Wind power control system based on wind speed prediction

Abstract

The invention provides a wind power control system based on wind speed prediction, and relates to the field of intelligent scheduling control, and the system obtains a time sequence of real-time wind speed values and historical data of the wind speed values in a preset time period, encodes the real-time wind speed time sequence and historical subsequences respectively, extracts global long-term dependence and local disturbance characteristics, and carries out the prediction of the wind speed values according to the global long-term dependence and local disturbance characteristics. Semantic association of real-time features and historical similar scenes is dynamically fused through decision anchor points, a high-precision wind speed prediction value is generated based on fusion, real-time deviation analysis of the prediction value and cut-out wind speed is carried out, and a hierarchical power limiting strategy is triggered by combining a dynamic threshold adjustment mechanism. According to the scheme, the nonlinear time sequence rule of the wind speed is automatically captured through deep learning, the actual working condition change is dynamically responded, the prediction precision is effectively improved, the control delay is shortened, the power generation efficiency is optimized, and the power grid voltage stability is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of intelligent dispatching control, and more particularly, in an embodiment of the present application, to a wind power control system based on wind speed prediction. Background Art

[0002] As the global energy transition process accelerates, wind power, as an important component of clean energy, continues to increase its share in the power system. However, wind power has strong randomness and volatility, and its output power is directly affected by changes in wind speed. Instantaneous fluctuations in wind speed may cause severe jitters in the output power of wind farms, thereby threatening the stability of the power grid and reducing power generation efficiency. Among them, the existing patent CN116960978A introduces an offshore wind power prediction method based on wind speed-power combined decomposition and reconstruction, which improves the accuracy of offshore wind power prediction through combined decomposition, fuzzy entropy reconstruction, LSTM modeling and Bayesian optimization.

[0003] However, there are still many problems with the existing wind power control technology. On the one hand, in the wind speed prediction link, the wind speed data was processed only by simple statistical models in the past, and the complex and changeable wind speed time series characteristics were not fully explored. For example, traditional methods are difficult to effectively capture the fluctuation patterns of wind speed on different time scales, and cannot fully utilize the complex relationship between real-time wind speed and historical wind speed data, resulting in low wind speed prediction accuracy. On the other hand, in terms of wind power control strategy, the traditional method lacks a dynamic adjustment mechanism, usually based on fixed thresholds for power control, and fails to make timely and accurate responses to changes in real-time wind speed.

[0004] Therefore, an optimized wind power control scheme based on wind speed prediction is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a wind power control system based on wind speed prediction, which first obtains the time series of real-time wind speed values ​​collected by the wind speed sensor within a predetermined time period, and obtains the historical data of the wind speed value, and uses data analysis and encoding technology based on deep learning to encode the real-time wind speed time series and historical subsequences respectively, extracts global long-term dependency and local disturbance features, and then dynamically fuses the semantic association of real-time features and historical similar scenes through decision anchor points, and then generates high-precision wind speed prediction values ​​based on the fusion, and triggers the hierarchical power limitation strategy based on the real-time deviation analysis between the predicted value and the cut-out wind speed, combined with the dynamic threshold adjustment mechanism. This solution automatically captures the nonlinear time series law of wind speed through deep learning, dynamically responds to changes in actual working conditions, effectively improves prediction accuracy, shortens control delays, and optimizes power generation efficiency and ensures grid voltage stability.

[0006] According to one aspect of the present application, a wind power control system based on wind speed prediction is provided, which includes: A real-time wind speed value acquisition module is used to obtain a time series of real-time wind speed values ​​within a predetermined time period acquired by a wind speed sensor; A wind speed value historical data collection module is used to obtain historical data of wind speed values; A query encoding module, used for query encoding the time series of the real-time wind speed value and the historical data of the wind speed value to obtain a short-term wind speed prediction value, wherein the query encoding module includes: a real-time historical wind speed time series encoding unit, used for performing wind speed semantic query dynamic encoding based on time series association characteristics on the time series of the real-time wind speed value and the historical data of the wind speed value to obtain a real-time wind speed semantic query dynamic response encoding feature; a wind speed short-term prediction unit, used for obtaining a wind speed short-term prediction value based on the real-time wind speed semantic query dynamic response encoding feature; The power limiting strategy determination module is used to calculate the difference between the short-term wind speed prediction value and the cut-out wind speed value, and determine whether to adopt the power limiting strategy based on the comparison between the difference and a preset threshold.

[0007] Compared with the prior art, the wind power control system based on wind speed prediction provided by the present application first obtains the time series of real-time wind speed values ​​collected by the wind speed sensor within a predetermined time period, and obtains the historical data of wind speed values, and uses data analysis and encoding technology based on deep learning to encode the real-time wind speed time series and historical subsequences respectively, extracts global long-term dependency and local disturbance features, and then dynamically fuses the semantic association of real-time features and historical similar scenes through decision anchor points, and then generates high-precision wind speed prediction values ​​based on the fusion, and triggers the hierarchical power limitation strategy based on the real-time deviation analysis between the prediction value and the cut-out wind speed, combined with the dynamic threshold adjustment mechanism. This solution automatically captures the nonlinear time series law of wind speed through deep learning, dynamically responds to changes in actual working conditions, effectively improves prediction accuracy, shortens control delays, and optimizes power generation efficiency and ensures grid voltage stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0009] Figure 1 4 is a system block diagram of a wind power control system based on wind speed prediction according to an embodiment of the present application.

