Multi-dimensional channel communication interference suppression method and system for wind-solar-storage hybrid station

Abstract

The application discloses a kind of multi-dimensional channel communication interference suppression method and system for wind light storage hybrid station, belong to wireless radio detection technical field.Method includes: obtaining the multi-source communication environment data in wind light storage hybrid station area, and the multi-source communication environment data is preprocessed;Based on Dempster-Shafer evidence theory, the multi-source communication environment data after preprocessing is weighted and fused, and environment fusion data is obtained;Based on the environment fusion data, interference signals are tracked and suppressed in real time by Bayesian inference.The preprocessing includes: identifying and removing outliers, filling missing values by interpolation;Low-pass filter is used to reduce noise;Normalization is processed by Z-Score.

Description

Technical Field

[0001] This invention belongs to the field of radio detection technology and relates to a method and system for suppressing multi-dimensional channel communication interference in wind-solar-storage hybrid power stations. Background Technology

[0002] With the continued growth in global demand for renewable energy and the gradual replacement of traditional fossil fuels, the development and utilization of clean energy sources such as wind and solar power have progressed rapidly. However, single wind or solar power generation is affected by natural conditions, exhibiting intermittency, volatility, and uncertainty, posing challenges to the safe and stable operation of the power grid. To improve energy efficiency and power supply reliability, hybrid wind-solar-storage power plants, which combine wind power generation, solar power generation, and energy storage systems, have become an important development trend in the industry. These power plants, through the peak shaving and valley filling and power smoothing functions of energy storage devices, can effectively mitigate fluctuations in wind and solar power output, achieving grid-friendly integration and stable energy output. In engineering practice, hybrid wind-solar-storage power plants typically cover several square kilometers or even wider geographical areas, integrating a large number of distributed energy resources (DERs), including wind turbine generators, solar arrays, energy storage converters, combiner boxes, data acquisition and monitoring terminals, etc. Reliable two-way communication links need to be established between these devices and between the devices and the remote control center to achieve status monitoring, power dispatching, fault early warning, and collaborative control of the equipment within the power plant. Therefore, an efficient and stable communication network is one of the key infrastructures for ensuring the safe, economical, and intelligent operation of wind-solar-storage hybrid power stations.

[0003] However, the communication environment of hybrid wind-solar-storage power stations is extremely complex, and existing communication technologies are clearly insufficient to cope with the multiple interferences in this scenario. First, the power station occupies a large area with complex terrain (such as mountains, hills, and deserts), and has numerous structures such as wind turbine towers and photovoltaic supports, which can easily lead to fading, multipath effects, and physical obstruction of wireless signals during propagation, causing communication interruptions or data packet loss. Second, the power station integrates a large number of power electronic devices (such as inverters, converters, and switching power supplies), which generate broadband electromagnetic interference during operation. This interference is coupled into the communication channel through radiation or conduction, significantly degrading the signal-to-noise ratio of wireless communication. Furthermore, in order to reduce construction and operation and maintenance costs, many wireless communication systems (such as ZigBee, Wi-Fi, LoRa, and dedicated wireless sensor networks) often share the unlicensed ISM band. In addition, the coexistence of proprietary communication protocols from different equipment manufacturers can easily cause co-channel or adjacent-channel interference, leading to channel congestion, increased retransmission rates, and in severe cases, even preventing the effective issuance of control commands.

[0004] In summary, existing communication methods for hybrid wind-solar-storage power plants have significant shortcomings in addressing multi-dimensional channel interference. They struggle to simultaneously suppress signal fading caused by terrain obstruction, electromagnetic interference generated by power electronic devices, and co-channel / adjacent-channel interference caused by multiple systems sharing the same frequency band. Therefore, providing a method to effectively suppress multi-dimensional channel communication interference in the complex electromagnetic and geographical environment of hybrid wind-solar-storage power plants, thereby improving the reliability, real-time performance, and anti-interference capability of communication within the power plant, is a pressing technical problem that needs to be solved in this field. Summary of the Invention

[0005] The purpose of this invention is to solve the technical problem that existing communication methods for wind-solar-storage hybrid power stations have obvious deficiencies in dealing with multi-dimensional channel interference, and to provide a multi-dimensional channel communication interference suppression method and system for wind-solar-storage hybrid power stations.

[0006] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, the present invention discloses a method for suppressing multi-dimensional channel communication interference in a wind-solar-storage hybrid power station, comprising: Acquire multi-source communication environment data within the area of ​​the wind-solar-storage hybrid power station, and preprocess the multi-source communication environment data; Based on the Dempster-Shafer evidence theory, the preprocessed multi-source communication environment data is weighted and fused to obtain environment fusion data; Based on the environmental fusion data, interference signals are tracked and suppressed in real time through Bayesian inference.

[0007] Further improvements are made in the following aspects: The preprocessing includes: Identify and remove outliers, and fill in missing values ​​using interpolation; Use low-pass filtering to reduce noise; Normalization was performed using Z-Score.

