Electric energy quality control system based on big data analysis

Abstract

The invention relates to the technical field of electric energy quality control, and discloses an electric energy quality control system based on big data analysis, which captures electric energy quality data such as voltage, current, frequency, harmonic waves and the like at any time without fear of complex electromagnetic interference. Various communication modes such as wired, 4G, 5G or industrial Internet of Things special frequency bands are utilized, a high-speed reliable protocol is followed, and collected data are accurately delivered to a big data processing center in real time. The big data processing center simulates a smart brain, stores mass data, deeply digs the electric energy quality problem by means of an analysis processor of advanced algorithms such as a decision tree and the like, and can dynamically and adaptively adjust algorithm parameters according to real-time operation of a power grid. And finally, the control decision is tightly linked with the execution module. The system has the advantages of accurate monitoring and comprehensive control, intelligent analysis and adaptive decision making, efficient regulation and control, energy conservation and efficiency improvement, visual interaction, convenient operation and maintenance, reliable operation and safety guarantee.

Description

Technical Field

[0001] The present invention relates to the technical field of power quality control, and in particular to a power quality control system based on big data analysis. Background Art

[0002] With the rapid development of modern industry and the widespread application of various new power electronic equipment, the power quality problem in the power grid has become increasingly prominent. Traditional power quality monitoring and control methods can no longer meet the increasingly complex power grid operation needs. In the past, power grid operation and maintenance personnel mainly relied on regular inspections and some simple monitoring instruments to obtain power quality information. This method is not only inefficient, but also the data obtained is extremely limited, and it cannot fully reflect the actual power quality status of the power grid in different periods and regions. For example, for some intermittent harmonic interference problems, traditional manual inspections are difficult to capture their occurrence patterns, and problems are often discovered only after the electrical equipment has been damaged.

[0003] At the same time, due to the lack of effective analysis methods for a large amount of historical data, it is difficult to grasp the changing trend of power quality from a macro perspective, and it is impossible to predict potential power quality risks in advance. Moreover, when facing power quality problems, the previous control strategies were mostly fixed modes, and did not fully consider factors such as the real-time load changes of the power grid and the peak and valley characteristics of electricity consumption. This led to over-compensation or under-compensation in the process of implementing power quality control, which not only wasted energy, but also failed to effectively solve the power quality problem, affecting the stability of industrial production and the electricity experience of residents. Furthermore, the power grid structure and power load characteristics in different regions vary greatly, and the traditional unified control method cannot accurately optimize the power quality according to local conditions. For example, in some areas dominated by heavy industry, high-power motors are frequently started and stopped, generating a large number of harmonics and voltage fluctuations, and targeted filtering and voltage regulation measures need to be strengthened; in some commercial center areas, inductive loads such as lighting and air conditioning are concentrated, and reactive power demand varies greatly, requiring extremely high timeliness and accuracy of reactive power compensation.

[0004] To sum up, there is an urgent need for a system that can collect power quality data in real time and comprehensively, deeply mine and analyze the laws behind the data, and flexibly and accurately adjust the power quality according to the analysis results to ensure the safe, stable and efficient operation of the power grid. This is exactly the key problem that the power quality control system based on big data analysis of the present invention is to solve. Summary of the invention

[0005] In order to solve the above-mentioned problems, the present invention proposes a power quality control system based on big data analysis.

[0006] In order to solve the above technical problems, the technical solution proposed by the present invention is: a power quality control system based on big data analysis, comprising:

[0007] A data acquisition module is used to collect power quality data in the power grid in real time. The power quality data includes at least voltage, current, frequency, and harmonic content information. The data acquisition module is connected to a plurality of sensors distributed at different positions in the power grid. The sensors are high-precision, anti-interference sensors that can adapt to complex electromagnetic environments.

[0008] A data transmission module is used to transmit the collected power quality data to a big data processing center. The data transmission module supports wired and wireless transmission modes and adopts a high-speed and reliable communication protocol to ensure the real-time and accuracy of data transmission. The wireless transmission mode includes but is not limited to 4G, 5G or industrial Internet of Things dedicated frequency band communication;

[0009] A big data processing center is configured with a big data storage device and a data analysis processor. The big data storage device is used to store massive historical power quality data and real-time collected data. The data analysis processor runs power quality analysis software based on a machine learning algorithm for in-depth mining and analysis of power quality data to identify abnormal patterns and potential problems of power quality. The machine learning algorithm includes but is not limited to a decision tree, a neural network, and a support vector machine algorithm, and can adaptively adjust algorithm parameters according to the operation status of the power grid;

[0010] A control decision module is connected to the big data processing center and generates control instructions based on the analysis results of the big data processing center. The control instructions are used to adjust the operating status of the power equipment in the power grid. The control decision module has a variety of preset control strategy templates built in, which can automatically match the best control strategy according to different types of power quality problems;

[0011] The execution module receives the control instructions issued by the control decision module and acts on the reactive compensation device, filter, voltage regulator and other power equipment in the power grid to achieve real-time control of power quality. The execution module has a feedback function and can transmit the execution result information back to the big data processing center to evaluate and optimize the control effect.