[0010] Figure 2 Schematic diagram of data flow of a wind power control system based on wind speed prediction according to an embodiment of the present application.

[0011] Figure 3 The block diagram is a query encoding module in a wind power control system based on wind speed prediction according to an embodiment of the present application.

[0012] Figure 4 The block diagram is a real-time historical wind speed time series encoding unit in a wind power control system based on wind speed prediction according to an embodiment of the present application.

[0013] Figure 5 The block diagram is a real-time wind speed semantic query subunit in a wind power control system based on wind speed prediction according to an embodiment of the present application.

[0014] Figure 6 The present invention is a block diagram of a secondary subunit for calculating a splicing weight factor in a wind power control system based on wind speed prediction according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0016] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0017] In addition, in order to better illustrate the present application, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present application can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present application.

[0018] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0019] In response to the above technical problems, the present application proposes a wind power control system based on wind speed prediction. Figure 1 4 is a system block diagram of a wind power control system based on wind speed prediction according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of data flow of a wind power control system based on wind speed prediction according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the wind speed prediction-based wind power control system 100 of the embodiment of the present application, it includes: a real-time wind speed value acquisition module 110, which is used to obtain the time series of real-time wind speed values ​​within a predetermined time period collected by the wind speed sensor; a wind speed value historical data acquisition module 120, which is used to obtain the historical data of the wind speed value; a query coding module 130, which is used to query and encode the time series of the real-time wind speed value and the historical data of the wind speed value to obtain a short-term prediction value of the wind speed; a power limiting strategy determination module 140, which is used to calculate the difference between the short-term prediction value of the wind speed and the cut-out wind speed value, and determine whether to adopt the power limiting strategy based on the comparison between the difference and the preset threshold.

[0020] In the above-mentioned wind power control system 100 based on wind speed prediction, the real-time wind speed value acquisition module 110 is used to obtain the time series of real-time wind speed values ​​collected by the wind speed sensor within a predetermined time period. It should be understood that by continuously monitoring and recording the wind speed within a predetermined time period by the wind speed sensor, the system can obtain a detailed and continuous dynamic data set. These data reflect the actual operating status of the wind farm within a specific time range, including the wind speed changes from seconds to hours or even longer time periods. Specifically, the high-precision wind speed sensors deployed on site will continuously measure the wind speed in the environment and transmit these measurement results to the control system in the form of a time series. This continuous data collection method helps to capture instantaneous fluctuations in wind speed and long-term trends. For example, in a short period of time, gusts may cause severe jitters in the output power of a wind farm; on a longer time scale, seasonal changes may affect the overall distribution pattern of wind speed. By accurately capturing these short-term and long-term wind speed characteristics, the system can better understand the current wind speed pattern and its future changing trends. In addition, since wind power is highly random and volatile, its output power is directly affected by wind speed changes. Accurately grasping real-time wind speed information can optimize wind power control. Specifically, wind speed sensors are usually installed in different locations of wind farms to fully cover the entire area and provide multi-dimensional data support. The data collected by the sensors is transmitted to the central control system via wired or wireless communication technology, where the data will be further processed and analyzed.

[0021] In the above-mentioned wind power control system 100 based on wind speed prediction, the wind speed value historical data acquisition module 120 is used to obtain historical data of wind speed values. It should be understood that due to the significant randomness and volatility of wind speed, it is difficult to capture all possible change patterns with real-time data alone. The historical data records various changes in wind speed over a long period of time, including typical wind speed distribution under normal operating conditions and extreme wind speed events under abnormal conditions (such as storms or strong gusts). These data can help the system learn and adapt to various wind speed scenarios, so as to make more accurate predictions and responses when facing similar situations in the future. For example, in a specific area, if strong winds in autumn often occur historically, the system can prepare in advance based on this experience and take corresponding preventive measures to ensure the safe and stable operation of the power grid. In addition, considering that the effectiveness of deep learning models is highly dependent on the quality and diversity of training data. Training using only real-time wind speed data often fails to cover all potential patterns, which may lead to overfitting or insufficient generalization of the model. Training in combination with historical data can enable the model to access a wider sample space, thereby improving its adaptability to unknown situations. Specifically, historical data can be used to generate a large number of training samples, covering the changes in wind speed under different time periods and different meteorological conditions. These diverse samples help the model learn more complex feature representations, thereby improving prediction accuracy. It is worth mentioning that many meteorological stations and research institutions publicly release detailed meteorological observation data, including long-term wind speed measurement results. These external resources can serve as supplementary data sources to enrich the system's training set.

[0022] Figure 3 FIG. 1 is a block diagram of a query encoding module in a wind power control system based on wind speed prediction according to an embodiment of the present application. Figure 3 As shown, the query encoding module 130 is used to query and encode the time series of the real-time wind speed value and the historical data of the wind speed value to obtain a short-term prediction value of the wind speed, including: a real-time historical wind speed time series encoding unit 131, used to dynamically encode the time series of the real-time wind speed value and the historical data of the wind speed value based on time series association characteristics to obtain a real-time wind speed semantic query dynamic response coding feature; a wind speed short-term prediction unit 132, used to obtain a short-term prediction value of the wind speed based on the real-time wind speed semantic query dynamic response coding feature.

