A deep peak regulation system and method for power plants based on big data

Abstract

The present invention belongs to the technical field of power plant peak regulation, and specifically relates to a power plant deep peak regulation system and method based on big data. The system includes a data acquisition module, a data storage module, a transmission calling module, a central processing module, a platform terminal module, a processing and analysis module and an optimization decision module. The data acquisition module controls the connection to the data storage module, the data storage module controls the connection to the transmission calling module, the transmission calling module controls the connection to the central processing module, and the central processing module controls the connection to the platform terminal module and the processing and analysis module respectively, the processing and analysis module controls the connection to the optimization decision module, and the optimization decision module controls the connection to the central processing module.

Description

Technical Field

[0001] The present invention belongs to the technical field of power plant peak regulation, and specifically relates to a power plant deep peak regulation system and method based on big data. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The deep peak regulation system of a power plant is a power grid management system designed to improve the safety, economy and efficiency of thermal power units during the deep peak regulation process. With the increasing degree of information integration in the power industry, big data and artificial intelligence technologies are gradually entering the power system and power generation field. Thermal power units play an important role in the power grid, especially in the context of the continuous increase in the installed capacity of new energy sources. Thermal power units need to participate more in deep peak regulation to ensure the stable operation of the power grid. Deep peak regulation refers to the thermal power units balancing the grid load by reducing their output when the grid load is low, and their load rate is usually lower than the basic peak regulation range.

[0004] The deep peak regulation system of existing power plants can basically meet the daily use needs, but there are still some shortcomings:

[0005] (1) The existing deep peak load regulation system requires manual deep peak load regulation after monitoring the grid load, which has a low degree of automation and increases the labor cost of grid operation.

[0006] (2) The existing deep peak-shaving system has a single data source, which limits the parameter optimization process of the peak-shaving calculation, thus affecting the accuracy of the peak-shaving operation;

[0007] (3) The data storage process in the existing deep peak-shaving system is simple. The stored data needs to be scanned in the entire repository for targeted calls at a later time, which increases the system load and reduces the system's operating efficiency. Summary of the invention

[0008] In order to solve the above problems, the present invention proposes a deep peak-shaving system and method for power plants based on big data. When storing data, the characteristic value of the data is marked to the front end of the data chain, and the storage path is recorded at the same time. When calling, it can be called from the specified location in combination with the characteristic value of the data, thereby reducing the memory usage during system data search and improving the operation efficiency of the system. The cloud data of the Internet of Things is connected through a big data docking module to optimize the parameters, and the peak-shaving algorithm of the power grid is optimized based on big data information, thereby enriching the data volume of the system and ensuring the accuracy of deep peak-shaving. When the power grid load is monitored to be at a low point, the peak-shaving instruction module issues a peak-shaving instruction to ensure the stable operation of the power grid. The entire process does not require human participation, thereby reducing the labor cost of power grid operation and improving the practicality of the system.

[0009] According to some embodiments, a first solution of the present invention provides a power plant deep peak regulation system based on big data, which adopts the following technical solutions:

[0010] A deep peak-shaving system for power plants based on big data comprises a data acquisition module, a data storage module, a transmission and call module, a central processing module, a platform terminal module, a processing and analysis module and an optimization and decision module, wherein the data acquisition module controls the connection to the data storage module, the data storage module controls the connection to the transmission and call module, the transmission and call module controls the connection to the central processing module, and the central processing module controls the connection to the platform terminal module and the processing and analysis module respectively, the processing and analysis module controls the connection to the optimization and decision module, and the optimization and decision module controls the connection to the central processing module.

[0011] As a further technical limitation, the data acquisition module is composed of a thermal power unit docking module, a fixed-point acquisition module, a data upload module, a data classification module, a clock recording module, a unit load module, a combustion parameter module, a steam parameter module and a coal quality characteristic module. The unit load module, the combustion parameter module, the steam parameter module and the coal quality characteristic module all control the connection data classification module.

[0012] As a further technical limitation, the data classification module controls the connection to the data upload module, the data upload module controls the connection to the clock recording module and the fixed-point acquisition module respectively, and the fixed-point acquisition module controls the connection to the thermal power unit docking module.

[0013] As a further technical limitation, the data storage module is composed of a storage receiving module, a feature marking module, a flash memory docking module, a storage library module, a storage calling module, a feature value entry module, a path marking module and a library space monitoring module. The feature value entry module controls the connection path marking module, and the path marking module controls the connection library space monitoring module and the storage calling module respectively.

