Photovoltaic generating capacity prediction method based on NGBoost algorithm and energy storage control
Through the NGBoost algorithm and energy storage control, combined with isolated forests, CEEMDAN and MPPT, the prediction accuracy and generality of photovoltaic power generation are solved, and high-precision and low-cost photovoltaic power generation prediction is achieved to meet the grid connection requirements.
Patent Information
- Application Number
- CN202411049941.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-01
AI Technical Summary
The existing photovoltaic power generation prediction method is not effective when the weather changes sharply and the time prediction scale is long. The fitting effect of a single model is not ideal, making it difficult to meet the high-precision requirements. The frequent adjustment of the model reduces the generality and increases the time. cost.
The NGBoost algorithm combined with energy storage control is used to detect outliers through the isolated forest method, the cubic spline interpolation correction data is corrected, the CEEMDAN frequency division algorithm decomposes the illumination intensity, the A-BiGRU point prediction model and the NGBoost interval prediction model are used to predict the illumination intensity, and the MPPT is used to predict the illumination intensity. The algorithm is converted into photovoltaic power generation and sets the energy storage control logic to improve prediction accuracy.
It improves the accuracy and generality of photovoltaic power generation prediction, meets grid-connected accuracy requirements, reduces the cost and time cost of energy storage systems, and enhances the interpretability of the prediction results.
Smart Images

Figure CN119067250A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power electronics technology, and in particular to a photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control. Background Art
[0002] As a new energy source, solar energy has attracted more and more attention due to its huge storage capacity and cleanliness. Photovoltaic power generation has become the main trend of current new energy power generation and has attracted the attention of countries around the world. Large-scale use of photovoltaic power generation has also become the preferred approach.
[0003] However, photovoltaic power generation is affected by many factors, and its output is indirect, random, and volatile, which will affect the safety and stability of the power grid during the grid connection process. Therefore, it is necessary to make reasonable and high-precision predictions of photovoltaic power generation. At present, photovoltaic power generation predictions are mainly calculated using physical, statistical, and machine learning methods.
[0004] The physical model has a narrow scope of application and is too simple in terms of conditions of use. It has poor prediction effects for weather conditions with drastic weather changes and solar irradiance with a long time prediction scale. The statistical method has high requirements for data volume and data quality. It needs to be trained with huge amounts of high-quality data so that the model can achieve ideal prediction accuracy, and is therefore subject to great limitations. A single machine learning method is often affected by the advantages and disadvantages of the model itself, and the prediction accuracy is often not high. The solar intensity has strong randomness and its value is affected by many factors and has strong uncertainty. The fitting effect of a single model is not ideal. Therefore, the current main research direction is to use artificial intelligence algorithms based on hybrid models for prediction. However, despite the use of hybrid models, the prediction accuracy of these methods is currently difficult to further improve, and there is still a gap with the actual accuracy requirements. To further improve the accuracy of the model, a more effective machine learning model is needed, or the model architecture is adjusted according to local conditions. The former is difficult and difficult to break through in a short time. Although the latter may perform well under special conditions, it is difficult to maintain high accuracy when the application scenario is changed. The model architecture needs to be adjusted again, and it can only be put into use after multiple attempts. This undoubtedly reduces the versatility of the method and increases unnecessary time costs. Summary of the invention
[0005] Purpose of the invention: The purpose of the present invention is to provide a photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control, so as to improve the prediction accuracy of photovoltaic power generation and meet the requirements of photovoltaic grid-connected accuracy.
