Electric energy quality monitoring system

Abstract

The invention relates to an electric energy quality monitoring system in the technical field of electric energy quality monitoring, and the system comprises a distributed processing and storage module which is used for carrying out the distributed processing and storage of collected electric energy quality data; the sensor network comprises a plurality of sensor nodes and is connected with the central processing module through a wireless communication protocol; the central processing module comprises a data screening unit, a data classification unit and a data transmission unit and is used for receiving the data from the sensor network, screening and classifying the data and then sending the data to the distributed processing and storage module; the method has high-efficiency data processing capability and expandability, and adapts to the increasing demand of future data volume; the reliability and the maintenance efficiency of the system are enhanced, and the requirement of manual inspection is reduced; accurate data analysis and prediction are provided, and the early warning capability and the decision support level are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power quality monitoring, and in particular, to a power quality monitoring system. Background Art

[0002] With the increasing complexity of power systems and the popularization of distributed energy systems, the requirements for power quality monitoring are getting higher and higher. Traditional monitoring methods usually rely on limited monitoring points and manual data analysis, which are inefficient and difficult to capture power quality problems accurately and in real time. In addition, traditional methods have insufficient processing capabilities when facing large-scale data sets and lack an effective fault self-diagnosis mechanism, resulting in high maintenance costs. At the same time, data security and privacy protection have also become important issues. Summary of the Invention

[0003] In order to overcome the deficiencies in the background art, the present invention discloses a power quality monitoring system.

[0004] To achieve the above-mentioned invention purpose, the present invention adopts the following technical solutions: A power quality monitoring system, comprising: A distributed processing and storage module for performing distributed processing and storage on the collected power quality data; A sensor network including multiple sensor nodes connected to a central processing module through a wireless communication protocol; A central processing module, including a data screening unit, a data classification unit, and a data transmission unit, for receiving data from the sensor network, screening and classifying it, and then sending it to the distributed processing and storage module; A data analysis module that uses machine learning algorithms to deeply analyze the data stored in the distributed processing and storage module, predict potential power quality problems, and provide optimization suggestions; A user interaction and visualization module, including an augmented reality application programming interface and personalized dashboard settings, to provide users with an intuitive data view and alarm settings; A security protection module that uses blockchain technology and a multi-level security protection system to ensure the data security and immutability of the system.

[0005] Preferably, each sensor node has a self-diagnosis function to facilitate automatic detection of faults and reporting to the central processing module.

[0006] Preferably, the distributed processing and storage module uses the Hadoop or Spark framework to implement data processing and storage.

[0007] Preferably, the data screening unit includes: A denoising processing unit for filtering the received data to remove noise interference; An outlier detection unit that identifies and eliminates outliers using statistical methods or machine learning algorithms; A threshold filtering unit that sets upper and lower threshold values for various power quality parameters according to preset criteria and marks data outside the threshold range as potential problem data.

[0008] Preferably, the data classification unit includes: A feature extraction unit that extracts key features from the original data; A rule matching unit that classifies the extracted features according to a predefined rule library; A model prediction unit that classifies data using a trained machine learning model.

[0009] Preferably, the data analysis module further includes a dynamic load balancing unit for adjusting the workload of different nodes according to the real-time workload.

[0010] A monitoring method for a power quality monitoring system includes the following steps: Step 1: Use multiple sensor nodes in the sensor network to collect power quality data in real time and transmit the data to the central processing module through a wireless communication protocol; Step 2: The central processing module receives and processes the data, specifically including: Use a denoising processing unit to filter the received data to remove noise interference; Use the outlier detection unit to identify and eliminate outliers; Set upper and lower threshold values for various power quality parameters according to preset criteria through the threshold filtering unit and mark data outside the threshold range as potential problem data; Extract the key features of the data and classify the data according to a predefined rule library and a trained machine learning model; Step 3: Send the classified data to the distributed processing and storage module for storage, and use machine learning algorithms by the data analysis module for in-depth analysis, predict potential power quality problems, and generate optimization suggestions; Step 4: The user obtains a real-time data view and alarm information through the user interaction and visualization module and adjusts the monitoring parameters as needed; Step 5: The security protection module ensures the data security and immutability of the entire system, preventing external attacks and data leakage.

