Safety control method and control system for power monitoring system

Abstract

The invention discloses an electric power monitoring system safety control method and control system, relates to the field of electric power monitoring system information safety, and aims to automatically generate a scheduling instruction according to fault prediction and demand prediction results, timely scheduling can be carried out before a fault or abnormity occurs, the dependence on artificial experience is reduced, and the safety of the electric power monitoring system is improved. Meanwhile, property loss caused by manual operation errors is avoided. The method comprises the following steps: acquiring to-be-detected data of the power monitoring system at the current moment; acquiring a plurality of pieces of first historical data corresponding to the power monitoring system, performing load prediction according to the to-be-detected data at the current moment and the plurality of pieces of first historical data, and generating a load prediction result; acquiring a plurality of second historical data corresponding to the power monitoring system, performing fault prediction according to the to-be-detected data at the current moment and the plurality of second historical data, and generating a fault prediction result; and determining a scheduling strategy according to the load prediction result and the fault prediction result, and sending a scheduling instruction according to the scheduling strategy to control the power monitoring system.

Description

Technical Field

[0001] The present application relates to the field of information security of electric power monitoring systems, and in particular to a safety control method and control system for electric power monitoring systems. Background Art

[0002] The power monitoring system is used to monitor and control the power production and supply process. It is a business system and intelligent equipment based on computer and network technology, as well as communication and data networks as the basic support. In the actual operation of the power monitoring system, its operating status will be affected by many factors such as temperature, humidity, load changes, etc. Therefore, the stable operation of the power monitoring system also needs to rely on regular manual inspection and testing.

[0003] In related technologies, when encountering system failures or abnormal situations, staff are often required to make judgments based on real-time monitoring data and experience, and control the operating status of the power monitoring system through manual scheduling to ensure the stable operation of the power system.

[0004] In the process of implementing this application, the applicant found that the related technology has at least the following problems:

[0005] Manually controlling the operating status of the power monitoring system after a fault occurs is time-consuming and labor-intensive, and the staff's experience, judgment, and operating skills will directly affect the efficiency and effectiveness of fault handling. If the fault is not handled in a timely manner, greater property losses will occur. Summary of the invention

[0006] In view of this, the present application provides a safety control method and control system for an electric power monitoring system. The main purpose is to solve the current problem of time-consuming and labor-intensive manual adjustments after a fault occurs, and the staff's experience, judgment and operating skills will directly affect the efficiency and effectiveness of fault handling. If the fault is not handled in a timely manner, greater property losses will occur.

[0007] According to a first aspect of the present application, a power monitoring system safety control method is provided, the method comprising:

[0008] Collecting the data to be detected of the power monitoring system at the current moment, the data to be detected includes a plurality of operating parameters to be detected;

[0009] Acquire a plurality of first historical data corresponding to the power monitoring system, perform load forecasting according to the data to be detected at the current moment and the plurality of first historical data, and generate a load forecasting result;

[0010] Acquire multiple second historical data corresponding to the power monitoring system, perform fault prediction based on the data to be detected at the current moment and the multiple second historical data, and generate a fault prediction result, wherein the fault prediction result is obtained based on the state monitoring result, the abnormality monitoring result and the trend prediction result;

[0011] The dispatching strategy is determined according to the load forecasting results and the fault prediction results, and the dispatching instructions are sent according to the dispatching strategy to control the power monitoring system.

[0012] Optionally, the data to be detected of the power monitoring system at the current moment is collected, and the data to be detected includes multiple operating parameters to be detected, including:

[0013] A plurality of target sensors are used to collect parameters of the power monitoring system to obtain a plurality of operating parameters to be detected, wherein the plurality of operating parameters to be detected include voltage parameters, current parameters, power parameters, temperature parameters and humidity parameters;

[0014] A data collector is used to process a plurality of operating parameters to be detected to obtain a data compression package of the data to be detected at the current moment, wherein the data processing includes signal conversion processing, filtering and denoising processing, and data compression processing;

[0015] The communication module is used to transmit the data compression package so that the data compression package is stored in a preset storage location.

[0016] Optionally, a plurality of first historical data corresponding to the power monitoring system is obtained, and load forecasting is performed according to the data to be detected at the current moment and the plurality of first historical data to generate a load forecasting result, including:

[0017] Obtain multiple data compression packages corresponding to multiple specified moments and decompress them to obtain multiple first historical data, where the time intervals of the multiple specified moments are the same;

[0018] Data processing is performed on multiple first historical data and the data to be detected at the current moment, and the processed multiple first historical data and the data to be detected at the current moment are input into a pre-trained data statistical model, so that the data statistical model performs load prediction based on the multiple first historical data and the data to be detected at the current moment, and outputs the load prediction result corresponding to the target time point or target time period.

[0019] Optionally, the method further comprises:

[0020] The data compression packages are distributedly stored and dispersedly stored on multiple nodes, wherein the data compression packages classified as sensitive data are encrypted for transmission and encrypted for storage.

[0021] Optionally, a plurality of second historical data corresponding to the power monitoring system is obtained, and fault prediction is performed according to the data to be detected at the current moment and the plurality of second historical data to generate a fault prediction result, including:

[0022] Acquire multiple data compression packages corresponding to multiple target moments and decompress them to obtain multiple second historical data;

[0023] Performing data processing on the plurality of second historical data and the data to be detected at the current moment, and performing state monitoring, abnormality monitoring, and trend prediction based on the processed plurality of second historical data and the data to be detected at the current moment, to obtain state monitoring results, abnormality monitoring results, and trend prediction results;

[0024] If any of the status monitoring results, abnormal monitoring results and trend prediction results indicates an abnormality, the big data analysis technology is used to predict the fault of the power monitoring system based on the historical fault information, and the predicted fault point and predicted fault mode are determined, and the predicted fault point and predicted fault mode are used as the fault prediction result;

[0025] If the monitoring results, abnormal monitoring results, and trend prediction results all indicate normal operation, a fault prediction result is generated to indicate normal operation.

