Intelligent substation wireless network signal coverage area analysis and detection method

Abstract

The invention discloses an intelligent substation wireless network signal coverage area analysis and detection method, and aims to overcome the defects of a traditional signal coverage prediction method. By combining substation equipment data and power GIS information, the system can accurately position the geographic position of equipment and perform signal feature analysis. The model can dynamically predict the signal coverage by using a machine learning algorithm, such as a support vector machine and a random forest, and can adjust the prediction result in real time according to the state data of the transformer. The system is combined with the GIS technology, the signal coverage range is visually displayed, and decision support is provided for network planning and optimization of the transformer substation. Through signal coverage prediction and optimization, efficient operation of a wireless network in the transformer substation is ensured, and the communication service quality and the utilization rate of network resources are improved. The method is particularly suitable for rapidly changing urban environments, planning, construction and maintenance of the wireless network can be effectively guided, and user experience and network operation efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and particularly to a method for analyzing and detecting the coverage range of wireless network signals in an intelligent substation. Background Art

[0002] With the rapid development of mobile communication technologies, the coverage quality and efficiency of wireless networks have become important indicators for measuring the quality of communication services. Traditional signal coverage prediction methods mainly rely on theoretical model calculations or field measurements. Theoretical models are usually calculated based on the basic physical principles of radio wave propagation. Although they have a certain degree of accuracy under ideal conditions, they often lack adaptability in complex actual scenarios. On the other hand, field measurement methods usually require the use of special instruments or mobile phone software on-site for detection. After connecting to the operator's base station, indicators such as the signal reception power and signal-to-noise ratio at the location are analyzed. These detection instruments are usually handheld or used in combination with external antennas. However, this method is not only costly but also inefficient and difficult to quickly respond to the dynamic changes in the network environment.

[0003] However, there are also obvious deficiencies in the existing technologies for signal coverage prediction. The Chinese invention patent authorization document CN116245260B proposes an optimization method for deploying 5G base stations based on substation resources. This method improves the layout efficiency of 5G base stations by optimizing the deployment of substation resource data. However, this invention fails to fully utilize machine learning technologies to predict the signal coverage range. Machine learning technologies can, through the training of large-scale data, automatically identify and learn the complex patterns in signal propagation and the mutual influence between adjacent sites, thereby achieving more efficient and accurate signal coverage prediction in complex urban environments. Therefore, there is an urgent need for a new technology that combines machine learning with existing optimization methods to overcome the limitations of current signal coverage prediction methods. Summary of the Invention

[0004] The present invention aims to provide a method for analyzing and detecting the wireless network signal coverage range in an intelligent substation, so as to overcome the deficiencies of traditional signal coverage prediction methods in actual scenarios. By introducing advanced data acquisition technologies and machine learning algorithms, this method can achieve efficient and accurate wireless network signal coverage prediction in complex urban environments, thereby improving the accuracy and efficiency of equipment installation and network planning within the substation. The present invention also has the following sub-goals: by combining substation equipment data and power GIS information, accurately locate the geographical positions of the equipment and provide more targeted signal coverage prediction; utilize substation environmental data and adjacent site relationship diagrams to deeply analyze signal characteristics, including intensity, interference, and time series characteristics, in order to identify complex patterns in signal propagation; collect transformer status data and integrate it with signal and environmental data, and use support vector machine or random forest algorithms to train and optimize the model to improve the model's sensitivity to transformer status changes; input transformer status data in real time during the machine learning process and dynamically adjust the model prediction results to adapt to real-time environmental changes; combine GIS data to display the signal coverage range and provide intuitive decision-making support for the network planning and optimization of the substation, helping to optimize the equipment installation location and operator selection.

[0005] The present invention proposes a method for analyzing and detecting the wireless network signal coverage range in an intelligent substation, characterized in that the method includes: collecting substation equipment data, combining power GIS information to obtain the geographical positioning of the equipment; collecting substation environmental data, constructing an adjacent site relationship diagram, and performing signal feature analysis based on the substation environmental data; constructing a machine learning model according to transformer data, and performing signal coverage prediction and optimization; combining GIS data to display the signal coverage range and providing optimization suggestions.

[0006] Preferably, this method exports the existing power terminal installation point information and signal strength data through the terminal network management system, combines the power GIS data to associate the terminal geographical position information, and uses special equipment to dynamically collect relevant parameters such as the real-time signal strength and geographical position information of wireless access points.