[0011] Preferably, in Step 2, the data classification unit includes a feature extraction unit, a rule matching unit, and a model prediction unit, which are respectively used to extract key features from the original data, classify the extracted features according to a predefined rule library, and classify the data using a trained machine learning model.

[0012] Preferably, in step three, the data analysis module further includes a dynamic load balancing unit for adjusting the workload of different nodes according to the real-time workload to ensure the efficient operation of the system.

[0013] Preferably, in step four, the augmented reality application interface provided by the user interaction and visualization module allows users to view the power grid status and historical data trends through mobile devices.

[0014] Due to the adoption of the above-mentioned technical solutions, the present invention has the following beneficial effects: high-efficient data processing capabilities and scalability to adapt to the future growth demand of data volume; enhanced system reliability and maintenance efficiency, reducing the need for manual inspections; providing accurate data analysis and prediction, improving the early warning ability and decision-making support level; dynamic load balancing ensures the efficient operation of the system, maximizing the utilization of system resources; user-friendly interaction experience, enhancing the user experience; strengthening data security protection, effectively preventing external attacks and data leakage. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a structural schematic block diagram of the present invention; Figure 2 It is a schematic block diagram of the central processing module in the present invention.

[0016] In the figure: 100, distributed processing and storage module; 200, sensor network; 210, sensor node; 300, central processing module; 310, data screening unit; 311, denoising processing unit; 312, outlier detection unit; 313, threshold filtering unit; 320, data classification unit; 321, feature extraction unit; 322, rule matching unit; 323, model prediction unit; 330, data transmission unit; 400, data analysis module; 410, dynamic load balancing unit; 500, user interaction and visualization module; 600, security protection module. DETAILED DESCRIPTION OF THE INVENTION

[0017] The present invention can be explained in detail through the following embodiments. The purpose of disclosing the present invention is to protect all technical improvements within the scope of the present invention. In the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "front", "rear", "left", "right", etc. indicating the orientation or positional relationship, it is only corresponding to the drawings of the present application for the convenience of describing the present invention; it should be understood that if there are terms such as "end", "side", "end part", "side part", "lateral", "longitudinal", etc. indicating the orientation or positional relationship, it is only corresponding to the length and width of the corresponding component, that is, the "end part" indicates the head and tail regions in the length direction of the corresponding component, and the "side part" indicates the head and tail regions in the width direction of the corresponding component; it is for the convenience of describing the present invention rather than indicating or implying that the device or element referred to must have a specific orientation.

[0018] Example 1, in combination with the attached Figure 1-2 , a power quality monitoring system, includes a distributed processing and storage module 100, a sensor network 200, a central processing module 300, a data analysis module 400, a user interaction and visualization module 500, and a security protection module 600; that is, through the integration of components such as distributed processing and storage, the sensor network 200, and the central processing module 300, an efficient and reliable power quality monitoring system is formed. According to needs, each module is developed independently and integrated through interfaces, which is convenient for maintenance and upgrade, enhancing the flexibility and scalability of the system.

[0019] Among them: The distributed processing and storage module 100 is used for distributed processing and storage of the collected power quality data; According to needs, the distributed processing and storage module 100 uses the Hadoop or Spark framework to implement data processing and storage; specifically, it is selected according to actual needs, and no specific limitation is made here; that is, by using distributed computing frameworks such as Hadoop or Spark, the system can efficiently process large-scale data sets, improving the data processing speed and system scalability, and can dynamically expand resources according to needs to adapt to the future growth of data volume, ensuring the long-term availability of the system.

[0020] The sensor network 200 includes multiple sensor nodes 210, which are connected to the central processing module 300 through a wireless communication protocol; According to needs, each sensor node 210 has a self-diagnosis function to facilitate automatic detection of faults and reporting to the central processing module 300; that is, the self-diagnosis function can automatically detect the faults of the sensor nodes 210 and report them to the central processing module 300 in a timely manner, reducing the need for manual inspection, improving the reliability and maintenance efficiency of the system; at the same time, once a fault is detected, the system can immediately take measures for repair or adjustment to avoid data loss or errors caused by the fault.

