A dynamic interval optimization scheduling method for microgrid considering source load uncertainty

Abstract

The application belongs to the field of micro-grid optimal scheduling, and discloses a micro-grid dynamic interval optimal scheduling method considering source-load uncertainty, comprising the following steps: step 1, photovoltaic power prediction; step 2, photovoltaic power dynamic interval prediction; step 3, power load prediction; step 4, load dynamic interval prediction; and step 5, dynamic interval optimal scheduling of the micro-grid considering source-load uncertainty, wherein a dynamic interval optimal scheduling model of the micro-grid considering source-load uncertainty is first established, a target function and a constraint condition of the dynamic interval optimal scheduling model of the micro-grid are further established, and an optimal scheduling result of the micro-grid is obtained by solving. The application uses a ConvLSTM-Attention-LSTM fusion prediction model to perform photovoltaic power prediction, and the model can more accurately capture the spatial and temporal dependencies in time series data, thereby improving the prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the field of microgrid optimization scheduling, and in particular to a microgrid dynamic interval optimization scheduling method considering source and load uncertainty. Background Art

[0002] With the rapid development of microgrids, their importance in power systems is becoming increasingly prominent. As small, independently operated power systems, microgrids typically consist of multiple energy resources and loads, offering high flexibility and reliability. However, due to the uncertainty of renewable energy and distributed energy resources contained in microgrids, as well as the randomness of loads, the optimal scheduling of microgrids faces significant challenges.

[0003] Traditional microgrid scheduling methods are mostly based on deterministic models for optimization, ignoring the impact of source-load uncertainty on system operation. Therefore, in order to better address source-load uncertainty and improve the operational efficiency and economic efficiency of microgrids, this patent proposes a dynamic interval optimization scheduling method for microgrids that considers source-load uncertainty. This method first obtains the range of source-load uncertainty by predicting the errors of photovoltaic power and power load in the microgrid. Then, based on the source-load range, dynamic intervals are used to schedule the microgrid to achieve optimal operation of the system in an uncertain environment. Compared with traditional deterministic optimization methods, this method fully considers the impact of source-load uncertainty and improves the operational stability and economic efficiency of the microgrid. Summary of the Invention

[0004] The purpose of the present invention is to provide a microgrid dynamic interval optimization scheduling method considering source-load uncertainty. First, the ConvLSTM-Attention-LSTM fusion prediction model is used to train and predict the photovoltaic power after data cleaning and feature screening. Then, power ramp clustering is used to perform weather analysis and ShapeDTW algorithm output dynamic interval prediction to obtain dynamic interval results. Then, the CEEMDAN sequence decomposition model is used to decompose the load characteristics and FEDformer is used for model training and prediction. After Kmeans load clustering, the prediction error is calculated and the dynamic interval prediction result is optimized. Finally, the objective function and constraint conditions are set and solved to obtain the microgrid optimization scheduling result, so as to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for dynamic interval optimization scheduling of a microgrid considering source and load uncertainty, the method comprising the following steps:

[0007] Step 1: PV power prediction. First, the original PV power data is processed and the Spearman correlation coefficient feature is screened. The PV data set is divided into a PV training set and a PV test set. Then, the ConvLSTM-Attention-LSTM fusion prediction model is used for training and prediction.

[0008] Step 2: PV power dynamic interval prediction. First, the PV power ramp clustering model is used to classify the PV test set prediction results into multiple weather types. Then, the dynamic interval prediction method based on the ShapeDTW algorithm is used to calculate the interval range to obtain the dynamic interval prediction results.

[0009] Step 3: Power load forecasting. First, the original load data is preprocessed and the Spearman correlation coefficient feature is screened. Then, the CEEMDAN sequence decomposition model is used to decompose the load features. The decomposed sequence and the screened data together constitute the training data. The load dataset is divided into a load training set, a load test set, and a load validation set. Finally, the FEDformer model is used for model training and forecasting.

[0010] Step 4: Load dynamic interval prediction. First, the Kmeans clustering model is used to classify the load test set prediction results into multiple categories. The dynamic interval calculation formula is then used to calculate the dynamic prediction errors of the multiple categories. The dynamic prediction errors are then superimposed on the point prediction results to obtain the final photovoltaic and load interval prediction results.

[0011] Step 5, dynamic interval optimization scheduling of microgrid considering source-load uncertainty, first establish a dynamic interval optimization scheduling model of microgrid considering source-load uncertainty, further establish the objective function and constraint conditions of the dynamic interval optimization scheduling model of microgrid, and solve to obtain the optimization scheduling result of microgrid.

[0012] Furthermore, the step 1 specifically includes:

[0013] Step 1.1: Preprocess the original PV power data to obtain initial features. Data preprocessing includes missing value processing, outlier processing, and data standardization.

[0014] Step 1.2: Use the Spearman correlation coefficient to analyze the correlation between features and power on the processed PV power station historical data. Remove features with low correlation to obtain filtered PV power station historical data. Divide the filtered PV power station historical data into a PV training set and a PV test set for the ConvLSTM-Attention-LSTM fusion prediction model.

[0015] In step 1.3, the ConvLSTM-Attention-LSTM fusion prediction model is used to train the filtered historical data of photovoltaic power stations and predict future data.

[0016] Furthermore, the ConvLSTM-Attention-LSTM fusion prediction model is:

[0017] (1) The ConvLSTM-Attention-LSTM fusion prediction model is first reshaped into the dimensions required by the model, passed through several ConvLSTM networks and applied to the input; local spatial features are extracted through convolution operations to maintain the spatial continuity of the data. The convolution kernel slides region by region on the input feature map to perform calculations, each time calculating the weighted sum of local features, and then updating the state in the LSTM based on these local features;

[0018] (2) The Attention mechanism is integrated into the ConvLSTM-Attention-LSTM fusion prediction model by using a custom attention function. First, the Permute layer is used to transpose the dimension of the input data. Then the data passes through a Dense layer and is processed using the softmax activation function. The output result can be regarded as the attention weight of each time step. Then the dimension of the attention weight is transposed again to restore it to the original order. Finally, the input data and the attention weight are multiplied at the element level. The output result is the data after the attention mechanism is applied.

[0019] (3) After completing the attention processing, the data is passed into several LSTM layers and the ReLU activation function is used; finally, the data is processed by the fully connected layer and the nonlinear transformation is completed by the ReLU activation function. Finally, after multiple iterations, the data is processed in the output layer to obtain the photovoltaic prediction result data.

