Two-stage distribution robustness line loss optimization method considering wind and light uncertainty

Abstract

The application provides a two-stage distribution robust line loss optimization method considering wind and light uncertainty, and belongs to the technical field of new energy sources. First, a day-ahead-real-time two-stage line loss optimization method is constructed. In the day-ahead stage, a multi-scenario sample set capable of reflecting wind and light output uncertainty is generated by combining a K-means clustering algorithm and a conditional generative adversarial network. In the real-time stage, based on the day-ahead optimization result and updated output information, a multi-scenario distribution robust optimization model is used to realize joint correction of line loss and economic dispatch. In the optimization solving process, a forward-backward substitution method is embedded into a power flow calculation model to accurately reflect line transmission loss of the distribution network in the transformer area. Secondly, a distribution robust optimization method based on scenario generation is constructed. A diversified scenario set is generated by using historical wind and light data through K-means clustering and a conditional generative adversarial network, and distribution robust optimization planning and correction are carried out under different scenarios.

Description

Technical Field

[0001] This invention belongs to the field of new energy technology, specifically relating to a two-stage split-blown bar line loss optimization method for transformer substations that considers the uncertainties of wind and solar power. Background Technology

[0002] Currently, the penetration rate of distributed wind power, photovoltaic power, and other renewable energy sources in distribution networks is continuously increasing. The randomness and volatility of wind and solar power output lead to greater uncertainty in power flow distribution and more complex line loss mechanisms in distribution networks. Currently, there are mainly line loss optimization methods based on deterministic optimal power flow and methods based on probabilistic power flow and fuzzy computation. However, both of these traditional line loss calculation and optimization methods face severe challenges, specifically:

[0003] 1. Line loss optimization methods based on deterministic optimal power flow: The core technology of this method lies in assuming that the wind and solar power output and load demand over a future period (e.g., the day-ahead) are known (usually using point forecasts), and establishing a deterministic optimal power flow model based on this. Optimization algorithms such as linear programming or interior-point methods are used to solve this model, yielding the optimal scheduling plan for distributed power sources, energy storage, and other resources. The fundamental flaw of this method lies in its "deterministic assumption." It completely ignores the inherent uncertainty of wind and solar power output, basing the optimization results on a single, potentially inaccurate, forecast scenario. Once the actual wind and solar power output deviates from the forecast, the optimized scheduling scheme formulated based on this method will no longer be the optimal solution, and may even lead to safety issues such as increased system line losses instead of reduced ones and node voltage exceeding limits. Its optimization results have poor robustness, weak anti-interference ability, and are difficult to maintain the expected economic and safety benefits in actual fluctuating environments.

[0004] 2. A line loss optimization method based on probabilistic power flow and fuzzy computing addresses the uncertainty of wind and solar power output through probabilistic statistics or fuzzy optimization. This method first describes wind and solar power output as random or fuzzy variables: the random method assumes it follows a specific probability distribution and uses Monte Carlo simulation of probabilistic power flow to obtain the probabilistic characteristics of system state and line loss; the fuzzy method characterizes output uncertainty through membership functions and uses fuzzy power flow calculation to obtain the fuzzy distribution of system line loss. Based on this, an optimization model is established with the objective of minimizing expected line loss or minimizing the probability of severe scenarios, and the scheduling scheme is obtained by solving it. The drawback of this method is that its optimization effect heavily relies on subjective assumptions about the uncertainty model. In probabilistic optimization methods, the validity of the solution is entirely based on the prior assumption that wind and solar power output follows a specific probability distribution. However, in actual engineering, it is difficult to obtain an accurate probability distribution model, and optimization based on incorrect distribution assumptions will lead to a significant decrease in the actual performance of the scheduling scheme. In fuzzy optimization methods, the optimization results are significantly affected by the shape and parameters of the fuzzy membership function, which are set manually. Different settings will result in very different optimization schemes, lacking an objective and unified evaluation standard.

[0005] Against this backdrop, on the one hand, the uncertainty of distributed power generation output significantly increases the difficulty of line loss calculation; on the other hand, existing optimization methods struggle to effectively address various possible power output fluctuation scenarios while ensuring economic efficiency. Therefore, how to achieve accurate calculation of line losses and optimized resource scheduling in distribution networks while fully considering the uncertainty of distributed energy output has become a critical technical problem urgently needing to be solved in the field of distribution networks. Summary of the Invention

[0006] The purpose of this invention is to provide a two-stage sub-Bluer bar line loss optimization method for transformer substations that considers the uncertainty of wind and solar power output. This method aims to solve key technical problems in existing technologies, such as poor adaptability and insufficient robustness of line loss optimization schemes in actual operation due to neglecting the uncertainty of wind and solar power output or relying on subjective probability assumptions.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0008] A two-stage sub-Bluerging line loss optimization method for distribution transformer areas considering wind and solar power uncertainties is proposed. First, a day-ahead and real-time two-stage line loss optimization method is constructed. In the day-ahead stage, a multi-scenario sample set reflecting the uncertainty of wind and solar power output is generated by combining K-means clustering and a Conditional Generative Adversarial Network (CGAN). In the real-time stage, based on the day-ahead optimization results and updated power output information, a multi-scenario sub-Bluerging optimization model is used to jointly correct line loss and economic dispatch. During the optimization solution process, a forward-backward sweep method is embedded in the power flow calculation model to accurately reflect the line transmission loss of the distribution network in the transformer area. Second, a scenario-based sub-Bluerging optimization method is constructed. Using historical wind and solar power data, diverse scenario sets are generated through K-means clustering and a CGAN, and sub-Bluerging optimization planning and correction are performed under different scenarios.