[0006] Technical solution: A photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control, including the following steps:
[0007] S1, the collected original data set is divided into multiple groups of feature columns according to time and features, and the isolation forest method is used to detect outliers for each feature column;
[0008] S2, use the cubic spline interpolation method to replace the outliers in each feature column, and then merge all feature columns to obtain the preprocessed data set;
[0009] S3, using CEEMDAN frequency division algorithm, decomposes the preprocessed light intensity into multiple modules; then divides the data of each module into point training set and point test set, trains and evaluates the A-BiGRU point prediction model respectively, and saves the best A-BiGRU point prediction model; uses meteorological data X as the input of the A-BiGRU point prediction model, linearly adds the point prediction results of each module, and obtains the point prediction light intensity result Y i ;
[0010] S4, using the preprocessed data set and the point prediction light intensity result, the predicted light intensity is interval predicted by the NGBoost interval prediction model to obtain the interval prediction light intensity result;
[0011] S5, using the MPPT algorithm to convert the light intensity into photovoltaic power generation, and obtain the predicted photovoltaic power generation and the photovoltaic power generation corresponding to the upper and lower limits of the light intensity range;
[0012] S6, select appropriate energy storage capacity according to the upper and lower limits of power generation, and build an energy storage control prediction system; set the energy storage control logic as follows: when the actual power generation is greater than the predicted power generation, the energy storage is charged; when the actual power generation is less than or equal to the predicted power generation, the energy storage is discharged.
[0013] Furthermore, the original data set includes historical meteorological data and light intensity data, and the features include humidity, temperature, wind direction, and air pressure. The implementation steps of using the isolation forest method to detect outliers for each feature column are as follows:
[0014] S11, put n samples of a single feature column into the root node of the tree;
[0015] S12, the isolation forest algorithm randomly specifies a dimension and randomly generates a cutting point in the current node data. The cutting point is generated between the maximum value and the minimum value of the specified dimension in the current node data;
[0016] S13, generate a hyperplane with the cutting point, and divide the data space of the current node into two subspaces: put the data less than p in the specified dimension in the left leaf of the current node, and put the data greater than or equal to p in the right leaf of the current node;
[0017] S14, looping steps S12 and S13 in the leaf nodes, continuously constructing new leaf nodes, until each leaf node contains only one data, and obtaining n isolation forests;
[0018] S15, repeat steps S11-S14, and filter out the outliers of each feature column by using the isolation forest method.
[0019] Furthermore, in step S2, the implementation steps of replacing the abnormal value of each feature column by using the cubic spline interpolation method are as follows:
[0020] S21, for a single feature column, after recording the sequence label corresponding to the outlier, remove the outlier;
[0021] S22, constructing a cubic spline interpolation function for the feature column after removing outliers;
[0022] S23, using the sequence label corresponding to the outlier as the input of the cubic spline interpolation function to obtain a corrected value, using the corrected value as new data to replace the missing outlier, and constructing a new feature column;
[0023] S24, repeating steps S21 to S23 to obtain each corrected feature column, and recombining the each corrected feature column to obtain a preprocessed data set.
[0024] Furthermore, in step S3, the implementation steps of using the CEEMDAN frequency division algorithm to divide the light intensity into multiple modules are as follows:
[0025] S31, add different white noise sequences to the original light intensity x(t) to form multiple noise-enhanced signals; let the added noise be ω i (t), we get:
[0026] x i (t) = x(t) + ω i (t)
[0027] Among them, x i (t) is the i-th noise-enhanced signal;
[0028] S32, performing EMD decomposition on each noise enhanced signal to obtain an intrinsic mode function IMF;
[0029] S33, average the first IMF obtained from all noise enhanced signals to obtain the first IMF1 of the original light intensity:
[0030]
[0031] Where, M is the number of noise-enhanced signals;
[0032] S34, subtract the first IMF1 from the original light intensity x(t) to obtain the residual signal:
[0033] r i (t) = x(t) - IMF1
[0034] Among them, r i (t) represents the residual signal;
[0035] S35, for the remaining signal r i (t) Repeat steps S31 to S34, continue to add white noise and perform EMD decomposition to obtain the IMF of the remaining signal, until all IMFs are extracted and the remaining signal becomes a monotonic function or white noise;
[0036] S36, synthesize all IMFs to obtain the complete original light intensity decomposition result.
