New energy consumption boundary identification method and system based on time series characteristics

Abstract

The present application discloses a method and system for identifying new energy consumption boundaries based on time series characteristics, the method comprising: obtaining a data set of a source domain and a data set of a target domain, the data set of the source domain comprising power generation data and meteorological data of the source domain within a set period, the data set of the target domain comprising meteorological data of the target domain within a set period and no power generation data of the target domain within the set period; determining source domain common features corresponding to the data set of the source domain and target domain common features corresponding to the data set of the target domain; generating a new energy output time series curve matching the target domain based on the source domain common features and the target domain common features; determining an optimization model based on the new energy output time series curve, power generation data of the source domain, meteorological data of the source domain and meteorological data of the target domain; and using the optimization model to identify the new energy consumption boundary corresponding to the target domain based on meteorological features extracted from the meteorological data of the target domain, thereby accurately identifying the new energy consumption boundary of the area to be identified.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method and system for identifying boundaries of renewable energy consumption based on time series characteristics. Background Art

[0002] Renewable energy consumption refers to the process of effectively integrating electricity generated by renewable energy sources (such as wind, solar, and hydropower) into the power grid and rationally distributing and utilizing it within the grid. Generally, renewable energy generation is significantly affected by meteorological conditions and exhibits significant volatility and randomness. Therefore, as the proportion of renewable energy connected to the grid continues to increase, it introduces significant uncertainty into the grid's balanced scheduling, power flow distribution, and system security.

[0003] Existing technologies for renewable energy consumption primarily rely on prediction methods based on physical models. These methods use historical regression analysis of meteorological variables such as wind speed and irradiance in the forecasted area, combined with historical power generation data from the area, to predict the short- and medium-term output of wind and photovoltaic power generation, thereby determining the renewable energy consumption boundary for the forecasted area. This technology performs well when meteorological conditions are stable and there is a large amount of historical meteorological and power generation data. However, when there is insufficient power generation data in the forecasted area (for example, for newly built renewable energy sites), the lack of power generation data in the area leads to low accuracy in the identified consumption boundary, which can affect power system security and fail to meet the power system's demand for high-precision scheduling. Summary of the Invention

[0004] In order to solve the above technical problems, the embodiment of the present application proposes a method and system for identifying new energy consumption boundaries based on time series characteristics, which can accurately identify the new energy consumption boundaries of the area to be identified without relying on the power generation data of the area to be identified, thereby improving the safety and scheduling accuracy of the power system.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying new energy consumption boundaries based on time series characteristics, including:

[0006] Acquire a data set of a source domain and a data set of a target domain, wherein the data set of the source domain includes power generation data and meteorological data of the source domain within a set period, and the data set of the target domain includes meteorological data of the target domain within the set period, but does not include power generation data of the target domain within the set period;

[0007] Determining source domain common features corresponding to the data set of the source domain and target domain common features corresponding to the data set of the target domain;

[0008] Based on the common characteristics of the source domain and the common characteristics of the target domain, generating a new energy output timing curve matching the target domain;

[0009] Determining an optimization model based on the new energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain;

[0010] The optimization model is used to identify a new energy consumption boundary corresponding to the target domain based on meteorological features extracted from meteorological data of the target domain.

[0011] Optionally, determining the source domain common features corresponding to the source domain dataset and the target domain common features corresponding to the target domain dataset includes:

[0012] Using a graph-based feature extractor, feature extraction is performed on the meteorological data in the source domain to generate the source domain common features, and feature extraction is performed on the meteorological data in the target domain to generate the target domain common features.

[0013] Optionally, the using a graph-based feature extractor to perform feature extraction on the meteorological data in the source domain to generate the source domain common features, and the performing feature extraction on the meteorological data in the target domain to generate the target domain common features, includes:

[0014] Inputting the meteorological data of the source domain into the feature extractor to obtain initial source domain common features output by the feature extractor;

[0015] Inputting the meteorological data of the target domain into the feature extractor to obtain initial target domain common features output by the feature extractor;

[0016] Mapping the initial source domain common features into the target space to obtain the source domain common features, and mapping the initial target domain common features into the target space to obtain the target domain common features;

[0017] The feature extractor is configured to perform feature extraction through empirical mode decomposition and multi-head attention mechanism.

[0018] Optionally, the target space includes a reproducing kernel Hilbert space, and mapping the initial source domain common features into the target space to obtain the source domain common features, and mapping the initial target domain common features into the target space to obtain the target domain common features, comprises:

[0019] Mapping the initial source domain common features to the reproducing kernel Hilbert space through a maximum mean difference function to obtain the source domain common features;

[0020] The initial target domain common features are mapped into the reproducing kernel Hilbert space by using a maximum mean difference function to obtain the target domain common features.

[0021] Optionally, determining the optimization model based on the new energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain includes:

[0022] Based on the renewable energy output time series curve and the power generation data of the source domain, a difference calculation is performed using a mean square error loss function to obtain a difference calculation result;

[0023] Based on the pre-trained target domain classifier, the difference calculation result, the meteorological data of the source domain and the meteorological data of the target domain, configuring a preset multi-objective optimization function to obtain the optimization model;

[0024] in,

[0025] The target domain classifier is constructed based on a domain classifier adversarial learning network, and the domain classifier adversarial learning network includes a gradient reversal layer;

[0026] The training process of the target domain classifier includes: optimizing and adversarializing the gradient reversal layer according to the data set of the source domain and the data set of the target domain to train the target domain classifier.