[0008] The weighted fusion of the preprocessed multi-source communication environment data based on Dempster-Shafer evidence theory includes: Key feature data were extracted from preprocessed multi-source communication environment data using signal processing techniques. Principal component analysis is used to reduce the dimensionality of high-dimensional key feature data, transforming key feature data of different dimensions into the same dimension; Based on the Dempster-Shafer theory, different types of key feature data are fused to form environmental fusion data, and a weighting mechanism is introduced to optimize the Dempster-Shafer theory. The specific steps for optimizing the Dempster-Shafer theory are as follows: Framework for defining interference source types based on communication environment data ; Based on each type of data and its corresponding model, calculate the basic probability allocation for each signal source. ; Weights are assigned to each data source based on an error model, according to each signal source. ; For multiple data sources, a weighted combination rule is used to adjust the basic probability allocation; The weights are assigned to each data source based on the error model. The specific steps are as follows: Calculate the error between the communication environment data and the reference true value of the communication environment data. ; The error magnitude of each data source is quantified based on mean squared error; Normalization is used to normalize the error metrics from different data sources to a uniform range; Weights are assigned based on the normalized error index.

[0009] For multiple data sources, a weighted combination rule is used to fuse and adjust the basic probability allocation. Its mathematical expression is:

[0010] in, ; In the formula, Indicates an event The basic probability allocation after fusion; Indicates the conflict factor, if A value close to 1 indicates a significant conflict. A value close to 0 indicates a very small number of conflicts. Represents the empty set; Indicates the credibility of evidence source 1; Indicate the credibility of evidence source 2; This represents the basic probability distribution of evidence source 1; This represents the basic probability distribution of evidence source 2; express event; express event; express Event; Conflict normalization for the fused Normalization is performed.

[0011] The method of tracking and suppressing interference signals in real time through Bayesian inference includes: Based on the communication environment state vector Define the state transition matrix and observation matrix Simultaneously, a periodic function and a masking signal factor are introduced to affect the state transition matrix. and observation matrix Optimization is performed to obtain the optimized state transition matrix. and observation matrix ; Construct an initial probability distribution based on the basic probability assignment of the fused interference types. And according to the initial probability distribution Determine the prior distribution; Based on the state transition matrix Control input matrix External inputs of the system and posterior state estimation Calculate the state prediction for the next time step and its covariance ; Based on the observation matrix Covariance matrix of process noise And the covariance prediction for the next time step. Calculate Kalman gain ; Based on Kalman gain Update state estimation and its covariance .

[0012] The optimized state transition matrix The specific steps involved are as follows: A periodic function is introduced into the state transition matrix to optimize it, based on the fundamental state transition matrix. With the periodic state transition matrix modulated by a sine function The state transition matrix under the shadow effect of large wind turbines is obtained through addition operations. The time dependence of the sine function is determined by the rotation period of the wind turbine blades. Decide; A shielding signal factor is introduced into the state transition matrix to optimize it, based on the shielding effect state transition matrix. The state transition matrix of the metal structure under electromagnetic wave shielding is obtained by multiplying it with a diagonal matrix containing signal strength attenuation factor and phase change factor. Among them, the signal strength attenuation factor and phase change factor These respectively reflect the influence of the metal structure on signal strength and phase; Based on the state transition matrix With the state transition matrix The final state transition matrix is ​​obtained through addition. .

[0013] The optimized observation matrix The specific steps involved are as follows: A periodic function is introduced into the observation matrix to optimize it, based on the fundamental observation matrix. With the periodic observation matrix modulated by a sine function The observation matrix under the shadow effect of large wind turbines is obtained through addition operations. The time dependence of the sine function is determined by the rotation period of the wind turbine blades. Decide; A shielding signal factor is introduced into the observation matrix to optimize it, based on the shielding effect observation matrix. With a signal strength attenuation factor and phase change factor The observation matrix under the electromagnetic wave shielding effect of the metal structure is obtained by multiplication of the diagonal matrix. Among them, the signal strength attenuation factor and phase change factor These reflect the independent effects of the metal structure on signal strength and phase, respectively. Based on observation matrix With observation matrix The final state transition matrix is ​​obtained through addition. .

[0014] Secondly, this invention discloses a multi-dimensional channel communication interference suppression system for wind-solar-storage hybrid power stations, comprising: The data acquisition module is used to acquire multi-source communication environment data within the wind-solar-storage hybrid power station area and to preprocess the multi-source communication environment data. The data fusion module is used to perform weighted fusion of the preprocessed multi-source communication environment data based on the Dempster-Shafer evidence theory to obtain environment fusion data. An interference signal suppression module is used to track and suppress interference signals in real time based on the environmental fusion data and through Bayesian inference.

[0015] Thirdly, the present invention discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations.

[0016] Fourthly, the present invention discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for suppressing multi-dimensional channel communication interference in hybrid wind-solar-storage power stations.