[0014] As a further technical limitation, the storage receiving module controls the connection feature marking module, the feature marking module controls the connection flash memory docking module, the flash memory docking module controls the connection feature value entry module and the storage library module respectively, and the storage library module controls the connection storage calling module and the library space monitoring module respectively.

[0015] As a further technical limitation, the processing and analysis module is composed of a data calling module, a parameter sorting module, a linear analysis module, a data cleaning module, a data conversion module and a data output module, and the data calling module controls the connection parameter sorting module.

[0016] Further, the parameter sorting module controls the connection to the linear analysis module, and the linear analysis module controls the connection to the data cleaning module, the data cleaning module controls the connection to the data conversion module, and the data conversion module controls the connection to the data output module.

[0017] As a further technical limitation, the optimization decision module is composed of a decision input module, a training classification module, a basic algorithm module, an optimization algorithm module, a big data docking module, an auxiliary decision module, a peak-shaving instruction module and a valley monitoring module. The training classification module controls the connection to the optimization algorithm module, and the optimization algorithm module controls the connection to the big data docking module.

[0018] As a further technical limitation, the decision input module controls the connection to the training classification module, the training classification module controls the connection to the basic algorithm module, the basic algorithm module controls the connection to the optimization algorithm module, the optimization algorithm module controls the connection to the auxiliary decision module, the auxiliary decision module controls the connection to the peak shaving instruction module, and the peak shaving instruction module controls the connection to the valley monitoring module.

[0019] According to some embodiments, the second solution of the present invention provides a power plant deep peak regulation method based on big data, which adopts the power plant deep peak regulation system based on big data provided by the first solution, and adopts the following technical solutions:

[0020] A deep peak regulation method for power plants based on big data, comprising:

[0021] Obtain data information of power plant power generation equipment;

[0022] Performing linear analysis on the acquired data information to obtain processed data;

[0023] The optimization algorithm is used to optimize and update the processed data, carry out regulation and control of the power plant, and complete the deep peak regulation of the power plant based on big data.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] After the data storage module receives the transmitted data, the present invention receives the data through the storage receiving module, and then marks the data characteristics through the feature marking module. The flash memory docking module docks with the storage library module inside the system to store the data; during the storage process, the feature value of the data is marked to the front end of the data chain through the feature value entry module, and then the transmission path is recorded through the path marking module. The entire storage library module is detected in real time by the library space monitoring module, and the storage library module stores the data chain to the corresponding position of the flash memory particle according to the recorded transmission path. During the calling process, the storage calling module docks with the path marking module, and directly calls from the specified position in combination with the feature value of the data. The calling process can be completed without browsing the entire storage library, thereby reducing the memory usage when searching for system data and improving the operation efficiency of the system.

[0026] In the present invention, the parameter model after basic training is sent to the optimization algorithm module, and the optimization training set is received by the optimization algorithm module for optimization training. At the same time, the big data docking module docks with the cloud data of the Internet of Things to optimize the parameters in the basic algorithm. The optimization algorithm after evolution processing is temporarily stored by the auxiliary decision-making module. At the same time, the algorithm synchronously optimized in the later stage is stored in real time in the auxiliary decision-making module to update the algorithm. The peak-shaving algorithm of the power grid is optimized based on the big data information of the Internet of Things, which enriches the optimization data volume of the system and ensures the accuracy of deep peak-shaving. When the power grid load is monitored to be at a low point, the peak-shaving instruction module issues a peak-shaving instruction, and the load parameters are sent to the auxiliary decision-making module. The optimization algorithm is combined to balance the power grid load by reducing the output to ensure the stable operation of the power grid. The whole process does not require human participation, which reduces the labor cost of power grid operation and improves the practicality of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0028] Figure 1 This is an architecture diagram of a power plant deep peak regulation system based on big data in Embodiment 1 of the present invention;

[0029] Figure 2 This is an architecture diagram of the data acquisition module in the first embodiment of the present invention;

[0030] Figure 3 This is an architecture diagram of a data storage module in Embodiment 1 of the present invention;

[0031] Figure 4 This is an architecture diagram of the processing and analysis module in the first embodiment of the present invention;

[0032] Figure 5 This is an architecture diagram of the optimization decision module in the first embodiment of the present invention;

[0033] Figure 6 This is a flow chart of a deep peak regulation method for a power plant based on big data in Embodiment 2 of the present invention;