[0007] Preferably, this method determines the adjacent sites of each site according to the geographical position information of the base station or wireless access point, and constructs an adjacent site relationship diagram.

[0008] Preferably, this method performs signal feature analysis according to the substation environmental data and the adjacent site relationship diagram.

[0009] Preferably, this method extracts signal intensity, interference, and time series characteristics, establishes a loss model and calculates the eccentricity value.

[0010] Preferably, the method collects the status data of the transformer, integrates it with the signal strength and environmental data, trains a model through a support vector machine or random forest algorithm, and adjusts the model parameters.

[0011] Preferably, the method performs cross-validation to calibrate the sensitivity of the model to the transformer status change.

[0012] Preferably, during the process of machine learning, the method inputs the transformer status data in real time for signal coverage prediction and dynamically adjusts the model prediction.

[0013] Preferably, the method combines GIS data to display the signal coverage range, providing intuitive decision-making support for the network planning and optimization of the substation.

[0014] Preferably, the method optimizes the equipment installation location and operator selection according to the prediction results.

[0015] Through comprehensive analysis of the signal data of adjacent stations and combination with advanced machine learning techniques, the present invention realizes accurate prediction of the wireless network signal coverage range, and has higher accuracy and efficiency compared with traditional methods. This method can effectively guide the planning, construction and maintenance of wireless networks. Especially in a rapidly changing urban environment, it helps to timely discover and solve the coverage blind area problem, improving the user experience and network operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0017] Figure 1 It is a flowchart of the method of the present invention;

[0018] Figure 2 It is a flowchart of machine learning of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In order to facilitate the understanding and implementation of the present invention by those of ordinary skill in the art, the following further describes the present invention in detail in combination with embodiments. It should be understood that the embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0020] Embodiment

[0021] According to Figure 1 As shown, the present invention proposes an intelligent substation wireless network signal coverage range analysis and detection method, including:

[0022] 1. Data collection

[0023] In the implementation process of the present invention, data collection is the key first step to ensure the accuracy and reliability of subsequent analysis and prediction. The data collection process starts from the startup phase, aiming to comprehensively collect relevant data inside and outside the substation, covering equipment, environment, and attribute information. First, collect substation equipment data, including the specific location of the equipment installation point, signal strength, and its geographical positioning information. These data provide the basis for subsequent signal propagation analysis.

[0024] Next, focus on collecting the environmental and attribute data of the substation. These data include, but are not limited to, environmental factors such as temperature, humidity, average daily current flowing in the station, water level, and dust density. At the same time, collect the attribute data of the substation, such as rated current, rated voltage, rated load, the location distance between the equipment and the edge data center system, and the building structure mechanical property values. These environmental and attribute data are crucial for understanding the physical environment of signal propagation.

[0025] In the data collection process, preprocessing is an essential step. All collected data must undergo integrity checks to ensure that there are no missing or incomplete records. If the data integrity check passes, the data format can be unified; otherwise, it is necessary to return to the data collection stage for supplementation and correction. In the process of unifying the data format, apply the environmental and attribute connotation unification factor so that data from different sources and types can be analyzed within a unified framework. This processing not only improves the usability of the data but also lays a solid foundation for subsequent feature extraction and model training. Through these steps, the high quality and consistency of the data are ensured, providing reliable data support for the analysis and detection of the wireless network signal coverage range of the intelligent substation.

[0026] 2. Adjacent site identification

[0027] After the data collection is completed and preprocessed, the next step is to identify adjacent sites, which is the basis for understanding the signal propagation path and mutual influence. In the analysis of the wireless network signal coverage range of the intelligent substation, the identification of adjacent sites is crucial because it can reveal potential signal propagation paths and possible interference sources.

[0028] First, based on the previously collected equipment geographical location information, use geographic information system (GIS) technology to construct an adjacent site relationship diagram. This relationship diagram details the spatial relationship between each site and its surrounding sites. By analyzing these relationships, it is possible to identify which sites may have a direct or indirect impact on signal propagation.

[0029] In the process of constructing the relationship graph, ensuring the accuracy and integrity of the data is crucial. First, the system calculates the distance between sites based on geographical coordinates and further corrects the adjacent relationships in combination with information on environmental obstacles such as buildings and trees. This step takes into account not only the physical distance but also the possible influence of environmental factors on the actual path of signal propagation.