[0026] Optionally, data processing is performed on the plurality of second historical data and the data to be detected at the current moment, and state monitoring, abnormality monitoring and trend prediction are performed according to the processed plurality of second historical data and the data to be detected at the current moment to obtain state monitoring results, abnormality monitoring results and trend prediction results, including:

[0027] Among them, condition monitoring includes:

[0028] Establishing a state monitoring model according to the plurality of second historical data, determining whether the data to be detected at the current moment is within the normal range of the state monitoring model; if so, outputting a state monitoring result indicating normality; if not, outputting a state monitoring result indicating abnormality;

[0029] Among them, abnormal monitoring includes:

[0030] Compare each parameter to be detected in the current moment's data to be detected with the preset operating parameter standard to determine whether each parameter to be detected is normal. If any parameter to be detected is abnormal, output an abnormal monitoring result indicating the abnormality; if each parameter to be detected is normal, output an abnormal monitoring result indicating normality;

[0031] Among them, trend forecasts include:

[0032] A time series model is established based on multiple second historical data, and the data to be detected at the current moment is input into the time series model to obtain the trend value corresponding to each parameter to be detected. If any trend value exceeds the corresponding preset range value, a trend prediction result indicating an abnormality is output; if each trend value does not exceed the corresponding preset normal value, a trend prediction result indicating a normality is output.

[0033] Optionally, determining a dispatch strategy according to the load prediction result and the fault prediction result, and sending a dispatch instruction according to the dispatch strategy to control the power monitoring system includes:

[0034] Determine at least one scheduling strategy corresponding to the load prediction result and the fault prediction result in the preset scheduling strategy, read at least one scheduling instruction corresponding to each scheduling strategy, and send at least one scheduling instruction to the corresponding execution unit through the communication network to control the power monitoring system, wherein the scheduling strategy includes but is not limited to the start and stop strategy of the generator and the load distribution scheduling strategy;

[0035] Determine the operating status and dispatch execution status of the power monitoring system, and send the operating status and dispatch execution status of the power monitoring system to the monitoring terminal for display;

[0036] After sending at least one scheduling instruction to a corresponding execution unit to control the power monitoring system, the method further includes:

[0037] When it is detected that the monitoring terminal issues a dispatch instruction, the dispatch instruction is sent to the corresponding execution unit to control the power monitoring system;

[0038] When it is detected that the monitoring terminal issues a scheduling policy modification instruction, the scheduling policy identifier to be modified and the content to be modified carried in the scheduling policy modification instruction are read, the scheduling policy to be modified corresponding to the scheduling policy identifier to be modified is determined in the preset scheduling policy, and the scheduling policy to be modified is modified using the content to be modified.

[0039] Optionally, the method further comprises:

[0040] Use smart meters and sensors to detect energy consumption information of the power monitoring system in real time;

[0041] Big data analysis technology is used to analyze historical energy consumption information, determine energy consumption peak information and inefficient link information, and determine the dispatch strategy based on the energy consumption peak information, inefficient link information and real-time detected energy consumption information. According to the dispatch strategy, dispatch instructions are sent to control the power monitoring system. The dispatch strategy includes but is not limited to the entire equipment operation time strategy and the optimized load distribution strategy.

[0042] Optionally, the method further comprises:

[0043] Set warning rules based on monitoring indicators;

[0044] Collect designated operation data of the power control system and use early warning rules to perform safety operation detection on the designated operation data;

[0045] When the specified operating data triggers the warning rule, the warning information is generated and sent to the monitoring terminal for display;

[0046] Determine the dispatching instruction and send the dispatching instruction to the corresponding execution unit to control the power monitoring system.

[0047] According to a second aspect of the present application, there is provided a power monitoring system safety control system, the system comprising:

[0048] The microcomputer protection measurement and control unit is used to collect the data to be detected of the power monitoring system at the current moment, and the data to be detected includes multiple operating parameters to be detected;

[0049] The communication server is used to obtain a plurality of first historical data corresponding to the power monitoring system, perform load forecasting according to the data to be detected at the current moment and the plurality of first historical data, and generate a load forecasting result;

[0050] The communication server is used to obtain a plurality of second historical data corresponding to the power monitoring system, perform fault prediction according to the data to be detected at the current moment and the plurality of second historical data, and generate a fault prediction result, wherein the fault prediction result is obtained based on the state monitoring result, the abnormality monitoring result and the trend prediction result;

[0051] The communication server is used to determine the dispatching strategy according to the load forecasting results and the fault prediction results, and send dispatching instructions according to the dispatching strategy to control the power monitoring system.

[0052] By means of the above technical scheme, the present application provides a method and system for safe control of an electric power monitoring system. The present application first collects the data to be detected of the electric power monitoring system at the current moment, wherein the data to be detected includes a plurality of operating parameters to be detected. Next, a plurality of first historical data corresponding to the electric power monitoring system is obtained, and load prediction is performed based on the data to be detected at the current moment and the plurality of first historical data, and a load prediction result is generated. Subsequently, a plurality of second historical data corresponding to the electric power monitoring system is obtained, and fault prediction is performed based on the data to be detected at the current moment and the plurality of second historical data, and a fault prediction result is generated. Finally, a scheduling strategy is determined based on the load prediction result and the fault prediction result, and a scheduling instruction is sent according to the scheduling strategy to control the electric power monitoring system. By collecting the data to be detected and the historical data of the electric power monitoring system at the current moment for load prediction and fault prediction, timely scheduling can be performed before a fault or anomaly occurs, reducing the reliance on human experience and judgment, and avoiding property losses caused by human operational errors.