[0037] Further, in step S3, for the A-BiGRU point prediction model, the meteorological data X is used as input and the light intensity decomposition state is used as output y i ; Input the point training set of each module into the A-BiGRU point prediction model for training, use the point test set of each module for point prediction, evaluate the A-BiGRU point prediction model, and obtain the final A-BiGRU point prediction model corresponding to each module.
[0038] Further, in step S4, the detailed steps of obtaining the target light intensity prediction interval are as follows:
[0039] S41, the pre-processed historical meteorological data X is input into the A-BiGRU point prediction model to obtain the light intensity point prediction value Y i ;
[0040] S42, the light intensity point prediction result Y i The error value with the actual light intensity Y is recorded as output δ, and a new interval prediction data set is constructed with the historical meteorological data X and the error value δ, and the interval prediction data set is divided into an interval training set and an interval test set;
[0041] S43, taking the historical meteorological data X as input and the error value δ as output, inputting the interval training set into the NGBoost interval prediction model, training the NGBoost interval prediction model, and using the interval test set to perform interval prediction to obtain a trained NGBoost interval prediction model;
[0042] S44, inputting the preprocessed historical meteorological data X and the point prediction error δ into the trained NGBoost interval prediction model to obtain the probability distribution parameter mean μ and standard deviation σ required to build the target light intensity prediction interval;
[0043] S45, obtain the target light intensity prediction interval according to the probability distribution parameter mean μ and standard deviation σ:
[0044] I α =[μ-z α2 σ,μ+z α2 σ]
[0045] Among them, α is the confidence interval, I α is the target prediction interval, z α2 is the corresponding standard score.
[0046] Compared with the prior art, the present invention has the following significant effects:
[0047] 1. The present invention detects outliers in the data by using the isolation forest method, and then corrects the outliers by using the cubic spline interpolation method, effectively avoiding the influence of the original data set errors on the prediction results;
[0048] 2. Use the CEEMDAN frequency division algorithm to divide the data set into multiple modules according to light intensity, and use the A-BiGRU point prediction model to predict each module, so that the prediction of light intensity is more targeted and flexible, and the versatility of the model is also improved;
[0049] 3. Input the obtained point prediction results into the NGBoost interval prediction model to obtain the interval prediction results of light intensity, and then obtain the distribution of light intensity, provide a measure of uncertainty, and enhance the interpretability of the prediction results;
[0050] 4. The MPPT algorithm is used to predict the light intensity range and obtain the upper and lower limits of the photovoltaic cell power generation range, so as to select the appropriate energy storage battery capacity, reduce the cost requirements of the energy storage system, and reduce the cost;
[0051] 5. The logic of energy storage control is set. When the power generation is greater than the predicted power generation, the energy storage system is charged; otherwise, the energy storage system is discharged, so that the final output power of the system is close to the predicted value, thereby improving the accuracy of the prediction and meeting the grid connection requirements. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] Figure 1 is a flow chart of the present invention;
[0053] Figure 2 It is a schematic diagram of photovoltaic battery-energy storage control system;
[0054] Figure 3 This is the flow chart of the conductivity increment method;
[0055] Figure 4 This is the control block diagram of the energy storage system;
[0056] Figure 5 It is a schematic diagram of the photovoltaic cell-energy storage control simulation system;
[0057] Figure 6 This is the simulation experiment result diagram under charging mode;
[0058] Figure 7 This is a schematic diagram of the DC power input for the hardware experiment in charging mode;
[0059] Figure 8 Input schematic diagram for hardware experiment battery in charging mode;
[0060] Fig. 9 This is a schematic diagram of the output of the hardware experimental system in charging mode;
[0061] Fig.10 This is the result of hardware simulation experiment of discharge mode;
[0062] Fig.11 This is the schematic diagram of DC power supply input for the discharge mode hardware experiment;
[0063] Fig.12 Input schematic diagram for battery in discharge mode hardware experiment;
[0064] Fig.13 Output schematic diagram of the discharge mode hardware experimental system;
[0065] Among them, in charging mode, CD1 is the input voltage, CD2 is the input current, and CD3 is the input power; in discharging mode, FD1 is the output voltage, FD2 is the output current, and FD3 is the output power. DETAILED DESCRIPTION
[0066] The present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0067] In order to solve the existing problems, the present invention proposes a method of combining an artificial intelligence algorithm with energy storage hardware. By introducing the energy storage hardware system, the prediction accuracy of the artificial intelligence algorithm is greatly improved while also improving the versatility of the method. For different application scenarios, the prediction method of the present invention can also be directly put into use without changing the artificial intelligence algorithm architecture and the energy storage hardware system.
