Intelligent monitoring method of substation based on cloud computing technology

Through the cloud computing platform, the operation data of the substation station is predicted and intelligently controlled, which solves the problem of power consumption interruption caused by unstable energy supply and fault repair, and achieves more stable enterprise operation and reduces operating losses.

CN117154945BActive Publication Date: 2024-12-03SHENZHEN HAOHAI YUNTIAN TECHNOLOGY CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202311159847.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-09-07
Publication Date
2024-12-03
Estimated Expiration
2043-09-07

AI Technical Summary

Technical Problem

Substation power stations are prone to oversupply or insufficient energy supply under different power load conditions, resulting in unstable operation of the enterprise, and power outage in case of failures, resulting in interruption of data transmission, resulting in operating losses.

Method used

Build a cloud computing platform, collect operation data of the substation power station, predict future operating trends through historical data, conduct intelligent fault detection and load fluctuation analysis, obtain intelligent control solutions, realize intelligent monitoring and control of the substation power station, and adjust the operating mode To adapt to different load states.

Benefits of technology

It avoids oversupply or insufficient energy supply, improves the stability of enterprise operation, reduces power consumption suspension and data transmission interruption caused by fault repairs, and reduces operating losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117154945B_ABST
    Figure CN117154945B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of intelligent monitoring technology. The present invention relates to an intelligent monitoring method for a substation based on cloud computing technology. It comprises the following steps: building a cloud computing platform and collecting the operation data of the substation; the cloud computing platform extracts historical operation data from the operation data, and predicts the future operation data of the substation according to the development trend of the historical operation data; intelligent fault detection is performed based on the predicted data combined with the historical operation data; load fluctuation analysis of the substation operation is performed based on the predicted data; the present invention predicts the future operation data of the substation, and controls the substation to adjust the corresponding operation mode according to different load fluctuations, so as to avoid the situation where the substation faces different power loads in the same operation mode. There will be oversupply or undersupply, which will lead to unstable operation of the enterprise and improve the guarantee of the operation of the enterprise.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring method for a transformer substation based on cloud computing technology. Background Art

[0002] The substation is the hub of the enterprise's power transmission and distribution network. Its safety status is the basis for the safe operation of the entire power grid system. However, during operation, if fault repair is carried out only when a problem occurs, the enterprise's power supply will need to be suspended. The suspension of enterprise power supply will lead to data transmission interruption and cause losses to the enterprise's operation. At the same time, the power required by the enterprise at different times is different, resulting in different load states of the substation. When the substation faces different power loads in the same operating mode, there will be oversupply or insufficient energy supply, resulting in unstable operation of the enterprise. Therefore, an intelligent monitoring method for substations based on cloud computing technology is proposed. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent monitoring method for a transformer substation based on cloud computing technology to solve the problems raised in the above background technology.

[0004] To achieve the above purpose, a method for intelligent monitoring of a substation based on cloud computing technology is provided, comprising the following steps:

[0005] S1. Build a cloud computing platform and collect the operation data of the substation;

[0006] S2. The cloud computing platform extracts historical operation data from the operation data and predicts the future operation data of the substation based on the development trend of the historical operation data;

[0007] S3, perform intelligent fault detection based on the data predicted by S2 and historical operation data;

[0008] S4, analyzing the load fluctuation of the substation operation according to the data predicted by S2, and obtaining intelligent control solutions for different load fluctuations of the substation;

[0009] S5. The cloud computing platform monitors the operating data and performs intelligent control of the substation based on the monitoring results and the intelligent control solution.

[0010] As a further improvement of the technical solution, S1 selects OpenStack cloud platform software to build a cloud computing platform for time series operation data.

[0011] As a further improvement of the technical solution, S1 collects the current and voltage of the power equipment in the substation in real time by deploying data collection sensors, including current sensors and voltage sensors, in the substation.

[0012] As a further improvement of the technical solution, the steps of S2 predicting the future operating state of the substation are as follows:

[0013] S2.1. Extract historical current and voltage data of substation from operation data;

[0014] S2.2, obtain the future operation decision of the substation;

[0015] S2.3, establish an intelligent prediction model, and input the historical current and voltage data extracted in S2.1 into the intelligent prediction model in combination with the future operation decision in S2.2;

[0016] S2.4. The intelligent prediction model outputs the future operation prediction data of the substation.