[0053] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0055] Figure 1 A schematic diagram of a safety control method for a power monitoring system provided in an embodiment of the present application is shown;

[0056] Figure 2 A schematic diagram of a safety control method for a power monitoring system provided in an embodiment of the present application is shown;

[0057] Figure 3 It is a structural diagram of data collection and processing in a power monitoring system safety control method provided by the present application;

[0058] Figure 4 It is a structural diagram of remote control and dispatching in a safety control method of a power monitoring system provided by the present application;

[0059] Figure 5 It is a structural schematic diagram of energy management and optimization in a power monitoring system safety control method provided by the present application;

[0060] Figure 6 It is a structural schematic diagram of a power monitoring system safety control system provided in this application. DETAILED DESCRIPTION

[0061] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0062] The power monitoring system is used to monitor and control the power production and supply process. It is a business system and intelligent equipment based on computer and network technology, as well as a communication and data network as a basic support. During the actual operation of the power monitoring system, its operating status will be affected by various factors such as temperature, humidity, and load changes. Therefore, the stable operation of the power monitoring system still needs to rely on regular manual inspections and tests. In the related technology, when encountering system failures or abnormal conditions, staff are often required to make judgments based on real-time monitoring data and experience, and control the operating status of the power monitoring system through manual scheduling to ensure the stable operation of the power system. However, the applicant recognizes that it is time-consuming and labor-intensive to control the operating status of the power monitoring system through manual scheduling after a fault occurs, and the staff's experience, judgment, and operating skills will directly affect the efficiency and effectiveness of fault handling. If the fault is not handled in time, greater property losses will occur. Therefore, the embodiment of the present application provides a method for safe control of a power monitoring system, such as Figure 1 As shown, the method includes:

[0063] 101. Collect data to be detected of the power monitoring system at the current moment, where the data to be detected includes a plurality of operating parameters to be detected.

[0064] The data to be detected includes a plurality of operating parameters to be detected. In the present application, the operating parameters to be detected are operating parameters selected from all operating parameters of the power monitoring system for performing fault prediction and load prediction.

[0065] Specifically, sensors can be used to collect parameters, and corresponding sensors can be deployed at various monitoring points in the power monitoring system to collect operating parameters. In the actual operation process, the data to be detected at each moment can be collected in real time for load prediction and fault prediction, or the data to be detected can be collected periodically at specific moments for load prediction and fault prediction. This application does not specifically limit the collection time.

[0066] 102. Acquire a plurality of first historical data corresponding to the power monitoring system, perform load forecasting based on the data to be detected at the current moment and the plurality of first historical data, and generate a load forecasting result.

[0067] Among them, the multiple first historical data are system operating parameters collected in the past period of time for load forecasting. Specifically, the multiple first historical data can be load data at the same time in previous years. For example, if the current time is 9:00 on September 13, 2024, the multiple historical data can be load data determined at 9:00 on September 13, 2021, 9:00 on September 13, 2022, and 9:00 on September 13, 2023. In the actual operation process, the safety control system can determine the load data at the current moment based on the data to be detected at the current moment, and then perform load forecasting based on the load data at the same time in previous years and the load data at the current moment, and obtain the load forecast results for a period of time in the future or a certain point in the future.

[0068] 103. Acquire multiple second historical data corresponding to the power monitoring system, perform fault prediction based on the data to be detected at the current moment and the multiple second historical data, and generate a fault prediction result, wherein the fault prediction result is obtained based on the state monitoring result, the abnormal monitoring result and the trend prediction result.

[0069] Among them, the second historical data is the system operation data of multiple power monitoring systems collected in the past period of time. Based on the past system operation data, status monitoring, abnormality monitoring and trend prediction are performed on the detection data to generate fault prediction results. The fault prediction results are used to predict whether the power monitoring system will fail while maintaining the current operating state.

[0070] 104. Determine the dispatching strategy according to the load forecasting results and the fault prediction results, and send dispatching instructions according to the dispatching strategy to control the power monitoring system.

[0071] Specifically, the dispatching strategy can be pre-uploaded to the safety control system by the technicians based on historical data and work experience, or it can be the default initial dispatching strategy in the safety control system. At least one dispatching strategy is determined based on the load forecasting results and the fault prediction results, and dispatching instructions are sent according to the instructions of the dispatching strategy to control the power monitoring system. Among them, the dispatching strategy can be the start and stop of the generator, the switching of the load, the reactive power compensation, or it can be a strategy to maintain the current operating state of the power monitoring system, so that the power monitoring system maintains the current operating state.

[0072] The safety control method of the power monitoring system provided in this embodiment first collects the data to be detected of the power monitoring system at the current moment, wherein the data to be detected includes multiple operating parameters to be detected. Next, multiple first historical data corresponding to the power monitoring system are obtained, and load prediction is performed based on the data to be detected at the current moment and the multiple first historical data to generate a load prediction result. Subsequently, multiple second historical data corresponding to the power monitoring system are obtained, and fault prediction is performed based on the data to be detected at the current moment and the multiple second historical data to generate a fault prediction result. Finally, a scheduling strategy is determined based on the load prediction results and the fault prediction results, and a scheduling instruction is sent according to the scheduling strategy to control the power monitoring system. By using big data analysis technology to perform load prediction and fault prediction on the power monitoring system, and automatically generating a scheduling instruction based on the fault prediction results and the load prediction results, potential faults can be discovered in advance and corresponding strategies can be adopted for scheduling, which can reduce the reliance on human experience and judgment, and can avoid property losses caused by human operational errors.