[0017] Compared with the prior art, the present invention has the following beneficial effects: This invention discloses a multi-dimensional channel communication interference suppression method for hybrid wind-solar-storage power stations. Firstly, by introducing Dempster-Shafer evidence theory, this invention performs weighted fusion of multi-source communication environment data, significantly improving the reliability and robustness of communication status perception in complex environments. Hybrid wind-solar-storage power stations typically deploy various types of sensors, each providing different data types, dimensions, and qualities. A single data source is susceptible to interference and cannot fully reflect the true state of the communication environment. This invention assigns weights to different data sources based on an error model and employs weighted combination rules for multi-source evidence fusion, effectively mitigating conflicts between multiple sources and improving the stability, consistency, and reliability of the fusion results, thereby enhancing the system's fault tolerance under complex terrain and harsh electromagnetic environments. Secondly, based on the fused environmental data, this invention further employs Bayesian inference to track interference signals in real time, achieving dynamic response to time-varying and nonlinear interference. Communication interference in hybrid wind-solar-storage power stations (such as electromagnetic interference and signal fluctuations caused by mechanical vibration) exhibits significant time-varying and nonlinear characteristics, making traditional static detection methods inadequate for handling sudden interference events. This invention establishes a dynamic system model to estimate and predict communication status in real time, dynamically tracking the changing trends of interference signals and providing timely and accurate decision-making basis for subsequent interference suppression, overcoming the shortcomings of traditional methods in terms of dynamic adaptability. Third, during the Bayesian inference process, this invention specifically optimizes the state transition matrix and observation matrix for the typical physical environment characteristics of wind-solar-storage hybrid power stations, significantly improving prediction accuracy. Specifically, by introducing periodic functions into the state transition matrix and observation matrix, the periodic shading effect caused by wind turbine blade rotation is accurately modeled; simultaneously, a shielding signal factor is introduced to accurately characterize the absorption, reflection, and phase change effects of electromagnetic waves by metal structures within the power station (such as wind turbine towers and photovoltaic supports). These optimizations enable the dynamic system model to realistically reflect the dynamic interference effects caused by wind turbine movement and metal structures, effectively solving the problem of communication status prediction errors caused by the inability of static models to describe these physical phenomena. Fourth, the synchronous optimization of the observation matrix further enhances the adaptability of the observation model to changes in the actual environment and improves the accuracy of interference identification. By simultaneously introducing periodic functions and shielding signal factors into the observation matrix, the observation model can work in conjunction with the state prediction model to form a complete multi-dimensional channel interference suppression framework for wind-solar-storage hybrid power stations, thus demonstrating higher reliability and practicality in actual engineering deployments.

[0018] This invention discloses a multi-dimensional channel communication interference suppression system for hybrid wind-solar-storage power stations. First, the system constructs a complete closed-loop processing architecture from data acquisition to interference suppression through the collaborative work of a data acquisition module, a data fusion module, and an interference signal suppression module. The data acquisition module is responsible for collecting and preprocessing communication environment data from multiple sources within the hybrid wind-solar-storage power station, providing a high-quality data foundation for subsequent fusion. The data fusion module performs weighted fusion of multi-source data based on Dempster-Shafer evidence theory, effectively overcoming the shortcomings of incomplete information and susceptibility to interference from single data sources, and significantly improving the system's perception capability of complex electromagnetic and geographical environments. The interference signal suppression module, based on the fused environmental information, tracks and suppresses interference signals in real time through Bayesian inference. The three modules are interconnected and logically clear, jointly achieving accurate identification and dynamic suppression of multi-dimensional channel interference. Second, the data fusion module in this system introduces a weighting mechanism based on an error model, which can dynamically allocate weights according to the historical performance of each data source, significantly improving the reliability and stability of the fusion results. In hybrid wind-solar-storage power stations, the accuracy, sampling frequency, and susceptibility to environmental interference vary among different sensors. Traditional equal-weight fusion or fixed-weight fusion methods are ill-suited to adapting to changing field conditions. This system calculates the error between each data source and its reference true value, quantifies performance indicators based on mean square error, and normalizes the weight allocation. This allows high-reliability data sources to have a greater weight in the fusion process, effectively mitigating conflicts between multiple sources of evidence and enhancing the system's fault tolerance and robustness in complex power station environments. Third, the interference signal suppression module in this system employs a Bayesian inference framework and optimizes the model for the typical physical characteristics of hybrid wind-solar-storage power stations, achieving dynamic tracking and real-time suppression of time-varying and nonlinear interference. Specifically, this module introduces periodic functions and shielding signal factors into the state transition matrix and observation matrix, respectively, to accurately model the periodic shading effect caused by wind turbine blade rotation and the shielding effect of the metal structure on electromagnetic waves. Through recursive updates using Kalman filtering, the system can estimate the changing trends of communication status in real time and dynamically adjust model parameters based on the latest observation data, thus effectively solving the technical problems of traditional static detection methods being unable to cope with sudden interference and having large prediction errors. Fourth, this system has good scalability and adaptability, and can be flexibly deployed in wind-solar-storage hybrid power stations of different sizes, terrain conditions, and equipment configurations. The data acquisition module supports the access of various types of sensor data, the weighting parameters of the data fusion module can be adaptively calibrated based on on-site measured data, and the model parameters of the interference signal suppression module can also be specifically adjusted according to specific scenarios such as wind turbine type and metal structure layout. Therefore, this system is not only suitable for standardized combined power stations, but also adaptable to personalized deployment needs in complex terrains such as mountains and deserts, and has broad engineering application prospects. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a multi-dimensional channel communication interference suppression method for a wind-solar-storage hybrid power station according to an embodiment of the present invention; Figure 2 This is a block diagram of a multi-dimensional channel communication interference suppression system for a wind-solar-storage hybrid power station according to an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0022] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0024] The present invention will now be described in further detail with reference to the accompanying drawings: See Figure 1 This invention discloses a method for suppressing multi-dimensional channel communication interference in hybrid wind-solar-storage power stations, characterized by comprising: S1, acquire multi-source communication environment data within the wind-solar-storage hybrid power station area, and preprocess the multi-source communication environment data; S2, based on the Dempster-Shafer evidence theory, the preprocessed multi-source communication environment data is weighted and fused to obtain environment fusion data; S3, based on the environmental fusion data, track and suppress interference signals in real time through Bayesian inference.