[0017] As a further improvement of the technical solution, the steps of performing intelligent fault detection in S3 are as follows:

[0018] S3.1. Extract the load status of current and voltage in normal operation of the substation from the historical operation data;

[0019] S3.2. Extract the load status of the substation when the current and voltage are the same as S3.1 in the future operation prediction data, and perform intelligent fault detection in combination with the load status extracted in S3.1. Send a fault inspection and maintenance notice to the substation through the cloud computing platform based on the detection results.

[0020] As a further improvement of the present technical solution, S3 also includes detecting and comparing the operating data with the future operating prediction data. When the data difference is greater than five percent, a fault repair notification is sent to the substation through the cloud computing platform, and feedback data from workers after the fault repair is collected to correct future operating data.

[0021] As a further improvement of the technical solution, the steps of S4 obtaining the intelligent control scheme for different fluctuations of the transformer substation are as follows:

[0022] S4.1. Extract the load fluctuation data and operation status of the substation during operation from the future operation prediction data;

[0023] S4.2, according to different fluctuation amplitudes of load fluctuation data and the operation status of the corresponding transformer substation, the fluctuation amplitude threshold affecting the transformer substation is obtained;

[0024] S4.3. The load fluctuation data exceeding the fluctuation amplitude threshold is combined with the substation for parameter analysis to obtain an intelligent control solution for adjusting the substation operating parameters when the fluctuation amplitude exceeds the threshold.

[0025] As a further improvement of the technical solution, the S4 further includes the following steps of adjusting the substation operation mode of the substation:

[0026] S4.4. Collect weather forecast data, and extract the consumption status of different operating modes of the substation under different weather conditions in combination with the operating data. Then, screen the different operating modes of the substation under different weather conditions according to the consumption status, obtain the operating mode with the lowest consumption status under the corresponding weather conditions, and send it to the cloud computing platform.

[0027] As a further improvement of the technical solution, the steps of S5 for intelligently controlling the substation are as follows:

[0028] S5.1. The cloud computing platform monitors the operation data according to the fluctuation amplitude threshold obtained in S4.2. When the fluctuation amplitude of the operation data is greater than the fluctuation amplitude threshold, the substation is adjusted according to the intelligent control solution obtained in S4.3. On the contrary, if the fluctuation amplitude is less than the fluctuation amplitude threshold, the monitoring is continued.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] In the intelligent monitoring method of substation based on cloud computing technology, the future operation data of the substation is predicted, and the substation is controlled to adjust the corresponding operation mode according to different load fluctuations, so as to avoid oversupply or undersupply when the substation faces different power loads in the same operation mode, resulting in unstable operation of the enterprise and improving the guarantee of the operation of the enterprise. At the same time, the predicted data is intelligently detected for faults to avoid repairing the faults only when problems occur, which leads to the need to suspend the power supply of the enterprise. The suspension of the power supply of the enterprise will cause data transmission interruption and cause losses to the operation of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is the overall flow chart of the present invention;

[0032] Figure 2 A flowchart of predicting future operation data of a transformer substation according to the present invention;

[0033] Figure 3 A flowchart of the intelligent fault detection process of the present invention;

[0034] Figure 4 The present invention is a flowchart of obtaining an intelligent control solution for different load fluctuations in a transformer substation. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] Example

[0037] See also Figure 1-Figure 4 As shown, a method for intelligent monitoring of a transformer substation based on cloud computing technology is provided, comprising the following steps:

[0038] S1. Build a cloud computing platform and collect the operation data of the substation;

[0039] For the time series operation data, S1 selects OpenStack cloud platform software to build a cloud computing platform.

[0040] Here are the steps:

[0041] Install and configure OpenStack: According to the official OpenStack documentation, select the appropriate version and follow the instructions to install and configure. This process involves the installation of the operating system, network configuration, database configuration, and the setting of computing nodes and storage nodes;

[0042] Virtualization environment configuration: Use the virtualization technology provided by OpenStack (such as KVM) to create virtual machine instances for time series data processing tasks to utilize computing resources for data processing;

[0043] Storage configuration: Configure OpenStack storage modules, such as Cinder (block storage) and Swift (object storage), to meet the storage requirements of time series data;

[0044] Network configuration: Use OpenStack to configure the network to ensure the communication of time series data between virtual machines and the connection with the external network;

[0045] Deploy a time series data processing framework: Deploy the corresponding software and tools on OpenStack based on the time series data processing framework you choose (such as Spark, TensorFlow, etc.).

[0046] The S1 collects the current and voltage of the power equipment in the substation in real time by deploying data collection sensors, including current sensors and voltage sensors, in the substation.