[0030] Once the adjacent site relationship graph is constructed, the system checks its integrity. The content of the check includes ensuring that all sites are correctly identified and connected, without any omissions or incorrect connections. If the integrity check of the relationship graph passes, then subsequent signal feature analysis can be carried out; if it fails, the data collection phase needs to be revisited to re-examine the accuracy and integrity of the data.

[0031] In this way, the identification of adjacent sites provides important basic data for subsequent signal feature analysis and machine learning models, making signal coverage prediction more accurate and practical. This process ensures the rationality of the signal propagation path and lays the foundation for optimizing the coverage of the wireless network.

[0032] 3. Signal Feature Analysis

[0033] After the identification of adjacent sites, signal feature analysis is an important step in analyzing the signal coverage of the wireless network in intelligent substations. The core task of this step is to deeply analyze the collected signal data and extract the key features that affect signal propagation, so as to provide strong support for the construction of machine learning models.

[0034] First, the system conducts a detailed analysis of the signal data of each site and its adjacent sites. This process involves extracting features such as signal strength, signal interference, and time series changes. Signal strength data can reflect the distribution of signals in space, while signal interference data helps identify external factors that may affect signal quality. Time series analysis helps understand the fluctuation trend of signals at different time points, thus identifying possible periodic changes or anomalies.

[0035] During the signal feature analysis process, the system will establish a loss model to better quantify and understand the deviation of signal propagation. The loss model evaluates the changes in signal strength at different locations and times by calculating the eccentricity value. The calculation of the eccentricity value can help identify abnormal patterns and potential problems in signal propagation, providing a reference for subsequent optimization.

[0036] To ensure the integrity of signal feature analysis, the system verifies the extracted features. The verification content includes: whether all key features have been correctly identified and extracted, and whether the analysis of signal data comprehensively covers all relevant factors. If the integrity check of feature extraction passes, the system will continue with the construction of the machine learning model; if not, it is necessary to return to the data collection stage and recheck the accuracy and integrity of the data.

[0037] Through this meticulous signal feature analysis, the system can identify the main factors affecting signal coverage, providing high-quality input data for subsequent machine learning model training. This process ensures the accuracy of signal prediction and lays a foundation for optimizing the wireless network coverage within the substation.

[0038] 4. Machine Learning Model Construction

[0039] According to Figure 2 as shown, the machine learning model construction process includes:

[0040] 4.1 Data Collection

[0041] In the initial stage of machine learning model construction, data collection is a crucial step. The goal of data collection is to obtain comprehensive and high-quality input data to support subsequent feature extraction and model training. In the analysis of the wireless network signal coverage in intelligent substations, data collection needs to cover a variety of data sources and types to ensure that the model can fully understand the complex factors in signal propagation.

[0042] First, the system collects the status data of the transformer. These data include information such as the real-time load, temperature, and physical location of the transformer. As the core equipment of the substation, the working status of the transformer has an important impact on signal propagation. The load data can reveal the working intensity of the transformer at different time points, while the temperature data may affect the signal transmission characteristics of the transformer. The physical location data is used to associate the spatial relationship between the transformer and other equipment and sites.

[0043] Secondly, the system integrates signal strength and environmental data. The signal strength data reflects the propagation of wireless signals within the substation, while the environmental data includes external factors such as temperature, humidity, and dust density, which may affect the signal propagation path and quality. By integrating these data together, the system can form a multi-dimensional data set to support subsequent feature extraction.

[0044] During the data collection process, ensuring the accuracy and integrity of the data is crucial. The system will conduct preliminary verification and cleaning of various types of data to remove noise and incorrect data. At the same time, the time synchronization of the data also needs to be ensured so that the dynamic relationship between different data can be correctly reflected during analysis.

[0045] Through comprehensive data collection, the system provides rich input information for the machine learning model. This not only helps improve the effect of model training but also lays a foundation for achieving more accurate signal coverage prediction. The quality of data collection directly affects the performance of the model, so the work in this stage is crucial.

[0046] 4.2 Feature Extraction

[0047] After data collection is completed, feature extraction is one of the key steps in building a machine learning model. The purpose of feature extraction is to identify and extract the most influential features for signal coverage prediction from a large amount of collected raw data. This process not only helps simplify the data dimension but also improves the efficiency and accuracy of model training.