[0068] The present invention first obtains a relatively accurate light intensity prediction result through a combined algorithm, and then corrects the prediction result of photovoltaic power generation by connecting the photovoltaic power generation system with the energy storage system, so as to greatly improve the prediction accuracy of photovoltaic power generation and meet the accuracy requirements of photovoltaic grid connection.
[0069] like Figure 1The flowchart of the present invention is shown. The prediction method proposed by the present invention specifically includes the following steps:
[0070] Step 1: Collect the original data set, including historical meteorological data (such as humidity, temperature, wind direction, air pressure, etc.) and light intensity data, divide the original data set into multiple groups of feature columns according to time and various characteristics (such as humidity, temperature, wind direction, air pressure, light intensity, etc.), and use the isolation forest method to detect outliers for each feature column.
[0071] The implementation steps of using the isolation forest method to detect outliers for each feature column are as follows:
[0072] Step 11, put n samples of a single feature column into the root node of the tree;
[0073] Step 12, the isolation forest algorithm randomly specifies a dimension and randomly generates a cutting point in the current node data, where the cutting point is generated between the maximum value and the minimum value of the specified dimension in the current node data;
[0074] Step 13, generate a hyperplane with the cutting point, and divide the data space of the current node into two subspaces: put the data less than p in the specified dimension in the left leaf of the current node, and put the data greater than or equal to p in the right leaf of the current node;
[0075] Step 14, looping steps 12 and 13 in the leaf nodes, continuously constructing new leaf nodes, until each leaf node has only one data, that is, it can no longer be cut or the leaf node has reached the specified height, and n isolated forests are obtained;
[0076] Step 15: Repeat steps 11 to 14 above to filter out outliers in each feature column using the isolation forest method.
[0077] Step 2: Use the cubic spline interpolation method to replace the outliers in each feature column, and then merge all feature columns to obtain the preprocessed data set.
[0078] The implementation steps of cubic spline interpolation to replace the outliers of each feature column are as follows:
[0079] Step 21: for a single feature column, after recording the sequence label corresponding to the outlier, remove the outlier;
[0080] Step 22, construct a cubic spline interpolation function for the feature column after removing outliers, with the sequence label as input and the sequence value as output;
[0081] Step 23, using the sequence labels corresponding to the outliers recorded in step 21 as the input of the cubic spline interpolation function to obtain the corrected values, and using the corrected values as new data to replace the missing outliers to construct a new feature column;
[0082] Step 24, repeat the above steps 21 to 23 to obtain the corrected feature columns, and recombine the corrected feature columns to obtain the preprocessed data set.
[0083] Step 3, the preprocessed (after isolation forest and cubic spline interpolation) dataset is decomposed into multiple modules using the CEEMDAN (Complete Empirical Mode Decomposition of Datasets plus Adaptive Noise) decomposition algorithm, which are respectively denoted as module 1, module 2, ..., module n.
[0084] The implementation steps of using CEEMDAN frequency division algorithm to divide the light intensity into multiple modules are as follows:
[0085] Step 31: Add white noise
[0086] Different white noise sequences are added to the original light intensity x(t) to form multiple noise-enhanced signals. Assume that the added noise is ω i (t), we get:
[0087] x i (t) = x(t) + ω i (t)(1)
[0088] Among them, x i (t) is the i-th noise enhanced signal.