[0027] Optionally, the using the optimization model to identify the new energy consumption boundary corresponding to the target domain based on meteorological features extracted from meteorological data of the target domain includes:

[0028] Based on the meteorological features extracted from the meteorological data of the target domain, generating the corresponding new energy power generation information of the target domain within the set time period using the optimization model;

[0029] Based on the new energy power generation information, a new energy consumption boundary corresponding to the target domain is identified.

[0030] Optionally, the identifying the new energy consumption boundary corresponding to the target domain based on the new energy power generation information includes:

[0031] Inputting the renewable energy generation information into a preset power system dispatch model, so that the power system dispatch model performs simulation based on the renewable energy generation information to generate optimized power resource configuration data corresponding to the target domain, wherein the optimized power resource configuration data at least includes renewable energy output data;

[0032] Extracting time similarity from the renewable energy output data, and determining spatial boundary nodes of the renewable energy output data;

[0033] Based on the temporal similarity and the spatial boundary nodes, a new energy consumption boundary corresponding to the target domain is determined.

[0034] Optionally, extracting time similarity from the renewable energy output data and determining spatial boundary nodes of the renewable energy output data includes:

[0035] Using the t-SNE algorithm, extracting the time similarity from the renewable energy output data;

[0036] Using a graph-based feature extractor, extract features from the renewable energy output data to generate renewable energy output data features represented by an adjacency matrix of the graph structure, wherein the graph structure includes a plurality of nodes, and the adjacency matrix is ​​determined by weights between each of the plurality of nodes;

[0037] According to the renewable energy output data characteristics, the spatial boundary node is determined among the multiple nodes using key node analysis.

[0038] Optionally, the new energy consumption boundary is used to determine the consumption space under the boundary scenario, wherein the consumption space is determined based on the difference between the load active power at the boundary moment corresponding to the new energy consumption boundary and the minimum technical output value of the power system.

[0039] In a second aspect, an embodiment of the present application provides a new energy consumption boundary identification system based on time series characteristics, including:

[0040] a data acquisition module, configured to acquire a data set of a source domain and a data set of a target domain, wherein the data set of the source domain includes power generation data and meteorological data of the source domain within a set period, and the data set of the target domain includes meteorological data of the target domain within the set period, but does not include power generation data of the target domain within the set period;

[0041] a common feature extraction module, configured to determine source domain common features corresponding to the source domain dataset and target domain common features corresponding to the target domain dataset;

[0042] An output curve determination module, configured to generate a new energy output timing curve matching the target domain based on the common characteristics of the source domain and the common characteristics of the target domain;

[0043] an optimization module, configured to determine an optimization model based on the renewable energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain;

[0044] An identification module is used to identify the new energy consumption boundary corresponding to the target domain based on the meteorological features extracted from the meteorological data of the target domain by using the optimization model.

[0045] In summary, the embodiments of the present application have at least the following beneficial effects:

[0046] According to an embodiment of the present application, a data set of a source domain and a data set of a target domain are obtained, wherein the data set of the source domain includes power generation data and meteorological data of the source domain within a set time period, and the data set of the target domain includes meteorological data of the target domain within the set time period, and there is no power generation data of the target domain within the set time period; source domain common features corresponding to the data set of the source domain and target domain common features corresponding to the data set of the target domain are determined; based on the source domain common features and the target domain common features, a new energy output timing curve matching the target domain is generated; based on the new energy output timing curve, the power generation data of the source domain, the meteorological data of the source domain and the meteorological data of the target domain, an optimization model is determined; using the optimization model, based on the meteorological features extracted from the meteorological data of the target domain, the new energy consumption boundary corresponding to the target domain is identified, so that the new energy consumption boundary of the area to be identified can be accurately identified by using sufficient and accurate data from other areas as auxiliary conditions without relying on the power generation data of the area to be identified, thereby improving the safety and scheduling accuracy of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a flow chart of a method for identifying new energy consumption boundaries based on time series characteristics provided in an embodiment of the present application;

[0048] Figure 2 is a schematic diagram of the analysis results on time similarity provided by an embodiment of the present application;

[0049] Figure 3 is a schematic diagram of the analysis results on spatial similarity provided by the embodiment of the present application;

[0050] Figure 4 It is a structural diagram of a new energy consumption boundary identification system based on time series characteristics provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0052] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, "multiple" means two or more. In the description of this application, the term "including" and its variations are open inclusions, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "according to" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments".

[0053] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0054] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meanings as those commonly understood by those skilled in the art. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit this application. Those of ordinary skill in the art will understand the specific meanings of the above terms in this application in specific circumstances.

[0055] First, see Figure 1 , shows a flow chart of a method for identifying new energy consumption boundaries based on time series characteristics provided by an embodiment of the present application, the method including steps S101-S105, specifically as follows:

[0056] S101, obtaining a data set of a source domain and a data set of a target domain, wherein the data set of the source domain includes power generation data and meteorological data of the source domain within a set time period, and the data set of the target domain includes meteorological data of the target domain within the set time period, and does not include power generation data of the target domain within the set time period; wherein the source domain and the target domain in this embodiment may represent different regions.