[0021] The central processing module 300, including a data screening unit 310, a data classification unit 320, and a data transmission unit 330, is used to receive data from the sensor network 200, screen and classify it, and then send it to the distributed processing and storage module 100; Furthermore, the data classification unit 320 includes a feature extraction unit 321, a rule matching unit 322, and a model prediction unit 323, which are respectively used to extract key features from the original data, classify the extracted features according to a predefined rule library, and classify the data using a trained machine learning model. By filtering the original data, detecting outliers, and filtering by thresholds, the accuracy and consistency of the data are ensured, providing a high-quality data basis for subsequent analysis. Also, by removing noise interference and eliminating outliers, the possibility of false alarms is reduced, and the credibility of the system is improved.

[0022] The data analysis module 400 uses machine learning algorithms to deeply analyze the data stored in the distributed processing and storage module 100, predict potential power quality problems, and provide optimization suggestions; As needed, the data analysis module 400 further includes a dynamic load balancing unit 410, which is used to adjust the workload of different nodes according to the real-time workload; that is, through dynamic load balancing technology, the workload of different nodes can be adjusted according to the real-time workload, avoiding the situation where some nodes are overloaded while others are idle, ensuring the efficient operation of the system, achieving reasonable allocation of computing resources, maximizing the use of system resources, and improving the overall performance and response speed.

[0023] As needed, the machine learning methods in the machine learning model: can be supervised learning, such as random forest, gradient boosting decision tree (GBDT), etc., which are suitable for labeled data sets and can be used for anomaly detection and classification tasks. It can also be unsupervised learning, such as K-means clustering, autoencoders, etc., which are suitable for exploratory data analysis and pattern discovery of unlabeled data. It can also be deep learning, such as convolutional neural network (CNN), recurrent neural network (RNN), which are particularly suitable for complex pattern recognition and time series data analysis. Specific selection is made according to actual needs and is not specifically limited here.

[0024] It should be noted that: the machine learning model is mainly applied to the automatic classification of data, the prediction of potential problems, and the generation of optimization suggestions, aiming to improve the accuracy and efficiency of monitoring.

[0025] The user interaction and visualization module 500, including an augmented reality application programming interface and personalized dashboard settings, provides users with an intuitive data view and alarm settings; The security protection module 600 adopts blockchain technology and a multi-level security protection system to ensure the data security and immutability of the system.

[0026] Specifically, the monitoring method of the power quality monitoring system includes the following steps: Step 1: Use multiple sensor nodes 210 in the sensor network 200 to collect power quality data in real time, and transmit the data to the central processing module 300 through a wireless communication protocol; Step 2: The central processing module 300 receives and processes the data, specifically including: Use the denoising processing unit 311 to filter the received data to remove noise interference; Use the outlier detection unit 312 to identify and remove outliers; Set the upper and lower limit thresholds of various power quality parameters according to preset standards through the threshold filtering unit 313, and mark the data outside the threshold range as potential problem data; Extract the key features of the data, and classify the data according to a predefined rule base and a trained machine learning model; Step 3: Send the classified data to the distributed processing and storage module 100 for storage, and the data analysis module 400 uses machine learning algorithms for in-depth analysis, predicts potential power quality problems, and generates optimization suggestions; Step 4: The user obtains a real-time data view and alarm information through the user interaction and visualization module 500, and adjusts the monitoring parameters as needed; Step 5: The security protection module 600 ensures the data security and immutability of the entire system, preventing external attacks and data leakage.

[0027] This method covers the entire process of power quality monitoring from data collection to final security protection, ensuring the effective connection and collaborative work of each link. It not only pays attention to the accuracy and real-time nature of the data, but also focuses on the user interaction experience and the security of the system, providing all-round protection; and through the combination of feature extraction, rule matching and model prediction, it realizes more accurate data classification and problem identification, improves the analysis ability of the system, and at the same time combines machine learning algorithms, the system can automatically generate classification results, reducing manual intervention and improving work efficiency.

