion rate of the new energy microgrid at 3 moments, is the total harmonic distortion threshold.

9. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 8, characterized in that: Step S3 also includes: Generate multiple groups of initial solutions through the objective function and constraint conditions of the multi-objective optimization algorithm, wherein the multiple groups of initial solutions satisfy the constraint conditions, and the multi-objective optimization algorithm minimizes the objective function based on the constraint conditions to screen out the optimal solution as the multi-objective scheduling solution; The steps of the multi-objective optimization algorithm include: Generate initial solution set , each solution in the initial solution set satisfies the constraints; For each solution in the initial solution set, calculate the objective function value corresponding to each solution, and select the optimal solution and the worst solution, wherein the objective function value corresponding to the optimal solution is the smallest, and the objective function value corresponding to the worst solution is the largest; Update each solution in the initial solution set. The calculation formula of the update process is: ； in, is the first j A solution, for The updated solution of is the optimal solution in the initial solution set, is the worst solution in the initial solution set, and is the optimal bias coefficient and the worst bias coefficient; Filter all update solutions based on the constraint conditions to obtain a first update solution set; Repeat the solution update until the preset number of iterations is reached; The optimal solution in the final updated solution set is output as a multi-objective scheduling scheme, wherein the multi-objective scheduling scheme includes a photovoltaic power generation control value, an energy storage power value control value, a load demand control value, and a total harmonic distortion rate control value.

10. A method for controlling power supply and generation based on a new energy microgrid with integrated photovoltaic storage and utilization as claimed in claim 9, characterized in that: Step S4 includes: Based on the multi-objective scheduling scheme, the power supply and generation management of the new energy microgrid is carried out, and the power supply and generation strategy of the new energy microgrid is adjusted. The power supply and generation strategy includes the power supply and generation state, the photovoltaic power generation state, the system load state and the harmonic suppression state. The current energy storage value of the new energy microgrid is compared with the energy storage value control value to determine the power supply and generation state of the new energy microgrid; the current photovoltaic power generation of the new energy microgrid is compared with the photovoltaic power generation control value to determine the photovoltaic power generation state of the new energy microgrid; the current load output of the new energy microgrid is compared with the load demand control value to determine the system load state of the new energy microgrid; the current total harmonic distortion rate of the new energy microgrid is compared with the total harmonic distortion rate control value to determine the harmonic suppression state of the new energy microgrid.

Images