[0073] Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully illustrate the implementation process of this embodiment, the embodiment of the present application provides a power monitoring system security control method, such as Figure 2 As shown, the method includes:

[0074] 201. Data collection and processing.

[0075] The power monitoring system is used to monitor and control the power production and supply process. It is a business system and intelligent equipment based on computer and network technology, as well as a communication and data network as a basic support. In the actual operation process of the power monitoring system, its operating state will be affected by various factors such as temperature, humidity, load changes, etc. Therefore, the stable operation of the power monitoring system also needs to rely on manual regular inspection and testing. In the related art, when encountering a system failure or an abnormal situation, the staff is often required to make judgments based on real-time monitoring data and experience, and control the operating state of the power monitoring system through manual scheduling to ensure the stable operation of the power system. However, the applicant recognizes that it is time-consuming and labor-intensive to control the operating state of the power monitoring system through manual scheduling after the failure occurs, and the experience, judgment and operating skills of the staff will directly affect the efficiency and effect of fault handling. If the fault is not handled in time, greater property losses will occur. Therefore, the embodiment of the present application provides a method for safe control of a power monitoring system, firstly collecting the data to be detected of the power monitoring system at the current moment, wherein the data to be detected includes multiple operating parameters to be detected. Next, multiple first historical data corresponding to the power monitoring system are obtained, and load forecasting is performed according to the data to be detected at the current moment and the multiple first historical data, and a load forecasting result is generated. Subsequently, multiple second historical data corresponding to the power monitoring system are obtained, and fault prediction is performed based on the data to be detected at the current moment and the multiple second historical data to generate a fault prediction result. Finally, the dispatching strategy is determined based on the load prediction results and the fault prediction results, and a dispatching instruction is sent according to the dispatching strategy to control the power monitoring system. By using big data analysis technology to perform load prediction and fault prediction on the power monitoring system, and automatically generating dispatching instructions based on the fault prediction results and the load prediction results, potential faults can be discovered in advance and corresponding strategies can be adopted for dispatching, which can reduce reliance on human experience and judgment, and can avoid property losses caused by human operational errors.

[0076] In the embodiments of the present application, Figure 3 As shown, the safety control system first uses multiple target sensors to collect parameters of the power monitoring system to obtain multiple operating parameters to be detected, including voltage parameters, current parameters, power parameters, temperature parameters and humidity parameters. Specifically, the technicians first deploy sensors configured with data collection purposes, ranges, and frequencies, as well as data collectors and communication modules. The sensors are specifically voltage sensors for voltage monitoring, current sensors for current monitoring, power sensors for power monitoring, temperature sensors for temperature monitoring, humidity sensors for humidity monitoring, and voltage sensors for voltage monitoring. In the actual implementation process, each sensor can be deployed at each detection point in the power monitoring system for real-time collection. This application does not specifically limit the deployment location of the sensor.

[0077] Furthermore, a data collector is used to process the multiple operating parameters to be detected to obtain a data compression package of the data to be detected at the current moment, and the data processing includes signal conversion processing, filtering and denoising processing, and data compression processing. In this step, the sensor transmits the collected operating parameters to be detected to the data collector via a wired transmission method, and the data collector converts the original signal collected by the sensor into a processable digital signal, and performs filtering and denoising processing on the digital signal, using digital filtering technology to remove noise and interference in the signal, improve data quality, and then compress a large amount of data to reduce the demand for storage space and transmission bandwidth.

[0078] Finally, the communication module is used to transmit the data compression package so that the data compression package is stored in the preset storage location. Specifically, the data collector cooperates with the communication module to encrypt and transmit the processed information to the security control system and the cloud data center, where the data stored in the security control system is used for subsequent automatic scheduling, and the data stored in the cloud data center is used for subsequent technicians to retrieve and use.

[0079] In this step, by setting the target, scope and frequency of data collection, deploying the sensor network, covering the key parameters of the power system such as voltage, current, frequency, harmonics, etc., the data collected by the sensors are automatically denoised, verified and preliminarily compressed through the data collector to reduce the demand for storage space and transmission bandwidth, ensuring the accuracy and efficiency of the data. Finally, the data is encrypted and transmitted to the central control system and cloud data center through the communication module, providing a solid foundation for subsequent analysis.

[0080] 202. Remote control and scheduling.

[0081] In the embodiments of the present application, Figure 4 As shown, remote control includes decompressing the data packet uploaded by the communication module in step 201 and processing the data through data processing, data analysis, fault diagnosis, demand forecasting, and scheduling optimization. Remote scheduling includes issuing instructions to personnel under real-time monitoring of the power monitoring system, and generating instructions and performing data scheduling control. The implementation steps of remote control and remote scheduling are as follows:

[0082] 1. Data processing

[0083] Specifically, multiple data compression packages corresponding to multiple specified moments are obtained and decompressed to obtain multiple first historical data, wherein the time intervals of the multiple specified moments are the same. Multiple data compression packages corresponding to multiple target moments are obtained and decompressed to obtain multiple second historical data. Data processing is performed on the multiple first historical data, the multiple second historical data, and the data to be detected at the current moment, that is, the obtained data is cleaned to remove noise, abnormal values, and redundant data, thereby improving data quality.

[0084] 2. Data Analysis

[0085] Use statistical analysis, data mining and other techniques to conduct in-depth analysis of the cleaned data and extract valuable information and patterns.