[0089] Step 32: Perform EMD decomposition
[0090] For each noise-enhanced signal x i (t) Perform EMD decomposition to obtain the intrinsic mode function (IMF).
[0091] Step 33, calculate the first IMF
[0092] The first IMF obtained by all noise-enhanced signals is averaged to obtain the first IMF1 of the original light intensity:
[0093]
[0094] Where M is the number of noise-enhanced signals.
[0095] Step 34, calculate the residual signal
[0096] Subtracting the first IMF1 from the original light intensity x(t) yields the residual signal:
[0097] ri (t) = x(t) - IMF1 (3)
[0098] Among them, r i (t) represents the residual signal.
[0099] Step 35, iterative decomposition
[0100] For the remaining signal r i (t) Repeat step 34, continue to add white noise and perform EMD decomposition to obtain the IMF of the remaining signal, until all IMFs are extracted and the remaining signal becomes a monotonic function or white noise.
[0101] Step 36: Synthesize the final IMF
[0102] All IMFs are combined to obtain the complete original light intensity decomposition result.
[0103] For each module after decomposition, the data of each module is divided into a point training set and a point test set, with meteorological data as input X and light intensity decomposition as output y. i , input the point training set of each module into the A-BiGRU point prediction model for training, use the point test set of each module for point prediction, evaluate the A-BiGRU point prediction model, and obtain the final A-BiGRU point prediction model corresponding to each module; then use the entire data set of each module as the input of the A-BiGRU point prediction model to obtain the point prediction results of each module, and then linearly add the point prediction results of each module to obtain the final point prediction light intensity result Y i .
[0104] Step 4: Use the NGBoost interval prediction model to perform interval prediction on the light intensity to obtain the interval predicted light intensity result.
[0105] There is an inevitable error between the point prediction result and the actual light intensity. Taking the historical meteorological data X as input, the point prediction result Y i The error value with the actual light intensity Y is taken as the output δ, and the output δ is divided into an interval training set and an interval test set. The interval training set part is input into the NGBoot interval prediction model for training, and then the interval test set is used for interval prediction. The NGBoot interval prediction model is evaluated to obtain the final trained NGBoost interval prediction model. Further calculation can obtain the lower limit value low, upper limit value high of the light intensity prediction interval and the final prediction value pre of the light intensity.
[0106] The detailed steps to obtain the target light intensity prediction interval are as follows:
[0107] Step 41, the historical meteorological data X of the preprocessed data set (after isolation forest and cubic spline interpolation) is input into the trained A-BiGRU point prediction model to obtain the light intensity point prediction value Y corresponding to the data set i ;
[0108] Step 42, the point prediction result Y obtained in step 41 i The error value with the actual light intensity Y is recorded as output δ. A new interval prediction data set is constructed with the historical meteorological data X and the error value δ for interval prediction. The interval prediction data set is divided into an interval training set and an interval test set.
[0109] Step 43, using the historical meteorological data X as input and the error value δ as output, inputting the above interval training set into the NGBoost interval prediction model, training the NGBoost interval prediction model, using the interval test set to perform interval prediction, evaluating the NGBoost interval prediction model, and obtaining the finally trained NGBoost interval prediction model;
[0110] Step 44, input the historical meteorological data X and the point prediction error δ of the preprocessed (isolation forest and cubic spline interpolation) data set into the trained NGBoost interval prediction model to obtain the probability distribution parameter mean μ and standard deviation σ required to build the target light intensity prediction interval;
[0111] Step 45, obtain the target light intensity prediction interval according to the probability distribution parameter mean μ and standard deviation σ:
[0112] I α =[μ-z α2 σ,μ+z α2 σ](4)
[0113] Among them, α is the confidence interval, I α is the target prediction interval, z α2 is the corresponding standard score.