[0057] In an example, the dataset of the source domain can be represented as , the dataset of the target domain can be expressed as ,in, represents the i-th type of meteorological data in the source domain, represents the i-th type of power generation data corresponding to the i-th type of meteorological data in the source domain, represents the jth type of meteorological data in the target domain, represents the number of samples in the dataset of the source domain, represents the number of samples in the dataset of the target domain, , ,Here, different kinds of data can represent differences in time or space.

[0058] In one example, meteorological data may include data collected by ground meteorological stations, data collected by remote sensing meteorological satellites, etc., ensuring the diversity and comprehensiveness of the data.

[0059] S102, determining source domain common features corresponding to the source domain dataset and target domain common features corresponding to the target domain dataset;

[0060] S103, generating a new energy output timing curve matching the target domain based on the common characteristics of the source domain and the common characteristics of the target domain;

[0061] S104, determining an optimization model based on the new energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain;

[0062] S105 , using the optimization model, based on meteorological features extracted from the meteorological data of the target domain, identifying a new energy consumption boundary corresponding to the target domain.

[0063] In this embodiment, the source domain data includes not only historical meteorological data but also actual output data related to power generation, while the target domain primarily contains current meteorological data. In the absence of labeled data in the target domain, differences in geographic location, meteorological conditions, and data annotation between the source and target domains are effectively addressed. By extracting domain-independent common features, the prediction model can be adapted to the target domain's meteorological conditions, thereby improving the accuracy of power generation forecasts.

[0064] In an optional implementation, determining the source domain common features corresponding to the source domain dataset and the target domain common features corresponding to the target domain dataset includes:

[0065] Using a graph-based feature extractor, feature extraction is performed on the meteorological data in the source domain to generate the source domain common features, and feature extraction is performed on the meteorological data in the target domain to generate the target domain common features.

[0066] In an optional embodiment, the step of using a graph-based feature extractor to perform feature extraction on the meteorological data in the source domain to generate the source domain common features, and the step of performing feature extraction on the meteorological data in the target domain to generate the target domain common features, includes:

[0067] Inputting the meteorological data of the source domain into the feature extractor to obtain initial source domain common features output by the feature extractor;

[0068] Inputting the meteorological data of the target domain into the feature extractor to obtain initial target domain common features output by the feature extractor;

[0069] The initial source domain common features are mapped into a target space to obtain the source domain common features, and the initial target domain common features are mapped into the target space to obtain the target domain common features.

[0070] The feature extractor is configured to perform feature extraction through empirical mode decomposition and multi-head attention mechanism.

[0071] In one example, the feature extractor can be configured to: perform empirical mode decomposition in time series on the input data to obtain multiple nodes of a graph structure, and use a multi-head attention mechanism to calculate the weights between the multiple nodes to generate an adjacency matrix of the graph structure based on the weights for characterizing the common features output in response to the input data.

[0072] In this embodiment, empirical mode decomposition can be performed on the meteorological time series of meteorological data, each subsequence in the meteorological time series can be regarded as a node of a graph, and the weights between the nodes can be calculated using a multi-head attention mechanism to generate an adjacency matrix of the graph. The adjacency matrix can be determined using the following formula:

[0073]

[0074] in, represents the i-th adjacency matrix, represents the first node feature matrix, represents the second node feature matrix, represents the first transformation matrix corresponding to the i-th adjacency matrix, The second transformation matrix corresponding to the i-th adjacency matrix, N is the number of nodes.

[0075] As described above, this embodiment can dynamically adjust the graph structure to capture the complex dependencies between meteorological variables, thereby improving the accuracy of power generation forecasts. To address the spatiotemporal dependencies in meteorological data, this embodiment employs a graph-based feature extraction method. By performing empirical mode decomposition on meteorological time series data, data at different time scales are treated as nodes of the graph. A multi-head attention mechanism is used to calculate the weights between nodes and dynamically generate an adjacency matrix. This embodiment can accurately capture the complex spatiotemporal dependencies between meteorological variables, ensuring that the model can identify the potential interactions between different meteorological variables, thereby enhancing the model's adaptability to changing meteorological conditions.

[0076] In an optional embodiment, the target space includes a reproducing kernel Hilbert space, and mapping the initial source domain common features into the target space to obtain the source domain common features, and mapping the initial target domain common features into the target space to obtain the target domain common features, includes:

[0077] Mapping the initial source domain common features to the reproducing kernel Hilbert space through a maximum mean difference function to obtain the source domain common features;

[0078] The initial target domain common features are mapped into the reproducing kernel Hilbert space by using a maximum mean difference function to obtain the target domain common features.

[0079] In this embodiment, a feature extractor is used to extract domain-independent common features from meteorological data in the source and target domains. The extracted features are then mapped to a reproducing kernel Hilbert space using the Maximum Mean Discrepancy (MMD) function to align the feature distributions of the source and target domains. This ensures that the corresponding features of the source and target domains remain consistent within the shared space, thereby reducing inter-domain differences.

[0080] This embodiment uses the maximum mean difference function to map meteorological data from the source and target domains onto the reproducing kernel Hilbert space, aligning their feature distributions. This embodiment effectively eliminates data discrepancies between the source and target domains. This allows the model to accurately predict power generation using the features of the source domain data, even when the target domain lacks labeled data. The introduction of this feature alignment process improves the model's domain adaptability and makes its performance more stable under different meteorological conditions.