[0086] 3. Fault prediction

[0087] According to the processed multiple second historical data and the data to be detected at the current moment, state monitoring, abnormality monitoring and trend prediction are performed to obtain state monitoring results, abnormality monitoring results and trend prediction results. Among them, the state monitoring process can be carried out through a state monitoring model. Specifically, a state monitoring model is established based on multiple second historical data to determine whether the data to be detected at the current moment is within the normal range of the state monitoring model; if so, a state monitoring result indicating normal is output; if not, a state monitoring result indicating abnormal is output. Abnormality monitoring can be carried out through a preset operating parameter standard. Specifically, each parameter to be detected in the data to be detected at the current moment is compared with a preset operating parameter standard to determine whether each parameter to be detected is normal. If any parameter to be detected is abnormal, an abnormal monitoring result indicating abnormality is output; if each parameter to be detected is normal, an abnormal monitoring result indicating normal is output. The trend prediction process can be carried out through a time series model. Specifically, a time series model is established based on multiple second historical data, and the data to be detected at the current moment is input into the time series model to obtain the trend value corresponding to each parameter to be detected. If any trend value exceeds the corresponding preset range value, a trend prediction result indicating an abnormality is output; if each trend value does not exceed the corresponding preset normal value, a trend prediction result indicating a normality is output. In the actual operation process, other methods can also be used for state monitoring, abnormality monitoring and trend prediction to obtain state monitoring results, abnormality monitoring results and trend prediction results.

[0088] Furthermore, if any of the status monitoring results, abnormal monitoring results, and trend prediction results indicates an abnormality, the big data analysis technology is used to predict the fault of the power monitoring system based on the historical fault information, determine the predicted fault point and predicted fault mode, and use the predicted fault point and predicted fault mode as the fault prediction result. If the monitoring results, abnormal monitoring results, and trend prediction results all indicate normality, a fault prediction result indicating normal operation is generated.

[0089] 4. Load forecasting

[0090] In this step, the processed multiple first historical data and the data to be detected at the current moment can be input into the pre-trained data statistical model, so that the data statistical model performs load prediction based on the multiple first historical data and the data to be detected at the current moment, and outputs the load prediction result corresponding to the target time point or target time period.

[0091] 5. Scheduling Optimization

[0092] Combined with factors such as power supply and demand balance, equipment status, and safety constraints, the optimal scheduling plan is formulated to achieve reasonable resource allocation and safe and stable operation of the power grid. Specifically, at least one scheduling strategy corresponding to the load prediction result and the fault prediction result is determined in the preset scheduling strategy, and at least one scheduling instruction corresponding to each scheduling strategy is read. At least one scheduling instruction is sent to the corresponding execution unit through the communication network to control the power monitoring system. The scheduling strategy includes but is not limited to the start and stop strategy of the generator and the load distribution scheduling strategy.

[0093] Next, the operating status and dispatch execution status of the power monitoring system are determined, and the operating status and dispatch execution status of the power monitoring system are sent to the monitoring terminal for display. Further, when it is detected that the monitoring terminal issues a dispatch instruction, the dispatch instruction is sent to the corresponding execution unit to control the power monitoring system. When it is detected that the monitoring terminal issues a dispatch policy modification instruction, the dispatch policy identifier to be modified and the content to be modified carried by the dispatch policy modification instruction are read, and the dispatch policy to be modified corresponding to the dispatch policy identifier to be modified is determined in the preset dispatch policy, and the dispatch policy to be modified is modified using the content to be modified.

[0094] The remote monitoring module analyzes cloud data in real time, and uses advanced data analysis algorithms for status monitoring, anomaly detection and trend prediction. The intelligent dispatching system automatically or semi-automatically adjusts power distribution according to the prediction results, grid load conditions and equipment status, optimizes grid operation efficiency and reduces energy waste. At the same time, the system supports remote command issuance to achieve precise control of power equipment; after fault diagnosis, the fault results are stored and the operation status of the power system is predicted using big data analysis technology, potential faults are discovered in advance and corresponding preventive measures are taken; dispatching instructions are automatically generated according to the fault prediction and demand prediction results, including the start and stop of generators, load switching and reactive power compensation, and then dispatching instructions are issued to each execution unit (such as power plants, substations, etc.) in real time through the communication network to ensure accurate communication and execution of instructions. Real-time monitoring displays the operation status and dispatching execution of the power system in real time through the large screen or client software of the monitoring center, establishes a feedback mechanism, receives the execution results and status information of the execution unit, and adjusts the dispatching strategy or issues new dispatching instructions in a timely manner.

[0095] 203. Energy management and optimization.

[0096] In the embodiments of the present application, Figure 5As shown, the safety control system can also be dispatched according to the energy consumption information. Specifically, the safety control system uses smart meters and sensors to detect the energy consumption information of the power monitoring system in real time. Furthermore, the historical energy consumption information is analyzed by big data analysis technology to determine the peak energy consumption information and the inefficient link information, and the dispatch strategy is determined according to the peak energy consumption information, the inefficient link information and the real-time detected energy consumption information, and the dispatch instruction is sent according to the dispatch strategy to control the power monitoring system. The dispatch strategy includes but is not limited to the whole equipment operation time strategy and the optimized load distribution strategy.

[0097] Energy management includes collecting and collecting data on energy consumption in the power system. Energy efficiency management uses smart meters and sensors in the power system to detect the energy consumption of the power system in real time. Energy utilization uses renewable resources such as solar energy and wind energy to establish a comprehensive energy utilization area. Energy storage and recovery recovers and reuses waste heat and excess pressure in the power system to improve the comprehensive utilization efficiency of energy.

[0098] The energy efficiency management system monitors the energy consumption of the power system in real time through smart meters, IoT sensors and other equipment. It combines big data analysis technology to identify energy consumption peaks and inefficient links, and formulates targeted energy-saving measures, such as adjusting equipment operating hours and optimizing load distribution, to achieve efficient use of energy. In addition, the system can also use renewable energy such as solar energy and wind energy to further reduce carbon emissions.

[0099] Energy utilization specifically involves planning the layout of solar energy and wind power system devices, optimizing the energy structure, and improving energy utilization efficiency, such as achieving cascade utilization of energy through combined heat, cooling and power generation, energy storage technology, etc.