[0020] Furthermore, the step 2 specifically includes:

[0021] Step 2.1: Cluster the photovoltaic test set prediction results into n weather types using the photovoltaic power ramping clustering model;

[0022] In step 2.2, the ShapeDTW algorithm is used to select k similar days of future prediction results from the PV test set prediction results, calculate the prediction error of the similar days, and obtain the interval range by taking the maximum absolute value of the prediction error. Finally, the interval range is superimposed on the prediction result to obtain the final interval prediction result.

[0023] Furthermore, the photovoltaic power ramping clustering model is implemented using an improved optimized power ramping calculation formula, which is as follows:

[0024] P t '=P t (sgn((P t -P t-1 )·(P t -P t+1 )>0)(1)

[0025] ΔP t+i =P t+i -P t '(i=1,…,τ) (2)

[0026] P ε =ηP d (3)

[0027] Where, t is the time of hill climbing detection; P t ——power at time t; P t '——Possible climbing point; ΔP t+i ——The power difference between time t+i and time t; P ε ——climbing threshold; τ——climbing duration threshold; P d ——PV installed capacity, η——ramp threshold as a percentage of installed capacity, sgn(*) is the sgn function;

[0028] The improved power ramp calculation formula traverses power data points to determine the ramp starting point and continuous ramping. A ramp threshold is set to filter regular daily power trend points, and a ramp time threshold is set to select irregular power fluctuations, thereby identifying valid ramping events.

[0029] Based on the improved power ramp calculation formula, the power ramp detection process is as follows:

[0030] S100, first traverse each power data from the first point, and use formula (1) to determine whether it is a possible power climbing point;

[0031] S101, then use formula (2) to determine whether it is a real climbing point;

[0032] S102, further determine the duration of the climb by t+i (i=1, 2, 3…), determine whether there is |ΔP t+i |>P ε (i=1,…,τ), when i<τ, the climbing value ΔP=ΔP t+i , when ΔP>0, it is an upward climbing point, and when ΔP<0, it is a downward climbing point; τ is the specified time threshold. When i>τ, the judgment of the current moment is stopped; the climbing judgment of the points after the continuous climbing interval t~t+i, if it exists, constitutes a continuous climbing point together with the climbing interval;

[0033] S103, continue judging other points until all points are traversed, and finally record the climbing value, climbing time, and climbing times of the climbing point;

[0034] Using an improved power ramp calculation formula, we constructed and calculated photovoltaic ramp characteristics, which include the photovoltaic power ramp value, ramp duration, and ramp number. The photovoltaic power ramp clustering model uses these photovoltaic ramp characteristics to classify daily data into four categories based on weather type: sunny, partly cloudy, cloudy, and rainy.

[0035] The workflow of the photovoltaic power ramping clustering model is as follows:

[0036] S200, based on the photovoltaic power ramp clustering model, first obtains data after photovoltaic power ramp detection, and counts the number of daily ramps and the daily average power in units of days;

[0037] S201, then preliminarily judge the weather type by the daily average power, if the daily average power is less than the threshold P mean , it is directly judged as a rainy day; if the daily average power is greater than or equal to the threshold P mean When the number of climbing times is 0, it is a sunny day; when the number of climbing times is between (0, N1], it is a partly cloudy weather type; when the number of climbing times is between (N1, N2], it is a cloudy weather type; when the number of climbing times is greater than N2, it is a rainy weather type; continue the judgment for other days until all days are traversed, and finally record the clustering results to complete the photovoltaic power climbing clustering detection process.

[0038] Furthermore, the photovoltaic power ramping clustering model is:

[0039] Based on the ShapeDTW algorithm, a photovoltaic power ramp-up similar day clustering model is constructed, and the photovoltaic power time series τ=(t1, t2,…t L ) T ,τ∈R L , R L Represents the L-dimensional space composed of real numbers R. First, at each time point t in the sequence i Extract a subsequence s of length l i ;Subsequence s i t i As the center, its length l is much smaller than L; a series of subsequences are obtained, namely S=(s1,s2,…s L ) T ,s i ∈R l , R l Represents the l-dimensional space composed of real numbers R, where s i Corresponding to time point t i;

[0040] Then, shape descriptors are used to represent subsequences. Subsequences with similar shapes have similar descriptors, while subsequences with different shapes have different descriptors. i The shape descriptor of naturally encodes the time point t i Surrounding local structural information;

[0041] Designing a shape descriptor boils down to designing a mapping function F(·) that maps the subsequence s i ∈R l to the shape descriptor d i ∈R m , R m Represents the m-dimensional space composed of real numbers R, that is, d i =F(s i ), using Euclidean distance to measure the similarity between descriptors; given a shape descriptor calculation function F(·), select the slope as the shape descriptor calculation function; convert the subsequence S into a descriptor sequence D; after the above conversion, use the DTW algorithm to align the two descriptor sequences, and points with similar local shapes tend to align;

[0042] D=(d1,d2,…d L ) T ,d i ∈R m

[0043] D=F(S)=[F(s1),F(s2),…,F(s L )] T .

[0044] Furthermore, the step 3 specifically includes:

[0045] Step 3.1, preprocess the original load data, including missing values, outliers and standardization processing;

[0046] Step 3.2: Analyze the periodicity of the original load data after preprocessing and use the Spearman correlation coefficient to perform feature screening to obtain load characteristics;

[0047] Step 3.3: Use the CEEMDAN sequence decomposition model to decompose the load characteristics, and the decomposed sequence and the filtered data together constitute the training data;

[0048] Step 3.4, finally, divide the training data into load training set, load test set and load verification set, use FEDformer model training until the model training is completed, and save the optimal training model.

[0049] Furthermore, the step 4 specifically includes:

[0050] Step 4.1: Obtain the load test set, use the optimal FEDformer model to predict the load test set, and obtain the prediction results of the load test set;

[0051] Step 4.2: Classify the prediction results of the load test set into m categories and obtain cluster prediction results of m categories;

[0052] Step 4.3: Calculate the cluster prediction error of m categories. Use the dynamic interval calculation formula to obtain the interval range of different categories. Superimpose the interval range on the prediction result to obtain the final interval prediction result. The dynamic interval calculation formula is as follows:

[0053]

[0054] Where, E negtive (t)——the lower bound of the interval at time t; E postive (t)——the upper bound of the interval at time t; e(t)——the prediction error at time t; e(t) Q(i) ——the i1, i2, i3, i4 quartiles of Q(i) that meet the conditions at time t; σ1, σ2——the set adjustment thresholds.