[0114] The lower limit of the light intensity prediction interval is low, that is, Y i +μ-z α2 σ, upper limit high, that is, Y i +μ+z α2 σ, the final predicted value of light intensity pre, that is, Y i +μ.
[0115] At this time, there is still an inevitable error between the predicted value of light intensity pre and the true value of light intensity real, and there are even still a few time points with large errors. Therefore, the photovoltaic-energy storage system is subsequently used to correct the results.
[0116] Step 5: Convert the light intensity into photovoltaic power generation through calculation, and use the MPPT algorithm to obtain the predicted photovoltaic power generation and the photovoltaic power generation corresponding to the upper and lower limits of the light intensity range.
[0117] Photovoltaic power generation is directly affected by light intensity and can be roughly regarded as a proportional relationship. In this embodiment, the conductance increment method in the MPPT algorithm is used to convert light intensity into photovoltaic power generation. The lower limit value Low, upper limit value High, predicted value Pre, and real value Real of photovoltaic power generation can be obtained from the lower limit value Low, upper limit value High, predicted value Pre, and real value Real of light intensity.
[0118] Conductivity increment method Figure 3 As shown, according to the PU curve of photovoltaic cells, in order to maximize the power generation, the power generation needs to be kept at the maximum power point, that is, when dP / dU = 0. Derivative of the formula P = UI, we get dP / dU = I + U * dI / dU
[0119] 1) When dP / dU>0, then dI / dU>-I / U, and the energy storage system works on the left side of the maximum power point. At this time, the reference voltage U ref (k+1)=U ref (k)+dU ref
[0120] 2) When dP / dU<0, then dI / dU<-I / U, and the energy storage system works on the right side of the maximum power point. At this time, the reference voltage U ref (k+1)=U ref (k)-dU ref
[0121] 3) When dP / dU=0, then dI / dU=-I / U, and the energy storage system works at the maximum power point. At this time, the reference voltage U ref (k+1)=U ref (k)
[0122] Through the above operations, the photovoltaic power generation can be controlled at the maximum power value, and the photovoltaic power generation lower limit value Low, upper limit value High, predicted value Pre, and real value Real can be obtained.
[0123] Step 6: Select appropriate energy storage capacity according to the upper and lower limits of photovoltaic power generation, and build an energy storage control prediction system; set the energy storage control logic to charge the energy storage when the actual power generation is greater than the predicted power generation; otherwise, discharge.
[0124] According to the maximum value of the difference between the lower limit value Low and the upper limit value High of the photovoltaic power generation, select the appropriate energy storage size, select capacitors (C1, C2, C3, C4), inductors (L1, L2) and switches (S1, S2, S3, S4) to build the following Figure 2 The photovoltaic-energy storage system shown in the figure, in which the control strategy of the bidirectional DC / DC converter at the photovoltaic cell end is the conductance increment method, and the control strategy at the energy storage system end is that when Real is greater than Pre, the battery is charged; conversely, when Real is less than or equal to Pre, the battery is discharged. The control block diagram of the bidirectional DC / DC converter is shown in the attached figure. Figure 4 As shown, the control method adopts voltage and current double closed-loop PI control, and its control process is:
[0125] The photovoltaic cell output voltage of Pre is set as the voltage reference value, and the bus terminal output voltage is collected. The difference between the two is PI-adjusted to obtain the battery output current reference value, which is subtracted from the collected battery output current and then PI-adjusted to obtain the switch tube duty cycle. Then, the control signal of the third switch tube S3 is obtained after PWM wave adjustment, and the control signal of the fourth switch tube S4 is obtained after inversion to change the bus terminal output voltage and the battery output current until the bus terminal output voltage converges with the reference voltage.
[0126] Through the above operations, when the photovoltaic cell output power Real, the final output power at the bus terminal can converge with the photovoltaic power generation Pre, so as to achieve the goal of greatly improving the prediction accuracy.
