Power utilization network management system based on big data

Abstract

The invention relates to a power utilization network management system based on big data. The power utilization network management system comprises a first big data network element, a second big data network element, an intelligent analysis mechanism, a distribution operation mechanism and a model establishment mechanism. The power utilization network management system based on the big data is stable in operation and convenient to operate.

Description

Technical Field

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

[0002] Big data includes structured, semi-structured and unstructured data, and unstructured data is becoming the main part of data. According to a survey report, 80% of the data in enterprises is unstructured data, and this data is growing exponentially by 60% every year. Big data is a manifestation or feature of the development of the Internet to the current stage. With the backdrop of technological innovation represented by cloud computing, these data that originally seemed difficult to collect and use have begun to be easily utilized. Through continuous innovation in all walks of life, big data will gradually create more value.

[0003] However, there is still a lot of room for development in the application of big data, and some existing big data application solutions in the developed fields are not yet mature. The former requires application development, and the latter requires solution transformation. For example, in the data management of photovoltaic energy storage information, it is specifically about how to predict based on the existing energy storage data whether the photovoltaic energy storage equipment will supply power to a certain power network in the future time segment. Similar segmented application areas still need to be specifically developed using big data. Summary of the invention

[0004] In order to solve technical problems in related fields, the present invention provides an electricity network management system based on big data, which can use an AI analysis model to intelligently analyze the predicted value of the energy value reserved by the photovoltaic energy storage array in the target time segment based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​reserved by the photovoltaic energy storage array in each target time segment corresponding to each day in the past, and determine whether the photovoltaic energy storage array can supply power to the power network alone in the future time segment based on the required energy of the power network in the target time segment and the predicted value, thereby completing the specific application of big data in subdivided fields.

[0005] The system comprises: A first large data network element is used to obtain various array information of the photovoltaic energy storage array, wherein the various array information of the photovoltaic energy storage array includes the number of photovoltaic energy storage devices in the photovoltaic energy storage array, the maximum energy storage capacity of a single photovoltaic energy storage device, the light receiving plane area of ​​a single photovoltaic energy storage device, and the light receiving elevation angle of the photovoltaic energy storage device; The second data network element is used to set the next time segment of the current time segment as the target time segment, and obtain the energy values ​​of the photovoltaic energy storage array respectively stored in each target time segment corresponding to each day in the past; An intelligent analysis mechanism, connected to the first big data network element and the second big data network element respectively, for using an AI analysis model to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each previous day; An allocation operation mechanism, connected to the intelligent analysis mechanism, is used to determine whether the photovoltaic energy storage array can supply power to the power network alone in a future time segment based on the energy demand of the power network in the target time segment and the predicted value; A model building mechanism, connected to the intelligent analysis mechanism, for performing various learning actions on the feedforward neural network to obtain the AI ​​analysis model, and sending various model parameters of the AI ​​analysis model to the intelligent analysis mechanism; Wherein, determining whether the photovoltaic energy storage array can supply power to the power network alone in the future time segment based on the demand energy of the power network in the target time segment and the predicted value includes: when the demand energy of the power network in the target time segment is less than or equal to the predicted value, determining that the photovoltaic energy storage array can supply power to the power network alone in the future time segment; Wherein, determining whether the photovoltaic energy storage array can supply power to the power network alone in the future time segment based on the energy demand of the power network in the target time segment and the predicted value further includes: when the energy demand of the power network in the target time segment is greater than the predicted value, determining that the photovoltaic energy storage array cannot supply power to the power network alone in the future time segment, and that an additional energy storage mechanism needs to be added in the future time segment to cooperate with the photovoltaic energy storage array to supply power to the power network; Wherein, performing each learning action on the feedforward neural network to obtain the AI ​​analysis model, and sending each model parameter of the AI ​​analysis model to the intelligent analysis mechanism includes: the number of learning actions performed on the feedforward neural network is proportional to the number of photovoltaic energy storage devices of the photovoltaic energy storage array; Among them, based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each past day, an AI analysis model is used to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment, including: the number of days in the past is monotonically positively correlated with the total number of power-consuming equipment in the power network. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The embodiments of the present invention will be described below with reference to the accompanying drawings.