[0034] Among them, 1. Data acquisition module; 2. Data storage module; 3. Transmission call module; 4. Central processing module; 5. Platform terminal module; 6. Processing and analysis module; 7. Optimization decision module; 11. Thermal power unit docking module; 12. Fixed-point acquisition module; 13. Data upload module; 14. Data classification module; 15. Clock recording module; 16. Unit load module; 17. Combustion parameter module; 18. Steam parameter module; 19. Coal quality characteristic module; 21. Storage receiving module; 22. Feature marking module; 23. Flash memory docking module; 24 , storage library module; 25, storage call module; 26, feature value entry module; 27, path marking module; 28, library space monitoring module; 61, data call module; 62, parameter sorting module; 63, linear analysis module; 64, data cleaning module; 65, data conversion module; 66, data output module; 71, decision input module; 72, training classification module; 73, basic algorithm module; 74, optimization algorithm module; 75, big data docking module; 76, auxiliary decision module; 77, peak-shaving instruction module; 78, valley monitoring module. DETAILED DESCRIPTION

[0035] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0036] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0037] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0038] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention and should not be understood as limitations on the present invention.

[0039] In the present invention, terms such as "fixed connection", "connected", "connection", etc. should be understood in a broad sense, indicating that it can be fixedly connected, integrally connected or detachably connected; it can be directly connected or indirectly connected through an intermediate medium. For relevant scientific research or technical personnel in this field, the specific meanings of the above terms in the present invention can be determined according to specific circumstances, and they cannot be understood as limitations on the present invention.

[0040] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0041] Embodiment 1

[0042] Embodiment 1 of the present invention introduces a deep peak regulation system for power plants based on big data.

[0043] like Figure 1 A power plant deep peak regulation system based on big data is shown, comprising a data acquisition module 1, a data storage module 2, a transmission and call module 3, a central processing module 4, a platform terminal module 5, a processing and analysis module 6 and an optimization decision module 7; the data acquisition module 1 controls the connection to the data storage module 2, the data storage module 2 controls the connection to the transmission and call module 3, the transmission and call module 3 controls the connection to the central processing module 4, and the central processing module 4 controls the connection to the platform terminal module 5 and the processing and analysis module 6 respectively, the processing and analysis module 6 controls the connection to the optimization decision module 7, and the optimization decision module 7 controls the connection to the central processing module 4.

[0044] like Figure 2 The data acquisition module 1 shown is composed of a thermal power unit docking module 11, a fixed-point acquisition module 12, a data upload module 13, a data classification module 14, a clock recording module 15, a unit load module 16, a combustion parameter module 17, a steam parameter module 18 and a coal quality characteristic module 19. The unit load module 16, the combustion parameter module 17, the steam parameter module 18 and the coal quality characteristic module 19 all control the connection to the data classification module 14; the data classification module 14 controls the connection to the data upload module 13, the data upload module 13 controls the connection to the clock recording module 15 and the fixed-point acquisition module 12 respectively, and the fixed-point acquisition module 12 controls the connection to the thermal power unit docking module 11.

[0045] like Figure 3The data storage module 2 shown is composed of a storage receiving module 21, a feature marking module 22, a flash memory docking module 23, a storage repository module 24, a storage calling module 25, a feature value entry module 26, a path marking module 27 and a library space monitoring module 28. The feature value entry module 26 controls the connection path marking module 27, and the path marking module 27 controls the connection library space monitoring module 28 and the storage calling module 25 respectively; the storage receiving module 21 controls the connection feature marking module 22, the feature marking module 22 controls the connection flash memory docking module 23, the flash memory docking module 23 controls the connection feature value entry module 26 and the storage repository module 24 respectively, and the storage repository module 24 controls the connection storage calling module 25 and the library space monitoring module 28 respectively.

[0046] like Figure 4 The processing and analysis module 6 shown is composed of a data calling module 61, a parameter sorting module 62, a linear analysis module 63, a data cleaning module 64, a data conversion module 65 and a data output module 66. The data calling module 61 controls the connection parameter sorting module 62; the parameter sorting module 62 controls the connection linear analysis module 63, and the linear analysis module 63 controls the connection data cleaning module 64, the data cleaning module 64 controls the connection data conversion module 65, and the data conversion module 65 controls the connection data output module 66.