[0047] Current sensor: The current value of the power equipment is measured by the current sensor. The current sensor can be a non-contact current clamp sensor or a Hall effect sensor.

[0048] Voltage sensor: The voltage value of the power equipment is measured through the voltage sensor. The voltage sensor can be a voltage converter or a voltage divider.

[0049] S2. The cloud computing platform extracts historical operation data from the operation data and predicts the future operation data of the substation based on the development trend of the historical operation data;

[0050] The steps of S2 predicting the future operating status of the substation are as follows:

[0051] S2.1. Extract historical current and voltage data of the substation from the operating data; mark the transmitted voltage data and current data in combination with the time node, and extract the marked data.

[0052] S2.2. Obtain the future operation decision of the substation; the steps are as follows:

[0053] Data collection and analysis: Collect historical operating data of substations, including key indicators such as current, voltage, and load. Use data analysis technology to conduct statistics and trend analysis on historical data, discover rules and patterns, and understand the operating characteristics of substations;

[0054] Risk assessment and decision making: By conducting risk assessment on future forecast results, considering the impact of various scenarios and factors, we can assess possible risks and problems. Based on the assessment results, we can make corresponding operational decisions, such as upgrading equipment, adjusting operating modes, optimizing network topology, etc.

[0055] S2.3, establish an intelligent prediction model, and input the historical current and voltage data extracted in S2.1 into the intelligent prediction model in combination with the future operation decision in S2.2;

[0056] Establish a prediction model: Based on historical data and load forecasts, establish a prediction model to predict future load changes, voltage and current fluctuations in substations. The commonly used prediction method is time series analysis;

[0057] S2.4. The intelligent prediction model outputs the future operation prediction data of the substation.

[0058] S3, perform intelligent fault detection based on the data predicted by S2 and historical operation data;

[0059] The steps of performing intelligent fault detection in S3 are as follows:

[0060] S3.1. Extract the load status of current and voltage in normal operation of the substation from the historical operation data; the steps are as follows:

[0061] Data feature extraction: Extract the load state characteristics of current and voltage from the operating data. The average value, maximum value, minimum value or peak value at each time point can be calculated to represent the load state of current and voltage;

[0062] Calibrate load status: According to the operating rules and characteristics of the substation, set certain thresholds or standards to classify the extracted load status features, such as normal load, high load or low load;

[0063] Data analysis and visualization: Use data analysis methods and tools to analyze and visualize the extracted load status. Statistical analysis, data mining or machine learning algorithms can be used to study the relationship between load status and other factors;

[0064] Interpretation and application of results: Based on the analysis results, the load status of current and voltage in the historical operation data of the substation is interpreted. These results can be applied to evaluate the stability of the power system, optimize the operation plan and formulate maintenance strategies;

[0065] S3.2: Extract the load status of the substation when the current and voltage are the same as those in S3.1 in the future operation prediction data, and perform intelligent fault detection in combination with the load status extracted in S3.1. Send a fault inspection and repair notice to the substation through the cloud computing platform based on the detection results. The steps are as follows:

[0066] Data collection and preprocessing: Collect the predicted values ​​of current and voltage from the future operation forecast data of the substation. Preprocess the collected data, such as removing outliers or noise, filling missing values, etc.

[0067] Load state extraction: Extract the load state of the substation based on the predicted values ​​of current and voltage. The load state can be classified into normal load, high load or low load according to the preset threshold or set rules;

[0068] Intelligent fault detection: Use data analysis and machine learning technologies to correlate the extracted load status with historical fault data or establish a fault detection model. Use the model to detect possible faults in the substation;

[0069] Notification sending: According to the results of fault detection, the fault maintenance notification is sent to the substation through the cloud computing platform. The message service or notification mechanism provided by the cloud computing platform can be used to ensure the timeliness and reliability of the maintenance notification;

[0070] Fault handling and recording: According to the detected fault situation, corresponding fault handling and maintenance work are carried out. At the same time, the fault information and handling process are recorded for subsequent analysis and improvement.