[0012] Preferably, the sensors in the data acquisition module have a self-diagnosis function and can monitor their own working status in real time. Once a fault or abnormality is found, an alarm message is automatically sent to the big data processing center, and a backup sensor is started to take over the work to ensure the continuity of data acquisition.

[0013] Preferably, the big data processing center is also connected to a visualization display terminal, which presents the analysis results of the power quality data, the power grid operation status and the control effect in an intuitive form of charts, curves and maps for real-time monitoring by operation and maintenance personnel. The visualization display terminal supports human-computer interaction, and the operation and maintenance personnel can perform data query and parameter setting operations by touch and gesture.

[0014] Preferably, when generating control instructions, the control decision module fully considers the load changes of the power grid and the peak and valley period factors of electricity consumption, and adopts a dynamic optimization algorithm to adjust the control strategy in real time to achieve economy and efficiency in power quality regulation.

[0015] Preferably, the system also includes a prediction module connected to the big data processing center, which uses time series analysis and deep learning prediction models based on historical power quality data and real-time data to predict the trend of power quality changes in the future, and provide early warning information for power grid operation and maintenance in advance so that preventive measures can be taken in advance.

[0016] Preferably, the connection between the execution module and the power equipment adopts an intelligent interface, which can automatically identify the type, model, and operating parameters of the power equipment, realize fast and accurate control command transmission, and reduce control delays. At the same time, the intelligent interface has an electrical isolation function to ensure the safety of the system.

[0017] Preferably, the big data processing center has a data encryption and security protection mechanism, and adopts a combination of symmetric encryption and asymmetric encryption to encrypt, store and transmit the power quality data to prevent data leakage. At the same time, firewalls and intrusion detection system security protection measures are set up to resist external network attacks and ensure the stable operation of the system.

[0018] Compared with the prior art, the present invention has the following advantages:

[0019] Accurate monitoring and comprehensive control: With widely distributed high-precision sensors and the processing of massive data by big data centers, the system can accurately obtain power quality information in every corner of the power grid in real time, breaking through traditional limitations. Short-term voltage flickers and hidden harmonics can be captured. Operation and maintenance personnel can use this to fully understand the power quality and detect hidden dangers in advance.

[0020] Intelligent analysis and adaptive decision-making: Relying on advanced machine learning algorithms, the system automatically learns the laws of power quality changes and identifies abnormal patterns. Unlike traditional fixed judgments, it can dynamically adjust according to the real-time load and peak-valley switching of the power grid to ensure accurate problem judgment. The control decision module can quickly match the optimal strategy based on this and enhance the targetedness of regulation.

[0021] Efficient regulation and energy saving: The execution and control decision modules work together to quickly execute optimization instructions to power equipment, dynamically adjust the power grid based on grid load and time characteristics, avoid overcompensation, reasonably allocate reactive power, filter harmonics, stabilize voltage, improve power utilization efficiency, help enterprises save energy, and ensure stable electricity consumption for residents.

[0022] Visual interaction and convenient operation and maintenance: The big data processing center is connected to the visual display terminal to intuitively present the power quality, power grid status and regulation effects with charts, etc., so that operation and maintenance personnel can see key information at a glance. It supports human-computer interaction, facilitates query and adjustment of parameters, and non-professionals can also easily assist in decision-making.

[0023] Reliable operation and safety assurance: The data acquisition module sensor self-diagnosis and the big data center encryption protection mechanism ensure the stability of the system from hardware to data core. Sensor self-diagnosis ensures continuous data collection, encrypted transmission and firewalls prevent leakage and attacks, create a safe environment, and prevent power grid accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a principle flow chart of a power quality control system based on big data analysis of the present invention. DETAILED DESCRIPTION

[0025] The present invention is further described in detail below with reference to the accompanying drawings.