[0007] Figure 1 It is a diagram showing the internal structure of a power network management system based on big data according to the first embodiment of the present invention.

[0008] Figure 2 It is a diagram showing the internal structure of a power network management system based on big data according to a second embodiment of the present invention.

[0009] Figure 3 It is a diagram showing the internal structure of a power network management system based on big data according to the third embodiment of the present invention. DETAILED DESCRIPTION

[0010] The implementation scheme of the power network management system based on big data of the present invention will be described in detail with reference to the accompanying drawings.

[0011] First embodiment Figure 1 This is an internal structure diagram of a power network management system based on big data according to a first embodiment of the present invention, wherein the system comprises: A first large data network element is used to obtain various array information of the photovoltaic energy storage array, wherein the various array information of the photovoltaic energy storage array includes the number of photovoltaic energy storage devices in the photovoltaic energy storage array, the maximum energy storage capacity of a single photovoltaic energy storage device, the light receiving plane area of ​​a single photovoltaic energy storage device, and the light receiving elevation angle of the photovoltaic energy storage device; The second data network element is used to set the next time segment of the current time segment as the target time segment, and obtain the energy values ​​of the photovoltaic energy storage array respectively stored in each target time segment corresponding to each day in the past; For example, network components with different capacities may be used to implement the first large data network element and the second large data network element respectively; An intelligent analysis mechanism, connected to the first big data network element and the second big data network element respectively, for using an AI analysis model to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each previous day; An allocation operation mechanism, connected to the intelligent analysis mechanism, is used to determine whether the photovoltaic energy storage array can supply power to the power network alone in a future time segment based on the energy demand of the power network in the target time segment and the predicted value; A model building mechanism, connected to the intelligent analysis mechanism, for performing various learning actions on the feedforward neural network to obtain the AI ​​analysis model, and sending various model parameters of the AI ​​analysis model to the intelligent analysis mechanism; Wherein, determining whether the photovoltaic energy storage array can supply power to the power network alone in the future time segment based on the demand energy of the power network in the target time segment and the predicted value includes: when the demand energy of the power network in the target time segment is less than or equal to the predicted value, determining that the photovoltaic energy storage array can supply power to the power network alone in the future time segment; Wherein, determining whether the photovoltaic energy storage array can supply power to the power network alone in the future time segment based on the energy demand of the power network in the target time segment and the predicted value further includes: when the energy demand of the power network in the target time segment is greater than the predicted value, determining that the photovoltaic energy storage array cannot supply power to the power network alone in the future time segment, and that an additional energy storage mechanism needs to be added in the future time segment to cooperate with the photovoltaic energy storage array to supply power to the power network; Wherein, performing each learning action on the feedforward neural network to obtain the AI ​​analysis model, and sending each model parameter of the AI ​​analysis model to the intelligent analysis mechanism includes: the number of learning actions performed on the feedforward neural network is proportional to the number of photovoltaic energy storage devices of the photovoltaic energy storage array; Among them, based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​of the photovoltaic energy storage array respectively stored in each target time segment corresponding to each previous day, the predicted value of the energy value stored in the photovoltaic energy storage array in the target time segment is analyzed by using an AI analysis model, including: the number of days in the past is monotonically positively correlated with the total number of power-consuming devices in the power network; Among them, based on the duration of the target time segment, the various array information of the photovoltaic energy storage array, and the various energy values ​​stored by the photovoltaic energy storage array in the target time segments corresponding to the target time segments in the past, the AI ​​analysis model is used to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segments, which also includes: inputting the duration of the target time segment, the various array information of the photovoltaic energy storage array, and the various energy values ​​stored by the photovoltaic energy storage array in the target time segments corresponding to the target time segments in the past into the AI ​​analysis model in parallel.

[0012] Second embodiment Figure 2 It is a diagram showing the internal structure of a power network management system based on big data according to a second embodiment of the present invention.