[0100] 204. Security assurance and early warning.

[0101] In an embodiment of the present application, an early warning rule is set according to the monitoring index. The designated operation data of the power control system is collected, and the designated operation data is tested for safe operation using the early warning rule. When the designated operation data triggers the early warning rule, early warning information is generated, and the early warning information is sent to the monitoring terminal for display. A scheduling instruction is determined, and the scheduling instruction is sent to the corresponding execution unit to control the power monitoring system.

[0102] Specifically, security protection includes physical protection, environmental monitoring, and regular inspections. Early warning protection sets early warning rules based on monitoring indicators. When monitoring data triggers early warning rules, the system automatically issues early warning information. The security monitoring system monitors the operating status of the power system in real time, including equipment health, network security, etc. Once potential safety hazards or failures are found, the system will immediately trigger the early warning mechanism and notify relevant personnel to handle them. At the same time, the system has emergency response capabilities and can automatically take protective measures in emergency situations, such as cutting off the power supply in the fault area and starting the backup power supply, etc., to ensure the safe and stable operation of the power grid. Physical security specifically refers to the physical protection of power monitoring equipment, such as setting up access control systems, surveillance cameras, anti-theft alarm devices, etc., to prevent equipment from being stolen or illegally destroyed. The operating environment of the power monitoring equipment is monitored based on the temperature sensor and humidity sensor in S1 to ensure that the equipment is under suitable temperature, humidity and power conditions to avoid environmental factors from causing damage to the equipment. The early warning mechanism is set specifically as monitoring indicators, such as equipment operating status, network traffic, abnormal login, etc., so as to detect abnormal situations in a timely manner. When monitoring data triggers early warning rules, the system automatically issues early warning information.

[0103] 205.Data storage and management.

[0104] In an embodiment of the present application, the data compression packages are distributedly stored and dispersedly stored on multiple nodes, wherein the data compression packages classified as sensitive data are encrypted for transmission and encrypted for storage.

[0105] Specifically, for large amounts of data and high concurrent access requirements, distributed storage is used to store data in multiple nodes to improve the scalability and fault tolerance of the system. Data classified as sensitive in the power system is encrypted for storage and transmission to prevent data leakage. Access to power monitoring data is strictly controlled to ensure that only authorized users can access relevant data. Distributed database and big data processing technology are used to efficiently store and manage massive power data. The system supports data classification, indexing, query and visualization, which facilitates users to quickly obtain the required information. At the same time, the system has built-in multiple data analysis tools, such as data mining and machine learning algorithms, to help users deeply explore the value of data and discover hidden laws and trends. Distributed storage distributes data on multiple nodes. Even if some nodes fail, data can still be recovered from other nodes, ensuring data availability and persistence. This is usually achieved through data redundancy (such as replication or sharding plus redundancy). As the amount of data continues to grow, the distributed storage system can easily add more storage nodes to expand storage capacity and performance without making large-scale architectural changes to the system. Distributed storage systems can improve performance by processing data access requests in parallel. Multiple clients can read or write data from multiple nodes at the same time, significantly improving throughput. The nodes can be deployed in different geographical locations, which makes distributed storage systems particularly suitable for handling the storage and access of data on a global scale. At the same time, it can improve the local access speed of data and reduce latency.

[0106] The method provided by the embodiment of the present application first collects the data to be detected of the power monitoring system at the current moment, wherein the data to be detected includes multiple operating parameters to be detected. Next, multiple first historical data corresponding to the power monitoring system are obtained, and load prediction is performed based on the data to be detected at the current moment and the multiple first historical data, and a load prediction result is generated. Subsequently, multiple second historical data corresponding to the power monitoring system are obtained, and fault prediction is performed based on the data to be detected at the current moment and the multiple second historical data, and a fault prediction result is generated. Finally, a scheduling strategy is determined based on the load prediction result and the fault prediction result, and a scheduling instruction is sent according to the scheduling strategy to control the power monitoring system. The system supports remote instruction issuance, realizes precise control of equipment in the power monitoring system, effectively reduces resource waste, and uses big data analysis technology to perform load prediction and fault prediction on the power monitoring system, and automatically generates scheduling instructions based on the fault prediction results and the load prediction results, which can detect potential faults in advance and adopt corresponding strategies for scheduling, can reduce dependence on human experience and judgment, and can avoid property losses caused by human operational errors.

[0107] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a power monitoring system safety control system, such as Figure 6 As shown, the device comprises:

[0108] Microcomputer protection and control unit for power system data collection and processing;

[0109] Communication servers for remote control and scheduling, as well as energy management and optimization;

[0110] The power base for security and early warning is managed by billing server;

[0111] Database server for data storage and management.

[0112] The microcomputer protection measurement and control unit is used to collect the data to be detected of the power monitoring system at the current moment, and the data to be detected includes multiple operating parameters to be detected;

[0113] The communication server is used to obtain a plurality of first historical data corresponding to the power monitoring system, perform load forecasting according to the data to be detected at the current moment and the plurality of first historical data, and generate a load forecasting result;

[0114] The communication server is used to obtain a plurality of second historical data corresponding to the power monitoring system, perform fault prediction according to the data to be detected at the current moment and the plurality of second historical data, and generate a fault prediction result, wherein the fault prediction result is obtained based on the state monitoring result, the abnormality monitoring result and the trend prediction result;

[0115] The communication server is used to determine the dispatching strategy according to the load forecasting results and the fault prediction results, and send dispatching instructions according to the dispatching strategy to control the power monitoring system.