[0055] Furthermore, the step 5 specifically includes:

[0056] Step 5.1: The objective function for optimizing the microgrid operation is to minimize the daily operating cost. This is calculated by calculating the total operating cost of each microgrid system. Environmental protection is determined by the equivalent cost of pollution emission control in the microgrid. Safety is achieved through the constraints of each microgrid system operation and system operation control.

[0057] The daily operating cost formula of the microgrid is as follows:

[0058]

[0059] Where, C is the total daily operating cost of the system (yuan); ac (t)——Daily operating cost of battery (yuan); C mt (t)——daily operating cost of micro gas turbine (yuan); C grid (t)——interaction cost between microgrid and distribution network; C ep (t)——total cost of environmental protection operation (yuan);

[0060] (1) Economic efficiency of microgrid operation

[0061] The average charge and discharge cost of the battery in period t is C ac (t) is expressed as:

[0062]

[0063] Where K ac ——Converted unit charging and discharging cost of energy storage; and ——represents the charging power and discharging power of the energy storage during period t; η ac ——Charging and discharging efficiency of the energy storage unit; Δt——scheduling step size;

[0064] The cost function of the microturbine is:

[0065] C mt (t) = [aP mt (t)+b]Δt

[0066] Where C mt (t)——operating cost of micro gas turbine in period t; P mt (t)——output power of micro gas turbine during period t; a, b——cost coefficients of fitting function;

[0067] The interaction cost between the microgrid and the distribution network can be expressed as:

[0068]

[0069] Where, λ(t) is the time-of-use electricity price of the distribution network; - The amount of electricity purchased and sold by the microgrid from the distribution grid;

[0070] (2) Environmental protection of microgrid operation

[0071] The calculation formula for the environmental protection of microgrid operation is as follows:

[0072]

[0073] In the formula, i represents different pollutants; β i ——the cost of treating pollutant i; P grid (t)——dispatching power of the power grid; ——emission fitting coefficient of distribution network pollutant i; ——emission fitting coefficient of micro gas turbine pollutant i;

[0074] (3) Microgrid operation safety

[0075] Microgrid security is achieved through the constraints of each system's operation and system operation control to realize the operation constraints of photovoltaic, energy storage, and micro gas turbine systems, and the energy balance constraint supply and demand balance; the microgrid power balance constraint is as follows:

[0076]

[0077] Where, ——is the actual absorption value of photovoltaic power; P mt (t)——power generated by the micro gas turbine; P load (t)——electrical load of the system; P ac (t)——battery charging and discharging power; ——Discharge and charge status, charge and discharge status are 0-1 variables;

[0078] Energy storage system operation constraints:

[0079] The operating constraints of the microgrid energy storage system include charging and discharging power constraints, equal initial and final capacities, and residual capacity. The energy storage unit constraints are as follows:

[0080]

[0081] Where, ——The maximum charge and discharge power allowed by energy storage; μ ac (t)——Charging and discharging state of energy storage, the discharge state value is 1, and the charging state value is 0; E ac (0)——the capacity of the energy storage at the initial moment, ——The minimum and maximum remaining capacity allowed during the energy storage dispatch process;

[0082] The operating constraints of the micro gas turbine are as follows:

[0083]

[0084] Where, - Minimum and maximum output power of the micro gas turbine;

[0085] Distribution network interaction constraints:

[0086] The constraints for power exchange between the microgrid and the distribution network are as follows:

[0087]

[0088] Where, ——The maximum value of the power exchanged between the microgrid and the distribution network; μ grid (t)——The power purchase and sale status between the microgrid and the distribution network. The value is 1 when the microgrid purchases power from the distribution network and 0 when the microgrid sells power to the distribution network.

[0089] In step 5.2, based on the interval prediction results of steps 2 and 4, the prediction error ranges of PV output and load power are constructed into an interval prediction uncertainty set U, as follows:

[0090]

[0091] Where, u is an uncertain variable; pv (t)——PV power uncertainty variable; u load (t)——load power uncertainty variable; ——Minimum and maximum values ​​of the PV power uncertainty variable; — minimum and maximum values ​​of load uncertainty variables; ——the set of real numbers; N——a positive real number;

[0092] The optimal scheduling result is obtained by solving the dynamic interval optimization scheduling model of the microgrid. The focus is on finding the most economically optimal and safest scheduling solution when the uncertain variable u changes towards the most unfavorable situation within the interval prediction uncertainty set u. It has the following form:

[0093]

[0094] Where min[·] is the first-stage optimization problem, with the optimization variable x; maxmin(·) is the second-stage optimization problem, with the optimization variables u and y. The minimization problem represents minimizing the operating cost; c is the objective function; and the maximization problem represents the scenario that leads to the most unfavorable operating cost.

[0095] In step 5.3, combined with the interval prediction uncertainty set U, the problem can be summarized as follows, and the optimal dispatch result of the microgrid is obtained:

[0096]

[0097] Where, D, K, F, G, I u ——The coefficient matrix of the variables under the corresponding constraints; d, h, γ, λ, ν, π——constant column vector; B pv (t), B load (t)——binary 0-1 variable; λ pv ——“uncertainty adjustment parameter” of photovoltaic power; λ load ——“Uncertainty adjustment parameter” of load power;

[0098] By solving the optimal scheduling variables based on the power and load uncertainty sets, the optimal scheduling variable values ​​and scheduling strategies that minimize the operating cost are obtained.

[0099] Compared with the prior art, the present invention has the following beneficial effects:

[0100] 1) The present invention uses the ConvLSTM-Attention-LSTM fusion prediction model to predict photovoltaic power. The model can more accurately capture the spatial and temporal dependencies in time series data, thereby improving the accuracy of prediction;

[0101] 2) This paper uses a photovoltaic dynamic interval prediction model based on power ramp clustering and ShapeDTW. The power ramp clustering model classifies the prediction results of the test data set into different weather types. The dynamic interval prediction method based on the ShapeDTW algorithm is further used to calculate the interval range. The model can effectively improve the accuracy of interval prediction.

[0102] 3) The present invention uses a load dynamic interval prediction model based on Kmeans clustering. The Kmeans clustering model is used to classify the prediction results of the test data set into different categories. The dynamic prediction errors of different categories are further calculated using the dynamic interval calculation formula to obtain the load interval prediction results. This model can effectively improve the load interval prediction accuracy and reduce the interval prediction width.