[0023] Figure 4 FIG. 1 is a block diagram of a real-time historical wind speed time series encoding unit in a wind power control system based on wind speed prediction according to an embodiment of the present application. Figure 4As shown, in an embodiment of the present application, the real-time historical wind speed time series encoding unit 131 includes: a wind speed value historical data sequence segmentation subunit 1311, which is used to perform sequence segmentation on the historical data of the wind speed value based on the predetermined time period to obtain a set of historical wind speed value time series subsequences; a wind speed time series encoding subunit 1312, which is used to perform time series encoding on the time series of the real-time wind speed value and each historical wind speed value time series subsequence in the set of historical wind speed value time series subsequences to obtain a real-time wind speed time series associated implicit feature coding vector and a set of historical wind speed local time series associated implicit feature coding vectors; a real-time wind speed semantic query subunit 1313, which is used to perform wind speed time series feature decision anchor point semantic adaptive query encoding on the set of the real-time wind speed time series associated implicit feature coding vector and the historical wind speed local time series associated implicit feature coding vector to obtain a real-time wind speed semantic query dynamic response coding vector as the real-time wind speed semantic query dynamic response coding feature.

[0024] In an embodiment of the present application, the wind speed value historical data sequence segmentation subunit 1311 is used to perform sequence segmentation on the historical data of the wind speed value based on the predetermined time period to obtain a set of historical wind speed value time series subsequences. It should be understood that, considering that the historical wind speed data contains local time series features similar to the current real-time wind speed evolution mode (such as gust precursors, periodic fluctuations), if the historical data is directly modeled as a whole, the local key mode will be submerged by the global statistical features due to the difference in time span, and the dynamic change law of the real-time wind speed cannot be effectively matched. To this end, the present application performs sequence segmentation of the historical data with equal time windows based on the predetermined time period to generate a set of historical wind speed value time series subsequences comparable to the current real-time sequence. That is, the unsegmented complete historical sequence will mask the interference of local features on the global modeling (for example, strong wind shear events are averaged), resulting in the model being unable to distinguish between long-term laws and transient anomalies, while the local features of different time scales can be separated by sequence segmentation, providing fine-grained input for the subsequent identification of the potential correlation law between the current wind speed trend and similar historical scenes.

[0025] In an embodiment of the present application, the wind speed time series encoding subunit 1312 is used to: perform time series encoding based on the LSTM model on the time series of the real-time wind speed value and each historical wind speed value time series subsequence in the set of the historical wind speed value time series subsequence to obtain the real-time wind speed time series associated implicit feature encoding vector and the set of the historical wind speed local time series associated implicit feature encoding vector. It should be understood that considering that the time series of the real-time wind speed value is the global dynamics at the current moment, that is, it represents the overall trend of the current operating state of the wind farm (such as the monthly wind speed distribution law), it is necessary to capture its continuous impact on power output from a global perspective; and each historical wind speed value time series subsequence has a local pattern in the entire historical data of a specific time window, and it is necessary to extract high-frequency fluctuations (such as a sudden drop in wind speed on a single day) or periodic laws (such as weekly cycle patterns) through local encoding. However, due to the lack of memory units and gating mechanisms, traditional linear models are difficult to capture long-term evolution laws and short-term disturbance patterns at the same time, resulting in significant deviations between real-time predictions and historical pattern matching. Based on this, this application uses time series coding based on the LSTM model to perform global time series modeling on the real-time wind speed time series, captures long-term dependencies through the forget gate and input gate mechanism, and generates real-time wind speed time series associated implicit feature coding vectors; at the same time, each subsequence in the historical wind speed subsequence set is LSTM encoded in parallel, and the local disturbance features are extracted using its cell state memory characteristics to form a set of historical wind speed local time series associated implicit feature coding vectors. In this way, through the nonlinear time series modeling capability of LSTM, the original wind speed sequence is compressed into a feature vector with high information density, realizing multi-scale dynamic feature decoupling. The real-time coding vector represents the macroscopic evolution trend of the current wind speed, and the historical wind speed local coding vector set stores the microscopic disturbance pattern.

[0026] Figure 5 FIG. 1 is a block diagram of a real-time wind speed semantic query subunit in a wind power control system based on wind speed prediction according to an embodiment of the present application. Figure 5As shown, in an embodiment of the present application, the real-time wind speed semantic query subunit 1313 includes: an anchor coding matrix calculation secondary subunit 1313-1, which is used to calculate the anchor coding matrix of each historical wind speed local time series associated implicit feature coding vector in the set of the real-time wind speed time series associated implicit feature coding vector and the historical wind speed local time series associated implicit feature coding vector to obtain a set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices; a splicing weight factor calculation secondary subunit 1313-2, which is used to determine the real-time wind speed-historical wind speed local time series feature response anchor coding matrix. The decision anchor adaptive splicing weight factors of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix in the set of time series feature response anchor coding matrices are used to obtain a set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing weight factors; the real-time wind speed semantic query feature fusion secondary subunit 1313-3 is used to fuse the set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices based on the set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing weight factors to obtain the real-time wind speed semantic query dynamic response coding vector.