[0025] This invention discloses a multi-dimensional channel communication interference suppression method for hybrid wind-solar-storage power stations. Firstly, by introducing Dempster-Shafer evidence theory, this invention performs weighted fusion of multi-source communication environment data, significantly improving the reliability and robustness of communication status perception in complex environments. Hybrid wind-solar-storage power stations typically deploy various types of sensors, each providing different data types, dimensions, and qualities. A single data source is susceptible to interference and cannot fully reflect the true state of the communication environment. This invention assigns weights to different data sources based on an error model and employs weighted combination rules for multi-source evidence fusion, effectively mitigating conflicts between multiple sources and improving the stability, consistency, and reliability of the fusion results, thereby enhancing the system's fault tolerance under complex terrain and harsh electromagnetic environments. Secondly, based on the fused environmental data, this invention further employs Bayesian inference to track interference signals in real time, achieving dynamic response to time-varying and nonlinear interference. Communication interference in hybrid wind-solar-storage power stations (such as electromagnetic interference and signal fluctuations caused by mechanical vibration) exhibits significant time-varying and nonlinear characteristics, making traditional static detection methods inadequate for handling sudden interference events. This invention establishes a dynamic system model to estimate and predict communication status in real time, dynamically tracking the changing trends of interference signals and providing timely and accurate decision-making basis for subsequent interference suppression, overcoming the shortcomings of traditional methods in terms of dynamic adaptability. Third, during the Bayesian inference process, this invention specifically optimizes the state transition matrix and observation matrix for the typical physical environment characteristics of wind-solar-storage hybrid power stations, significantly improving prediction accuracy. Specifically, by introducing periodic functions into the state transition matrix and observation matrix, the periodic shading effect caused by wind turbine blade rotation is accurately modeled; simultaneously, a shielding signal factor is introduced to accurately characterize the absorption, reflection, and phase change effects of electromagnetic waves by metal structures within the power station (such as wind turbine towers and photovoltaic supports). These optimizations enable the dynamic system model to realistically reflect the dynamic interference effects caused by wind turbine movement and metal structures, effectively solving the problem of communication status prediction errors caused by the inability of static models to describe these physical phenomena. Fourth, the synchronous optimization of the observation matrix further enhances the adaptability of the observation model to changes in the actual environment and improves the accuracy of interference identification. By simultaneously introducing periodic functions and shielding signal factors into the observation matrix, the observation model can work in conjunction with the state prediction model to form a complete multi-dimensional channel interference suppression framework for wind-solar-storage hybrid power stations, thus demonstrating higher reliability and practicality in actual engineering deployments.

[0026] The present invention will be described in detail below with reference to specific embodiments: This embodiment provides a multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations, including the following steps: S1. Collect communication environment data within the wind-solar-storage hybrid power station area using sensors, and perform preprocessing operations on the collected communication environment data.

[0027] In this embodiment S1, communication environment data within the wind-solar-storage hybrid power station area is collected by sensors. The specific steps of the preprocessing operation are as follows: S1.1 Identify and remove outliers using statistical methods, and fill in missing values ​​using interpolation. S1.2, Based on S1.1, the communication environment data reduces the impact of noise on communication environment measurements through low-pass filtering technology; S1.3. Based on the filtered communication environment data, Z-Score is used for normalization to convert data of different scales to the same range.

[0028] S2. Based on the Dempster-Shafer theory, the preprocessed communication environment data is fused to form environment fusion data.

[0029] In this embodiment S2, the preprocessed communication environment data is fused to form environment fused data based on the Dempster-Shafer theory. The specific steps for fusing the preprocessed communication environment data to form environment fused data are as follows: S2.1. Key features are extracted from preprocessed data of various types using signal processing techniques; S2.2 Use principal component analysis to reduce the dimensionality of high-dimensional feature data, transforming feature data of different dimensions into the same dimension; S2.3. Based on the Dempster-Shafer theory, different types of feature data are fused to form environmental fusion data. Considering that the signal sources have different importance, a weighting mechanism is introduced to optimize the Dempster-Shafer theory.

[0030] In this embodiment S2.3, the specific steps for optimizing the Dempster-Shafer theory are as follows: S2.3.1 Framework for Defining Interference Source Types Based on Communication Environment Data Then the interference source type framework The mathematical expression is: ; In the formula, Indicates electromagnetic interference; Indicates interference from physical obstacles; Indicates environmental noise interference; This indicates multipath propagation interference; S2.3.2 Based on the data for each type of interference source in S2.3.1, calculate the basic probability allocation for each signal source. ; S2.3.3. Assign weights to each data source based on the error model according to each signal source. And the sum of all weights is 1; S2.3.4 For multiple data sources, use weighted combination rules to adjust the basic probability allocation.