[0103] 4) The present invention uses a dynamic interval optimization scheduling model for microgrids that considers source-load uncertainty, establishes a two-stage robust optimization model that considers source-load uncertainty, and optimizes microgrid scheduling by constructing the interval prediction results of photovoltaic output and load power into an interval prediction uncertainty set. The model fully considers source-load uncertainty and ensures the safe and stable operation of the microgrid. BRIEF DESCRIPTION OF THE DRAWINGS

[0104] Figure 1 Flowchart of the present invention;

[0105] Figure 2 This is the flow chart for photovoltaic dynamic interval prediction;

[0106] Figure 3 This is the workflow diagram of the load dynamic interval prediction model. DETAILED DESCRIPTION

[0107] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0108] like Figure 1 As shown, a dynamic interval optimization scheduling method for a microgrid considering source and load uncertainty includes the following steps:

[0109] Step 1: PV power prediction. First, the raw PV power data is processed and the Spearman correlation coefficient feature is screened. The raw PV power data comes from an open source dataset. The PV dataset is divided into a PV training set and a PV test set. Then, the ConvLSTM-Attention-LSTM fusion prediction model is used for training and prediction. This model is a deep learning model that combines Convolutional Long Short-Term Memory (ConvLSTM), Attention Mechanism (Attention), and LSTM. Specifically, the following steps are performed:

[0110] In step 1.1, the raw PV power data (i.e., historical PV power station data) is preprocessed to obtain initial features. Data preprocessing includes missing value processing, outlier processing, and data standardization. In this implementation, missing values ​​are filled in with forward and backward terms, and outliers are not processed.

[0111] In step 1.2, the processed data is further analyzed for correlation between features and power using the Spearman correlation coefficient. Features with low correlation are deleted to obtain filtered historical data of photovoltaic power stations. The filtered historical data of photovoltaic power stations is divided into photovoltaic training set and photovoltaic test set for the ConvLSTM-Attention-LSTM fusion prediction model. In this implementation case, the photovoltaic test set data is data 180 days after the original data.

[0112] In step 1.3, the ConvLSTM-Attention-LSTM fusion prediction model is used to train the filtered historical data of photovoltaic power stations and predict future data to obtain the prediction results of the photovoltaic test set. In this implementation case, the data of 96 points in the next day are predicted.

[0113] The above ConvLSTM-Attention-LSTM fusion prediction model is:

[0114] (1) The fusion prediction model is first reshaped into the required dimensions, passed through several ConvLSTM networks, and applied to the input. The convolution operation extracts local spatial features and maintains the spatial continuity of the data. The convolution kernel slides region by region on the input feature map to perform calculations, each time calculating the weighted sum of local features. The state in the LSTM is then updated based on these local features.

[0115] (2) The Attention mechanism is integrated into the fusion model by using a custom attention function. First, the Permute layer is used to transpose the dimensions of the input data. The data is then passed through a Dense layer and processed using the softmax activation function. The output can be regarded as the attention weight for each time step. The dimensions of the attention weights are then transposed again to restore them to their original order. Finally, the input data and the attention weights are element-wise multiplied. The output is the data after the attention mechanism is applied.

[0116] (3) After the attention processing is completed, the data is passed to several LSTM layers and the ReLU activation function is used. Finally, the data is processed by the fully connected layer and the nonlinear transformation is completed by the ReLU activation function. Finally, after multiple iterations, the data is processed in the output layer to obtain the photovoltaic prediction result data.

[0117] Step 2: PV power dynamic interval prediction. First, the PV power ramp clustering model is used to classify the PV test set prediction results into multiple weather types. Then, the dynamic interval prediction method based on the ShapeDTW algorithm is used to calculate the interval range to obtain the dynamic interval prediction results. Specifically, the following are performed:

[0118] In step 2.1, the photovoltaic power ramp clustering model is used to cluster the photovoltaic test set prediction results into n weather types. The principle of the power ramp clustering model is as follows:

[0119] The power ramp clustering model is implemented using an improved power ramp calculation formula, which includes the power ramp value and ramp time. The formula is as follows:

[0120] P t '=P t (sgn((P t -P t-1 )·(P t -P t+1 )>0) (1)

[0121] ΔP t+i =P t+i -P′ t (i=1,…,τ) (2)

[0122] P ε =ηP d (3)

[0123] Where, t is the time of hill climbing detection; P t ——power at time t; P t '——possible climbing point; ΔPt+i——power difference between time t+i and time t; P ε——climbing threshold; τ——climbing duration threshold; P d ——PV installed capacity, η——ramp threshold as a percentage of installed capacity. In this implementation case, η is 20%, and sgn(*) is the sgn function.

[0124] The improved power ramp calculation formula determines the ramp starting point and continuous ramping by traversing power data points; a ramp threshold is set to filter regular daily power trend points, and a ramp time threshold is set to select irregular power fluctuations, thereby identifying effective ramping events.

[0125] Based on the above optimized photovoltaic power ramp detection formula, the power ramp detection process is as follows:

[0126] S100, first traverse each power data starting from the first point, and use formula (1) to determine whether it is a possible power climbing point.

[0127] S101, then use formula (2) to determine whether it is a real climbing point.

[0128] S102, further determine the duration of the climb by t+i (i=1, 2, 3…), determine whether there is |ΔP t+i |>P ε (i=1,…,τ), when i<τ, the climbing value ΔP=ΔP t+i , when ΔP>0, it is an upward climbing point, and when ΔP<0, it is a downward climbing point; τ is the specified time threshold. When i>τ, the judgment at the current moment is stopped; the climbing judgment of the points after the continuous climbing interval t~t+i, if it exists, constitutes a continuous climbing point together with the climbing interval.

[0129] S103, continue judging other points until all points are traversed, and finally record the climbing value, climbing time, and climbing times of the climbing point.

[0130] The photovoltaic power ramping clustering model is:

[0131] Based on the ShapeDTW algorithm, a photovoltaic power ramp-up similar day clustering model is constructed, and the photovoltaic power time series τ=(t1, t2,…t L ) T ,τ∈R L , R L Represents the L-dimensional space composed of real numbers R. First, at each time point t in the sequence i Extract a subsequence s of length l i . subsequences i t i As the center, its length l is much smaller than L. We get a series of subsequences, namely S=(s1,s2,…sL ) T ,s i ∈R l , R l Represents the l-dimensional space composed of real numbers R, where s i Corresponding to time point t i .

[0132] Then, shape descriptors are used to represent subsequences. Subsequences with similar shapes have similar descriptors, while subsequences with different shapes have different descriptors. i The shape descriptor of naturally encodes the time point t i The surrounding local structural information.

[0133] Designing a shape descriptor boils down to designing a mapping function F(·) that maps the subsequence s i ∈R l to the shape descriptor d i ∈R m , R m Represents the m-dimensional space composed of real numbers R, that is, d i =F(s i ), using Euclidean distance to measure the similarity between descriptors. Given a shape descriptor calculation function F(·), the slope is selected as the shape descriptor calculation function to convert the subsequence S into a descriptor sequence D. After the above conversion, the DTW algorithm is used to align the two descriptor sequences. Points with similar local shapes tend to align.