[0009] The detailed steps of the two-stage Bruker line loss optimization method for transformer substations, which considers the uncertainties of wind and solar power, are as follows:

[0010] Step 1: A method for generating landscape scenes with uncertainties based on conditional generative adversarial networks

[0011] Step 1.1 Collect historical measured data and day-ahead forecast data of wind and solar power output as training sample set, use day-ahead forecast data as condition label, and use historical measured wind and solar power data as real sample;

[0012] Step 1.2 Constructing a generator and discriminator Adversarial game network model; where the generator A convolutional neural network structure is used, with the input being random noise that follows a normal distribution. and the label of the forecast conditions The output is the generated wind and solar power scene sample. Discriminator Also using a convolutional neural network structure, with real samples as input. Or generate samples and the corresponding tags Its function is to determine whether the input sample comes from real historical data or is generated by the generator;

[0013] Step 1.3 Define the objective function of the conditional generative adversarial network to characterize the minimax game between the generator and the discriminator; based on this objective function, train the model using an alternating optimization approach; using the trained generator, input a large amount of random noise and specific pre-dawn prediction data to generate a large-scale set of wind and solar power output scenarios.

[0014] Step 1.4 verifies the accuracy of the temporal correlation and uncertainty description of the generated scene by introducing the autocorrelation coefficient. With partial autocorrelation coefficient Perform correlation analysis;

[0015] Step 1.5: Through network training and evaluation, a set of scenes that meets the day-ahead prediction conditions and fully reflects the uncertainty of wind and solar power output is obtained; the K-means clustering algorithm is used to perform pattern segmentation on the high-quality scene set generated by CGAN, and the sample allocation and center position are iteratively updated to finally obtain... Each sample represents a typical power output pattern, and each type of sample corresponds to different weather scenario characteristics.

[0016] Step 2: Construct a day-ahead optimization scheduling model that considers line losses in transformer areas.

[0017] Step 2.1 Based on the day-ahead forecast data of wind and solar power, formulate a day-ahead dispatch plan with the goal of minimizing line loss in the transformer area and economic dispatch costs;

[0018] Step 2.2 Taking into account the operating characteristics of wind and solar power, energy storage, electric vehicles and adjustable loads, and with the objective function of minimizing transformer area line loss and economic dispatch cost, a day-ahead optimization dispatch model considering transformer area line loss is constructed.

[0019] Step 2.3 Establish the system active / reactive power balance constraints, wind power and photovoltaic output constraints, energy storage equipment operation constraints, electric vehicle cluster operation constraints, transferable load (TL), and interruptible load for the day-ahead phase.

[0020] Step 2.4 embeds the forward-backward substitution method into the optimization scheduling model to accurately solve the power flow of the distribution network. After the power flow calculation converges, the total theoretical line loss of the system is calculated by combining the branch current values. Feeding this back into the objective function, the final solution model yields a day-ahead resource scheduling scheme that balances economy and low line loss.

[0021] Step 3: Construct a real-time distributed bar optimization scheduling model that considers wind and solar uncertainties.

[0022] Step 3.1 The K-means clustering obtained in Step 1 Based on the day-ahead scheduling scheme of the extreme wind scenarios and step 2, the real-time stage considers wind power uncertainties and dynamically corrects the day-ahead decisions; the distributed bar optimization method is used to construct a set of probabilistic uncertainties with extreme scenarios as candidate distributions. And through weights Construct an extreme value distribution to incorporate the system risk under the worst-case scenario into the optimization objective;

[0023] Step 3.2 Establish real-time system active / reactive power balance constraints, real-time output constraints for wind power and photovoltaics, real-time operation constraints for energy storage devices, real-time operation constraints for EV clusters, real-time operation constraints for transferable loads, and real-time operation constraints for interruptible loads.

[0024] Step 3.3 uses K-means clustering to obtain k extreme landscape scenes, each denoted as . (in In the sub-Bruker optimization framework, the worst-case distribution is considered, which is a discrete distribution composed of these extreme scenarios combined with certain probability weights.

[0025] Step 3.4 involves constructing a probabilistically uncertain set. Weights need to be adjusted. Two types of constraints are imposed: First, the weighted mean of all extreme scenarios should lie within a confidence interval centered on the historical data mean; second, the Wasserstein distance between this extreme value distribution and the empirical distribution must not exceed a given ambiguity parameter. ;

[0026] Step 3.5: The Blue Bar optimization model is based on the worst-case distribution. The goal is to find a scheduling strategy that minimizes the sum of expected operating costs and line losses. By solving this model, a robust real-time resource scheduling scheme that takes into account the uncertainties of wind and solar power can be obtained, along with the corresponding theoretical line loss value.