[0116] A power monitoring system safety control system further expands its functions and also includes:

[0117] Load forecasting and management system for intelligent forecasting and dispatching of power load;

[0118] Remote operation and maintenance platform for remote maintenance and fault diagnosis of power equipment;

[0119] Log audit server for centralized storage and analysis of system logs and events;

[0120] A simulation test center for simulating and verifying the performance of power systems.

[0121] The load forecasting and management system collects historical data, weather information and other multiple factors, and uses forecasting algorithms to accurately forecast power load. This not only helps the power dispatching department to arrange power generation plans reasonably, but also effectively alleviates the contradiction between power supply and demand and improves the stability of the power system.

[0122] The remote operation and maintenance platform provides great convenience for the maintenance of power equipment. Operation and maintenance personnel can perform operations such as fault diagnosis, software upgrades, and parameter adjustments on equipment through remote connections without having to visit the site in person. This not only improves maintenance efficiency, but also reduces operation and maintenance costs.

[0123] The log audit server is responsible for collecting, storing and analyzing various logs and event information generated in the power monitoring system. Through in-depth mining of this information, potential safety hazards can be discovered in a timely manner, providing strong protection for the safe and stable operation of the system.

[0124] The simulation test center simulates and verifies the system's performance by building a virtual power system environment, which helps to comprehensively evaluate the system's performance, stability and safety before it is officially put into operation, and provides a scientific basis for the optimization and improvement of the system.

[0125] The device provided in the embodiment of the present application can first collect the data to be detected of the power monitoring system at the current moment, wherein the data to be detected includes multiple operating parameters to be detected. Next, multiple first historical data corresponding to the power monitoring system are obtained, and load prediction is performed based on the data to be detected at the current moment and the multiple first historical data, and a load prediction result is generated. Subsequently, multiple second historical data corresponding to the power monitoring system are obtained, and fault prediction is performed based on the data to be detected at the current moment and the multiple second historical data, and a fault prediction result is generated. Finally, a scheduling strategy is determined based on the load prediction results and the fault prediction results, and a scheduling instruction is sent according to the scheduling strategy to control the power monitoring system. By using big data analysis technology to perform load prediction and fault prediction on the power monitoring system, and automatically generating scheduling instructions based on the fault prediction results and the load prediction results, potential faults can be discovered in advance and corresponding strategies can be adopted for scheduling, which can reduce the reliance on human experience and judgment, and can avoid property losses caused by human operational errors.

[0126] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product. The software product to be identified can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0127] Through the description of the above implementation methods, the technical personnel in this field can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. By applying the technical solution of the present application, firstly, the data to be detected of the power monitoring system at the current moment is collected, wherein the data to be detected includes multiple operating parameters to be detected. Next, multiple first historical data corresponding to the power monitoring system are obtained, and load prediction is performed according to the data to be detected at the current moment and the multiple first historical data, and a load prediction result is generated. Subsequently, multiple second historical data corresponding to the power monitoring system are obtained, and fault prediction is performed according to the data to be detected at the current moment and the multiple second historical data, and a fault prediction result is generated. Finally, the scheduling strategy is determined according to the load prediction result and the fault prediction result, and the scheduling instruction is sent according to the scheduling strategy to control the power monitoring system. Compared with the prior art, by collecting the data to be detected and the historical data of the power monitoring system at the current moment for load prediction and fault prediction, timely warning can be given before a fault or abnormality occurs, reducing the dependence on human experience and judgment, and avoiding property losses caused by human operation errors.

[0128] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present application.

[0129] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0130] The above application serial numbers are for description only and do not represent the advantages or disadvantages of the implementation scenarios.

[0131] The above disclosure only discloses several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by technicians in this field should fall within the scope of protection of the present application.

Claims

1. A safety control method for an electric power monitoring system, characterized in that: include: Collecting data to be detected of the power monitoring system at the current moment, wherein the data to be detected includes a plurality of operating parameters to be detected; Acquire a plurality of first historical data corresponding to the power monitoring system, perform load forecasting according to the data to be detected at the current moment and the plurality of first historical data, and generate a load forecasting result; Acquire multiple second historical data corresponding to the power monitoring system, perform fault prediction based on the data to be detected at the current moment and the multiple second historical data, and generate a fault prediction result, wherein the fault prediction result is obtained based on the state monitoring result, the abnormality monitoring result and the trend prediction result; A dispatching strategy is determined according to the load prediction result and the fault prediction result, and a dispatching instruction is sent according to the dispatching strategy to control the power monitoring system.

2. The power monitoring system safety control method according to claim 1, characterized in that: The data to be detected of the power monitoring system at the current moment is collected, and the data to be detected includes multiple operating parameters to be detected, including: Using multiple target sensors to collect parameters of the power monitoring system to obtain multiple operating parameters to be detected, wherein the multiple operating parameters to be detected include voltage parameters, current parameters, power parameters, temperature parameters and humidity parameters; Using a data collector to process the plurality of operating parameters to be detected to obtain a data compression package of the data to be detected at the current moment, wherein the data processing includes signal conversion processing, filtering and denoising processing, and data compression processing; The communication module is used to transmit the data compression package so that the data compression package is stored in a preset storage location.

3. The power monitoring system safety control method according to claim 2, characterized in that: The acquiring of a plurality of first historical data corresponding to the power monitoring system, performing load forecasting according to the data to be detected at the current moment and the plurality of first historical data, and generating a load forecasting result includes: Acquire multiple data compression packages corresponding to the multiple specified moments and decompress them to obtain multiple first historical data, wherein the time intervals of the multiple specified moments are the same; Data processing is performed on the multiple first historical data and the data to be detected at the current moment, and the processed multiple first historical data and the data to be detected at the current moment are input into a pre-trained data statistical model, so that the data statistical model performs load forecasting based on the multiple first historical data and the data to be detected at the current moment, and outputs the load forecasting result corresponding to the target time point or target time period.