[0134] D=(d1,d2,…d L ) T ,d i ∈R m

[0135] D=F(S)=[F(s1),F(s2),…,F(s L )] T .

[0136] Using the improved power ramp calculation formula, the photovoltaic ramp characteristics are constructed and calculated and counted. The photovoltaic ramp characteristics include the photovoltaic power ramp value, ramp duration, and ramp number. The photovoltaic power ramp clustering model uses these photovoltaic ramp characteristics to divide the data of each day into four categories according to the weather type: sunny, partly cloudy, cloudy, and rainy.

[0137] The workflow of the photovoltaic power ramping clustering model is as follows:

[0138] S200 , based on the photovoltaic power ramp clustering model, first obtain the data after the photovoltaic power ramp detection, and count the number of daily ramps and the daily average power in units of days.

[0139] S201, then preliminarily judge the weather type based on the daily average power, and divide the weather into 4 types: sunny, partly cloudy, cloudy, and rainy. If the daily average power is less than the threshold value P mean , it is directly judged as a rainy day; if the daily average power is greater than the threshold P mean , when the number of climbing times is 0, it is sunny; when the number of climbing times is (0, N1], it is n1 weather type; when the number of climbing times is (N1, N2], it is n2 weather type; when the number of climbing times is greater than N2, it is n2 weather type; continue the judgment of other days until all days are traversed, and finally record the clustering results to complete the photovoltaic power climbing clustering detection process. In this implementation case, the daily average power is greater than the threshold P mean When the number of climbing is 0, it is sunny; when the number of climbing is between (0, N1], it is partly cloudy; when the number of climbing is between (N1, N2], it is cloudy; when the number of climbing is greater than N2, it is rainy.

[0140] In step 2.2, use the ShapeDTW algorithm to select k similar days from the PV test set prediction results. Calculate the prediction error for these similar days, find the maximum absolute value of the prediction error, and then superimpose the interval on the prediction results to obtain the final interval prediction result. In this implementation, k is set to 5.

[0141] Step 3, power load forecasting, first preprocesses the original load data and screens the Spearman correlation coefficient features. Then, the CEEMDAN sequence decomposition model is used to decompose the load features. The decomposed sequence and the screened data together constitute the training data. The load dataset is divided into a load training set, a load test set, and a load verification set. Finally, FEDformer is used for model training and forecasting, which specifically includes:

[0142] Step 3.1: Preprocess the original load data, including missing values, outliers, and standardization. In this implementation case, missing values ​​are filled with the previous day's adjacent date, and outliers are filled with the previous and next items.

[0143] In step 3.2, the periodicity of the original load data after preprocessing is further analyzed, and the Spearman correlation coefficient is used for feature screening to obtain the load characteristics.

[0144] In step 3.3, the CEEMDAN sequence decomposition model is used to decompose the load characteristics, and the decomposed sequence and the filtered data together constitute the training data.

[0145] In step 3.4, the training data is divided into a load training set, a load test set, and a load verification set. The FEDformer model is used for training until the model training is completed, and the optimal training model is saved.

[0146] Step 4: Load dynamic interval prediction. First, the Kmeans clustering model is used to classify the load test set prediction results into multiple categories. The dynamic interval calculation formula is then used to calculate the dynamic prediction errors of the multiple categories. The dynamic prediction errors are superimposed on the point prediction results to obtain the final photovoltaic and load interval prediction results, which specifically include:

[0147] Step 4.1: Obtain the load test set, use the optimal FEDformer model to predict the load test set, and obtain the prediction result of the load test set.

[0148] Step 4.2: Classify the prediction results of the load test set into m categories to obtain cluster prediction results of m categories. In this implementation case, m is 4, which is divided into 4 categories: high load, medium-high load, medium-low load, and low load.

[0149] Step 4.3: Calculate the cluster prediction errors of the four categories, use the dynamic interval calculation formula to obtain the interval ranges of different categories, and superimpose the interval ranges on the point prediction results to obtain the final interval prediction results. The dynamic interval calculation formula is as follows:

[0150]

[0151] Where, E negtive (t)——the lower bound of the interval at time t; E postive (t)——the upper bound of the interval at time t; e(t)——the prediction error at time t; e(t) Q(i) — the i1, i2, i3, and i4 quartiles of Q(i) that meet the conditions at time t; σ1 and σ2 are the set adjustment thresholds. In this implementation, Q(i) is the upper quartile.

[0152] Step 5: Dynamic interval optimization scheduling of the microgrid considering source-load uncertainty. First, a dynamic interval optimization scheduling model of the microgrid considering source-load uncertainty is established. Then, the objective function and constraints of the dynamic interval optimization scheduling model of the microgrid are established. The optimization scheduling results of the microgrid are obtained by solving the problem, which specifically includes:

[0153] In step 5.1, the microgrid's optimized operation is based on minimizing daily operating costs to ensure the microgrid's economic, environmental, and safety. Economic efficiency is calculated through the total operating cost of each microgrid system. Environmental efficiency is determined by the equivalent cost of pollution emission control. Safety is achieved through the constraints of each system's operation and system operation control. Specifically, the microgrid's daily operating cost can be expressed by the following formula:

[0154]

[0155] Where, minC is the minimum value of the system's total daily operating cost C (yuan); C ac (t)——Daily operating cost of battery (yuan); C mt (t)——daily operating cost of micro gas turbine (yuan); C grid (t)——interaction cost between microgrid and distribution network; C ep (t)——Total cost of environmental protection operation (yuan).

[0156] (1) Economic efficiency of microgrid operation

[0157] The average charge and discharge cost of the battery in period t is C ac (t) is expressed as:

[0158]

[0159] Where K ac ——Converted unit charging and discharging cost of energy storage; and ——represents the charging power and discharging power of the energy storage during period t; η ac ——Charging and discharging efficiency of the energy storage unit; Δt——scheduling step size.

[0160] The cost function of the microturbine is:

[0161] C mt (t) = [aP mt (t)+b]Δt

[0162] Where C mt (t)——operating cost of micro gas turbine in period t; P mt (t)——output power of micro gas turbine during period t; a, b——cost coefficients of fitting function.

[0163] The interaction cost between the microgrid and the distribution network can be expressed as:

[0164]

[0165] Where, λ(t) is the time-of-use electricity price of the distribution network; ——The electric power purchased and sold by the microgrid from the distribution network.