[0027] In an embodiment of the present application, the real-time wind speed semantic query subunit 1313 is used to perform wind speed time series feature decision anchor semantic adaptive query encoding on the set of the real-time wind speed time series associated implicit feature coding vector and the historical wind speed local time series associated implicit feature coding vector to obtain the real-time wind speed semantic query dynamic response coding vector as the real-time wind speed semantic query dynamic response coding feature. It should be understood that, considering that in the wind power control scenario, the real-time wind speed time series associated implicit feature coding vector and the historical wind speed local time series associated implicit feature coding vector respectively carry complementary information of the global dynamic mode and multi-scale local disturbance. However, due to the lack of dynamic feature fusion mechanism, the traditional method is difficult to coordinate the interaction between global and local features, resulting in prediction errors and control lags. For example, if the global and local dynamic alignment is not achieved, the problem of "long-term trend drowning short-term mutation" or "local noise interfering with global modeling" may occur, which directly affects the wind speed prediction accuracy and the adaptability of the power control strategy. Based on this, the present application performs wind speed time series feature decision anchor semantic adaptive query encoding on the set of the real-time wind speed time series associated implicit feature encoding vector and the historical wind speed local time series associated implicit feature encoding vector to obtain the real-time wind speed semantic query dynamic response encoding vector. In this way, through semantic response decision anchoring, taking the global encoding of real-time wind speed as the anchor point, dynamically quantify the semantic contribution strength of historical local features, and then generate an adaptive splicing factor sequence through weight normalization, so as to achieve global-local semantic alignment, dynamic feature screening and multi-granularity feature fusion, and generate a real-time wind speed semantic query dynamic response encoding vector that integrates global trend constraints and historical experience migration.

[0028] In an embodiment of the present application, the anchor coding matrix calculation secondary subunit 1313-1 is used to: perform deep implicit feature fully connected coding on the real-time wind speed time series associated implicit feature coding vector to obtain a real-time wind speed time series associated depth implicit coding vector; perform deep implicit feature fully connected coding on each historical wind speed local time series associated implicit feature coding vector in the set of historical wind speed local time series associated implicit feature coding vectors to obtain a set of historical wind speed local time series associated depth implicit coding vectors; perform wind speed time series semantic response decision anchoring on the real-time wind speed time series associated depth implicit coding vector and each historical wind speed local time series associated depth implicit coding vector in the set of historical wind speed local time series associated depth implicit coding vectors to obtain a set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices.

[0029] Specifically, the real-time wind speed time series associated implicit feature coding vector is subjected to deep implicit feature full connection coding to obtain a real-time wind speed time series associated deep implicit coding vector, which is expressed as a deep implicit feature full connection coding formula:

[0030] in, is the real-time wind speed time series associated implicit feature coding vector, is matrix multiplication, and are the real-time wind speed weight matrix and the real-time wind speed bias vector respectively, is the activation function, is the deep implicit coding vector associated with the real-time wind speed time series. It should be understood that although the real-time wind speed time series associated implicit feature coding vector has captured the global long-term dependency through the LSTM model, its potential high-order nonlinear features and multi-scale interaction patterns still need to be further decoupled. The dense connection characteristics of the fully connected neural network provide an adaptive tool for this. By mapping the real-time wind speed time series associated implicit feature coding vector to a higher-dimensional latent space, the system can break through the linear expression limitations of the original feature space and explicitly enhance the semantic representation ability of the feature. This process not only learns the abstract expression of the global statistical law through the weight matrix, but also reveals the complex interactive relationship hidden in the real-time wind speed sequence (such as the coupling effect of wind speed fluctuations in different time windows) with the help of nonlinear activation functions (such as sigmoid), thereby constructing a more accurate feature basis for the subsequent dynamic semantic alignment with historical local disturbance features. In this way, the nonlinear compression and reconstruction of global features are achieved through deep implicit coding, so that it can not only retain the key information of long-term trends, but also provide more discriminative feature anchors for local feature matching with historical similar scenes.

[0031] Specifically, each historical wind speed local time series associated implicit feature coding vector in the set of historical wind speed local time series associated implicit feature coding vectors is subjected to deep implicit feature full connection coding to obtain a set of historical wind speed local time series associated deep implicit coding vectors, which is expressed as follows:

[0032]

[0033] in, is the set of implicit feature coding vectors associated with the local time series of historical wind speed, , , and are respectively the first, second, and third in the set of the historical wind speed local time series associated implicit feature coding vectors. and The local temporal correlation implicit feature encoding vector of historical wind speed, and are the historical wind speed weight matrix and historical wind speed bias vector respectively, is the first in the set of historical wind speed local time series correlation depth implicit coding vectors A historical wind speed local time series associated deep implicit coding vector. It should be understood that the set of historical wind speed local time series associated implicit feature coding vectors is also processed independently. Unlike the single representation of the real-time wind speed time series associated implicit feature coding vector, the set of historical wind speed local time series associated implicit feature coding vectors contains multiple features that need to be encoded one by one. Specifically, since the historical wind speed contains local correlation patterns of different time periods (such as minute-level fluctuations and hour-level trends), and these patterns may be affected by the geographical environment or meteorological conditions and show spatial heterogeneity, a single global coding is difficult to capture the semantic differences of all local features at the same time. In the technical solution of the present application, a fully connected network is also used to extract the deep implicit representation of each historical wind speed local time series associated implicit feature coding vector. By independently processing each historical wind speed local time series associated implicit feature coding vector, the system can perform customized mining for local laws of different time windows or physical locations to avoid feature confusion caused by global coding. The dense parameter matrix of the fully connected network provides a flexible nonlinear mapping capability for this purpose. It can perform high-dimensional projection on the implicit feature encoding features of each historical wind speed local temporal correlation, and explicitly reconstruct its implicit temporal correlation pattern (such as wind speed gradient changes or turbulence intensity fluctuations). In this way, the nonlinear compression and semantic enhancement of historical local features are achieved through deep implicit coding, which not only retains the details of short-term disturbances (such as sudden gust events), but also refines long-term statistical laws (such as seasonal wind speed distribution), and constructs multi-granular feature anchors for subsequent dynamic matching of global-local features with real-time wind speed, thereby reducing overfitting and improving generalization capabilities through multi-historical scene feature learning.