[0027] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0028] 1) This invention proposes a two-stage line loss optimization method (day-ahead / real-time) for economic dispatch and operational optimization of distribution transformer areas. The method performs overall dispatch planning in the day-ahead stage and dynamically adjusts the method based on the latest load and output data in the real-time stage, achieving both line loss minimization and safety constraints. During the optimization process, a forward-backward substitution method is embedded for power flow calculation, accurately simulating bidirectional power flow characteristics, branch currents, and node voltage distribution. By coordinating various distributed resources such as wind power, photovoltaics, energy storage, electric vehicles, and adjustable loads, the method improves the operational efficiency and power supply reliability of the distribution network in the distribution area while ensuring system safety.

[0029] 2) This invention constructs a scenario-based sub-Brussels bar optimization method to characterize the volatility and uncertainty of wind and solar power output, enabling adaptive adjustment of the scheduling scheme to uncertainty. Utilizing historical wind and solar data, diverse scenario sets are generated through K-means clustering and conditional generative adversarial networks, and sub-Brussels bar optimization planning and correction are performed under different scenarios. This method ensures that the scheduling scheme maintains low line loss, controllable economic efficiency, and system robustness under different wind and solar power output fluctuations, effectively overcoming the limitations of traditional methods that rely on subjective probability assumptions or artificial membership functions. Attached Figure Description

[0030] Figure 1 This is the overall flowchart for optimizing line loss in the transformer area.

[0031] Figure 2 The line loss curve for today.

[0032] Figure 3 These are line loss comparison curves for four scenarios in the real-time phase.

[0033] Figure 4-7 These are resource scheduling diagrams for extreme scenarios ①, ②, ③, and ④. Detailed Implementation

[0034] The present invention will be further described in detail below with reference to the embodiments and accompanying drawings.

[0035] Example 1

[0036] like Figure 1 As shown, this invention provides a two-stage sub-Bruker bar optimization method for transformer substations considering wind and solar power uncertainties. First, a day-ahead / real-time two-stage optimization framework is constructed. In the day-ahead stage, a multi-scenario sample set reflecting the uncertainty of wind and solar power output is generated by combining K-means clustering algorithm and Conditional Generative Adversarial Network (CGAN). In the real-time stage, based on the day-ahead optimization results and updated power output information, a multi-scenario sub-Bruker bar optimization model is used to jointly correct line loss and economic dispatch. During the optimization solution process, a forward-backward sweep method is embedded in the power flow calculation model to accurately reflect the line transmission loss of the transformer substation distribution network. The model takes minimizing transformer substation line loss and economic dispatch cost as the objective function, comprehensively considering the uncertainty of renewable energy output, power flow constraints, and resource operation boundaries to achieve optimal operation of the transformer substation that balances economy and robustness. Detailed steps are as follows:

[0037] Step 1: A method for generating landscape scenes with uncertainties based on conditional generative adversarial networks

[0038] Historical measured data and day-ahead forecast data of wind and solar power output were collected as training sample sets, with day-ahead forecast data used as conditional labels and historical measured wind and solar power data used as real samples.

[0039] Build containing generators and discriminator An adversarial game network model. The generator... A convolutional neural network structure is used, with the input being random noise that follows a normal distribution. and the label of the forecast conditions The output is the generated wind and solar power scene sample. Its function is to learn the probability distribution characteristics of wind and solar power output and generate simulated samples that are as realistic as possible; the discriminator Also using a convolutional neural network structure, with real samples as input. Or generate samples and the corresponding tags Its function is to determine whether the input sample comes from real historical data or is generated by the generator.

[0040] The model's loss function and optimization objective need to be defined. The generator's loss function aims to maximize the discriminator's probability of classifying the generated scene, and its expression is:

[0041]

[0042] In the formula, This represents the expected value of the corresponding distribution; The probability distribution represented; This indicates that the discriminator is targeting "generated samples". Meet the conditions The closer the value of the output to 1, the better. The closer it is to the real sample.

[0043] The loss function of the discriminator is defined as:

[0044]

[0045] In the formula, This represents the probability distribution of the generated samples; For the discriminator in "condition" Given the given conditions, determine the input sample. The probability that it is a "real sample".

[0046] The objective function of a conditional generative adversarial network is defined to characterize the minimax game between the generator and the discriminator, and its definition is as follows:

[0047]

[0048] To address the training instability and mode collapse issues caused by the use of Jensen-Shannon divergence in the original generative adversarial networks (GANs), Wasserstein distance is used instead of JS divergence as the loss function metric. This metric is used to calculate the probability distribution of wind and solar power output generated by the generator. Probability distribution with real historical data The distance between the generated and real distributions. Its advantage lies in the fact that it can still provide meaningful distance values ​​and gradient information even when the generated distributions have little overlap with the real distributions (i.e., the generated simulated data is poor). This effectively solves the gradient vanishing problem caused by the inability to accurately measure distribution distances in traditional methods, thus avoiding model training failure. The Wasserstein distance is defined as:

[0049]

[0050] In the formula, express and The joint probability distribution of ; This represents a distance measure between scenes.

[0051] To address the difficulty of directly calculating the Wasserstein distance in high-dimensional continuous wind and solar power output data space, the Kantorovich-Rubinstein duality theorem can be used to mathematically transform the primal minimization problem of finding the optimal joint distribution into a maximization problem on a class of 1-Lipschitz continuous functions. This dual form is expressed as:

[0052]

[0053] In the formula, This indicates that the constraint discriminator D satisfies 1-Lipschitz continuity.