[0048] First, features are extracted from the state data of the transformer. Information such as the load, temperature, and location of the transformer is quantified as part of the feature vector. The load feature can reveal the changes in signal propagation under different load conditions, while the temperature feature may affect the signal attenuation characteristics. By analyzing the location feature of the transformer, its role in the signal path can be understood. Especially in a complex substation environment, the transformer may form shielding or reflection for signal propagation.

[0049] Secondly, feature extraction is performed on signal strength and environmental data. Signal strength features include average strength, maximum strength, and signal fluctuation amplitude, etc. These features can help the model capture the change patterns of signals in space and time. Environmental features such as temperature, humidity, and dust density are used to evaluate the impact of environmental conditions on signal propagation. Through the combination of multi-dimensional features, the system can more comprehensively describe the complexity of signal propagation.

[0050] During the feature extraction process, feature selection algorithms are used to identify and screen out the most critical features. Feature selection can not only reduce data redundancy but also improve the generalization ability of the model. Commonly used feature selection methods include correlation-based screening and information gain-based selection, which can help identify features that make significant contributions to signal coverage prediction.

[0051] Through meticulous feature extraction, the system provides high-quality input data for the training of the machine learning model. This process ensures that the model can accurately identify and understand the key factors in signal propagation, thereby improving the accuracy and reliability of signal coverage prediction. The quality of feature extraction directly affects the performance of the model, so the work in this stage requires special attention and optimization.

[0052] 4.3 Model Selection and Training

[0053] After feature extraction is completed, model selection and training are crucial steps in the machine learning process. The goal of this stage is to select an appropriate machine learning algorithm and optimize the model using training data so that it can accurately predict the wireless signal coverage of an intelligent substation.

[0054] First, model selection is determined based on the nature of the feature data and the specific requirements of the task. In the present invention, since signal coverage prediction involves complex non-linear relationships and multi-dimensional features, algorithms such as support vector machine (SVM), random forest (RF), and deep neural network (DNN) are preferred choices. Support vector machine is suitable for dealing with non-linear classification problems in high-dimensional spaces, while random forest improves the stability and accuracy of the model through the method of ensemble learning. Deep neural networks can capture complex patterns and feature interactions in the data through multi-level neuron connections.

[0055] Once the appropriate algorithm is selected, model training begins. The training process uses the previously extracted feature vectors and the corresponding signal coverage labels as input and output. To improve the performance of the model, parameter adjustment (such as learning rate, regularization parameter, etc.) is required during the training process to optimize the prediction ability of the model. Usually, hyperparameter tuning is performed through methods such as grid search or random search to find the optimal parameter combination.

[0056] During the training process, the model continuously adjusts its internal parameters to minimize the prediction error. Through repeated iterations, the model gradually learns the complex patterns in the data and the characteristics of signal propagation. The training dataset is usually divided into a training set and a validation set to evaluate the performance of the model in real-time during the training process and prevent overfitting.

[0057] The core of the entire model selection and training process lies in ensuring that the model can accurately predict the wireless signal coverage under different environmental conditions and device states. By selecting a suitable algorithm and a refined training process, the model can achieve efficient signal coverage prediction in a complex substation environment, providing a solid foundation for subsequent real-time prediction and optimization.

[0058] 4.4 Model Validation and Calibration

[0059] After completing model selection and training, model validation and calibration are important steps to ensure the reliability and accuracy of the model. The purpose of this stage is to evaluate the performance of the model on unseen data and improve the adaptability of the model to the actual application scenario through calibration.

[0060] First, model validation is carried out through techniques such as cross-validation. Cross-validation is a commonly used model evaluation method. It divides the dataset into multiple mutually exclusive subsets, and cyclically uses one subset as the validation set and the other subsets as the training set for multiple trainings and validations to evaluate the stability and generalization ability of the model. Specifically, k-fold cross-validation is relatively commonly used, where the data is divided into k subsets, and the model will be trained k times, each time using a different subset as the validation set and the rest as the training set. Through this method, the dependence of the model on a specific dataset can be effectively reduced, and a more comprehensive evaluation of the model performance can be obtained.

[0061] During the validation process, the prediction performance of the model is evaluated through a series of metrics, such as accuracy, mean squared error (MSE), F1-score, etc. These metrics help identify the performance differences of the model under different feature combinations and environmental conditions, and then guide the further optimization of the model.

[0062] Calibration is an important step after validation, especially when the model needs to make predictions under different environmental conditions and transformer states. The purpose of calibration is to adjust the model so that its sensitivity to different input conditions remains consistent. Specific methods include adjusting the output probability of the model to make it more accurately reflect the actual signal coverage probability. This may involve readjusting the parameters of the output layer of the model or post-processing the model to ensure the consistency between the confidence of its output and the actual observations.