[0166] (2) Environmental protection of microgrid operation

[0167] The environmental friendliness of microgrid operation is determined by the equivalent cost of pollution emission control of the system, where the pollution emission control equivalent is determined by the amount of natural gas consumed by the micro gas turbine and the amount of electricity purchased from the distribution network. The formula for calculating the environmental friendliness of microgrid operation is as follows:

[0168]

[0169] In the formula, i represents different pollutants, including CO2, SO2 and NO X Several types of pollutants; β i ——the cost of treating pollutant i; P grid (t)——dispatching power of distribution network; P mt (t) — dispatch power of micro gas turbine; ——emission fitting coefficient of distribution network pollutant i; ——Emission fitting coefficient of micro gas turbine pollutant i. In this implementation case, CO2, SO2 and NO X The treatment costs are 0.02, 2.375 and 2.12 respectively. The CO2, SO2 and NO X The pollutant emission coefficients are 0.22 and 1.8×10 -3 and 1.6×10 -3 , CO2, SO2 and NO in micro gas turbines X The pollutant emission coefficients are 0.968, 0.968 and 1.98×10 -6 .

[0170] (3) Microgrid operation safety

[0171] Microgrid security is achieved through the operating constraints and system operation control of each microgrid system, including photovoltaic, energy storage, and micro gas turbine system operation constraints, and energy balance constraints on supply and demand balance.

[0172] The power balance constraint of the microgrid requires that all sources and loads in the microgrid maintain a balance to ensure the balance of power supply and demand in the microgrid. The power balance constraint of the microgrid is as follows:

[0173]

[0174] Where, ——Power purchased from the power grid; ——Power sold by the power grid; ——actual absorption value of photovoltaic power; P mt(t)——power generated by the micro gas turbine; P load (t)——microgrid electric load; P ac (t)——battery charging and discharging power; ——Discharge and charge status, charge and discharge status are 0-1 variables.

[0175] The operating constraints of the microgrid energy storage system include charge and discharge power constraints, equal initial and final capacities, and residual capacity. The energy storage unit must meet the following constraints during operation:

[0176]

[0177]

[0178] Where, ——The maximum charge and discharge power allowed by energy storage; μ ac (t)——Charging and discharging state of energy storage, the discharge state value is 1, and the charging state value is 0; E ac (0)——the capacity of the energy storage at the initial moment, ——The minimum and maximum remaining capacity allowed during the energy storage dispatch process. 500kW, 1600kWh, 80kWh, E ac (0) is 800kWh.

[0179] The power output of the micro gas turbine should meet the load demand within the microgrid. At the same time, the maximum power output limit of the micro gas turbine must also be considered. The micro gas turbine only considers the output power constraint:

[0180]

[0181] Where, ——The minimum and maximum output power of the micro gas turbine. In the implementation case, 300Kw, is 0.

[0182] The power interaction between the microgrid and the distribution network mainly includes the purchase and sale of electricity. The power exchange between the microgrid and the distribution network must comply with certain constraints:

[0183]

[0184] Where, ——The maximum value of the power exchanged between the microgrid and the distribution network; - The amount of electricity purchased and sold by the microgrid from the distribution grid; μ ——The electric power purchased and sold by the microgrid from the distribution network. grid (t)——The state of electricity purchase and sale between the microgrid and the distribution network. When the microgrid purchases electricity from the distribution network, the value is 1; when the microgrid sells electricity to the distribution network, the value is 0. It is 400kW.

[0185] In step 5.2, a two-stage robust optimization model considering source-load uncertainty is established to obtain the optimal optimization scheduling result. Based on the interval prediction results of steps 2 and 4, the prediction error range of photovoltaic output and load power is constructed into an interval prediction uncertainty set U, as follows:

[0186]

[0187] Where, u is an uncertain variable; pv (t)——PV power uncertainty variable; u load (t)——load power uncertainty variable; ——Minimum and maximum values ​​of the PV power uncertainty variable; — minimum and maximum values ​​of load uncertainty variables; ——The set of real numbers; N——a positive real number.

[0188] The two-stage robust optimization model considering the dynamic range of source and load aims to find the most economically optimal and safest scheduling solution when the uncertain variable u changes towards the most unfavorable situation within the uncertainty set U. It has the following form:

[0189]

[0190] Where min[·] is the first-stage optimization problem with the optimization variable x; maxmin(·) is the second-stage optimization problem with the optimization variables u and y. The minimization problem represents minimizing the operating cost; c is the objective function; and the maximization problem represents the scenario that leads to the most unfavorable operating cost.

[0191] In step 5.3, combined with the uncertainty set, the problem can be summarized as follows to obtain the optimal dispatch result of the microgrid:

[0192]

[0193] Where, D, K, F, G, I u ——The coefficient matrix of the variables under the corresponding constraints; d, h, γ, λ, ν, π——constant column vector; B pv (t), B load (t)——binary 0-1 variable; λ pv ——“uncertainty adjustment parameter” of photovoltaic power; λload ——“uncertainty adjustment parameter” of load power. In the implementation case, λ pv ,λ load Both are taken as 24.

[0194] By solving the optimal scheduling variables based on the power and load uncertainty sets, the optimal scheduling variable values ​​and scheduling strategies that minimize the operating cost are obtained.