[0034] Specifically, each historical wind speed local time series associated depth implicit coding vector in the set of the real-time wind speed time series associated depth implicit coding vector and the historical wind speed local time series associated depth implicit coding vector is anchored with a wind speed time series semantic response decision to obtain a set of the real-time wind speed-historical wind speed local time series feature response anchor coding matrices, which is expressed as follows:

[0035] in, yes The transposed vector of yes Length, It is the first in the set of anchor coding matrices of real-time wind speed-historical wind speed local time series characteristic response. The real-time wind speed-historical wind speed local time series feature response anchor coding matrix is ​​constructed. It should be understood that although the global coding of real-time wind speed has captured the monthly wind speed evolution law through the LSTM model, its potential nonlinear interaction relationship still needs to be explicitly decoupled; and the local coding set of historical wind speed contains multi-scale features such as minute-level gusts and hour-level fluctuations, which need to be semantically associated with real-time features through a dynamic anchoring mechanism. Through the decision anchoring technology, the global implicit features of the real-time wind speed time series associated deep implicit coding vector are used as a dynamic benchmark, the semantic contribution weight of each historical wind speed local time series associated deep implicit coding vector is quantified, and a set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices with global reference characteristics are constructed. This anchoring mechanism not only explicitly represents the coupling relationship between real-time and historical features, but also provides composable building block components for subsequent feature fusion, which are suitable for combining and splicing in a specific way to form a complete deep implicit representation of the decision anchor. Among them, each real-time wind speed-historical wind speed local time series feature response anchor coding matrix corresponds to the feature response mode of a specific time window or meteorological condition, and multi-granularity semantic alignment can be achieved through weight normalization. Here, the set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices not only represents the interactive information between the real-time wind speed time series associated deep implicit coding features and the historical wind speed local time series associated deep implicit coding features, but also serves as a bridge to capture the global-local semantic alignment relationship.

[0036] Figure 6 FIG. 1 is a block diagram of a secondary subunit for calculating splicing weight factors in a wind power control system based on wind speed prediction according to an embodiment of the present application. Figure 6 As shown, in an embodiment of the present application, the splicing weight factor calculation secondary subunit 1313-2 includes: a splicing factor calculation tertiary subunit 1313-21, which is used to determine the decision anchor adaptive splicing factors of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix based on the feature distribution of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix in the set of the real-time wind speed-historical wind speed local time series feature response anchor coding matrix to obtain a set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factors; a weighting processing tertiary subunit 1313-22, which is used to perform weighting processing on the set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factors based on the Softmax function to obtain the set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing weight factors.

[0037] In an embodiment of the present application, the splicing factor calculation three-level sub-unit 1313-21 includes: based on the maximum value, mean, variance and difference magnification coefficient of the real-time wind speed-historical wind speed local time series feature response anchor coding matrix and the real-time wind speed-historical wind speed drift coefficient, obtaining the real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factor corresponding to the real-time wind speed-historical wind speed local time series feature response anchor coding matrix; wherein the difference magnification coefficient is the number of eigenvalues ​​of the real-time wind speed-historical wind speed local time series feature response anchor coding matrix; the real-time wind speed-historical wind speed drift coefficient is obtained by performing global smooth state transition processing on the real-time wind speed-historical wind speed local time series feature response anchor coding matrix.

[0038] Specifically, the splicing factor calculation tertiary subunit 1313-21 is used to determine the decision anchor adaptive splicing factor of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix based on the feature distribution of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix in the set of the real-time wind speed-historical wind speed local time series feature response anchor coding matrix to obtain a set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factors, which is expressed as follows:

[0039]

[0040]

[0041]

[0042] in, express The variance of express The mean of For calculation The number of eigenvalues ​​of express The difference amplification factor, express The maximum value of ， Indicates the real-time wind speed-historical wind speed drift coefficient, It is an intermediate state transition. yes No. eigenvalues, It is the number of factors in the set of adaptive splicing factors of the local temporal decision anchor of real-time wind speed and historical wind speed. A real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factor. It should be understood that the global encoding of the real-time wind speed and the local encoding set of the historical wind speed carry wind speed laws of different time granularities (such as long-term trends and short-term disturbances), but the nonlinear coupling relationship between the feature spaces of the two needs to be dynamically aligned through an interpretable weight mechanism. The traditional feature fusion method is prone to "long-tail feature drowning" or "local noise amplification" problems due to the lack of refined modeling of feature contributions. In the technical solution of the present application, after generating the real-time wind speed-historical wind speed local time series feature response anchor coding matrix, the module needs to further extract and model the feature contribution of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix, which is the role of the real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factor. By analyzing the feature distribution of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix, the real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factor of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix is ​​determined. These real-time wind speed-historical wind speed local temporal decision anchor adaptive splicing factors measure the dominance of local features in specific tasks or contexts, and serve as the weight basis for subsequent feature fusion.

[0043] Preferably, for the drift coefficient in the real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factor , the input feature set distribution of the anchor coding matrix for the local time series feature response of the real-time wind speed-historical wind speed transitions from the state of weak overall interpretability of the mean to strong local interpretability of the maximum value, through the drift coefficient The weak to strong interpretable generalization is used to enhance the global dominance of local features.