[0081] In an optional embodiment, determining the optimization model based on the new energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain includes:

[0082] Based on the new energy output time series curve and the power generation data of the source domain, a difference calculation is performed using a mean square error loss function to obtain a difference calculation result.

[0083] Based on the pre-trained target domain classifier, the difference calculation result, the meteorological data of the source domain and the meteorological data of the target domain, configuring a preset multi-objective optimization function to obtain the optimization model;

[0084] in,

[0085] The target domain classifier is constructed based on a domain classifier adversarial learning network, and the domain classifier adversarial learning network includes a gradient reversal layer;

[0086] The training process of the target domain classifier includes: optimizing and adversarializing the gradient reversal layer according to the data set of the source domain and the data set of the target domain to train the target domain classifier.

[0087] In this embodiment, the generated new energy output time series curve of the target domain is compared with the actual power generation data of the source domain, and the mean square error loss function is minimized. , to ensure that the generated new energy output curve is highly consistent with the actual power generation data, thereby improving the accuracy of output prediction.

[0088] In one example, the mean squared error loss function It can be expressed by the following formula:

[0089]

[0090] in, represents the number of samples in the dataset of the source domain, represents the i-th type of power generation data in the source domain, Represents the data value corresponding to the i-th type of power generation data in the renewable energy output time series curve. In this embodiment, a wind and solar power generation prediction generator can be used to generate a renewable energy output time series curve based on the common characteristics of the source domain and the common characteristics of the target domain. The generator can dynamically generate a renewable energy output time series curve (including the power curves of wind power generation and photovoltaic power generation) based on the input characteristics and optimize it using a mean square error loss function to ensure that the generated renewable energy output time series curve is highly consistent with the power generation data in the source domain. This embodiment not only improves prediction accuracy but also ensures a close match between the prediction curve and actual meteorological conditions, providing a reliable numerical basis for the stable operation of the power system.

[0091] In one example, the loss function for the target domain classifier is It can be expressed by the following formula:

[0092]

[0093] in, represents the parameters of the feature extractor, represents the parameters of the domain classifier, represents the number of samples in the dataset of the source domain, , represents the prediction of the domain classifier for the i-th source domain data sample, represents the output probability value of the domain classifier for the i-th source domain data sample. In this embodiment, by optimizing this loss function, the model can better distinguish between the source domain and the target domain, thereby enhancing the domain adaptability of the model. In this embodiment, by combining the domain classifier with the gradient reversal layer, the adversarial learning process between the source domain and the target domain is optimized. By maximizing the domain classifier's ability to distinguish between the source domain and the target domain data, the model can better identify the differences between the source domain and the target domain, thereby enhancing the model's generalization ability and adaptability, enabling it to accurately estimate power output under different meteorological conditions.

[0094] In one example, the optimization model can be expressed as follows:

[0095]

[0096] in, represents the parameters of the feature extractor, represents the parameters of the domain classifier, represents the mean square error loss function, It represents the process of generating the common features of the source domain and the common features of the target domain according to the meteorological data of the source domain and the target domain through the maximum mean difference function. represents the loss function of the target domain classifier, is the weight used to control the maximum mean difference function, are weights used to control the loss of the target domain classifier. In this embodiment, these weights can be dynamically adjusted to gradually optimize the model's alignment ability and prediction accuracy during the training process. This embodiment introduces a multi-objective optimization strategy. By dynamically adjusting the weights of the maximum mean difference loss function and the domain classification loss function, the model is ensured to align the data distribution of the source and target domains while improving the accuracy of power generation prediction. This multi-objective optimization strategy further optimizes the overall performance of the model by balancing the conflict between feature alignment and power generation prediction, enabling it to maintain high robustness under complex meteorological conditions.

[0097] In an optional embodiment, the using of the optimization model to identify the new energy consumption boundary corresponding to the target domain based on meteorological features extracted from meteorological data of the target domain includes:

[0098] Based on the meteorological features extracted from the meteorological data of the target domain, generating the corresponding new energy power generation information of the target domain within the set time period using the optimization model;

[0099] Based on the new energy power generation information, a new energy consumption boundary corresponding to the target domain is identified.

[0100] In an optional implementation, the identifying the new energy consumption boundary corresponding to the target domain based on the new energy power generation information includes:

[0101] Inputting the renewable energy generation information into a preset power system dispatch model, so that the power system dispatch model performs simulation based on the renewable energy generation information to generate optimized power resource configuration data corresponding to the target domain, wherein the optimized power resource configuration data at least includes renewable energy output data;

[0102] Extracting time similarity from the renewable energy output data, and determining spatial boundary nodes of the renewable energy output data;

[0103] Based on the temporal similarity and the spatial boundary nodes, a new energy consumption boundary corresponding to the target domain is determined.

[0104] In one example, the power system dispatch model can be used to perform real-time sequential production operation simulation to generate an optimized power resource configuration, wherein the power system dispatch model It can be expressed by the following formula:

[0105]

[0106] in, Indicates the total running time of the time series production simulation, usually set to 8760 hours; Represents wind power at time The maximum accessible capacity within Represents photovoltaic at time The maximum accessible capacity within the range. During the optimization simulation, at least one of the following constraints can be considered: power balance constraint, spinning reserve constraint, conventional unit output constraint, ramp rate constraint, start-up and shutdown constraint, renewable energy output constraint, and power flow constraints such as node power balance and line capacity.