[0054] To strictly ensure that the discriminator satisfies the above 1-Lipschitz continuity constraint during training, a gradient penalty term is introduced, thereby constructing the overall objective function of the improved Wasserstein conditional generative adversarial network:

[0055]

[0056] In the formula, The norm of the discriminator gradient is represented. It is a penalty function.

[0057] Based on the above objective function, the model is trained using an alternating optimization approach.

[0058] The collected historical measured data and current-day forecast data are processed. A high-dimensional noise vector conforming to a standard normal distribution is randomly extracted from the latent space. This noise vector is then vertically concatenated with the conditional data (current-day forecast values) in the training samples to construct the generator's input matrix. This input matrix is ​​then fed into the generator network, and after convolution operations, the generator outputs generated samples containing simulated wind and solar power output.

[0059] To enable the discriminator to learn to distinguish between real and fake data, two sets of inputs are needed. The first set involves concatenating the conditional data from the training set with the corresponding real samples (historical measured values) vertically, and then inputting this concatenation into the discriminator to obtain its discrimination value for the real data. The second set involves concatenating the conditional data from the training set with the generated samples output by the generator vertically, and then inputting this concatenation into the discriminator to obtain its discrimination value for the generated data.

[0060] Select gradient penalty sampling points, calculate the loss functions of the generator and discriminator, and update the network weights of the generator and discriminator respectively. If training is not yet complete, return to the next round of training.

[0061] Once training is complete (i.e., the loss function converges or the maximum number of iterations is reached), the trained generator network in the CGAN model is extracted.

[0062] Using a trained generator, a large amount of random noise and specific pre-dated forecast data are input to generate a large-scale set of wind and solar power output scenarios. To verify the accuracy of the generated scenarios in describing temporal correlation and uncertainty, an autocorrelation coefficient is introduced. With partial autocorrelation coefficient The expression for correlation analysis is as follows:

[0063]

[0064]

[0065]

[0066] In the formula, For real samples or generated samples Output value at any given moment This is the mean of the output sequence. For time intervals, For and between Output value at each moment The correlation.

[0067] To evaluate the effectiveness of the scenario set in characterizing uncertainty, coverage and power range width metrics are defined, with the following expressions:

[0068]

[0069]

[0070] In the formula, For confidence level Coverage below The total number of sampling points in the test set. Indicates confidence level The total number of measured wind and solar power values ​​falling within the predicted confidence interval. For confidence level The average width of the power range below, , The nth sampling point is at a confidence level The maximum and minimum power values ​​under these conditions.

[0071] Through the above network training and evaluation process, a set of high-quality scenarios that meet the day-ahead forecast conditions and can fully reflect the uncertainty of wind and solar power output can be obtained.

[0072] The K-means clustering algorithm was used to classify the high-quality scene set generated by CGAN. Through cluster analysis, typical meteorological and power output patterns can be identified, and a large number of samples can be divided into several classes, thereby generating more representative landscape scenes under different climatic characteristics.

[0073] Let the scene dataset be The number of clusters is The optimization objective of K-means clustering is to minimize the sum of squared errors from sample points to cluster centers, as expressed below:

[0074]

[0075] In the formula, Indicates the first Clusters, This is the center vector of the cluster.

[0076] By iteratively updating the sample allocation and center position, the final result is obtained. Each sample represents a typical output pattern, and each type of sample corresponds to different weather scenario characteristics, providing data support for the subsequent two-stage sub-Bruker optimization.

[0077] Step 2: Construct a day-ahead optimization scheduling model that considers line losses in transformer areas.

[0078] Based on the day-ahead forecast data of wind and solar power, a day-ahead dispatch plan is formulated with the goal of minimizing line loss in the transformer area and economic dispatch costs.

[0079] Taking into account the operational characteristics of wind and solar power, energy storage, electric vehicles, and adjustable loads, and with the objective function of minimizing transformer area line loss and economic dispatch cost, a day-ahead optimization dispatch model considering transformer area line loss is constructed as follows:

[0080]

[0081]

[0082] In the formula, This is the loss cost coefficient; This represents the cost coefficient for interacting with the power grid; This represents the cost coefficient for wind curtailment. , , For the operating cost coefficients of wind power, photovoltaic, and energy storage; , The compensation price coefficient for transferable and interruptible loads; The subsidy cost coefficient for coordinating dispatch of electric vehicles; The current day electricity price; This indicates the power exchanged with the power grid (positive for purchasing electricity, negative for selling electricity). , , , , , , , , , , At the node ,time The curtailed wind power, curtailed solar power, actual wind power output, charging power of energy storage devices, discharging power of energy storage devices, input and output power of transferable loads, interruption power of interruptible loads, charging power of electric vehicles, and discharging power of electric vehicles.

[0083] Establish system active / reactive power balance constraints for the day-ahead phase:

[0084]

[0085] In the formula, , Indicates time node The active and reactive loads.

[0086] Establish day-ahead output constraints for wind and solar power:

[0087] ;

[0088]

[0089]

[0090]

[0091]

[0092]

[0093] In the formula, , This represents the maximum output power of the wind power and photovoltaic units at node s at time t. Indicates the amount of wind power curtailed and the amount of solar power curtailed; , This indicates the predicted power of wind and solar power.