[0044] In particular, As an intermediate state transition representation from weak interpretability to strong interpretability, each eigenvalue of the anchor encoding matrix is ​​responded to for the local time series feature of real-time wind speed-historical wind speed , taking it as the input real-time wind speed-historical wind speed local time series feature response anchor encoding matrix for the importance score of global smooth state transition, to analyze the intermediate state transition The importance score weights relative to the global state transition are globally controlled to achieve interpretable generalized inference of the weight-dependent adaptive splicing factors of the real-time wind speed-historical wind speed local temporal decision anchors.

[0045] Specifically, the weighted processing third-level subunit 1313-22 is used to perform weighted processing based on the Softmax function on the set of real-time wind speed-historical wind speed local temporal decision anchor adaptive splicing factors to obtain the set of real-time wind speed-historical wind speed local temporal decision anchor adaptive splicing weight factors, which is expressed as follows:

[0046] in, is the normalization function, is the set of adaptive splicing weight factors of the local temporal decision anchor of real-time wind speed and historical wind speed. A real-time wind speed-historical wind speed local time series decision anchor adaptive splicing weight factor. It should be understood that since the local feature encoding set of real-time wind speed and historical wind speed carries nonlinear correlation information of different time scales (such as long-term trends and short-term disturbances), and the dynamic weights of these features need to be adjusted in real time according to actual working conditions, the traditional linear weighting method is difficult to balance global stability and local sensitivity. In the technical solution of the present application, the set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factors is weighted based on the Softmax function, that is, the sequence of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factors is normalized into a weight sequence with probability distribution properties by using the Softmax function, and the set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factors is converted into a probability distribution form. In this way, the normalization constraint that the sum of weight values ​​is 1 is guaranteed, and the relative importance of key features is highlighted through the nonlinear amplification mechanism. This conversion can effectively solve the problem that the contribution of local features at specific moments (such as wind speed mutation periods) may be diluted by global statistical features, while avoiding prediction bias caused by uneven weight distribution. Through probabilistic weight representation, it can provide a discriminative decision basis for subsequent feature fusion, that is, features corresponding to high-probability weight factors (such as historical local patterns that are highly matched with current working conditions) will be adopted first, while low-probability factors will be suppressed, thereby achieving adaptive screening and dynamic alignment of global-local features.

[0047] Specifically, the real-time wind speed semantic query feature fusion secondary subunit 1313-3 is used to fuse the set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices based on the set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing weight factors to obtain the real-time wind speed semantic query dynamic response coding vector. The process is expressed by the formula:

[0048] in, is the set of adaptive splicing weight factors of the local temporal decision anchor of real-time wind speed and historical wind speed. The real-time wind speed-historical wind speed local time series decision anchor adaptive splicing weight factor, is the real-time wind speed semantic query dynamic response encoding matrix, is the reshaping operation, It is the dynamic response encoding vector of the real-time wind speed semantic query. It should be understood that the real-time wind speed time series provides global dynamic information at the current moment, reflecting the overall trend of the current operating status of the wind farm; while the historical wind speed data contains rich local patterns, such as short-term fluctuations or periodic laws. Traditional methods find it difficult to establish effective associations between global and local features, resulting in increased prediction errors and control lags. In the technical solution of the present application, the concepts of decision anchor adaptive splicing weight factors and feature response anchor coding matrices are introduced to achieve refined processing and dynamic fusion of these features. Specifically, the set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing weight factors and the set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices are fused by weighted summation.

[0049] In an embodiment of the present application, the wind speed short-term prediction unit 132 is used to: input the real-time wind speed semantic query dynamic response encoding vector into a decoder-based wind speed short-term predictor to obtain the wind speed short-term prediction value. It should be understood that the real-time wind speed semantic query dynamic response encoding vector integrates the complex interactive information of global long-term dependency (such as monthly wind speed trend) and local disturbance characteristics (such as hourly turbulence events), but its essence still needs to be restored to quantifiable wind speed prediction values ​​through inverse mapping. The decoder converts the nonlinear features extracted by the encoder (such as implicit global-local associations) into accurate predictions of future wind speeds through time series modeling capabilities. Its structure (such as a gated recurrent unit or a Transformer) allows adaptive capture of time series dependencies, avoids the limitations of traditional linear regression models, and finally outputs high-precision short-term wind speed prediction values. It is worth mentioning that after the wind speed prediction is performed, in order to more accurately control the power. The short-term wind speed prediction value is converted into a preliminary power prediction value through a power curve (such as an S-shaped curve). At this time, the predicted power may contain high-frequency jitter or nonlinear distortion (such as power jump caused by a sudden change in wind speed gradient). Therefore, it is necessary to dynamically correct the predicted power based on the wind speed prediction. In other words, smoothing helps to reduce noise interference and enhance the stability and continuity of the signal. Common smoothing techniques include moving average, exponentially weighted moving average and Kalman filtering. Through these methods, the system can effectively remove high-frequency noise and retain low-frequency trend components, thereby improving the accuracy of subsequent predictions. Preferably, in a specific embodiment of the present application, first, by using the wind power curve, the wind speed prediction value is mapped to a power value. Then, by introducing a "weighted smoothing model", the predicted power data is smoothed to prevent sudden fluctuations from affecting the power grid. Among them, the weighted smoothing model formula is expressed as:

[0050] in, Indicates at time The output power, Indicates at time The predicted power, Indicates that at the previous moment The output power, is the smoothing factor, where Dynamically adjust according to actual fluctuations. Through smoothing, data quality and model performance can be significantly improved. In other words, smoothing is applied to the preliminary power forecast value to suppress the impact of short-term power mutations on grid voltage stability.