[0127] Attached Figure 5 For the system model built by simulink simulation, Figure 6 A schematic diagram of the simulation result of an example where Pre is less than Real obtained through artificial intelligence (Real is 52.21W, Pre is 41.37W) and Fig.10 It is a schematic diagram of simulation results of an example where Pre is greater than Real obtained through artificial intelligence (Real is 48.49W, Pre is 68.96W); Figure 7 , Figure 8 , Fig. 9 They are respectively the schematic diagram of DC power input of the hardware experiment where Pre is smaller than Real instance, the schematic diagram of battery input of the hardware experiment, and the schematic diagram of system output of the hardware experiment. Fig.11 , Fig.12 , Fig.13 They are respectively the schematic diagram of the DC power input of the hardware experiment where Pre is greater than Real, the schematic diagram of the battery input of the hardware experiment, and the schematic diagram of the output of the hardware experiment system. Figure 6 , Figure 7 , Figure 8 , Fig. 9It can be seen that when the Pre obtained by artificial intelligence is smaller than Real, the proposed method can make the final output power of the system close to Pre, which greatly improves the prediction accuracy. Fig.10 , Fig.11 , Fig.12 , Fig.13 It can be seen that when Pre obtained by artificial intelligence is greater than Real, the prediction method of the present invention can also make the final output power of the system close to Pre, thereby greatly improving the prediction accuracy. From the simulation and experimental results, it can be seen that the prediction method of the present invention can effectively and greatly improve the accuracy of photovoltaic power generation prediction by combining artificial intelligence algorithm with energy storage system control.
Claims
1. A photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control, characterized in that: The steps include: S1, the collected original data set is divided into multiple groups of feature columns according to time and features, and the isolation forest method is used to detect outliers for each feature column; S2, use the cubic spline interpolation method to replace the outliers in each feature column, and then merge all feature columns to obtain the preprocessed data set; S3, using CEEMDAN frequency division algorithm, decomposes the preprocessed light intensity into multiple modules; then divides the data of each module into point training set and point test set, trains and evaluates the A-BiGRU point prediction model respectively, and saves the best A-BiGRU point prediction model; uses meteorological data X as the input of the A-BiGRU point prediction model, linearly adds the point prediction results of each module, and obtains the point prediction light intensity result Y i ; S4, using the preprocessed data set and the point prediction light intensity result, the predicted light intensity is interval predicted by the NGBoost interval prediction model to obtain the interval prediction light intensity result; S5, using the MPPT algorithm to convert the light intensity into photovoltaic power generation, and obtain the predicted photovoltaic power generation and the photovoltaic power generation corresponding to the upper and lower limits of the light intensity range; S6, select appropriate energy storage capacity according to the upper and lower limits of power generation, and build an energy storage control prediction system; set the energy storage control logic as follows: when the actual power generation is greater than the predicted power generation, the energy storage is charged; when the actual power generation is less than or equal to the predicted power generation, the energy storage is discharged.
2. The photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control according to claim 1 is characterized in that: The original data set includes historical meteorological data and light intensity data, and the features include humidity, temperature, wind direction, and air pressure. The implementation steps of using the isolation forest method to detect outliers for each feature column are as follows: S11, put n samples of a single feature column into the root node of the tree; S12, the isolation forest algorithm randomly specifies a dimension and randomly generates a cutting point in the current node data. The cutting point is generated between the maximum value and the minimum value of the specified dimension in the current node data; S13, generate a hyperplane with the cutting point, and divide the data space of the current node into two subspaces: put the data less than p in the specified dimension in the left leaf of the current node, and put the data greater than or equal to p in the right leaf of the current node; S14, looping steps S12 and S13 in the leaf nodes, continuously constructing new leaf nodes, until each leaf node contains only one data, and obtaining n isolation forests; S15, repeat steps S11-S14, and filter out the outliers of each feature column by using the isolation forest method.