[0071] S3 also includes testing and comparing the operating data with the future operating prediction data. When the data difference is greater than 5%, a fault repair notice is sent to the substation through the cloud computing platform, and feedback data from workers after the fault repair is collected to correct the future operating data. The steps are as follows:

[0072] Data difference calculation: By comparing the operating data with the future forecast data, the difference between current and voltage is calculated. The formula can be used:

[0073] Data difference = actual value - predicted value / actual value * 100%;

[0074] Anomaly detection: When the data difference exceeds a preset threshold (such as 5%), it indicates an abnormal situation and a fault maintenance notification needs to be sent;

[0075] Notification sending: send fault repair notifications to substations through the cloud computing platform. You can use the message service or notification mechanism provided by the cloud computing platform to ensure the timeliness and reliability of notifications;

[0076] Fault inspection and recording: After receiving the notification, the substation will conduct fault inspection and recording. At the same time, the specific situation and handling process of the fault will be recorded;

[0077] Feedback data collection: Collect feedback data from workers after troubleshooting, including repair time, repair method, repair results, etc.;

[0078] Data correction: Correct the future operation prediction data based on the feedback data. You can use correction factors or correction models to apply the actual repair situation to the future operation prediction data to improve the prediction accuracy.

[0079] S4, analyzing the load fluctuation of the substation operation according to the data predicted by S2, and obtaining intelligent control solutions for different load fluctuations of the substation;

[0080] The steps of S4 for obtaining intelligent control solutions for different fluctuations in the transformer substation are as follows:

[0081] S4.1. Extract the load fluctuation data and the operation status of the substation during operation from the future operation prediction data; the steps are as follows:

[0082] Load fluctuation extraction: By analyzing the forecast data, the fluctuation degree of the substation load is calculated. Statistical indicators such as standard deviation or variance can be used to measure the load change and extract the fluctuation data;

[0083] Operation status extraction: Extract the operation status of the substation based on the forecast data and load fluctuation data. The operation status can be judged according to the degree and trend of load change, such as high load, low load, stable, change trend, etc.

[0084] Data analysis and visualization: Use data analysis methods and tools to analyze and visualize the extracted load fluctuation data and operating status. Statistical analysis, time series analysis, data mining and other methods can be used to study the relationship between load fluctuation and operating status.

[0085] S4.2. According to different fluctuation amplitudes of load fluctuation data and the operation status of the corresponding transformer substation, the fluctuation amplitude threshold affecting the transformer substation is obtained; the steps are as follows:

[0086] Data collection: Obtain the fluctuation amplitude data and corresponding operation status information of the substation from the load fluctuation data;

[0087] Fluctuation range screening: According to the definition of substation operation status, the fluctuation range data is screened. Determine which fluctuation ranges are considered to be the threshold that affects the operation of the substation.

[0088] S4.3. Combine the load fluctuation data exceeding the fluctuation amplitude threshold with the substation for parameter analysis to obtain an intelligent control solution for adjusting the substation operating parameters when the fluctuation amplitude exceeds the threshold. The steps are as follows:

[0089] Parameter analysis: Analyze the data exceeding the fluctuation amplitude threshold with the operating parameters of the substation. Determine which operating parameters are associated with the fluctuation amplitude exceeding the threshold;

[0090] Intelligent control scheme design: Based on the results of parameter analysis, an intelligent control scheme is proposed to change the operating parameters of the distribution station when the fluctuation amplitude exceeds the threshold. According to different fluctuation conditions, the operation mode of the equipment can be adjusted, the load can be increased or decreased, the power supply configuration can be changed, etc.

[0091] Implementation and monitoring: Apply the intelligent control solution to the substation, implement and monitor it. Adjust and optimize according to the actual situation to improve the operation efficiency and stability of the substation.

[0092] The step S4 also includes the following steps of adjusting the substation operation mode of the substation:

[0093] S4.4, collect weather forecast data, and extract the consumption status of different operation modes of substations under different weather conditions in combination with operation data, and then screen different operation modes of substations under different weather conditions according to the consumption status, obtain the operation mode with the lowest consumption status under the corresponding weather conditions, and send it to the cloud computing platform. The steps are as follows:

[0094] Weather forecast data collection: Collect weather forecast data from reliable weather forecast channels or services, including temperature, humidity, wind speed and other weather parameters related to substation operation;

[0095] Operation data collection: collect the actual operation data of the substation, including key indicators such as load, current, and voltage;

[0096] Data preprocessing: preprocess the collected weather forecast data and operation data, including data quality check, missing value processing, etc.;

[0097] Consumption status extraction: Combine weather forecast data and operation data to extract the consumption status of the substation under different weather conditions. The consumption status can be determined based on load, energy consumption or other relevant indicators;

[0098] Operation mode screening: Screen the operation modes of the substation in different weather conditions according to the consumption status, and find the operation mode with the lowest consumption status in specific weather conditions;

[0099] The results are sent to the cloud computing platform: the operation mode results with the lowest consumption obtained by screening are sent to the cloud computing platform, and the message service or notification mechanism provided by the cloud computing platform is used for implementation.