[0051] In the above-mentioned wind power control system 100 based on wind speed prediction, the power limiting strategy determination module 140 is used to calculate the difference between the short-term predicted value of the wind speed and the cut-out wind speed value, and determine whether to adopt the power limiting strategy based on the comparison between the difference and the preset threshold. It should be understood that the instantaneous fluctuation of wind speed may cause the predicted value to deviate from the actual operating condition. If there is no dynamic response mechanism, it may cause severe jitter of power output or out-of-bounds of grid voltage. The fixed threshold strategy is prone to "excessive power restriction" or "insufficient power restriction" because it cannot adapt to the nonlinear change of wind speed. Therefore, this application uses the difference comparison as the core basis for dynamic threshold adjustment, and determines whether the current working condition needs to trigger the hierarchical power limiting strategy by calculating the real-time deviation between the predicted value and the cut-out wind speed, combined with the preset threshold (such as a dynamic confidence interval based on historical data statistics). Specifically, if the deviation exceeds the threshold, the power limiting protection is started to ensure the stability of the grid voltage; if the deviation is within the threshold, the wind farm is allowed to output at maximum power, thereby avoiding the loss of power generation efficiency caused by conservative power restriction. Afterwards, the smoothed power value is used as the input of the control strategy to avoid false triggering of power-limiting protection due to prediction noise.

[0052] In a specific embodiment, a historical wind speed sequence containing 432 data points (sampling interval of 10 minutes, covering 72 hours) and a real-time wind speed time series (14 data points, interval of 10 minutes) are used as input. The real-time wind speed sequence is globally time-series encoded by the LSTM model to extract the implicit feature vector containing the long-term dependency relationship; after the historical wind speed sequence is sequence segmented, a set of historical wind speed local time-series associated implicit feature encoding vectors is generated by the LSTM model. Further, the decision anchor semantic adaptive query encoding of the wind speed time series feature is calculated, and the decision anchor adaptive splicing weight factor of the real-time feature and the historical scene is calculated, so as to obtain the real-time wind speed semantic query dynamic response encoding vector by fusion, and the real-time wind speed semantic query dynamic response encoding vector is decoded by a decoder to obtain the short-term wind speed prediction value. The results show that the mean absolute error (MAE) between the predicted wind speed sequence and the true value of this scheme is 0.32 m / s, which is 60.9% lower than the 0.82 m / s of the traditional LSTM method; the root mean square error (RMSE) is 0.45 m / s, a decrease of 57.1%; the coefficient of determination (R²) reaches 0.982, indicating that the model has strong explanatory power. Through the characteristic response anchoring mechanism and dynamic weight calculation, the system decision-making efficiency is improved by 63%, and the total processing delay is reduced to 85 ms, meeting the real-time requirements of wind power control. The hierarchical power limitation strategy reduces the power fluctuation rate from 21.4% of the traditional scheme to 12.7%, and reduces the number of wind speed trigger levels by 100%; the grid voltage fluctuation amplitude is controlled within ±1.02%, and the total harmonic distortion (THD) is 3.1%, which is significantly better than the ±2.35% and 7.8% of the traditional scheme. The above data verify the effectiveness of this solution in improving prediction accuracy, shortening control delay, optimizing power generation efficiency and ensuring grid stability, providing reliable technical support for large-scale wind power grid connection.

[0053] In summary, a wind power control system 100 based on wind speed prediction according to an embodiment of the present application is explained, which obtains the time series of real-time wind speed values ​​collected by the wind speed sensor within a predetermined time period, and obtains the historical data of the wind speed values, and uses data analysis and encoding technology based on deep learning to encode the real-time wind speed time series and historical subsequences respectively, extracts global long-term dependency and local disturbance features, and then dynamically fuses the semantic association of real-time features with historical similar scenes through decision anchor points, and then generates high-precision wind speed prediction values ​​based on the fusion, and triggers the hierarchical power limitation strategy based on the real-time deviation analysis between the prediction value and the cut-out wind speed, combined with the dynamic threshold adjustment mechanism. This solution automatically captures the nonlinear time series law of wind speed through deep learning, dynamically responds to changes in actual working conditions, effectively improves prediction accuracy, shortens control delays, and optimizes power generation efficiency and ensures grid voltage stability.

[0054] As described above, the wind power control system 100 based on wind speed prediction according to the embodiment of the present application can be implemented in various terminal devices. In one example, the wind power control system 100 based on wind speed prediction can be integrated into the terminal device as a software module and / or a hardware module. For example, the wind power control system 100 based on wind speed prediction can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the wind power control system 100 based on wind speed prediction can also be one of the many hardware modules of the terminal device.

[0055] Alternatively, in another example, the wind speed prediction based wind power control system 100 and the terminal device may also be separate devices, and the wind speed prediction based wind power control system 100 may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0056] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0057] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0058] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0059] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0060] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0061] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit of the technical solution of the present invention.

Claims

1. A wind power control system based on wind speed prediction, characterized in that: include: A real-time wind speed value acquisition module is used to obtain a time series of real-time wind speed values ​​within a predetermined time period acquired by a wind speed sensor; A wind speed value historical data collection module is used to obtain historical data of wind speed values; A query encoding module, used for query encoding the time series of the real-time wind speed value and the historical data of the wind speed value to obtain a short-term wind speed prediction value, wherein the query encoding module includes: a real-time historical wind speed time series encoding unit, used for performing wind speed semantic query dynamic encoding based on time series association characteristics on the time series of the real-time wind speed value and the historical data of the wind speed value to obtain a real-time wind speed semantic query dynamic response encoding feature; a wind speed short-term prediction unit, used for obtaining a wind speed short-term prediction value based on the real-time wind speed semantic query dynamic response encoding feature; The power limiting strategy determination module is used to calculate the difference between the short-term wind speed prediction value and the cut-out wind speed value, and determine whether to adopt the power limiting strategy based on the comparison between the difference and a preset threshold.