[0107] In this embodiment, based on the optimized power generation forecast model, time-series output scenarios for renewable energy can be generated and applied to power system scheduling and resource allocation. During the simulation process, the system not only considers changes in the power generation curve, but also comprehensively considers various constraints such as power balance, spinning reserve, and conventional unit output, thereby optimizing the operating efficiency of the power grid. By accurately simulating power generation under different meteorological conditions, the power dispatch system can more flexibly respond to changing weather conditions and ensure the security and stability of the power grid.

[0108] In an optional implementation, extracting time similarity from the renewable energy output data and determining spatial boundary nodes of the renewable energy output data includes:

[0109] Using a t-SNE (t-Distributed Stochastic Neighbor Embedding) algorithm, extracting the time similarity from the renewable energy output data;

[0110] Using a graph-based feature extractor, extract features from the renewable energy output data to generate renewable energy output data features represented by an adjacency matrix of the graph structure, wherein the graph structure includes a plurality of nodes, and the adjacency matrix is ​​determined by weights between each of the plurality of nodes;

[0111] According to the renewable energy output data characteristics, the spatial boundary node is determined among the multiple nodes using key node analysis.

[0112] In one example, in a high-dimensional space, the t-SNE algorithm first calculates the similarity between each pair of data points. and , whose similarity is expressed by conditional probability, reflecting the Select point Probability :

[0113]

[0114] in, is the standard deviation parameter, which controls the distance weight distribution between data points.

[0115] Then define the joint probability for:

[0116]

[0117] In low-dimensional space, the point and The similarity probability between pass Distributed computing:

[0118]

[0119] The goal of t-SNE is to minimize the Kullback-Leibler divergence (KL divergence) to make the similarity in low-dimensional space As close as possible to similarity in high-dimensional space The formula is as follows:

[0120]

[0121] The loss function is minimized by gradient descent. t-SNE optimizes the embedding by updating the position of the points in the low-dimensional space so that the similarity distribution between the high-dimensional and low-dimensional spaces is as consistent as possible.

[0122] In one example, based on the renewable energy output data characteristics, using key node analysis to determine the spatial boundary node among the multiple nodes can include: in the spatial dimension, based on the power flow characteristics of the main grid represented by the renewable energy output data characteristics, sorting and reducing the dimensions of the multiple nodes, and using key node analysis to determine the spatial boundary node among the sorted and reduced nodes.

[0123] In this example, the t-SNE algorithm, using spatiotemporal similarity extraction technology, identifies the renewable energy absorption boundaries and calculates the absorption capacity. This process dynamically identifies the maximum and minimum boundaries of renewable energy absorption capacity by analyzing the similarities between different nodes, and generates corresponding absorption scenarios. This method not only improves the power system's absorption capacity when a high proportion of renewable energy is connected, but also provides a basis for the optimal allocation of power resources, making the system more flexible and efficient in dealing with complex weather conditions and load fluctuations.

[0124] See also Figure 2 , shows the analysis results obtained by analyzing the time similarity after adopting this embodiment. In this embodiment, all 8760 hours of operation data are divided into five clusters (i.e., corresponding to Figure 2 In the five coordinate systems from top to bottom in the figure, the number of instances in each cluster are 1442, 1474, 1995, 1818 and 2051 respectively. Figure 2 The results show that: 1) spatial nodes 16 and 40 are more likely to experience significant wind power curtailment; 2) in the fourth cluster (corresponding to Figure 2 In the fourth coordinate system from top to bottom in the figure, all nodes show obvious wind power curtailment.

[0125] See also Figure 3 , shows the analysis results obtained from the spatial similarity analysis after adopting this embodiment. In this embodiment, the whole year is divided into 8760 hours. The clustering curve shows significant wind power curtailment peaks at the 852nd and 3685th time steps, corresponding to 12:00 on February 5 and 01:00 on June 3, respectively, indicating that these time points are low load demand periods. In addition, it can be observed that the fourth category (i.e. corresponding to Figure 2 The 4th coordinate system from top to bottom) and the 5th type (corresponding to Figure 2 The clusters (the fifth coordinate system from top to bottom) generally show a high level of wind power curtailment, indicating that other factors may limit the absorption of renewable energy at these nodes. Figure 2 The analysis results are similar to those in , where it can be observed that nodes 16 and 40 are classified into the 4th and 5th clusters respectively.

[0126] In an optional embodiment, the new energy consumption boundary is used to determine the consumption space under the boundary scenario, wherein the consumption space is determined based on the difference between the load active power at the boundary moment corresponding to the new energy consumption boundary and the minimum technical output value of the power system.

[0127] In one example, the absorption space It can be determined by the following formula:

[0128]

[0129] in, is the load active power at the boundary moment corresponding to the new energy consumption boundary, Indicates the minimum technical output value of the power system corresponding to the new energy consumption boundary.

[0130] On the second aspect, accordingly, the embodiment of the present application also provides a new energy consumption boundary identification system based on time series characteristics, which can implement all the processes of the new energy consumption boundary identification method based on time series characteristics provided in the above embodiment.