[0195] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic interval optimization scheduling method for microgrids considering source and load uncertainty, characterized in that: The method comprises the following steps: Step 1: PV power prediction. First, the original PV power data is processed and the Spearman correlation coefficient feature is screened. The PV data set is divided into a PV training set and a PV test set. Then, the ConvLSTM-Attention-LSTM fusion prediction model is used for training and prediction. Step 2: PV power dynamic interval prediction. First, the PV power ramp clustering model is used to classify the PV test set prediction results into multiple weather types. Then, the dynamic interval prediction method based on the ShapeDTW algorithm is used to calculate the interval range to obtain the dynamic interval prediction results. Specifically, the following are performed: Step 2.1: Cluster the photovoltaic test set prediction results into n weather types using the photovoltaic power ramping clustering model; Step 2.2: Use the ShapeDTW algorithm to select k similar days of future prediction results from the PV test set prediction results, calculate the prediction error of the similar days, find the maximum absolute value of the prediction error to obtain the interval range, and finally superimpose the interval range on the prediction result to obtain the final interval prediction result; The photovoltaic power ramp clustering model is implemented using an improved optimized power ramp calculation formula, which is as follows: (1) (2) (3) Where, t is the time of hill climbing detection; P t ——power at time t; P t ’ ——Possible climbing point; △P t+i ——The power difference between time t+i and time t; P ε ——climbing threshold; P d ——PV installed capacity, η——ramp threshold as a percentage of installed capacity; The improved power ramp calculation formula traverses power data points to determine the ramp starting point and continuous ramping. A ramp threshold is set to filter regular daily power trend points, and a ramp time threshold is set to select irregular power fluctuations, thereby identifying valid ramping events. Based on the improved power ramp calculation formula, the power ramp detection process is as follows: S100, first traverse each power data from the first point, and use formula (1) to determine whether it is a possible power climbing point; S101, then use formula (2) to determine whether it is a real climbing point; S102, further determine the duration of the climb by t+i In the equation, determine whether there is |△P t+i |>P ε The climbing point, i=1,…,τ, when i<τ, the climbing value △P=△P t+i , when △P>0, it is an upward climbing point, and when △P<0, it is a downward climbing point; τ is the specified time threshold. When i>τ, the judgment of the current moment is stopped; the climbing judgment of the points after the continuous climbing interval t~t+1, if it exists, constitutes a continuous climbing point together with the climbing interval; S103, continue judging other points until all points are traversed, and finally record the climbing value, climbing time, and climbing times of the climbing point; Using an improved power ramp calculation formula, we constructed and calculated photovoltaic ramp characteristics, which include the photovoltaic power ramp value, ramp duration, and ramp number. The photovoltaic power ramp clustering model uses these photovoltaic ramp characteristics to classify daily data into four categories based on weather type: sunny, partly cloudy, cloudy, and rainy. The workflow of the photovoltaic power ramping clustering model is as follows: S200, based on the photovoltaic power ramp clustering model, first obtains data after photovoltaic power ramp detection, and counts the number of daily ramps and the daily average power in units of days; S201, then preliminarily judge the weather type by the daily average power, if the daily average power is less than the threshold P mean , it is directly judged as a rainy day; if the daily average power is greater than or equal to the threshold P mean When the number of ramps is 0, it is a sunny day; when the number of ramps is between (0, N1], it is a partly cloudy weather type; when the number of ramps is between (N1, N2], it is a cloudy weather type; when the number of ramps is greater than N2, it is a rainy weather type; continue the judgment for other days until all days are traversed, and finally record the clustering results to complete the photovoltaic power ramp clustering detection process; Step 3: Power load forecasting. First, the original load data is preprocessed and the Spearman correlation coefficient feature is screened. Then, the CEEMDAN sequence decomposition model is used to decompose the load features. The decomposed sequence and the screened data together constitute the training data. The load dataset is divided into a load training set, a load test set, and a load validation set. Finally, the FEDformer model is used for model training and forecasting. Step 4: Load dynamic interval prediction. First, the Kmeans clustering model is used to classify the load test set prediction results into multiple categories. The dynamic interval calculation formula is then used to calculate the dynamic prediction errors of the multiple categories. The dynamic prediction errors are then superimposed on the point prediction results to obtain the final photovoltaic and load interval prediction results. Step 5, dynamic interval optimization scheduling of microgrid considering source-load uncertainty, first establish a dynamic interval optimization scheduling model of microgrid considering source-load uncertainty, further establish the objective function and constraint conditions of the dynamic interval optimization scheduling model of microgrid, and solve to obtain the optimization scheduling result of microgrid.

2. A microgrid dynamic interval optimization scheduling method considering source and load uncertainty according to claim 1, characterized in that: The step 1 specifically includes: Step 1.1: Preprocess the original PV power data to obtain initial features. Data preprocessing includes missing value processing, outlier processing, and data standardization. Step 1.2: Use the Spearman correlation coefficient to analyze the correlation between features and power on the processed PV power station historical data. Remove features with low correlation to obtain filtered PV power station historical data. Divide the filtered PV power station historical data into a PV training set and a PV test set for the ConvLSTM-Attention-LSTM fusion prediction model. In step 1.3, the ConvLSTM-Attention-LSTM fusion prediction model is used to train the filtered historical data of photovoltaic power stations and predict future data.

3. A microgrid dynamic interval optimization scheduling method considering source and load uncertainty according to claim 1, characterized in that: The ConvLSTM-Attention-LSTM fusion prediction model is: (1) The ConvLSTM-Attention-LSTM fusion prediction model is first reshaped into the dimensions required by the model, passed through several ConvLSTM networks and applied to the input; local spatial features are extracted through convolution operations to maintain the spatial continuity of the data. The convolution kernel slides region by region on the input feature map to perform calculations, each time calculating the weighted sum of local features, and then updating the state in the LSTM based on these local features; (2) The Attention mechanism is integrated into the ConvLSTM-Attention-LSTM fusion prediction model by using a custom attention function. First, the Permute layer is used to transpose the dimension of the input data; then the data passes through a Dense layer and is processed using the softmax activation function. The output result is regarded as the attention weight of each time step; Then the dimensions of the attention weights are transposed back to their original order, and finally the input data and the attention weights are element-wise multiplied. The output is the data after the attention mechanism is applied. (3) After completing the attention processing, the data is passed to several LSTM layers and the ReLU activation function is used; finally, the data is processed by the fully connected layer and the nonlinear transformation is completed by the ReLU activation function. Finally, after multiple iterations, the data is processed in the output layer to obtain the photovoltaic prediction result data.

4. A microgrid dynamic interval optimization scheduling method considering source and load uncertainty according to claim 1, characterized in that: The photovoltaic power ramping clustering model is: Based on the ShapeDTW algorithm, a photovoltaic power ramp-up similar day clustering model is constructed, and the photovoltaic power time series with a length of L is selected. , R L Represents the L-dimensional space composed of real numbers R. First, at each time point t in the sequence i Extract a subsequence s of length l i ;Subsequence s i t i As the center, its length l is much smaller than L; a series of subsequences are obtained, namely , R l Represents the l-dimensional space composed of real numbers R, where s i Corresponding to time point t i ; Then, shape descriptors are used to represent subsequences. Subsequences with similar shapes have similar descriptors, while subsequences with different shapes have different descriptors. i The shape descriptor of naturally encodes the time point t i Surrounding local structural information; Designing a shape descriptor boils down to designing a mapping function F(·), mapping the subsequence To shape descriptor , R m Represents the m-dimensional space composed of real numbers R, that is, d i =F(s i ), the Euclidean distance is used to measure the similarity between descriptors; Given a shape descriptor calculation function F(·), the slope is selected as the shape descriptor calculation function; the subsequence S is converted into a descriptor sequence D; after the above conversion, the DTW algorithm is used to align the two descriptor sequences. Points with similar local shapes tend to be aligned. ， 。 5. A method for dynamic interval optimization scheduling of a microgrid considering source and load uncertainty according to claim 1, characterized in that: The step 3 specifically includes: Step 3.1, preprocess the original load data, including missing values, outliers and standardization processing; Step 3.2: Analyze the periodicity of the original load data after preprocessing and use the Spearman correlation coefficient to perform feature screening to obtain load characteristics; Step 3.3: Use the CEEMDAN sequence decomposition model to decompose the load characteristics, and the decomposed sequence and the filtered data together constitute the training data; Step 3.4, finally, divide the training data into load training set, load test set and load verification set, use FEDformer model training until the model training is completed, and save the optimal training model.