[0094] Establish day-ahead operational constraints for energy storage devices:

[0095]

[0096]

[0097]

[0098]

[0099]

[0100] In the formula, express At every moment The state of charge in which energy is stored; , For charge and discharge efficiency; For time step; , This indicates the lower and upper limits of the state of charge. , This represents the charging and discharging state variables at time t; , This indicates the maximum charging and discharging power.

[0101] Establishing the EV cluster: Current operational constraints

[0102]

[0103]

[0104]

[0105]

[0106] In the formula, , The maximum and minimum capacity of electric vehicles, with the minimum capacity required to meet the travel needs of vehicle owners in emergency situations; , For electric vehicle charging (discharging) efficiency; The capacity of the electric vehicle's battery when leaving home; The daily travel distance of the s-th electric vehicle; The amount of electricity required for an electric vehicle to travel 100km.

[0107] Transferable loads (TL) must meet the following constraints: constant total power before and after transfer, transfer ratio, and transfer status.

[0108]

[0109]

[0110]

[0111]

[0112] Where TL represents the category of transferable load, . and These represent the input power and output power of the TL at time t, respectively. and These are the state variables that can be transferred in and out of TL, respectively; and These represent the maximum power input and maximum power output limits of TL, respectively.

[0113] Interruptible loads (ILs) must meet constraints related to interruption ratio, interruption duration, and number of interruptions:

[0114]

[0115]

[0116]

[0117] Where IL represents the category of interruptible load. . It is an interruptible variable in IL. It is an interruptible state variable of IL. It is the maximum interruptible value of IL. and These represent the longest continuous interruptible time and the maximum number of interruptibles for the IL during the scheduling period, respectively.

[0118] The forward-backward substitution method is embedded in the optimization scheduling model to accurately solve the power flow of the distribution network.

[0119] Perform initialization by setting the initial values ​​for all node voltages, typically the rated voltage, with a phase angle of 0, i.e.:

[0120]

[0121] The superscript (0) indicates the 0th iteration.

[0122] The back-substitution process begins at the load node and, based on Kirchhoff's current law, calculates the complex current of each branch layer upstream. The calculation formula is as follows:

[0123]

[0124] in, , Net active and reactive power is injected into the nodes; For nodes Flow to Node The branch current; , for the node A set of directly connected downstream branches;

[0125] The forward calculation process involves obtaining the complex currents of each branch and, starting from the root node with a known voltage, calculating the complex voltages of each node segment by segment downstream, taking into account the branch impedances. The calculation formula is as follows:

[0126]

[0127] At the same time, the node voltage must meet the safety operation constraints:

[0128]

[0129] in, , Downstream nodes and upstream nodes voltage, Type is a connection node With nodes The branch impedance; and These represent the upper and lower limits of the node voltage amplitude, respectively.

[0130] To determine convergence of the iteration, first calculate the correction amount for the voltage amplitude of all nodes compared to the voltage amplitude of the previous iteration:

[0131]

[0132] In the formula, , The first The voltage amplitude of the next iteration and the first Next iteration voltage amplitude. Find the maximum voltage amplitude correction value among all nodes. Determine the convergence condition ,in This is the preset convergence threshold. If the condition is met, the iteration ends; otherwise, the above back-substitution and forward push processes are repeated using the newly calculated nodal complex voltage values ​​until convergence.

[0133] After the power flow calculation converges, the total theoretical line loss of the system is calculated by combining the branch current values. :

[0134]

[0135] In the formula, This represents the total theoretical line loss in the transformer area. Fixed losses of distribution transformers (including no-load losses, auxiliary component losses, etc.). For nodes To the node The current value of the branch circuit; For nodes To the node The resistance of the branch circuit; This is the calculation period.

[0136] The above line loss values Feedback is fed into the objective function, and the final solution model yields a day-ahead resource scheduling scheme that balances economy and low line loss.

[0137] Step 3: Construct a real-time distributed bar optimization scheduling model that considers wind and solar uncertainties.

[0138] The K-means clustering obtained in step 1 Based on the day-ahead scheduling scheme of the extreme wind scenarios and step 2, the real-time stage considers wind power uncertainties and dynamically adjusts the day-ahead decisions. This stage employs the distributed Blue bar optimization method to construct a set of probabilistic uncertainties with extreme scenarios as candidate distributions. And through weights An extreme value distribution is constructed to incorporate the system risk under the worst-case scenario into the optimization objective. Based on this, the model can achieve coordinated and corrective scheduling of resources such as energy storage, electric vehicles, and adjustable loads, effectively suppressing cost increases caused by extreme fluctuations and further reducing line losses in the transformer area.

[0139] Taking into account the operational characteristics of wind and solar power, energy storage, electric vehicles, and adjustable loads, and with the objective function of minimizing transformer line loss and economic dispatch cost, a real-time distributed bar optimization model considering uncertainties is constructed:

[0140]

[0141] Scene index, used to traverse different scenes; This represents the set of weights for extreme scenarios. For the first Weights for extreme scenarios It is by A set of probabilistic uncertainties constructed; , , , , , , , , , Indicates at time Penalty cost coefficients for wind power output adjustment, photovoltaic power output adjustment, loss adjustment, energy storage equipment charging and discharging adjustment, transferable load output and input adjustment, interruptible load adjustment, and electric vehicle charging and discharging adjustment; , Indicates the first A scene, a moment The predicted output of wind power and solar power; , Indicates the first A scene, a moment The actual output of wind power and solar power; , , Indicates the first A scene, a moment The amount of loss adjustment and the amount of charging and discharging power adjustment of energy storage equipment; , , Indicates the first A scene, a moment Adjustments to the transferable load output, transferable load input, and interruptible load; , This represents the adjustment amount of the charging and discharging power of the electric vehicle at time t in the k-th scenario. Node set; Branch set, for branch Its first node is denoted as The end node is denoted as .