[0026] Example 1

[0027] Power quality optimization in industrial plants

[0028] In a large industrial plant mainly engaged in mechanical manufacturing, there are a large number of high-power electrical equipment such as machine tools, welding machines, cranes, etc. These equipment are frequently started and stopped during operation, generating strong harmonic interference and causing large fluctuations in the grid voltage, seriously affecting the normal operation of other precision production equipment and product quality.

[0029] The power quality control system of the present invention plays a full role in this scenario. First, the data acquisition module installs high-precision, anti-interference sensors at key nodes such as the power distribution room in the factory area and the power distribution cabinet of the main production line to collect power quality data such as voltage, current, and harmonics in real time. For example, at the power distribution cabinet in the welding workshop where electric welding machines are concentrated, the sensor accurately captures the current spikes and the accompanying high-order harmonics caused by each welding moment, and the data is quickly transmitted to the big data processing center through the 5G wireless transmission module. The big data processing center stores massive historical data, including the power quality conditions under different production shifts and different equipment combinations. Its data analysis processor runs a neural network algorithm, and after learning long-term data, it identifies that whenever several large machine tools are started at the same time, a harmonic resonance of a specific frequency will be triggered, resulting in an abnormal mode of a sudden drop in the local power grid voltage. Based on the analysis results, the control decision module selects strategies for harmonic suppression and voltage regulation from the built-in control strategy template to generate control instructions. After receiving the instruction, the execution module drives the active filter installed in the factory power grid to start, accurately filter out specific harmonics, and adjust the reactive compensation device to stabilize the power grid voltage. During an actual production process, the system detected that due to the commissioning of a new production line, the harmonic content of the power grid increased sharply and the voltage fluctuation exceeded the allowable range. The system responded quickly and completed the regulation in just a few minutes, reducing the harmonic distortion rate from more than 15% to less than 5%, and stabilizing the voltage fluctuation within ±3%, ensuring the normal operation of the production equipment in the entire factory area. The defective rate was reduced by about 10% due to the improvement of power quality.

[0030] Example 2

[0031] Power supply guarantee for commercial complexes

[0032] A prosperous commercial complex houses many businesses, including shopping malls, restaurants, cinemas, office buildings, etc. During the day, a large number of inductive loads such as lighting, air conditioning, and elevators are in concentrated operation, and the reactive power demand is huge; at night, as some businesses close, the power load drops sharply, but at the same time, some large advertising screens, server rooms and other equipment continue to operate, the load characteristics change significantly, and the power quality issues are complex and diverse.

[0033] After the deployment of this power quality control system, the sensors of the data acquisition module are distributed throughout the distribution rooms on each floor of the commercial complex and the distribution boxes of key tenants. During the peak period of electricity consumption in summer, the air conditioning system is running at full load. The data acquisition module monitors the voltage drop and the serious shortage of reactive power in real time, and quickly sends the data to the big data processing center through a mixed data transmission method of wired and 4G. The big data processing center uses the decision tree algorithm to analyze historical data and finds that due to the centralized start-up of air conditioners during this period, the reactive power demand can increase by more than 50% in a short period of time, which is very likely to cause the risk of voltage collapse. The control decision module quickly formulates control instructions including emergency reactive compensation input and optimization of voltage regulator parameters. The execution module acts immediately, and the intelligent interface quickly identifies and controls the reactive compensation capacitor groups distributed on each floor to be put into operation, and at the same time adjusts the voltage regulator to increase the bus voltage. After regulation, the voltage qualification rate is increased from less than 80% to more than 95%, effectively avoiding accidents such as elevator sudden stop and damage to merchant electrical equipment caused by power quality problems, ensuring the normal operation of the commercial complex, and reducing the economic losses caused by power outages for merchants by hundreds of thousands of yuan per year.

[0034] Example 3

[0035] Improvement of power quality when renewable energy generation is connected to the grid

[0036] In a new energy grid-connected area that includes wind farms and photovoltaic power stations, new energy power generation is intermittent and highly volatile. A large amount of new energy electricity is injected into the power grid, which brings great challenges to the power quality indicators such as frequency stability and voltage harmonics of the power grid.