[0028] The parts not detailed in the present invention are prior arts. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, aiming to include all changes falling within the meaning and scope of equivalent elements in the present invention.

Claims

1. A power quality monitoring system, characterized in that: include: A distributed processing and storage module (100) is used to perform distributed processing and storage on the collected power quality data; A sensor network (200) comprising a plurality of sensor nodes (210) connected to a central processing module (300) via a wireless communication protocol; The central processing module (300) comprises a data screening unit (310), a data classification unit (320) and a data transmission unit (330), and is used to receive data from the sensor network (200), screen and classify the data, and then send the data to the distributed processing and storage module (100); A data analysis module (400) uses a machine learning algorithm to perform in-depth analysis on the data stored in the distributed processing and storage module (100), predict potential power quality problems, and provide optimization suggestions; A user interaction and visualization module (500), including an augmented reality application program interface and a personalized dashboard setting, providing users with intuitive data views and alarm settings; The security protection module (600) uses blockchain technology and a multi-level security protection system to ensure the data security and non-tamperability of the system.

2. The power quality monitoring system according to claim 1, characterized in that: Each sensor node (210) has a self-diagnosis function so as to automatically detect faults and report them to the central processing module (300).

3. The power quality monitoring system according to claim 1, characterized in that: The distributed processing and storage module (100) uses Hadoop or Spark framework to implement data processing and storage.

4. The power quality monitoring system according to claim 1, characterized in that: The data screening unit (310) comprises: A denoising processing unit (311) is used to filter the received data to remove noise interference; An outlier detection unit (312) uses a statistical method or a machine learning algorithm to identify and remove outliers; The threshold filtering unit (313) sets upper and lower thresholds of various power quality parameters according to preset standards, and marks data exceeding the threshold range as potential problem data.

5. The power quality monitoring system according to claim 1, characterized in that: The data classification unit (320) comprises: A feature extraction unit (321) extracts key features from the original data; A rule matching unit (322) classifies the extracted features according to a predefined rule base; The model prediction unit (323) uses the trained machine learning model to classify the data.

6. The power quality monitoring system according to claim 1, characterized in that: The data analysis module (400) further comprises a dynamic load balancing unit (410) for adjusting the workload of different nodes according to the real-time workload.

7. The power quality monitoring system according to claim 1, characterized in that: The monitoring method of the power quality monitoring system comprises the following steps: Step 1: using a plurality of sensor nodes (210) in a sensor network (200) to collect power quality data in real time, and transmitting the data to a central processing module (300) via a wireless communication protocol; Step 2: The central processing module (300) receives and processes the data, specifically including: Using a denoising processing unit (311) to filter the received data to remove noise interference; Using an outlier detection unit (312) to identify and remove outliers; The threshold filtering unit (313) sets upper and lower thresholds of various power quality parameters according to preset standards, and marks data exceeding the threshold range as potential problem data; Extract key features of data and classify the data based on predefined rule base and trained machine learning models; Step 3: Send the classified data to the distributed processing and storage module (100) for storage, and the data analysis module (400) uses a machine learning algorithm to perform in-depth analysis to predict potential power quality issues and generate optimization suggestions; Step 4: The user obtains real-time data view and alarm information through the user interaction and visualization module (500), and adjusts monitoring parameters as needed; Step 5: The security protection module (600) ensures the data security and non-tamperability of the entire system, and prevents external attacks and data leakage.

8. The power quality monitoring system according to claim 7, characterized in that: In step 2, the data classification unit (320) includes a feature extraction unit (321), a rule matching unit (322) and a model prediction unit (323), which are respectively used to extract key features from raw data, classify the extracted features according to a predefined rule base, and classify the data using a trained machine learning model.

9. The power quality monitoring system according to claim 7, characterized in that: In step three, the data analysis module (400) further includes a dynamic load balancing unit (410) for adjusting the workload of different nodes according to the real-time workload to ensure efficient operation of the system.

10. The power quality monitoring system according to claim 7, characterized in that: In step 4, the augmented reality application program interface provided by the user interaction and visualization module (500) allows the user to view the power grid status and historical data trends through a mobile device.

Images