[0142] Establish active / reactive power balance constraints for the system in the real-time phase:

[0143]

[0144] In the formula, , Indicates time node The active and reactive loads.

[0145] Establish real-time stage output constraints for wind and solar power:

[0146]

[0147]

[0148]

[0149]

[0150] In the formula, , Let be the wind power and solar power deviation in the k-th scenario.

[0151] Establish real-time phased operational constraints for energy storage devices:

[0152]

[0153]

[0154]

[0155]

[0156]

[0157] Establish real-time operational constraints for the EV cluster:

[0158]

[0159]

[0160]

[0161]

[0162]

[0163] In the formula, , These are the maximum and minimum values ​​for the adjustment amount of the energy storage device.

[0164] Real-time operational constraints for transferable loads:

[0165]

[0166]

[0167]

[0168]

[0169]

[0170] In the formula, , Input the minimum and maximum values ​​of the adjustment amount for transferable loads; , Input the minimum and maximum values ​​of the adjustment amount for the transferable load.

[0171] Interruptible load real-time phase operation constraints:

[0172]

[0173]

[0174] In the formula, , These are the minimum and maximum values ​​for interruptible load adjustments.

[0175] This invention uses K-means clustering to obtain k extreme landscape scenes, each denoted as . (in In the sub-Bruker optimization framework, the worst-case distribution is considered, which is a discrete distribution composed of these extreme scenarios combined with certain probability weights. This extreme value distribution can be expressed as:

[0176]

[0177] In the formula, These are the weights corresponding to the extreme scenario k, satisfying... and , It is the Dirac delta function.

[0178] To construct a probabilistically uncertain set Weights need to be adjusted. Two types of constraints are imposed: First, the weighted mean of all extreme scenarios should lie within a confidence interval centered on the historical data mean; second, the Wasserstein distance between this extreme value distribution and the empirical distribution must not exceed a given ambiguity parameter. Based on this, the set of uncertainties is defined as follows:

[0179]

[0180] In the formula, It is the probability weight of the k-th extreme scenario. and These are the lower and upper bounds of the population mean, respectively; It is the observation value of the i-th reference sample. It is a fuzzy parameter of the distribution. It represents the total number of reference samples.

[0181] The optimal model of the blue bar is based on the worst distribution. The goal is to find a scheduling strategy that minimizes the sum of expected operating cost and line loss. By solving this model, a robust real-time resource scheduling scheme that considers the uncertainties of wind and solar power can be obtained, along with the corresponding theoretical line loss value.

[0182] Example 2

[0183] The improved IEEE-15 node distribution area was selected as the test object. The network has a typical radial topology, 14 branches, a total active load of 1226 kW, a total reactive load of 1251 kVA, a rated voltage of 11 kV, and a base capacity of 1 MVA. Day-ahead and real-time scheduling results, comparisons of four extreme scenarios, and comparisons with deterministic models are presented, demonstrating the advantages in reducing line losses.

[0184] The four extreme scenarios were derived as follows: First, quantile statistics were performed on the hourly output data of wind and solar power to divide the output into ranges. Hourly output was divided into three levels: less than 25% (L), 25%–75% (M), and greater than 75% (H). Given that both wind and solar scenarios operate on a 24-hour cycle, they were simplified into six four-hour periods, each corresponding to one of the three levels. Based on the quantile results, S scenarios were coded as combinations of L / M / H. Each scenario code was then matched against rows in an orthogonal array. The S scenarios were ranked according to the matching degree, and rows containing combinations of extreme levels were selected, resulting in S extreme scenarios. The top four scenarios were then selected based on their scores.

[0185] Figure 2 The study demonstrates the intraday distribution characteristics of line losses in a distribution substation under typical daily operation. Peak periods, corresponding to peak load times and periods of concentrated distributed energy output, are the main contributors to line losses. These results provide a basis for subsequent two-stage sub-Bruker optimization.

[0186] Figure 3 The paper presents line loss comparison curves in real-time under four extreme scenarios. Multi-scenario analysis can cover various manifestations of wind power uncertainty, thus avoiding misjudgment of line loss patterns based on a single scenario. Decision-making based on the constructed scenario set achieves an overall reduction in line loss.

[0187] Figure 4-7 The resource scheduling performance of the SDRO model under four scenarios is demonstrated. It shows good results in all scenarios, effectively reducing line losses through flexible adjustments to the coordinated use of resources such as energy storage and electric vehicles. Although the total cost of the model fluctuates slightly, it successfully achieves significant optimization of line loss costs, forming a reasonable trade-off between system operating efficiency and robustness.