[0013] exist Figure 2 In, with Figure 1 Differently, the power network management system based on big data shown in the second embodiment of the present invention may also include: A first large data network element is used to obtain various array information of the photovoltaic energy storage array, wherein the various array information of the photovoltaic energy storage array includes the number of photovoltaic energy storage devices in the photovoltaic energy storage array, the maximum energy storage capacity of a single photovoltaic energy storage device, the light receiving plane area of ​​a single photovoltaic energy storage device, and the light receiving elevation angle of the photovoltaic energy storage device; The second data network element is used to set the next time segment of the current time segment as the target time segment, and obtain the energy values ​​of the photovoltaic energy storage array respectively stored in each target time segment corresponding to each day in the past; An intelligent analysis mechanism, connected to the first big data network element and the second big data network element respectively, for using an AI analysis model to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each previous day; An allocation operation mechanism, connected to the intelligent analysis mechanism, is used to determine whether the photovoltaic energy storage array can supply power to the power network alone in a future time segment based on the energy demand of the power network in the target time segment and the predicted value; A model building mechanism, connected to the intelligent analysis mechanism, for performing various learning actions on the feedforward neural network to obtain the AI ​​analysis model, and sending various model parameters of the AI ​​analysis model to the intelligent analysis mechanism; a fault self-detection device, connected to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism, respectively, and used to measure the current fault code inside each of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism; Wherein, the fault self-checking device is respectively connected with the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism, and is used to respectively measure the current fault codes inside the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism, including: the fault self-checking device includes a plurality of fault self-checking units, which are respectively connected with the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism, so as to respectively measure the current fault codes inside the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism; The fault self-checking device includes a plurality of fault self-checking units, which are respectively connected to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism to respectively measure the current fault codes inside the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism, including: the internal structures of the plurality of fault self-checking units respectively used by the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism are the same; Among them, the fault self-detection device includes multiple fault self-detection units, which are used to respectively connect with the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism to respectively measure the current fault codes inside the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism. It also includes: the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism respectively use multiple fault self-detection units to perform internal self-detection operations.

[0014] Third embodiment Figure 3 It is a diagram showing the internal structure of a power network management system based on big data according to the third embodiment of the present invention.

[0015] exist Figure 3 In, with Figure 1 Differently, the power network management system based on big data shown in the third embodiment of the present invention may also include: A first large data network element is used to obtain various array information of the photovoltaic energy storage array, wherein the various array information of the photovoltaic energy storage array includes the number of photovoltaic energy storage devices in the photovoltaic energy storage array, the maximum energy storage capacity of a single photovoltaic energy storage device, the light receiving plane area of ​​a single photovoltaic energy storage device, and the light receiving elevation angle of the photovoltaic energy storage device; The second data network element is used to set the next time segment of the current time segment as the target time segment, and obtain the energy values ​​of the photovoltaic energy storage array respectively stored in each target time segment corresponding to each day in the past; An intelligent analysis mechanism, connected to the first big data network element and the second big data network element respectively, for using an AI analysis model to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each previous day; An allocation operation mechanism, connected to the intelligent analysis mechanism, is used to determine whether the photovoltaic energy storage array can supply power to the power network alone in a future time segment based on the energy demand of the power network in the target time segment and the predicted value; A model building mechanism, connected to the intelligent analysis mechanism, for performing various learning actions on the feedforward neural network to obtain the AI ​​analysis model, and sending various model parameters of the AI ​​analysis model to the intelligent analysis mechanism; The signal identification device is arranged near the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism and is respectively connected to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism, and is used for real-time measurement of the computing utilization percentage of the respective operators of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism.

[0016] Next, the specific structure of the big data-based power network management system of the present invention will be further described.

[0017] In the power network management system based on big data according to any embodiment of the present invention: The first large data network element, the second large data network element, the intelligent analysis mechanism and the model building mechanism all include a signal input unit and a signal output unit, and the signal input unit and the signal output unit both include a ground terminal.

[0018] And in the big data-based power network management system according to any embodiment of the present invention: The first large data network element, the second large data network element, the intelligent analysis mechanism and the model building mechanism are respectively implemented by different CPLD chips, and the CPLD chips are designed by VHDL language.