[0031] In this embodiment S2.3.3, weights are assigned to each data source based on the error model according to each signal source. Weights are assigned to each data source based on an error model. The specific steps are as follows: Calculate the error between the communication environment data and the reference true value of the communication environment data. Then the mathematical expression related to the calculation error is: ; in, ; In the formula, Indicates the first The error of each data source measures the difference between the model's predictions and the actual observations. Indicates the first The measurement value from the first data source is the first value transmitted by the sensor. One communication environment data value; This indicates that the communication environment data references the actual value, where This represents an index used to identify specific observations in a dataset; This indicates the rotation period of the wind turbine blades; Indicates the current time point; Indicates the maximum fluctuation amplitude of the interference signal; The error magnitude of each data source is quantified based on mean squared error; Normalization is used to normalize the error metrics from different data sources to a uniform range; Based on the weights assigned to the normalized error index, the mathematical expression for weight allocation is as follows: ; In the formula, Indicates the first The weight of each data source; Indicates the first Performance metrics for each data source; Indicates the first Performance metrics of data sources, among which Indicates the index, used to traverse from 1 to... All data sources; This indicates the overall independent data source.

[0032] In this embodiment S2.3.4, the specific steps for adjusting the basic probability allocation using a weighted combination rule for multiple data sources are as follows: For multiple assigned weights and basic probability allocation The data is used for multi-source evidence fusion, and the mathematical expression involved in multi-source evidence fusion is as follows: ; in, ; In the formula, Indicates an event The basic probability allocation after fusion; Indicates the conflict factor, if A value close to 1 indicates a significant conflict. A value close to 0 indicates a very small number of conflicts. Represents the empty set; Indicates the credibility of evidence source 1; Indicate the credibility of evidence source 2; This represents the basic probability distribution of evidence source 1; This represents the basic probability distribution of evidence source 2; express event; express event; express event; After fusion, the conflict normalization method is used to analyze the results. Normalization is performed.

[0033] Hybrid wind, solar, and energy storage power stations typically deploy multiple types of sensors, which provide different data types and qualities. Multi-source evidence fusion can integrate information from multiple sources. By fusing information from multiple data sources, outliers can be more easily identified, removed, or corrected, thereby improving the reliability of the system.

[0034] S3. Based on environmental fusion data, Bayesian inference is used to track and suppress interference signals in real time.

[0035] The operating environment of hybrid wind-solar-storage power stations is complex and variable, with factors such as wind speed, light intensity, and temperature constantly changing, all of which affect communication channels. Bayesian inference allows for real-time monitoring of these changes and dynamic adjustment of model parameters to adapt to new environmental conditions. Interference signals (such as electromagnetic interference and mechanical vibration) are typically dynamic. Bayesian inference can update state estimates based on the latest observation data, thereby enabling real-time tracking of interference signals.

[0036] In this embodiment S3, the specific steps for real-time tracking and suppression of interference signals based on environmental fusion data and Bayesian inference are as follows: S3.1, Based on the communication environment state vector Define the state transition matrix and observation matrix Simultaneously, a periodic function and a masking signal factor are introduced to affect the state transition matrix. and observation matrix Optimization is performed to obtain the optimized state transition matrix. and observation matrix Then the mathematical expression for the state transition matrix before optimization is: ; in, ; In the formula, The communication environment state vector is an abstracted state vector obtained by extracting, fusing and modeling features from the data of stages S1 and S2. Represents the state transition matrix; Indicates the system at the previous time point The state vector; Represents the control input matrix; Indicates at a point in time External input applied to the system; Process noise is typically represented by a zero-mean Gaussian distribution. ; The mathematical expression for the observation matrix before optimization is: ; In the formula, Indicates the system at a given time point. The observation vector; Represents the observation matrix; This represents observation noise, which is also a zero-mean Gaussian distribution. ; S3.2 Constructing an initial probability distribution based on the basic probability allocation of the fused interference types And according to the initial probability distribution Given the prior distribution, an initial probability distribution is constructed based on the basic probability assignment of the fused interference types. The mathematical expression is: ; In the formula, Indicates the initial probability distribution; Indicates the first Interference types The basic probability distribution; Indicates the specific type of interference; S3.3, Based on the state transition matrix Control input matrix External inputs of the system and posterior state estimation Calculate the state prediction for the next time step and its covariance Then the mathematical expression involved in predicting the state at the next moment is: ; In the formula, This indicates a prediction of the state at the next moment. Indicates time step Posterior state estimation; The mathematical expression for the covariance at the next moment is: ; In the formula, This represents the covariance prediction for the next time step; Represents the state transition matrix transpose; The covariance matrix represents the process noise; S3.4, Based on the observation matrix Covariance matrix of process noise And the covariance prediction for the next time step. Calculate Kalman gain Then the mathematical expression related to the Kalman gain is: ; In the formula, Indicates Kalman gain; Represents the observation matrix transpose; S3.5, Kalman gain based on S3.4 Update state estimation and its covariance Then the mathematical expression involved in updating the state estimate is: ; In the formula, Indicates time step Posterior state estimation; The mathematical expression for updating the covariance is: ; In the formula, Indicates time step The posterior estimation error covariance matrix; This represents the identity matrix, used to ensure dimensional consistency and the correctness of mathematical operations.

[0037] After completing the state estimation, the system will automatically select the optimal communication parameter configuration based on the current channel state, including but not limited to: switching to a less interfered frequency band, enabling anti-interference modulation mode, increasing transmit power, and activating forward error correction mechanism.