[0188] In summary, this invention proposes a two-stage distributed grid optimization scheduling method for wind power, photovoltaics, energy storage, electric vehicles, and adjustable loads under uncertainties in wind power and photovoltaic power distribution networks. This method can effectively reduce line active power losses and suppress cost fluctuations under extreme conditions, and has good engineering application value.

Claims

1. A two-stage Bruker line loss optimization method for transformer substations considering wind and solar uncertainties, characterized in that, First, a two-stage line loss optimization method was constructed, which combines day-ahead and real-time. In the day-ahead stage, a multi-scenario sample set that can reflect the uncertainty of wind and solar power output is generated by combining K-means clustering algorithm with conditional generative adversarial network. In the real-time phase, based on the day-ahead optimization results and updated output information, a multi-scenario sub-Bluer bar optimization model is used to achieve joint correction of line loss and economic dispatch. In the optimization solution process, the forward-backward substitution method is used to embed the power flow calculation model to accurately reflect the line transmission loss of the distribution network in the transformer area. Secondly, a scenario-based sub-Bluer bar optimization method is constructed. Using historical wind and solar data, K-means clustering and conditional generative adversarial network are used to generate a diverse set of scenarios, and sub-Bluer bar optimization planning and correction are performed under different scenarios. The specific steps are as follows: Step 1: A method for generating landscape scenes with uncertainties based on conditional generative adversarial networks Step 1.1 Collect historical measured data and day-ahead forecast data of wind and solar power output as training sample set, use day-ahead forecast data as condition label, and use historical measured wind and solar power data as real sample; Step 1.2 Constructing a generator and discriminator Adversarial game network model; where the generator A convolutional neural network structure is used, with the input being random noise that follows a normal distribution. and the label of the forecast conditions The output is the generated wind and solar power scene sample. Discriminator Also using a convolutional neural network structure, with real samples as input. Or generate samples and the corresponding tags Its function is to determine whether the input sample comes from real historical data or is generated by the generator; Step 1.3 Define the objective function of the conditional generative adversarial network to characterize the minimax game between the generator and the discriminator; based on this objective function, train the model using an alternating optimization approach; using the trained generator, input a large amount of random noise and current day prediction data to generate a large-scale set of wind and solar power output scenes; Step 1.4 verifies the accuracy of the temporal correlation and uncertainty description of the generated scene by introducing the autocorrelation coefficient. With partial autocorrelation coefficient Perform correlation analysis; Step 1.5: Through network training and evaluation, a set of scenes that meets the day-ahead prediction conditions and fully reflects the uncertainty of wind and solar power output is obtained; the K-means clustering algorithm is used to perform pattern segmentation on the high-quality scene set generated by CGAN, and the sample allocation and center position are iteratively updated to finally obtain... Each sample represents a typical power output pattern, and each type of sample corresponds to different weather scenario characteristics. Step 2: Construct a day-ahead optimization scheduling model that considers line losses in transformer areas. Step 2.1 Based on the day-ahead forecast data of wind and solar power, formulate a day-ahead dispatch plan with the goal of minimizing line loss in the transformer area and economic dispatch costs; Step 2.2 Taking into account the operating characteristics of wind and solar power, energy storage, electric vehicles and adjustable loads, and with the objective function of minimizing transformer area line loss and economic dispatch cost, a day-ahead optimization dispatch model considering transformer area line loss is constructed. Step 2.3 Establish the day-ahead system active / reactive power balance constraints, the day-ahead output constraints of wind power and photovoltaics, the day-ahead operation constraints of energy storage devices, the day-ahead operation constraints of electric vehicle clusters, transferable loads, and interruptible loads; Step 2.4 embeds the forward-backward substitution method into the optimization scheduling model to accurately solve the power flow of the distribution network. After the power flow calculation converges, the total theoretical line loss of the system is calculated by combining the branch current values. ; Feeding this back into the objective function, the final solution model yields a day-ahead resource scheduling scheme that balances economy and low line loss. Step 3: Construct a real-time distributed bar optimization scheduling model that considers wind and solar uncertainties. Step 3.1 The K-means clustering obtained in Step 1 Based on the day-ahead scheduling scheme of the extreme wind scenarios and step 2, the real-time stage considers wind power uncertainties and dynamically corrects the day-ahead decisions; a distributed bar optimization method is used to construct a set of probabilistic uncertainties with extreme scenarios as candidate distributions. And through weights Construct an extreme value distribution to incorporate the system risk under the worst-case scenario into the optimization objective; Step 3.2 Establish real-time system active / reactive power balance constraints, real-time output constraints for wind power and photovoltaics, real-time operation constraints for energy storage devices, real-time operation constraints for EV clusters, real-time operation constraints for transferable loads, and real-time operation constraints for interruptible loads. Step 3.3 uses K-means clustering to obtain k extreme landscape scenes, each denoted as . ,in In the sub-Bruker optimization framework, the worst-case distribution is considered, which is a discrete distribution composed of these extreme scenarios combined with certain probability weights. Step 3.4 involves constructing a probabilistically uncertain set. Weights need to be adjusted. Two types of constraints are imposed: First, the weighted mean of all extreme scenarios should lie within a confidence interval centered on the historical data mean; second, the Wasserstein distance between this extreme value distribution and the empirical distribution must not exceed a given ambiguity parameter. ; Step 3.5: The Blue Bar optimization model is based on the worst-case distribution. The goal is to find a scheduling strategy that minimizes the sum of expected operating costs and line losses. By solving this model, a robust real-time resource scheduling scheme that takes into account the uncertainties of wind and solar power can be obtained, along with the corresponding theoretical line loss value.