[0063] Through model validation and calibration, it is ensured that the model not only performs well on the training data but also can accurately predict the signal coverage range in actual applications. This process improves the adaptability of the model in the complex environment of the substation, ensuring its robustness and reliability under different equipment states and environmental conditions. Finally, the validated and calibrated model provides a solid foundation for real-time signal coverage prediction, which can support network optimization and decision-making in intelligent substations.

[0064] 4.5 Real-time Prediction and Adjustment

[0065] After the model is validated and calibrated, real-time prediction and adjustment are the key steps to achieve dynamic analysis of the wireless signal coverage range in intelligent substations. The core of this stage lies in using the trained model to process real-time input data and making prediction adjustments according to the changing environment and equipment states to provide continuous and accurate signal coverage predictions.

[0066] First, real-time prediction utilizes the substation data collected in real time, including the current status of transformers (such as load, temperature), signal strength, and environmental data (such as temperature, humidity, dust density), etc. These data are input into a trained and calibrated model, and the model outputs the prediction results of the signal coverage range within a short time. By quickly processing this real-time data, the system can dynamically analyze the wireless network situation within the substation.

[0067] During the real-time prediction process, considering the changes in environmental conditions and equipment status, the model needs to have the ability to dynamically adjust. Specifically, when significant changes in transformer load or environmental conditions are detected, the model will adjust its internal parameters according to these changes to ensure the accuracy of the prediction results. This adjustment can be achieved through online learning or incremental learning techniques, enabling the model to gradually optimize its performance during uninterrupted operation.

[0068] In addition, the results of real-time prediction will be continuously monitored and evaluated to ensure that the output signal coverage range conforms to the actual observed data. When there is a deviation between the prediction results and the actual situation, the system will trigger an alarm and recommend recalibrating or training the model to maintain the high accuracy and reliability of the prediction.

[0069] Through real-time prediction and adjustment, the system can provide accurate signal coverage prediction under changing environmental and equipment conditions. This not only helps optimize the installation and configuration of equipment within the substation but also provides decision-making support for operators to ensure the efficient operation of the wireless network and the improvement of service quality. Ultimately, real-time prediction and adjustment provide a flexible and powerful tool for the network management of intelligent substations, capable of coping with complex and changing practical application scenarios.

[0070] 5. Signal Coverage Prediction and Optimization

[0071] After completing real-time prediction and adjustment, signal coverage prediction and optimization are key steps to ensure the efficient operation of the wireless network within the intelligent substation. The goal of this stage is to utilize the optimized machine learning model to continuously predict the signal coverage situation and perform optimized adjustment of network configuration and resources according to the prediction results.

[0072] First, signal coverage prediction is based on the real-time input data. The system uses the previously trained and calibrated model, combined with the current environmental parameters and equipment status (such as the load, temperature of the transformer, etc.), to generate a signal coverage map within a specific area. These prediction results can help identify areas with insufficient or excessive signal strength, thereby providing data support for further optimization.

[0073] While performing signal coverage prediction, the optimization process is also carried out simultaneously. The system analyzes the prediction results to identify bottlenecks and potential problems in the network. For example, signal coverage may be poor in certain areas due to equipment obstruction or environmental interference. In response to these problems, the system will provide specific optimization suggestions.

[0074] Optimization measures may include adjusting the equipment installation location, reconfiguring wireless access points, or selecting a more suitable carrier service. These adjustments are aimed at improving the signal propagation path and coverage area to ensure that all critical areas within the substation can obtain stable and high-quality wireless network services.

[0075] In addition, the system continuously evaluates the effectiveness of the optimization measures through a feedback mechanism. By comparing the signal coverage before and after optimization, the system can judge the effectiveness of the measures taken and make further adjustments and improvements based on the actual results. This closed-loop optimization mechanism ensures the continuous improvement of signal coverage and the efficient utilization of network resources.

[0076] Through signal coverage prediction and optimization, intelligent substations can achieve active management and dynamic optimization of wireless networks. This not only improves the accuracy and stability of signal coverage but also provides strong support for the safe operation and daily management of substations. Ultimately, this process lays the foundation for efficient communication and reliable services within intelligent substations.