[0037] The data acquisition module of this system densely arranges sensors at the grid connection points, collection lines and key nodes of the surrounding power grid of the new energy power station to collect power quality data in all directions. When the wind speed changes suddenly and causes the output power of the wind turbine to fluctuate greatly, the data acquisition module quickly captures the abnormal changes in voltage and frequency, and transmits the data to the big data processing center through the dedicated frequency band of the industrial Internet of Things. The big data processing center uses the support vector machine algorithm combined with massive historical meteorological data and power generation data to analyze and predict the impact trend of the current new energy power generation fluctuations on the power quality of the power grid. Based on this, the control decision module formulates a comprehensive control strategy including energy storage system charging and discharging control, dynamic reactive compensation adjustment and harmonic control. On the one hand, the execution module controls the energy storage system to respond quickly, stores electricity when there is excess power generation, releases electricity when there is insufficient power generation, and stabilizes the frequency of the power grid; on the other hand, it accurately adjusts the reactive compensation device and filter to suppress harmonics and maintain voltage stability. For example, during a period of strong winds, the wind power generation output fluctuated by more than 60% within half an hour. The system successfully controlled the grid frequency deviation within ±0.1Hz and maintained the voltage harmonic distortion rate below the national standard through a series of control measures, ensuring the reliable grid connection of new energy electricity and the stable operation of surrounding power grids, and providing a solid power quality assurance foundation for large-scale access of new energy to the power grid.

[0038] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A power quality control system based on big data analysis, characterized in that: include: A data acquisition module is used to collect power quality data in the power grid in real time. The power quality data includes at least voltage, current, frequency, and harmonic content information. The data acquisition module is connected to a plurality of sensors distributed at different positions in the power grid. The sensors are high-precision, anti-interference sensors that can adapt to complex electromagnetic environments. A data transmission module is used to transmit the collected power quality data to a big data processing center. The data transmission module supports wired and wireless transmission modes and adopts a high-speed and reliable communication protocol to ensure the real-time and accuracy of data transmission. The wireless transmission mode includes but is not limited to 4G, 5G or industrial Internet of Things dedicated frequency band communication; A big data processing center is configured with a big data storage device and a data analysis processor. The big data storage device is used to store massive historical power quality data and real-time collected data. The data analysis processor runs power quality analysis software based on a machine learning algorithm for in-depth mining and analysis of power quality data to identify abnormal patterns and potential problems of power quality. The machine learning algorithm includes but is not limited to a decision tree, a neural network, and a support vector machine algorithm, and can adaptively adjust algorithm parameters according to the operation status of the power grid; A control decision module is connected to the big data processing center and generates control instructions based on the analysis results of the big data processing center. The control instructions are used to adjust the operating status of the power equipment in the power grid. The control decision module has a variety of preset control strategy templates built in, which can automatically match the best control strategy according to different types of power quality problems; The execution module receives the control instructions issued by the control decision module and acts on the reactive compensation device, filter, voltage regulator and other power equipment in the power grid to achieve real-time control of power quality. The execution module has a feedback function and can transmit the execution result information back to the big data processing center to evaluate and optimize the control effect.

2. The power quality control system based on big data analysis according to claim 1, characterized in that: The sensors in the data acquisition module have a self-diagnosis function and can monitor their own working status in real time. Once a fault or abnormality is found, it automatically sends an alarm message to the big data processing center and starts the backup sensor to take over the work to ensure the continuity of data collection.

3. The power quality control system based on big data analysis according to claim 1, characterized in that: The big data processing center is also connected to a visualization display terminal, which presents the analysis results of power quality data, power grid operation status and control effects in an intuitive form of charts, curves and maps for real-time monitoring by operation and maintenance personnel. The visualization display terminal supports human-computer interaction, and operation and maintenance personnel can perform data query and parameter setting operations through touch and gesture.

4. The power quality control system based on big data analysis according to claim 1, characterized in that: When generating control instructions, the control decision module fully considers the load changes of the power grid and the peak and valley period factors of electricity consumption, and uses a dynamic optimization algorithm to adjust the control strategy in real time to achieve economic and efficient power quality control.

5. The power quality control system based on big data analysis according to claim 1, characterized in that: The system also includes a prediction module connected to the big data processing center. The prediction module uses time series analysis and deep learning prediction models based on historical power quality data and real-time data to predict the trend of power quality changes in the future, and provide early warning information for power grid operation and maintenance in advance so that preventive measures can be taken in advance.

6. The power quality control system based on big data analysis according to claim 1, characterized in that: The connection between the execution module and the power equipment adopts an intelligent interface, which can automatically identify the type, model, and operating parameters of the power equipment, realize fast and accurate control command transmission, and reduce control delay. At the same time, the intelligent interface has an electrical isolation function to ensure the safety of the system.

7. The power quality control system based on big data analysis according to claim 1, characterized in that: The big data processing center is equipped with a data encryption and security protection mechanism, which uses a combination of symmetric encryption and asymmetric encryption to encrypt, store and transmit power quality data to prevent data leakage. At the same time, firewalls and intrusion detection system security protection measures are set up to resist external network attacks and ensure the stable operation of the system.

Images