[0131] See also Figure 4 , shows a schematic structural diagram of a new energy consumption boundary identification system based on time series characteristics provided in an embodiment of the present application, the new energy consumption boundary identification system comprising:

[0132] The data acquisition module 401 is configured to acquire a data set of a source domain and a data set of a target domain, wherein the data set of the source domain includes power generation data and meteorological data of the source domain within a set period, and the data set of the target domain includes meteorological data of the target domain within the set period, but does not include power generation data of the target domain within the set period;

[0133] A common feature extraction module 402 is configured to determine source domain common features corresponding to the source domain dataset and target domain common features corresponding to the target domain dataset;

[0134] An output curve determination module 403 is configured to generate a new energy output time series curve matching the target domain based on the common characteristics of the source domain and the common characteristics of the target domain;

[0135] An optimization module 404 is configured to determine an optimization model based on the renewable energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain;

[0136] The identification module 405 is configured to use the optimization model to identify the new energy consumption boundary corresponding to the target domain based on meteorological features extracted from the meteorological data of the target domain.

[0137] In an optional implementation, determining the source domain common features corresponding to the source domain dataset and the target domain common features corresponding to the target domain dataset includes:

[0138] Using a graph-based feature extractor, feature extraction is performed on the meteorological data in the source domain to generate the source domain common features, and feature extraction is performed on the meteorological data in the target domain to generate the target domain common features.

[0139] In an optional embodiment, the step of using a graph-based feature extractor to perform feature extraction on the meteorological data in the source domain to generate the source domain common features, and the step of performing feature extraction on the meteorological data in the target domain to generate the target domain common features, includes:

[0140] Inputting the meteorological data of the source domain into the feature extractor to obtain initial source domain common features output by the feature extractor;

[0141] Inputting the meteorological data of the target domain into the feature extractor to obtain initial target domain common features output by the feature extractor;

[0142] Mapping the initial source domain common features into the target space to obtain the source domain common features, and mapping the initial target domain common features into the target space to obtain the target domain common features;

[0143] The feature extractor is configured to perform feature extraction through empirical mode decomposition and multi-head attention mechanism.

[0144] In an optional embodiment, the target space includes a reproducing kernel Hilbert space, and mapping the initial source domain common features into the target space to obtain the source domain common features, and mapping the initial target domain common features into the target space to obtain the target domain common features, includes:

[0145] Mapping the initial source domain common features to the reproducing kernel Hilbert space through a maximum mean difference function to obtain the source domain common features;

[0146] The initial target domain common features are mapped into the reproducing kernel Hilbert space by using a maximum mean difference function to obtain the target domain common features.

[0147] In an optional embodiment, determining the optimization model based on the new energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain includes:

[0148] Based on the renewable energy output time series curve and the power generation data of the source domain, a difference calculation is performed using a mean square error loss function to obtain a difference calculation result;

[0149] Based on the pre-trained target domain classifier, the difference calculation result, the meteorological data of the source domain and the meteorological data of the target domain, configuring a preset multi-objective optimization function to obtain the optimization model;

[0150] in,

[0151] The target domain classifier is constructed based on a domain classifier adversarial learning network, and the domain classifier adversarial learning network includes a gradient reversal layer;

[0152] The training process of the target domain classifier includes: optimizing and adversarializing the gradient reversal layer according to the data set of the source domain and the data set of the target domain to train the target domain classifier.

[0153] In an optional embodiment, the using of the optimization model to identify the new energy consumption boundary corresponding to the target domain based on meteorological features extracted from meteorological data of the target domain includes:

[0154] Based on the meteorological features extracted from the meteorological data of the target domain, generating the corresponding new energy power generation information of the target domain within the set time period using the optimization model;

[0155] Based on the new energy power generation information, a new energy consumption boundary corresponding to the target domain is identified.

[0156] In an optional implementation, the identifying the new energy consumption boundary corresponding to the target domain based on the new energy power generation information includes:

[0157] Inputting the renewable energy generation information into a preset power system dispatch model, so that the power system dispatch model performs simulation based on the renewable energy generation information to generate optimized power resource configuration data corresponding to the target domain, wherein the optimized power resource configuration data at least includes renewable energy output data;

[0158] Extracting time similarity from the renewable energy output data, and determining spatial boundary nodes of the renewable energy output data;

[0159] Based on the temporal similarity and the spatial boundary nodes, a new energy consumption boundary corresponding to the target domain is determined.

[0160] In an optional implementation, extracting time similarity from the renewable energy output data and determining spatial boundary nodes of the renewable energy output data includes:

[0161] Using the t-SNE algorithm, extracting the time similarity from the renewable energy output data;

[0162] Using a graph-based feature extractor, extract features from the renewable energy output data to generate renewable energy output data features represented by an adjacency matrix of the graph structure, wherein the graph structure includes a plurality of nodes, and the adjacency matrix is ​​determined by weights between each of the plurality of nodes;

[0163] According to the renewable energy output data characteristics, the spatial boundary node is determined among the multiple nodes using key node analysis.

[0164] In an optional embodiment, the new energy consumption boundary is used to determine the consumption space under the boundary scenario, wherein the consumption space is determined based on the difference between the load active power at the boundary moment corresponding to the new energy consumption boundary and the minimum technical output value of the power system.