[0077] 6. Display and Decision Support

[0078] After signal coverage prediction and optimization are completed, display and decision support are important links in transforming technical achievements into practical applications. The core of this stage lies in displaying the signal coverage situation through visualization means and providing scientific decision support for the network planning and management of substations.

[0079] First of all, in the display stage, Geographic Information System (GIS) technology is used to present the predicted signal coverage range in an intuitive map form. By combining the geographical location and equipment layout of the substation, the generated signal coverage map can clearly mark the signal strength and coverage quality of each area. This visual display not only facilitates technicians to quickly identify signal blind spots and weak coverage areas but also helps management intuitively understand the overall operation status of the network.

[0080] During the display process, the system will also attach relevant environmental and equipment status information, such as the load condition of transformers, environmental temperature and humidity, etc. Combining this information with the signal coverage map can provide more comprehensive background information to help users understand the dynamic changes of signal coverage and potential influencing factors.

[0081] Decision support is a further extension of the display, aiming to provide a scientific basis for network optimization and resource allocation in substations. Based on signal coverage prediction and optimization results, the system generates a series of data-driven suggestions and solutions. For example, the system may recommend reconfiguring the positions of certain devices, increasing or decreasing access points, or adjusting operator settings to improve network service quality.

[0082] In addition, the system also provides effect prediction and cost analysis of different optimization solutions to help decision-makers weigh and choose among multiple strategies. By simulating the implementation effects of different solutions, the system can provide the optimal decision-making path for management to ensure the efficient allocation and use of network resources.

[0083] The ultimate goal of the display and decision support is to transform complex technical data into a management tool that is easy to understand and operate, helping the substation achieve intelligent management and optimization of the network. This process not only improves the communication service quality of the substation but also provides a solid technical guarantee for its safe, stable, and efficient operation. Through effective display and decision support, the intelligent substation can maintain the best state and performance in daily operations.

[0084] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of this technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should fall within the protection scope of the present invention.

Claims

1. A method for analyzing and detecting the coverage of wireless network signals in smart substations, characterized in that: The method comprises: Collect substation equipment data and combine it with power GIS information to obtain the geographic location of the equipment; Collect substation environmental data, build a relationship diagram of adjacent sites, and perform signal feature analysis based on the substation environmental data; build a machine learning model based on transformer data to predict and optimize signal coverage; Combined with GIS data, it displays signal coverage and provides optimization suggestions.

2. A method for analyzing and detecting the coverage range of wireless network signals in a smart substation according to claim 1, characterized in that: The method exports the existing power terminal installation point information and signal strength data through the terminal network management system, associates the terminal geographical location information with the power GIS data, and uses special equipment to dynamically collect the real-time signal strength and geographical location information related parameters of the wireless access point.

3. The method for analyzing and detecting the coverage range of wireless network signals in a smart substation according to claim 1, characterized in that: The method determines the adjacent sites of each site according to the geographical location information of the base station or the wireless access point, and constructs an adjacent site relationship diagram.

4. A method for analyzing and detecting the coverage of wireless network signals in smart substations according to claim 1 or 3, characterized in that: The method performs signal feature analysis based on substation environment data and the adjacent site relationship diagram.

5. A method for analyzing and detecting the coverage range of wireless network signals in a smart substation according to claim 4, characterized in that: The method extracts signal strength, interference, and time series features, establishes a loss model, and calculates eccentricity values.

6. The method for analyzing and detecting the coverage range of wireless network signals in a smart substation according to claim 1, characterized in that: The method collects transformer status data and integrates it with signal strength and environmental data, trains the model through a support vector machine or a random forest algorithm, and adjusts the model parameters.

7. A method for analyzing and detecting the coverage of wireless network signals in a smart substation according to claim 1 or 6, characterized in that: The method is cross-validated to calibrate the model's sensitivity to transformer state changes.

8. A method for analyzing and detecting the coverage of wireless network signals in a smart substation according to claim 1 or 7, characterized in that: In the process of machine learning, the method inputs transformer status data in real time to perform signal coverage prediction and dynamically adjusts model prediction.

9. The method for analyzing and detecting the coverage range of wireless network signals in a smart substation according to claim 1, characterized in that: The method combines GIS data to display signal coverage, providing intuitive decision support for network planning and optimization of substations.

10. A method for analyzing and detecting the coverage of wireless network signals in a smart substation according to claim 1 or 9, characterized in that: The method optimizes equipment installation location and operator selection according to the prediction results.

Images