2. The two-stage sub-Bruker line loss optimization method for transformer areas considering wind and solar uncertainties as described in claim 1, characterized in that, In step 1.3, the objective function of the conditional generative adversarial network is defined to characterize the minimax game between the generator and the discriminator. Its definition is as follows: In the formula, For generator; It is a discriminator.

3. The two-stage sub-Bruker line loss optimization method for transformer substations considering wind and solar uncertainties as described in claim 1, characterized in that, Step 1.4 verifies the accuracy of the temporal correlation and uncertainty description of the generated scene by introducing the autocorrelation coefficient. With partial autocorrelation coefficient The expression for correlation analysis is as follows: In the formula, For real samples or generated samples Output value at any given moment The mean of the output sequence. For time intervals, for and between Output value at each moment The correlation.

4. The two-stage sub-Bluer beam line loss optimization method for transformer substations considering wind and solar uncertainties as described in claim 1, characterized in that, In step 1.5, cluster analysis identifies typical weather and power output patterns, dividing a large number of samples into several classes. This generates more representative landscape scenes under different climatic characteristics. Let the scene dataset be... The number of clusters is The optimization objective of K-means clustering is to minimize the sum of squared errors from sample points to cluster centers, as expressed below: In the formula, Indicates the first Clusters, This is the center vector of the cluster.

5. The two-stage sub-Bluer beam line loss optimization method for transformer substations considering wind and solar uncertainties as described in claim 1, characterized in that, The objective function of the day-ahead optimization scheduling model considering transformer area line losses, constructed in step 2.2, is as follows: In the formula, This is the loss cost coefficient; This represents the cost coefficient for interacting with the power grid; This represents the cost coefficient for wind curtailment. , , For the operating cost coefficients of wind power, photovoltaic, and energy storage; , The compensation price coefficient for transferable and interruptible loads; The subsidy cost coefficient for coordinating dispatch of electric vehicles; The current day electricity price; Indicates the power interacting with the power grid; , , , , , , , , , , These represent the nodes respectively. ,time The curtailed wind power, curtailed solar power, actual wind power output, charging power of energy storage devices, discharging power of energy storage devices, input and output power of transferable loads, interruption power of interruptible loads, charging power of electric vehicles, and discharging power of electric vehicles.

6. The two-stage sub-Bluer beam line loss optimization method for transformer substations considering wind and solar uncertainties as described in claim 1, characterized in that, In step 2.4, after the power flow calculation converges, the total theoretical line loss of the system is calculated by combining the branch current values. : In the formula, This represents the total theoretical line loss in the transformer area. Fixed losses of distribution transformers include no-load losses and auxiliary component losses; For nodes To the node The current value of the branch circuit; For nodes To the node The resistance of the branch circuit; This is the calculation period.

7. The two-stage sub-Bruker line loss optimization method for transformer substations considering wind and solar uncertainties as described in claim 1, characterized in that, Step 3.1 involves constructing a real-time distributed bar optimization model that considers uncertainties: Used as a scene index to traverse different scenes; This represents the set of weights for extreme scenarios. For the first Weights for extreme scenarios It is by A set of probabilistic uncertainties constructed; , , , , , , , , , Indicates at time Penalty cost coefficients for wind power output adjustment, photovoltaic power output adjustment, loss adjustment, energy storage equipment charging and discharging adjustment, transferable load output and input adjustment, interruptible load adjustment, and electric vehicle charging and discharging adjustment; , Indicates the first A scene, a moment The predicted output of wind power and solar power; , Indicates the first A scene, a moment The actual output of wind power and solar power; , , Indicates the first A scene, a moment The amount of loss adjustment and the amount of charging and discharging power adjustment of energy storage equipment; , , Indicates the first A scene, a moment Adjustments to the transferable load output, transferable load input, and interruptible load; , This represents the adjustment amount of the charging and discharging power of the electric vehicle at time t in the k-th scenario; Node set; Branch set, for branch Its first node is denoted as The end node is denoted as .

8. The two-stage sub-Bruker line loss optimization method for transformer substations considering wind and solar uncertainties as described in claim 1, characterized in that, Step 3.3 uses K-means clustering to obtain k extreme landscape scenes, each denoted as . ,in In the sub-Bruker optimization framework, the worst-case distribution is considered, which is a discrete distribution composed of these extreme scenarios combined with certain probability weights; this extreme value distribution can be expressed as: In the formula, These are the weights corresponding to the extreme scenario k, satisfying... and , It is the Dirac delta function.

9. The two-stage sub-Bruker line loss optimization method for transformer substations considering wind and solar uncertainties as described in claim 1, characterized in that, In step 3.4, the set of uncertainties is defined as follows: In the formula, It is the probability weight of the k-th extreme scenario. and These are the lower and upper bounds of the population mean, respectively; It is the observation value of the i-th reference sample. It is a fuzzy parameter of the distribution. This is the total number of reference samples; The optimal model of the blue bar is based on the worst distribution. The goal is to find a scheduling strategy that minimizes the sum of expected operating costs and line losses.

Images