[0038] In this embodiment S3.1, the state transition matrix is ​​optimized. The specific steps involved are as follows: Based on the influence of the shadowing effect of large wind turbines on the signal, a periodic function is introduced into the state transition matrix to optimize it. This optimization is based on the fundamental state transition matrix. With the periodic state transition matrix modulated by a sine function The state transition matrix under the shadow effect of large wind turbines is obtained through addition operations. The time dependence of the sine function is determined by the rotation period of the wind turbine blades. The decision is based on the state transition matrix under the shadow effect of large wind turbines. The mathematical expression is: ; in, ; In the formula, This represents the state transition matrix under the shadow effect of large wind turbines; Represents the basic state transition matrix; This represents the periodic state transition matrix after modulation by a sine function; Represents a periodic state transition matrix; The rotation of large wind turbine blades can cause periodic obstruction of communication channels, resulting in periodic fluctuations in signal strength over time. By introducing a periodic function (such as a sine function) into the state transition matrix, this periodic variation can be captured more accurately; since the periodic function can better capture the periodic fluctuations in signal strength, prediction errors can be significantly reduced.

[0039] The operating environment of a wind-solar-storage hybrid power station is dynamic, especially in the presence of large wind turbines, where the signal propagation path constantly changes with the rotation of the turbine blades. By introducing a periodic function, these changes can be tracked in real time, and model parameters can be dynamically adjusted to adapt to new environmental conditions.

[0040] Based on the shielding effect of metallic structures on electromagnetic waves, a shielding signal factor is introduced into the state transition matrix to optimize it. This results in a state transition matrix based on the shielding effect. The state transition matrix of the metal structure under electromagnetic wave shielding is obtained by multiplying it with a diagonal matrix containing signal strength attenuation factor and phase change factor. Among them, the signal strength attenuation factor and phase change factor These reflect the effects of the metal structure on signal strength and phase, respectively. Therefore, the state transition matrix based on the shielding effect of the metal structure on electromagnetic waves is... The mathematical expression is: ; In the formula, This represents the state transition matrix of a metal structure under electromagnetic wave shielding. Represents the state transition matrix for the shielding effect; Indicates the signal strength attenuation factor; This indicates the phase change caused by the shielding effect during signal propagation; Metal structures (such as wind turbine towers and photovoltaic panel supports) absorb, reflect, or scatter electromagnetic waves, thereby altering the signal propagation path and intensity. By introducing a shielding signal factor into the state transition matrix, the impact of this shielding effect on the communication channel can be modeled more accurately. Traditional static models cannot effectively describe these complex shielding effects, while introducing a shielding signal factor allows the model to better reflect actual physical phenomena, thus improving prediction accuracy.

[0041] The operating environment of a hybrid wind-solar-storage power station is dynamic, especially in the presence of numerous metal structures, where signal propagation paths are constantly affected. By introducing a shielding signal factor, these changes can be tracked in real time, and model parameters can be dynamically adjusted to adapt to new environmental conditions.

[0042] Based on the state transition matrix With the state transition matrix The final state transition matrix is ​​obtained through addition. Then the optimized state transition matrix The mathematical expression is: .

[0043] The periodic shading effect caused by the rotation of wind turbine blades and the shielding effect of metal structures on electromagnetic waves are two different physical phenomena, but they coexist and affect communication channels. By... and By combining these two main influencing factors, a unified state transition matrix can be formed.

[0044] In this embodiment S3.1, the observation matrix is ​​optimized. The specific steps involved are as follows: Based on the influence of the shadowing effect of large wind turbines on the signal, a periodic function is introduced into the observation matrix to optimize it, based on the fundamental observation matrix. With the periodic observation matrix modulated by a sine function The observation matrix under the shadow effect of large wind turbines is obtained through addition operations. The time dependence of the sine function is determined by the rotation period of the wind turbine blades. The decision is based on the observation matrix under the shadow effect of large wind turbines. The mathematical expression is: ; in, ; In the formula, This represents the observation matrix under the shadow effect of large wind turbines; Represents the basic observation matrix; This represents a periodic observation matrix modulated by a sine function; Represents a periodic observation matrix; Based on the shielding effect of metallic structures on electromagnetic waves, a shielding signal factor is introduced into the observation matrix to optimize it. This results in an observation matrix based on the shielding effect. With a signal strength attenuation factor and phase change factor The observation matrix under the electromagnetic wave shielding effect of the metal structure is obtained by multiplication of the diagonal matrix. Among them, the signal strength attenuation factor and phase change factor These reflect the independent effects of the metal structure on signal strength and phase, respectively. Therefore, the observation matrix based on the shielding effect of the metal structure on electromagnetic waves... The mathematical expression is: ; In the formula, This represents the observation matrix under the electromagnetic wave shielding effect of the metal structure. Represents the observation matrix of the shielding effect; Indicates the signal strength attenuation factor; This indicates the phase change caused by the shielding effect during signal propagation; Based on observation matrix With observation matrix The final state transition matrix is ​​obtained through addition. Then the optimized observation matrix The mathematical expression is: .

[0045] This embodiment has the following beneficial effects: 1. In this multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations, the DS evidence theory is used to fuse multiple types of data, and a weighting mechanism is introduced to optimize the basic probability allocation, improve the credibility of the fusion results, enhance the consistency and redundancy of multi-source information, and strengthen the robustness and fault tolerance of the system in complex environments. This solves the problem that single sensors or data sources are easily interfered with and cannot fully reflect the state of complex communication environments.