[0165] In summary, the embodiments of the present application have at least the following beneficial effects:

[0166] According to an embodiment of the present application, a data set of a source domain and a data set of a target domain are obtained, wherein the data set of the source domain includes power generation data and meteorological data of the source domain within a set time period, and the data set of the target domain includes meteorological data of the target domain within the set time period, and there is no power generation data of the target domain within the set time period; source domain common features corresponding to the data set of the source domain and target domain common features corresponding to the data set of the target domain are determined; based on the source domain common features and the target domain common features, a new energy output timing curve matching the target domain is generated; based on the new energy output timing curve, the power generation data of the source domain, the meteorological data of the source domain and the meteorological data of the target domain, an optimization model is determined; using the optimization model, based on the meteorological features extracted from the meteorological data of the target domain, the new energy consumption boundary corresponding to the target domain is identified, so that the new energy consumption boundary of the area to be identified can be accurately identified by using sufficient and accurate data from other areas as auxiliary conditions without relying on the power generation data of the area to be identified, thereby improving the safety and scheduling accuracy of the power system.

[0167] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary hardware platform, and of course, it can also be implemented entirely through hardware. Based on this understanding, all or part of the contribution of the technical solution of the present application to the background technology can be embodied in the form of a software product. The computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of the present application.

[0168] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A method for identifying the boundary of new energy consumption based on time series characteristics, characterized in that: include: Acquire a data set of a source domain and a data set of a target domain, wherein the data set of the source domain includes power generation data and meteorological data of the source domain within a set period, and the data set of the target domain includes meteorological data of the target domain within the set period, but does not include power generation data of the target domain within the set period; Determining source domain common features corresponding to the data set of the source domain and target domain common features corresponding to the data set of the target domain; Based on the common characteristics of the source domain and the common characteristics of the target domain, generating a new energy output timing curve matching the target domain; Determining an optimization model based on the new energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain; Using the optimization model, based on meteorological features extracted from meteorological data of the target domain, identifying a new energy consumption boundary corresponding to the target domain; The step of determining the optimization model based on the new energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain includes: Based on the renewable energy output time series curve and the power generation data of the source domain, a difference calculation is performed using a mean square error loss function to obtain a difference calculation result; Based on the pre-trained target domain classifier, the difference calculation result, the meteorological data of the source domain and the meteorological data of the target domain, configuring a preset multi-objective optimization function to obtain the optimization model; in, The target domain classifier is constructed based on a domain classifier adversarial learning network, and the domain classifier adversarial learning network includes a gradient reversal layer; The training process of the target domain classifier includes: optimizing and confronting the gradient reversal layer according to the data set of the source domain and the data set of the target domain to train the target domain classifier; The determining of the source domain common features corresponding to the source domain dataset and the target domain common features corresponding to the target domain dataset includes: Using a graph-based feature extractor, feature extraction is performed on the meteorological data in the source domain to generate the source domain common features, and feature extraction is performed on the meteorological data in the target domain to generate the target domain common features; The step of using a graph-based feature extractor to perform feature extraction on the meteorological data in the source domain to generate the source domain common features, and the step of performing feature extraction on the meteorological data in the target domain to generate the target domain common features, includes: Inputting the meteorological data of the source domain into the feature extractor to obtain initial source domain common features output by the feature extractor; Inputting the meteorological data of the target domain into the feature extractor to obtain initial target domain common features output by the feature extractor; Mapping the initial source domain common features into the target space to obtain the source domain common features, and mapping the initial target domain common features into the target space to obtain the target domain common features; The step of using the optimization model to identify the new energy consumption boundary corresponding to the target domain based on meteorological features extracted from meteorological data of the target domain includes: Based on the meteorological features extracted from the meteorological data of the target domain, generating the corresponding new energy power generation information of the target domain within the set time period using the optimization model; Based on the new energy power generation information, identifying the new energy consumption boundary corresponding to the target domain; The step of identifying the new energy consumption boundary corresponding to the target domain based on the new energy power generation information includes: Inputting the renewable energy generation information into a preset power system dispatch model, so that the power system dispatch model performs simulation based on the renewable energy generation information to generate optimized power resource configuration data corresponding to the target domain, wherein the optimized power resource configuration data at least includes renewable energy output data; Extracting time similarity from the renewable energy output data, and determining spatial boundary nodes of the renewable energy output data; Determining a new energy consumption boundary corresponding to the target domain based on the temporal similarity and the spatial boundary nodes; The step of determining the spatial boundary nodes of the renewable energy output data includes: Using a graph-based feature extractor, extract features from the renewable energy output data to generate renewable energy output data features represented by an adjacency matrix of the graph structure, wherein the graph structure includes a plurality of nodes, and the adjacency matrix is ​​determined by weights between each of the plurality of nodes; Determining the spatial boundary node from the plurality of nodes using key node analysis based on the renewable energy output data characteristics, including: sorting and reducing the dimensions of the plurality of nodes in a spatial dimension based on power flow characteristics of the main grid represented by the renewable energy output data characteristics, and determining the spatial boundary node from the plurality of nodes after sorting and reducing the dimensions using key node analysis; The feature extractor is configured to perform empirical mode decomposition on the input data in time series to obtain multiple nodes of a graph structure, and use a multi-head attention mechanism to calculate weights between the multiple nodes to generate an adjacency matrix of the graph structure according to the weights, so as to characterize the common features output in response to the input data; The new energy consumption boundary is used to determine the consumption space under the boundary scenario, wherein the consumption space is determined according to the difference between the load active power at the boundary moment corresponding to the new energy consumption boundary and the minimum technical output value of the power system; The step of extracting time similarity from the renewable energy output data includes: The time similarity is extracted from the renewable energy output data using the t-SNE algorithm.