4. The method according to claim 2, characterized in that: The method further comprises: The data compression packages are distributedly stored and dispersedly stored on multiple nodes, wherein the data compression packages classified as sensitive data are encrypted for transmission and encrypted for storage.

5. The method according to claim 1, characterized in that The acquiring of a plurality of second historical data corresponding to the power monitoring system, performing fault prediction according to the data to be detected at the current moment and the plurality of second historical data, and generating a fault prediction result includes: Acquire multiple data compression packages corresponding to the multiple target moments and decompress them to obtain multiple second historical data; Performing data processing on the plurality of the second historical data and the data to be detected at the current moment, and performing status monitoring, abnormality monitoring, and trend prediction according to the processed plurality of the second historical data and the data to be detected at the current moment, to obtain the status monitoring result, abnormality monitoring result, and trend prediction result; If any of the state monitoring results, abnormal monitoring results and trend prediction results indicates an abnormality, a big data analysis technology is used to predict the fault of the power monitoring system according to historical fault information, and a predicted fault point and a predicted fault mode are determined, and the predicted fault point and the predicted fault mode are used as the fault prediction result; If the monitoring results, abnormal monitoring results and trend prediction results all indicate normal operation, a fault prediction result indicating normal operation is generated.

6. The method according to claim 5, characterized in that The data processing is performed on the plurality of the second historical data and the data to be detected at the current moment, and status monitoring, abnormality monitoring and trend prediction are performed according to the processed plurality of the second historical data and the data to be detected at the current moment to obtain the status monitoring result, abnormality monitoring result and trend prediction result, include: Among them, condition monitoring includes: Establishing a state monitoring model according to the plurality of the second historical data, determining whether the data to be detected at the current moment is within the normal range of the state monitoring model; if so, outputting a state monitoring result indicating normality; if not, outputting a state monitoring result indicating abnormality; Among them, abnormal monitoring includes: Compare each parameter to be detected in the current moment's data to be detected with the preset operating parameter standard to determine whether each parameter to be detected is normal. If any parameter to be detected is abnormal, output an abnormal monitoring result indicating the abnormality; if each parameter to be detected is normal, output an abnormal monitoring result indicating normality; Among them, trend forecasts include: A time series model is established based on multiple second historical data, and the data to be detected at the current moment is input into the time series model to obtain the trend value corresponding to each parameter to be detected. If any trend value exceeds the corresponding preset range value, a trend prediction result indicating an abnormality is output; if each trend value does not exceed the corresponding preset normal value, a trend prediction result indicating a normality is output.

7. The method according to claim 1, characterized in that The determining of a dispatching strategy according to the load prediction result and the fault prediction result, and sending a dispatching instruction according to the dispatching strategy to control the power monitoring system includes: Determine at least one scheduling strategy corresponding to the load prediction result and the fault prediction result in the preset scheduling strategy, read at least one scheduling instruction corresponding to each of the scheduling strategies, and send at least one scheduling instruction to a corresponding execution unit through a communication network to control the power monitoring system, wherein the scheduling strategy includes but is not limited to a generator start-stop strategy and a load distribution scheduling strategy; Determine the operating status and dispatch execution status of the power monitoring system, and send the operating status and dispatch execution status of the power monitoring system to the monitoring terminal for display; Wherein, after sending at least one of the scheduling instructions to a corresponding execution unit to control the power monitoring system, the method further includes: When it is detected that the monitoring terminal issues a dispatch instruction, the dispatch instruction is sent to a corresponding execution unit to control the power monitoring system; When it is detected that the monitoring terminal issues a scheduling policy modification instruction, the scheduling policy identifier to be modified and the content to be modified carried by the scheduling policy modification instruction are read, the scheduling policy to be modified corresponding to the scheduling policy identifier to be modified is determined in the preset scheduling policy, and the scheduling policy to be modified is modified using the content to be modified.

8. The method according to claim 1, characterized in that The method further comprises: Using smart meters and sensors to detect energy consumption information of the power monitoring system in real time; Big data analysis technology is used to analyze historical energy consumption information to determine energy consumption peak information and inefficient link information, and a scheduling strategy is determined based on the energy consumption peak information, inefficient link information and the energy consumption information detected in real time. A scheduling instruction is sent according to the scheduling strategy to control the power monitoring system. The scheduling strategy includes but is not limited to the whole equipment operation time strategy and the optimized load distribution strategy.

9. The method according to claim 1, characterized in that: The method further comprises: Set warning rules based on monitoring indicators; Collecting designated operation data of the power control system, and performing safety operation detection on the designated operation data using the early warning rule; When the designated operation data triggers the warning rule, generating warning information, and sending the warning information to the monitoring terminal for display; Determine a scheduling instruction, and send the scheduling instruction to a corresponding execution unit to control the power monitoring system.

10. A power monitoring system safety control system, characterized in that: include: A microcomputer protection measurement and control unit is used to collect the data to be detected of the power monitoring system at the current moment, wherein the data to be detected includes a plurality of operating parameters to be detected; A communication server, used for acquiring a plurality of first historical data corresponding to the power monitoring system, performing load forecasting according to the data to be detected at the current moment and the plurality of first historical data, and generating a load forecasting result; A communication server, configured to obtain a plurality of second historical data corresponding to the power monitoring system, perform fault prediction according to the data to be detected at the current moment and the plurality of second historical data, and generate a fault prediction result, wherein the fault prediction result is obtained based on the state monitoring result, the abnormality monitoring result and the trend prediction result; The communication server is used to determine a dispatching strategy according to the load prediction result and the fault prediction result, and send a dispatching instruction according to the dispatching strategy to control the power monitoring system.

Images