6. A method for dynamic interval optimization scheduling of a microgrid considering source and load uncertainty according to claim 1, characterized in that: The step 4 specifically includes: Step 4.1: Obtain the load test set, use the optimal FEDformer model to predict the load test set, and obtain the prediction results of the load test set; Step 4.2: Classify the prediction results of the load test set into m categories and obtain cluster prediction results of m categories; Step 4.3: Calculate the cluster prediction error of m categories. Use the dynamic interval calculation formula to obtain the interval range of different categories. Superimpose the interval range on the prediction result to obtain the final interval prediction result. The dynamic interval calculation formula is as follows: ， Where, E negtive (t)——the lower bound of the interval at time t; E postive (t)——the upper bound of the interval at time t; e(t)——the prediction error at time t; e(t) Q(i) ——the i1, i2, i3, i4 quartiles of Q(i) that meet the conditions at time t; σ1, σ2——the set adjustment thresholds.

7. A method for dynamic interval optimization scheduling of a microgrid considering source and load uncertainty according to claim 1, characterized in that: The step 5 specifically includes: Step 5.1: The objective function for optimizing the microgrid operation is to minimize the daily operating cost. This is calculated by calculating the total operating cost of each microgrid system. Environmental protection is determined by the equivalent cost of pollution emission control in the microgrid. Safety is achieved through the constraints of each microgrid system operation and system operation control. The daily operating cost formula of the microgrid is as follows: ， Where, C is the total daily operating cost of the system (yuan); ac (t)——Daily operating cost of battery (yuan); C mt (t)——daily operating cost of micro gas turbine (yuan); C grid (t)——interaction cost between microgrid and distribution network; C ep (t)——total cost of environmental protection operation (yuan); (1) Economic efficiency of microgrid operation Battery in Average charging and discharging cost C during the period ac (t) is expressed as: ， Where K ac ——Converted unit charging and discharging cost of energy storage; and ——respectively The charging power and discharging power of the energy storage during the time period; η ac ——Charge and discharge efficiency of energy storage unit; △t——scheduling step length; The cost function of the microturbine is: ， Where C mt (t)——operating cost of micro gas turbine in period t; P mt (t)——output power of micro gas turbine during period t; a, b——cost coefficients of fitting function; The interaction cost between the microgrid and the distribution network can be expressed as: ， Where, λ(t) is the time-of-use electricity price of the distribution network; 、 - The amount of electricity purchased and sold by the microgrid from the distribution grid; (2) Environmental friendliness of microgrid operation The calculation formula for the environmental protection of microgrid operation is as follows: ， In the formula, i represents different pollutants; β i ——the cost of treating pollutant i; P grid (t)——dispatching power of the power grid; ——emission fitting coefficient of distribution network pollutant i; ——emission fitting coefficient of micro gas turbine pollutant i; (3) Microgrid operation safety Microgrid security is achieved through the constraints of each system's operation and system operation control to realize the operation constraints of photovoltaic, energy storage, and micro gas turbine systems, and the energy balance constraint supply and demand balance; the microgrid power balance constraint is as follows: ， Where, ——is the actual absorption value of photovoltaic power; P mt (t)——power generated by the micro gas turbine; P load (t)——electrical load of the system; P ac (t)——battery charging and discharging power; 、 ——Discharge and charge status, charge and discharge status are 0-1 variables; Energy storage system operation constraints: The operating constraints of the microgrid energy storage system include charging and discharging power constraints, equal initial and final capacities, and residual capacity. The energy storage unit constraints are as follows: ， ， ， Where, ——The maximum charge and discharge power allowed by energy storage; μ ac (t)——Charging and discharging state of energy storage, the discharge state value is 1, and the charging state value is 0; E ac (0)——the capacity of the energy storage at the initial moment, 、 ——The minimum and maximum remaining capacity allowed during the energy storage dispatch process; The operating constraints of the micro gas turbine are as follows: ， Where, 、 - Minimum and maximum output power of the micro gas turbine; Distribution network interaction constraints: The constraints for power exchange between the microgrid and the distribution network are as follows: ， ， Where, ——The maximum value of the power exchanged between the microgrid and the distribution network; ——The power purchase and sale status of the microgrid and the distribution network. When the microgrid purchases power from the distribution network, the value is 1; when the microgrid sells power to the distribution network, the value is 0; In step 5.2, based on the interval prediction results of steps 2 and 4, the prediction error ranges of PV output and load power are constructed into an interval prediction uncertainty set U, as follows: ， Where, ——uncertain variable; u pv (t)——PV power uncertainty variable; u load (t)——load power uncertainty variable; 、 ——Minimum and maximum values ​​of the PV power uncertainty variable; 、 — minimum and maximum values ​​of load uncertainty variables; ——the set of real numbers; N——a positive real number; Solve the microgrid dynamic interval optimization scheduling model to obtain the optimal optimization scheduling result, focusing on finding the uncertain variables Predicting an uncertain set in an interval The most economically optimal and safest scheduling solution when the internal situation changes towards the most unfavorable situation has the following form: ， Where min[·] is the first stage optimization problem, the optimization variable is x; max min(·) is the second stage optimization problem, the optimization variable is and , where the minimization problem represents minimizing the operating cost; c is the objective function; the maximization problem represents the scenario that leads to the most unfavorable operating cost; Step 5.3: Combine interval prediction with uncertainty set , the problem can be summarized as follows, and the optimal dispatch result of the microgrid is obtained: ， Where, D, K, F, G, I u ——The coefficient matrix of the variables under the corresponding constraints; ——constant column vector; B pv (t), B load (t)——binary 0-1 variable; λ pv ——"uncertainty adjustment parameter" of photovoltaic power; λ load ——"uncertainty adjustment parameter" of load power; By solving the optimal scheduling variables based on the power and load uncertainty sets, the optimal scheduling variable values ​​and scheduling strategies that minimize the operating cost are obtained.

Images