[0046] 2. In this multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations, a weighted DS combination rule is introduced to fuse multi-source evidence, which effectively alleviates the conflict between multi-source evidence and improves the stability and consistency of the fusion results.

[0047] 3. In this multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations, a dynamic system model is established to realize real-time state estimation and prediction, dynamically track the changing trend of interference signals, and provide a decision basis for interference suppression. This solves the problem that communication interference is time-varying and nonlinear, and static detection methods are difficult to deal with sudden interference events.

[0048] 4. In this multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations, the periodic shading effect caused by wind turbine rotation and the influence of the power station's metal structure on signal strength and phase are more accurately modeled by optimizing the state transition matrix. This effectively solves the problem that static models cannot reflect the dynamic interference caused by wind turbine movement and metal structure, thereby reducing the communication state prediction error caused by them.

[0049] 5. In this multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations, the observation matrix is ​​optimized to improve the adaptability of the observation model to changes in the actual environment, enhance the accuracy of interference identification, and solve the problem that fixed observation models cannot adapt to complex and ever-changing communication environments.

[0050] See Figure 2 This invention also discloses a multi-dimensional channel communication interference suppression system for wind-solar-storage hybrid power stations, comprising: The data acquisition module is used to acquire multi-source communication environment data within the wind-solar-storage hybrid power station area and to preprocess the multi-source communication environment data. The data fusion module is used to perform weighted fusion of the preprocessed multi-source communication environment data based on the Dempster-Shafer evidence theory to obtain environment fusion data. An interference signal suppression module is used to track and suppress interference signals in real time based on the environmental fusion data and through Bayesian inference.

[0051] This invention discloses a multi-dimensional channel communication interference suppression system for hybrid wind-solar-storage power stations. First, the system constructs a complete closed-loop processing architecture from data acquisition to interference suppression through the collaborative work of a data acquisition module, a data fusion module, and an interference signal suppression module. The data acquisition module is responsible for collecting and preprocessing communication environment data from multiple sources within the hybrid wind-solar-storage power station, providing a high-quality data foundation for subsequent fusion. The data fusion module performs weighted fusion of multi-source data based on Dempster-Shafer evidence theory, effectively overcoming the shortcomings of incomplete information and susceptibility to interference from single data sources, and significantly improving the system's perception capability of complex electromagnetic and geographical environments. The interference signal suppression module, based on the fused environmental information, tracks and suppresses interference signals in real time through Bayesian inference. The three modules are interconnected and logically clear, jointly achieving accurate identification and dynamic suppression of multi-dimensional channel interference. Second, the data fusion module in this system introduces a weighting mechanism based on an error model, which can dynamically allocate weights according to the historical performance of each data source, significantly improving the reliability and stability of the fusion results. In hybrid wind-solar-storage power stations, the accuracy, sampling frequency, and susceptibility to environmental interference vary among different sensors. Traditional equal-weight fusion or fixed-weight fusion methods are ill-suited to adapting to changing field conditions. This system calculates the error between each data source and its reference true value, quantifies performance indicators based on mean square error, and normalizes the weight allocation. This allows high-reliability data sources to have a greater weight in the fusion process, effectively mitigating conflicts between multiple sources of evidence and enhancing the system's fault tolerance and robustness in complex power station environments. Third, the interference signal suppression module in this system employs a Bayesian inference framework and optimizes the model for the typical physical characteristics of hybrid wind-solar-storage power stations, achieving dynamic tracking and real-time suppression of time-varying and nonlinear interference. Specifically, this module introduces periodic functions and shielding signal factors into the state transition matrix and observation matrix, respectively, to accurately model the periodic shading effect caused by wind turbine blade rotation and the shielding effect of the metal structure on electromagnetic waves. Through recursive updates using Kalman filtering, the system can estimate the changing trends of communication status in real time and dynamically adjust model parameters based on the latest observation data, thus effectively solving the technical problems of traditional static detection methods being unable to cope with sudden interference and having large prediction errors. Fourth, this system has good scalability and adaptability, and can be flexibly deployed in wind-solar-storage hybrid power stations of different sizes, terrain conditions, and equipment configurations. The data acquisition module supports the access of various types of sensor data, the weighting parameters of the data fusion module can be adaptively calibrated based on on-site measured data, and the model parameters of the interference signal suppression module can also be specifically adjusted according to specific scenarios such as wind turbine type and metal structure layout. Therefore, this system is not only suitable for standardized combined power stations, but also adaptable to personalized deployment needs in complex terrains such as mountains and deserts, and has broad engineering application prospects.

[0052] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0055] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0056] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for suppressing multi-dimensional channel communication interference in a wind-solar-storage hybrid power station, characterized in that, include: Acquire multi-source communication environment data within the area of ​​the wind-solar-storage hybrid power station, and preprocess the multi-source communication environment data; Based on the Dempster-Shafer evidence theory, the preprocessed multi-source communication environment data is weighted and fused to obtain environment fusion data; Based on the environmental fusion data, interference signals are tracked and suppressed in real time through Bayesian inference.