[0047] like Figure 5 The optimization decision module 7 shown is composed of a decision input module 71, a training classification module 72, a basic algorithm module 73, an optimization algorithm module 74, a big data docking module 75, an auxiliary decision module 76, a peak-shaving instruction module 77 and a valley monitoring module 78. The training classification module 72 controls the connection to the optimization algorithm module 74, and the optimization algorithm module 74 controls the connection to the big data docking module 75; the decision input module 71 controls the connection to the training classification module 72, the training classification module 72 controls the connection to the basic algorithm module 73, the basic algorithm module 73 controls the connection to the optimization algorithm module 74, the optimization algorithm module 74 controls the connection to the auxiliary decision module 76, the auxiliary decision module 76 controls the connection to the peak-shaving instruction module 77, and the peak-shaving instruction module 77 controls the connection to the valley monitoring module 78.

[0048] In this embodiment, the characteristic value of the data is marked to the front end of the data chain when the data is stored, and the storage path is recorded at the same time. When calling, the data can be called from the specified location in combination with the characteristic value of the data, thereby reducing the memory usage when the system searches for data and improving the operation efficiency of the system; the cloud data of the Internet of Things is connected through the big data connection module to optimize the parameters, and the peak-shaving algorithm of the power grid is optimized based on the big data information, which enriches the data volume of the system and ensures the accuracy of deep peak-shaving; when the power grid load is monitored to be low, the peak-shaving instruction module issues a peak-shaving instruction to ensure the stable operation of the power grid. The entire process does not require human participation, which reduces the labor cost of power grid operation and improves the practicality of the system.

[0049] Embodiment 2

[0050] Embodiment 2 of the present invention introduces a deep peak regulation method for power plants based on big data.

[0051] like Figure 6 A deep peak regulation method for power plants based on big data is shown, comprising:

[0052] Step 1: Power plant data collection;

[0053] Step 2: Data tag storage;

[0054] Step 3: Output call analysis;

[0055] Step 4: Auxiliary decision output.

[0056] As a further technical limitation, in step one, the thermal power unit docking module in the data acquisition module is used to dock with the power generation equipment of the power plant, and then the data acquisition instruction is issued at a predetermined time through the fixed-point acquisition module. After the sensor terminal collects the instruction, the collected terminal data is transmitted to the data classification module through the data upload module. At the same time, during the data upload process, the clock recording module is used to mark the time of data upload. After uploading to the data classification module, the sensor data is analyzed respectively through the unit load module, combustion parameter module, steam parameter module and coal quality characteristic module to convert the corresponding data into the load data of the thermal power unit, the combustion data of the unit combustion box, the steam generation data of the unit and the coal quality characteristic data of the unit; then the corresponding drilling data is sent to the data storage module through the data acquisition module.

[0057] As a further technical limitation, in step two, after the data storage module receives the transmitted data, it is received through the storage receiving module, and then the data characteristics are marked through the feature marking module. After that, the flash memory docking module docks with the storage library module inside the system to store the data; during the storage process, the feature value of the data is first marked to the front end of the data chain through the feature value entry module, and then the transmission path is recorded through the path marking module. The entire storage library module is detected in real time by the library space monitoring module, and then the storage library module stores the data chain to the corresponding position of the flash memory particle according to the recorded transmission path.

[0058] As a further technical limitation, in step three, when data call is required, the call instruction is sent to the transmission call module through the central processing module, and then the corresponding data is called from the storage repository module through the storage call module, and during the call process, the storage call module is connected to the path marking module, and directly called from the specified position in combination with the characteristic value of the data, and the call process can be completed without browsing the entire repository; after the data is called, it is sent to the processing and analysis module through the data upload module, and then received by the data call module, and then the parameter sorting module sorts the data according to the timing parameters, and cooperates with the linear analysis module to perform linear analysis on the sorted data. After the linear analysis is completed, the data cleaning module cleans the data with abnormal deviations and abnormalities in combination with the analysis results, and eliminates duplicate invalid data, and then converts the data into the internal format of the system through the data conversion module. After the conversion is completed, it is sent to the optimization decision module through the data output module.