2. The method for identifying new energy consumption boundaries based on time series characteristics according to claim 1, characterized in that: The target space includes a reproducing kernel Hilbert space, and mapping the initial source domain common features into the target space to obtain the source domain common features, and mapping the initial target domain common features into the target space to obtain the target domain common features, includes: Mapping the initial source domain common features to the reproducing kernel Hilbert space through a maximum mean difference function to obtain the source domain common features; The initial target domain common features are mapped into the reproducing kernel Hilbert space by using a maximum mean difference function to obtain the target domain common features.

3. A new energy consumption boundary identification system based on time series characteristics, characterized by: include: a data acquisition module, configured to acquire a data set of a source domain and a data set of a target domain, wherein the data set of the source domain includes power generation data and meteorological data of the source domain within a set period, and the data set of the target domain includes meteorological data of the target domain within the set period, but does not include power generation data of the target domain within the set period; a common feature extraction module, configured to determine source domain common features corresponding to the source domain dataset and target domain common features corresponding to the target domain dataset; An output curve determination module, configured to generate a new energy output timing curve matching the target domain based on the common characteristics of the source domain and the common characteristics of the target domain; an optimization module, configured to determine an optimization model based on the renewable energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain; an identification module, configured to identify a new energy consumption boundary corresponding to the target domain based on meteorological features extracted from meteorological data of the target domain using the optimization model; The step of determining the optimization model based on the new energy output time series curve, the power generation data of the source domain, the meteorological data of the source domain, and the meteorological data of the target domain includes: Based on the renewable energy output time series curve and the power generation data of the source domain, a difference calculation is performed using a mean square error loss function to obtain a difference calculation result; Based on the pre-trained target domain classifier, the difference calculation result, the meteorological data of the source domain and the meteorological data of the target domain, configuring a preset multi-objective optimization function to obtain the optimization model; in, The target domain classifier is constructed based on a domain classifier adversarial learning network, and the domain classifier adversarial learning network includes a gradient reversal layer; The training process of the target domain classifier includes: optimizing and confronting the gradient reversal layer according to the data set of the source domain and the data set of the target domain to train the target domain classifier; The determining of the source domain common features corresponding to the source domain dataset and the target domain common features corresponding to the target domain dataset includes: Using a graph-based feature extractor, feature extraction is performed on the meteorological data in the source domain to generate the source domain common features, and feature extraction is performed on the meteorological data in the target domain to generate the target domain common features; The step of using a graph-based feature extractor to perform feature extraction on the meteorological data in the source domain to generate the source domain common features, and the step of performing feature extraction on the meteorological data in the target domain to generate the target domain common features, includes: Inputting the meteorological data of the source domain into the feature extractor to obtain initial source domain common features output by the feature extractor; Inputting the meteorological data of the target domain into the feature extractor to obtain initial target domain common features output by the feature extractor; Mapping the initial source domain common features into the target space to obtain the source domain common features, and mapping the initial target domain common features into the target space to obtain the target domain common features; The step of using the optimization model to identify the new energy consumption boundary corresponding to the target domain based on meteorological features extracted from meteorological data of the target domain includes: Based on the meteorological features extracted from the meteorological data of the target domain, generating the corresponding new energy power generation information of the target domain within the set time period using the optimization model; Based on the new energy power generation information, identifying the new energy consumption boundary corresponding to the target domain; The step of identifying the new energy consumption boundary corresponding to the target domain based on the new energy power generation information includes: Inputting the renewable energy generation information into a preset power system dispatch model, so that the power system dispatch model performs simulation based on the renewable energy generation information to generate optimized power resource configuration data corresponding to the target domain, wherein the optimized power resource configuration data at least includes renewable energy output data; Extracting time similarity from the renewable energy output data, and determining spatial boundary nodes of the renewable energy output data; Determining a new energy consumption boundary corresponding to the target domain based on the temporal similarity and the spatial boundary nodes; The step of determining the spatial boundary nodes of the renewable energy output data includes: Using a graph-based feature extractor, extract features from the renewable energy output data to generate renewable energy output data features represented by an adjacency matrix of the graph structure, wherein the graph structure includes a plurality of nodes, and the adjacency matrix is ​​determined by weights between each of the plurality of nodes; Determining the spatial boundary node from the plurality of nodes using key node analysis based on the renewable energy output data characteristics, including: sorting and reducing the dimensions of the plurality of nodes in a spatial dimension based on power flow characteristics of the main grid represented by the renewable energy output data characteristics, and determining the spatial boundary node from the plurality of nodes after sorting and reducing the dimensions using key node analysis; The feature extractor is configured to perform empirical mode decomposition on the input data in time series to obtain multiple nodes of a graph structure, and use a multi-head attention mechanism to calculate weights between the multiple nodes to generate an adjacency matrix of the graph structure according to the weights, so as to characterize the common features output in response to the input data; The new energy consumption boundary is used to determine the consumption space under the boundary scenario, wherein the consumption space is determined according to the difference between the load active power at the boundary moment corresponding to the new energy consumption boundary and the minimum technical output value of the power system; The step of extracting time similarity from the renewable energy output data includes: The time similarity is extracted from the renewable energy output data using the t-SNE algorithm.

Images