[0019] And in the big data-based power network management system according to any embodiment of the present invention: The first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are each provided with a plurality of heat dissipation holes on their respective shells, and the plurality of heat dissipation holes of any device of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are evenly distributed on their shells; Among them, the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are respectively provided with a plurality of heat dissipation holes on their respective outer shells, and the plurality of heat dissipation holes of any one of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are evenly distributed on their outer shells, including: the aperture values ​​of each of the plurality of heat dissipation holes of any one of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are the same.

[0020] In addition, in the big data-based electricity network management system, based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​respectively reserved by the photovoltaic energy storage array in each target time segment corresponding to each day in the past, an AI analysis model is used to intelligently analyze the predicted value of the energy value reserved by the photovoltaic energy storage array in the target time segment, which also includes: running the AI ​​analysis model to obtain the predicted value of the energy value reserved by the photovoltaic energy storage array in the target time segment output by the AI ​​analysis model.

[0021] It can be seen that the present invention has at least the following significant substantive features: First, multiple reliable basic data are selected for intelligent prediction of the total energy storage of the photovoltaic energy storage array in future time segments. The multiple basic data include the number of photovoltaic energy storage devices in the photovoltaic energy storage array, the maximum energy storage capacity of a single photovoltaic energy storage device, the light receiving plane area of ​​a single photovoltaic energy storage device, and the light receiving elevation angle of the photovoltaic energy storage device. It also includes the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each day in the past, thereby ensuring the validity of the intelligent prediction results; Second, performing each learning action on the feedforward neural network to obtain an AI analysis model for intelligent prediction, wherein the number of learning actions performed on the feedforward neural network is proportional to the number of photovoltaic energy storage devices in the photovoltaic energy storage array; Third: Based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each day in the past, an AI analysis model is used to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment, thereby providing valuable reference information for the subsequent power supply management of the photovoltaic energy storage array for the power network.

[0022] The foregoing description of the exemplary embodiments of the present invention is provided for the purpose of illustration and description. It is not intended to be exhaustive or to limit the present invention to the exact form disclosed. Obviously, many modifications and variations are obvious to those skilled in the art. The exemplary embodiments are selected and described in order to best illustrate the principles of the present invention and its practical application, so that other persons skilled in the art can understand the various embodiments and various variations of the present invention applicable to the specific purpose contemplated. It is intended that the scope of the present invention be limited by the appended claims and their equivalents.

Claims

1. A power network management system based on big data, characterized in that: The system comprises: A first large data network element is used to obtain various array information of the photovoltaic energy storage array, wherein the various array information of the photovoltaic energy storage array includes the number of photovoltaic energy storage devices in the photovoltaic energy storage array, the maximum energy storage capacity of a single photovoltaic energy storage device, the light receiving plane area of ​​a single photovoltaic energy storage device, and the light receiving elevation angle of the photovoltaic energy storage device; The second data network element is used to set the next time segment of the current time segment as the target time segment, and obtain the energy values ​​of the photovoltaic energy storage array respectively stored in each target time segment corresponding to each day in the past; An intelligent analysis mechanism, connected to the first big data network element and the second big data network element respectively, for using an AI analysis model to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each previous day; An allocation operation mechanism, connected to the intelligent analysis mechanism, is used to determine whether the photovoltaic energy storage array can supply power to the power network alone in a future time segment based on the energy demand of the power network in the target time segment and the predicted value; A model building mechanism, connected to the intelligent analysis mechanism, for performing various learning actions on the feedforward neural network to obtain the AI ​​analysis model, and sending various model parameters of the AI ​​analysis model to the intelligent analysis mechanism; Wherein, determining whether the photovoltaic energy storage array can supply power to the power network alone in the future time segment based on the demand energy of the power network in the target time segment and the predicted value includes: when the demand energy of the power network in the target time segment is less than or equal to the predicted value, determining that the photovoltaic energy storage array can supply power to the power network alone in the future time segment; Wherein, determining whether the photovoltaic energy storage array can supply power to the power network alone in the future time segment based on the energy demand of the power network in the target time segment and the predicted value further includes: when the energy demand of the power network in the target time segment is greater than the predicted value, determining that the photovoltaic energy storage array cannot supply power to the power network alone in the future time segment, and that an additional energy storage mechanism needs to be added in the future time segment to cooperate with the photovoltaic energy storage array to supply power to the power network; Wherein, performing each learning action on the feedforward neural network to obtain the AI ​​analysis model, and sending each model parameter of the AI ​​analysis model to the intelligent analysis mechanism includes: the number of learning actions performed on the feedforward neural network is proportional to the number of photovoltaic energy storage devices of the photovoltaic energy storage array; Among them, based on the duration of the target time segment, various array information of the photovoltaic energy storage array, and the energy values ​​stored by the photovoltaic energy storage array in each target time segment corresponding to each past day, an AI analysis model is used to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment, including: the number of days in the past is monotonically positively correlated with the total number of power-consuming equipment in the power network.