[0100] S5. The cloud computing platform monitors the operating data and performs intelligent control of the substation based on the monitoring results and the intelligent control solution.

[0101] The steps of S5 for intelligent control of the substation are as follows:

[0102] S5.1, the cloud computing platform monitors the operation data according to the fluctuation amplitude threshold obtained in S4.2. When the fluctuation amplitude of the motion data is greater than the fluctuation amplitude threshold, the substation is adjusted according to the intelligent control solution obtained in S4.3. On the contrary, if the fluctuation amplitude is less than the fluctuation amplitude threshold, the monitoring is continued. The formula is as follows:

[0103] If the fluctuation range > fluctuation range threshold:

[0104] Adjustment status = intelligent control scheme (operation data);

[0105] Otherwise: Adjust status = continue monitoring.

[0106] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. The intelligent monitoring method of substation based on cloud computing technology is characterized by: The following steps are involved: S1. Build a cloud computing platform and collect the operation data of the substation; The S1 collects the current and voltage of the power equipment in the substation in real time by deploying data collection sensors, including current sensors and voltage sensors, in the substation; S2. The cloud computing platform extracts historical operation data from the operation data and predicts the future operation data of the substation based on the development trend of the historical operation data; The steps of S2 predicting the future operating status of the substation are as follows: S2.

1. Extract historical current and voltage data of substation from operation data; S2.2, obtain the future operation decision of the substation; S2.3, establish an intelligent prediction model, and input the historical current and voltage data extracted in S2.1 into the intelligent prediction model in combination with the future operation decision in S2.2; S2.4, the intelligent prediction model outputs the future operation prediction data of the substation; S3, perform intelligent fault detection based on the data predicted by S2 and historical operation data; The steps of performing intelligent fault detection in S3 are as follows: S3.

1. Extract the load status of current and voltage in normal operation of the substation from the historical operation data; S3.2, extract the load status of the substation when the current and voltage are the same as those in S3.1 from the future operation prediction data, and perform intelligent fault detection in combination with the load status extracted in S3.1, and send a fault inspection and repair notice to the substation through the cloud computing platform based on the detection results; The S3 also includes testing and comparing the operation data with the future operation prediction data. When the data difference is greater than 5%, a fault repair notice is sent to the substation through the cloud computing platform, and feedback data from workers after the fault repair is collected to correct the future operation data. S4, analyzing the load fluctuation of the substation operation according to the data predicted by S2, and obtaining intelligent control solutions for different load fluctuations of the substation; The steps of S4 obtaining the intelligent control scheme for different load fluctuations of the substation are as follows: S4.

1. Extract the load fluctuation data and operation status of the substation during operation from the future operation prediction data; S4.2, according to different fluctuation amplitudes of load fluctuation data and the operation status of the corresponding transformer substation, the fluctuation amplitude threshold affecting the transformer substation is obtained; S4.3, combining the load fluctuation data exceeding the fluctuation amplitude threshold with the substation for parameter analysis, and obtaining an intelligent control scheme for adjusting the substation operating parameters when the fluctuation amplitude exceeds the threshold; The step S4 also includes the following steps of adjusting the substation operation mode of the substation: S4.4, collect weather forecast data, and extract the consumption status of different operation modes of the substation under different weather conditions in combination with the operation data, and then screen the different operation modes of the substation under different weather conditions according to the consumption status, obtain the operation mode with the lowest consumption status under the corresponding weather conditions, and send it to the cloud computing platform; S5. The cloud computing platform monitors the operation data and performs intelligent control of the substation based on the monitoring results and the intelligent control solution; The steps of S5 for intelligent control of the substation are as follows: S5.

1. The cloud computing platform monitors the operation data according to the fluctuation amplitude threshold obtained in S4.

2. When the fluctuation amplitude of the operation data is greater than the fluctuation amplitude threshold, the substation is adjusted according to the intelligent control solution obtained in S4.

3. On the contrary, if the fluctuation amplitude is less than the fluctuation amplitude threshold, the monitoring is continued.

2. The intelligent monitoring method for transformer substation based on cloud computing technology according to claim 1 is characterized in that: For the time series operation data, S1 selects OpenStack cloud platform software to build a cloud computing platform.

Citation Information

Patent Citations

  • Intelligent analysis system based on big data

    CN115965266A