3. The photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control according to claim 1 is characterized in that: In step S2, the implementation steps of replacing the outliers of each feature column using the cubic spline interpolation method are as follows: S21, for a single feature column, after recording the sequence label corresponding to the outlier, remove the outlier; S22, constructing a cubic spline interpolation function for the feature column after removing outliers; S23, using the sequence label corresponding to the outlier as the input of the cubic spline interpolation function to obtain a corrected value, using the corrected value as new data to replace the missing outlier, and constructing a new feature column; S24, repeating steps S21 to S23 to obtain each corrected feature column, and recombining the each corrected feature column to obtain a preprocessed data set.
4. The photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control according to claim 1 is characterized in that: In step S3, the implementation steps of using the CEEMDAN frequency division algorithm to divide the light intensity into multiple modules are as follows: S31, add different white noise sequences to the original light intensity x(t) to form multiple noise-enhanced signals; let the added noise be ω i (t), we get: x i (t)=x(t)+ω i (t) Among them, x i (t) is the i-th noise-enhanced signal; S32, performing EMD decomposition on each noise enhanced signal to obtain an intrinsic mode function IMF; S33, average the first IMF obtained from all noise enhanced signals to obtain the first IMF1 of the original light intensity: Where, M is the number of noise-enhanced signals; S34, subtract the first IMF1 from the original light intensity x(t) to obtain the residual signal: r i (t)=x(t)-IMF1 Among them, r i (t) represents the residual signal; S35, for the remaining signal r i (t) Repeat steps S31 to S34, continue to add white noise and perform EMD decomposition to obtain the IMF of the remaining signal, until all IMFs are extracted and the remaining signal becomes a monotonic function or white noise; S36, synthesize all IMFs to obtain the complete original light intensity decomposition result.
5. The photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control according to claim 4 is characterized in that: In step S3, for the A-BiGRU point prediction model, the meteorological data X is used as input and the light intensity decomposition state is used as output y i ; Input the point training set of each module into the A-BiGRU point prediction model for training, use the point test set of each module for point prediction, evaluate the A-BiGRU point prediction model, and obtain the final A-BiGRU point prediction model corresponding to each module.
6. The photovoltaic power generation prediction method based on NGBoost algorithm and energy storage control according to claim 5 is characterized in that: In step S4, the detailed steps for obtaining the target light intensity prediction interval are as follows: S41, the pre-processed historical meteorological data X is input into the A-BiGRU point prediction model to obtain the light intensity point prediction value Y i ; S42, the light intensity point prediction result Y i The error value with the actual light intensity Y is recorded as output δ. A new interval prediction data set is constructed with the historical meteorological data X and the error value δ, and the interval prediction data set is divided into an interval training set and an interval test set. S43, taking the historical meteorological data X as input and the error value δ as output, inputting the interval training set into the NGBoost interval prediction model, training the NGBoost interval prediction model, and using the interval test set to perform interval prediction to obtain a trained NGBoost interval prediction model; S44, inputting the preprocessed historical meteorological data X and the point prediction error δ into the trained NGBoost interval prediction model to obtain the probability distribution parameter mean μ and standard deviation σ required to build the target light intensity prediction interval; S45, obtain the target light intensity prediction interval according to the probability distribution parameter mean μ and standard deviation σ: I α =[μ-z α2 s,m+z α2 [s] Among them, α is the confidence interval, I α is the target prediction interval, z α2 is the corresponding standard score.
Citation Information
Patent Citations
Photovoltaic power generation power short-term rolling prediction method based on improved MKPLS
CN113361782A
Power cable joint temperature abnormity early warning method combining EEMD-LSTM and isolated forest algorithm
CN114169237A
Photovoltaic power probability prediction method, medium and system
CN114819329A
Microgrid photovoltaic short-term power interval prediction method based on EEMD-LSTM
CN115222138A
Thermal power plant power generation capability evaluation method and system based on NGBoost, and storage medium
CN117077885A
Cited By
Photovoltaic electric quantity and power prediction method under different time scales
CN119294618A
Scheduling method and device for photovoltaic resources
CN121303704A