2. The multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations according to claim 1, characterized in that, The preprocessing includes: Identify and remove outliers, and fill in missing values ​​using interpolation; Use low-pass filtering to reduce noise; Normalization was performed using Z-Score.

3. The multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations according to claim 1, characterized in that, The weighted fusion of the preprocessed multi-source communication environment data based on Dempster-Shafer evidence theory includes: Key feature data were extracted from preprocessed multi-source communication environment data using signal processing techniques. Principal component analysis is used to reduce the dimensionality of high-dimensional key feature data, transforming key feature data of different dimensions into the same dimension; Based on the Dempster-Shafer theory, different types of key feature data are fused to form environmental fusion data, and a weighting mechanism is introduced to optimize the Dempster-Shafer theory. The specific steps for optimizing the Dempster-Shafer theory are as follows: Framework for defining interference source types based on communication environment data ; Based on each type of data and its corresponding model, calculate the basic probability allocation for each signal source. ; Weights are assigned to each data source based on an error model, according to each signal source. ; For multiple data sources, a weighted combination rule is used to adjust the basic probability allocation; The weights are assigned to each data source based on the error model. The specific steps are as follows: Calculate the error between the communication environment data and the reference true value of the communication environment data. ; The error magnitude of each data source is quantified based on mean squared error; Normalization is used to normalize the error metrics from different data sources to a uniform range; Weights are assigned based on the normalized error index.

4. The multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations according to claim 3, characterized in that, For multiple data sources, a weighted combination rule is used to fuse and adjust the basic probability allocation. Its mathematical expression is: in, ; In the formula, Indicates an event The basic probability allocation after fusion; Indicates the conflict factor, if A value close to 1 indicates a significant conflict. A value close to 0 indicates a very small number of conflicts. Represents the empty set; Indicates the credibility of evidence source 1; Indicate the credibility of evidence source 2; This represents the basic probability distribution of evidence source 1; This represents the basic probability distribution of evidence source 2; express event; express event; express Event; Conflict normalization for the fused Normalization is performed.

5. The multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations according to claim 1, characterized in that, The method of tracking and suppressing interference signals in real time through Bayesian inference includes: Based on the communication environment state vector Define the state transition matrix and observation matrix Simultaneously, a periodic function and a masking signal factor are introduced to affect the state transition matrix. and observation matrix Optimization is performed to obtain the optimized state transition matrix. and observation matrix ; Construct an initial probability distribution based on the basic probability assignment of the fused interference types. And according to the initial probability distribution Determine the prior distribution; Based on the state transition matrix Control input matrix External inputs of the system and posterior state estimation Calculate the state prediction for the next time step and its covariance ; Based on the observation matrix Covariance matrix of process noise And the covariance prediction for the next time step. Calculate Kalman gain ; Based on Kalman gain Update state estimation and its covariance .

6. The multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations according to claim 5, characterized in that, The optimized state transition matrix The specific steps involved are as follows: A periodic function is introduced into the state transition matrix to optimize it, based on the fundamental state transition matrix. With the periodic state transition matrix modulated by a sine function The state transition matrix under the shadow effect of large wind turbines is obtained through addition operations. The time dependence of the sine function is determined by the rotation period of the wind turbine blades. Decide; A shielding signal factor is introduced into the state transition matrix to optimize it, based on the shielding effect state transition matrix. The state transition matrix of the metal structure under electromagnetic wave shielding is obtained by multiplying it with a diagonal matrix containing signal strength attenuation factor and phase change factor. Among them, the signal strength attenuation factor and phase change factor These respectively reflect the influence of the metal structure on signal strength and phase; Based on the state transition matrix With the state transition matrix The final state transition matrix is ​​obtained through addition. .

7. The multi-dimensional channel communication interference suppression method for wind-solar-storage hybrid power stations according to claim 5, characterized in that, The optimized observation matrix The specific steps involved are as follows: A periodic function is introduced into the observation matrix to optimize it, based on the fundamental observation matrix. With the periodic observation matrix modulated by a sine function The observation matrix under the shadow effect of large wind turbines is obtained through addition operations. The time dependence of the sine function is determined by the rotation period of the wind turbine blades. Decide; A shielding signal factor is introduced into the observation matrix to optimize it, based on the shielding effect observation matrix. With a signal strength attenuation factor and phase change factor The observation matrix under the electromagnetic wave shielding effect of the metal structure is obtained by multiplication of the diagonal matrix. Among them, the signal strength attenuation factor and phase change factor These reflect the independent effects of the metal structure on signal strength and phase, respectively. Based on observation matrix With observation matrix The final state transition matrix is ​​obtained through addition. .

8. A multi-dimensional channel communication interference suppression system for a wind-solar-storage hybrid power station, characterized in that, include: The data acquisition module is used to acquire multi-source communication environment data within the wind-solar-storage hybrid power station area and to preprocess the multi-source communication environment data. The data fusion module is used to perform weighted fusion of the preprocessed multi-source communication environment data based on the Dempster-Shafer evidence theory to obtain environment fusion data. An interference signal suppression module is used to track and suppress interference signals in real time based on the environmental fusion data and through Bayesian inference.

9. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the multi-dimensional channel communication interference suppression method for a wind-solar-storage hybrid power station as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the multi-dimensional channel communication interference suppression method for a wind-solar-storage hybrid power station as described in any one of claims 1-7.

Images