2. The power network management system based on big data according to claim 1, characterized in that: Based on the duration of the target time segment, the various array information of the photovoltaic energy storage array, and the energy values ​​respectively stored by the photovoltaic energy storage array in each target time segment corresponding to each day in the past, an AI analysis model is used to intelligently analyze the predicted value of the energy value stored by the photovoltaic energy storage array in the target time segment, which also includes: inputting the duration of the target time segment, the various array information of the photovoltaic energy storage array, and the energy values ​​respectively stored by the photovoltaic energy storage array in each target time segment corresponding to each day in the past into the AI ​​analysis model in parallel.

3. The power network management system based on big data according to claim 2, characterized in that: The system comprises: a fault self-detection device, connected to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism, respectively, and used to measure the current fault code inside each of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism; Among them, the fault self-detection device is respectively connected to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism, and is used to respectively measure the current fault codes inside the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism. The fault self-detection device includes multiple fault self-detection units, which are respectively connected to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism, so as to respectively measure the current fault codes inside the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism.

4. The power network management system based on big data according to claim 3, characterized in that: The fault self-detection device includes multiple fault self-detection units, which are used to connect to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism respectively, so as to respectively measure the current fault codes inside the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism. The internal structures of the multiple fault self-detection units respectively used by the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism are the same.

5. The power network management system based on big data according to claim 4, characterized in that: The fault self-detection device includes multiple fault self-detection units, which are used to connect to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism respectively, so as to respectively measure the current fault codes inside the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism. It also includes: the first big data network element, the second big data network element, the intelligent analysis mechanism and the model establishment mechanism respectively use multiple fault self-detection units to perform internal self-detection operations.

6. The power network management system based on big data according to claim 2, characterized in that: The system further comprises: The signal identification device is arranged near the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism and is respectively connected to the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism, and is used for real-time measurement of the computing utilization percentage of the respective operators of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism.

7. The power network management system based on big data according to any one of claims 2 to 6, characterized in that: The first large data network element, the second large data network element, the intelligent analysis mechanism and the model building mechanism all include a signal input unit and a signal output unit, and the signal input unit and the signal output unit both include a ground terminal.

8. The power network management system based on big data according to any one of claims 2 to 6, characterized in that: The first large data network element, the second large data network element, the intelligent analysis mechanism and the model building mechanism are respectively implemented by different CPLD chips, and the CPLD chips are designed by VHDL language.

9. The power network management system based on big data according to any one of claims 2 to 6, characterized in that: The first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are each provided with a plurality of heat dissipation holes on their respective shells, and the plurality of heat dissipation holes of any device of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are evenly distributed on their shells; Among them, the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are respectively provided with a plurality of heat dissipation holes on their respective outer shells, and the plurality of heat dissipation holes of any one of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are evenly distributed on their outer shells, including: the aperture values ​​of each of the plurality of heat dissipation holes of any one of the first big data network element, the second big data network element, the intelligent analysis mechanism and the model building mechanism are the same.

Images