[0059] As a further technical limitation, in step four, after the optimization decision module receives the data, it is received by the decision input module, and then the training classification module divides the received data into a basic training set and an optimized training set. The basic training set is sent to the basic algorithm module for training the basic algorithm. After the basic training is completed, the parameter model is sent to the optimization algorithm module, and the optimization training set is received by the optimization algorithm module for optimization training. At the same time, the big data docking module docks with the cloud data of the Internet of Things to optimize the parameters in the basic algorithm. The optimized algorithm after evolution processing is temporarily stored by the auxiliary decision module. At the same time, the algorithm optimized synchronously in the later stage is stored in real time in the auxiliary decision module to update the algorithm. During the operation of the power plant, the valley monitoring module continuously monitors the operating load of the power grid. When the grid load is detected to be valley, the peak-shaving instruction module issues a peak-shaving instruction, and the load parameters are sent to the auxiliary decision module. Combined with the optimization algorithm, the power grid load is balanced by reducing the output to ensure the stable operation of the power grid.

[0060] The detailed steps are the same as the working principles of the power plant deep peak regulation system based on big data provided in Example 1, and will not be repeated here.

[0061] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A power plant deep peak regulation system based on big data, including a data acquisition module, a data storage module, a transmission and call module, a central processing module, a platform terminal module, a processing and analysis module and an optimization and decision module, characterized in that: The data acquisition module controls the connection to the data storage module, the data storage module controls the connection to the transmission calling module, the transmission calling module controls the connection to the central processing module, and the central processing module controls the connection to the platform terminal module and the processing and analysis module respectively, the processing and analysis module controls the connection to the optimization decision module, and the optimization decision module controls the connection to the central processing module; The data storage module is composed of a storage receiving module, a feature marking module, a flash memory docking module, a storage library module, a storage calling module, a feature value entry module, a path marking module and a library space monitoring module. The feature value entry module controls the connection path marking module, and the path marking module controls the connection library space monitoring module and the storage calling module respectively.

2. A power plant deep peak regulation system based on big data as described in claim 1, characterized in that: The data acquisition module is composed of a thermal power unit docking module, a fixed-point acquisition module, a data upload module, a data classification module, a clock recording module, a unit load module, a combustion parameter module, a steam parameter module and a coal quality characteristic module. The unit load module, the combustion parameter module, the steam parameter module and the coal quality characteristic module all control the connection to the data classification module.

3. A power plant deep peak regulation system based on big data as described in claim 2, characterized in that: The data classification module controls the connection to the data upload module, the data upload module controls the connection to the clock recording module and the fixed-point acquisition module respectively, and the fixed-point acquisition module controls the connection to the thermal power unit docking module.

4. A power plant deep peak regulation system based on big data as described in claim 1, characterized in that: The storage receiving module controls the connection feature marking module, the feature marking module controls the connection flash docking module, the flash docking module controls the connection feature value entry module and the storage library module respectively, and the storage library module controls the connection storage calling module and the library space monitoring module respectively.

5. A power plant deep peak regulation system based on big data as described in claim 1, characterized in that: The processing and analysis module is composed of a data calling module, a parameter sorting module, a linear analysis module, a data cleaning module, a data conversion module and a data output module. The data calling module controls the connection parameter sorting module.

6. A power plant deep peak regulation system based on big data as described in claim 5, characterized in that: The parameter sorting module controls the connection to the linear analysis module, and the linear analysis module controls the connection to the data cleaning module, the data cleaning module controls the connection to the data conversion module, and the data conversion module controls the connection to the data output module.

7. A power plant deep peak regulation system based on big data as described in claim 1, characterized in that: The optimization decision module is composed of a decision input module, a training classification module, a basic algorithm module, an optimization algorithm module, a big data docking module, an auxiliary decision module, a peak-shaving instruction module and a valley monitoring module. The training classification module controls the connection to the optimization algorithm module, and the optimization algorithm module controls the connection to the big data docking module.

8. A power plant deep peak regulation system based on big data as described in claim 7, characterized in that: The decision input module controls the connection to the training classification module, the training classification module controls the connection to the basic algorithm module, the basic algorithm module controls the connection to the optimization algorithm module, the optimization algorithm module controls the connection to the auxiliary decision module, the auxiliary decision module controls the connection to the peak-shaving instruction module, and the peak-shaving instruction module controls the connection to the valley monitoring module.

9. A deep peak-shaving method for power plants based on big data, using the deep peak-shaving system for power plants based on big data as described in any one of claims 1 to 8, characterized in that: include: Obtain data information of power plant power generation equipment; Performing linear analysis on the acquired data information to obtain processed data; The optimization algorithm is used to optimize and update the processed data, carry out regulation and control of the power plant, and complete the deep peak regulation of the power plant based on big data.

Images