2. The wind power control system based on wind speed prediction according to claim 1, characterized in that: The real-time historical wind speed time series encoding unit comprises: A wind speed value historical data sequence segmentation subunit, used for performing sequence segmentation on the historical data of the wind speed value based on the predetermined time period to obtain a set of historical wind speed value time series subsequences; A wind speed time series encoding subunit, used for performing time series encoding on the time series of the real-time wind speed value and each historical wind speed value time series subsequence in the set of the historical wind speed value time series subsequences to obtain a set of real-time wind speed time series associated implicit feature encoding vectors and historical wind speed local time series associated implicit feature encoding vectors; The real-time wind speed semantic query subunit is used to perform wind speed time series feature decision anchor point semantic adaptive query encoding on the set of the real-time wind speed time series associated implicit feature coding vector and the historical wind speed local time series associated implicit feature coding vector to obtain a real-time wind speed semantic query dynamic response coding vector as the real-time wind speed semantic query dynamic response coding feature.

3. The wind power control system based on wind speed prediction according to claim 2 is characterized in that: The wind speed time series encoding subunit is used to: perform time series encoding based on the LSTM model on the time series of the real-time wind speed value and each historical wind speed value time series subsequence in the set of historical wind speed value time series subsequences to obtain a set of the real-time wind speed time series associated implicit feature encoding vector and the historical wind speed local time series associated implicit feature encoding vector.

4. The wind power control system based on wind speed prediction according to claim 3 is characterized in that: The real-time wind speed semantic query subunit includes: Anchor coding matrix calculation secondary subunit, used to calculate the anchor coding matrix of each historical wind speed local time series associated implicit feature coding vector in the set of the real-time wind speed time series associated implicit feature coding vector and the historical wind speed local time series associated implicit feature coding vector to obtain a set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices; The splicing weight factor calculation secondary subunit is used to determine the decision anchor adaptive splicing weight factor of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix in the set of real-time wind speed-historical wind speed local time series feature response anchor coding matrix to obtain a set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing weight factors; The real-time wind speed semantic query feature fusion secondary sub-unit is used to adaptively splice the set of weight factors based on the real-time wind speed-historical wind speed local temporal series decision anchor, and fuse the set of real-time wind speed-historical wind speed local temporal series feature response anchor coding matrices to obtain the real-time wind speed semantic query dynamic response coding vector.

5. The wind power control system based on wind speed prediction according to claim 4 is characterized in that: The anchor coding matrix calculates the secondary subunit, which is used to: Performing deep implicit feature fully connected encoding on the real-time wind speed time series associated implicit feature encoding vector to obtain a real-time wind speed time series associated deep implicit encoding vector; Performing deep implicit feature fully connected coding on each historical wind speed local time series associated implicit feature coding vector in the set of historical wind speed local time series associated implicit feature coding vectors to obtain a set of historical wind speed local time series associated deep implicit coding vectors; Wind speed time series semantic response decision anchoring is performed on each historical wind speed local time series association depth implicit coding vector in the set of the real-time wind speed time series association depth implicit coding vector and the historical wind speed local time series association depth implicit coding vector to obtain a set of real-time wind speed-historical wind speed local time series feature response anchor coding matrices.

6. The wind power control system based on wind speed prediction according to claim 5, characterized in that: The splicing weight factor calculation secondary subunit includes: The third-level subunit for calculating the splicing factor is used to determine the decision anchor adaptive splicing factor of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix based on the feature distribution of each real-time wind speed-historical wind speed local time series feature response anchor coding matrix in the set of the real-time wind speed-historical wind speed local time series feature response anchor coding matrix to obtain a set of real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factors; The weighted processing third-level sub-unit is used to perform weighted processing on the set of real-time wind speed-historical wind speed local temporal decision anchor adaptive splicing factors based on the Softmax function to obtain the set of real-time wind speed-historical wind speed local temporal decision anchor adaptive splicing weight factors.

7. The wind power control system based on wind speed prediction according to claim 6, characterized in that: The splicing factor calculation three-level subunit includes: Based on the maximum value, mean value, variance and difference magnification coefficient of the real-time wind speed-historical wind speed local time series feature response anchor coding matrix and the real-time wind speed-historical wind speed drift coefficient, the real-time wind speed-historical wind speed local time series decision anchor adaptive splicing factor corresponding to the real-time wind speed-historical wind speed local time series feature response anchor coding matrix is ​​obtained; Wherein, the difference amplification coefficient is the number of eigenvalues ​​of the anchor coding matrix of the local time series characteristic response of the real-time wind speed-historical wind speed; The real-time wind speed-historical wind speed drift coefficient is obtained by performing global smooth state transition processing on the real-time wind speed-historical wind speed local time series characteristic response anchor coding matrix.

8. The wind power control system based on wind speed prediction according to claim 7, characterized in that: The wind speed short-term prediction unit is used to: input the real-time wind speed semantic query dynamic response encoding vector into a decoder-based wind speed short-term predictor to obtain the wind speed short-term prediction value.

Images