Transmission side real-time data processing system and method based on multi-level deployment architecture

Abstract

The present invention discloses a real-time data processing system for transmission side based on a multi-level deployment architecture, including: a load data acquisition module, used to acquire the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment, an environmental data acquisition module, used to acquire the target environmental data associated with the target power grid at the current moment, a service resource acquisition module, used to acquire the power service acquisition resources of the target power grid at the current moment and the lowest power service acquisition resources within a preset time period, and a power grid load prediction module, used to receive data transmitted by each module, and determine the predicted load data of the target power grid in the preset time period according to the historical power load data, power demand data, target environmental data, the power service acquisition resources at the current moment and the lowest power service acquisition resources, and send the predicted load data to the distribution end through the communication module. It can improve the timeliness of load prediction and the accuracy of load prediction.

Description

Technical Field

[0001] The present invention relates to the field of power monitoring technology, and in particular to a real-time data processing system and method for power transmission side based on a multi-level deployment architecture. Background Art

[0002] With the continuous development of power technology, the scale of the power grid is also expanding. During the operation of the power grid, it has become an urgent problem to detect the power data in the power grid and ensure the balance between the power consumption end and the power transmission end.

[0003] In the prior art, historical power load data over a period of time is generally analyzed at a fixed node, and future loads are predicted using simple statistical methods.

[0004] In the above technical solution, data can only be analyzed at specific nodes, and the real-time performance is poor. In addition, the historical power load data cannot reflect the overall situation of the power grid operation, and the prediction results are less accurate. Summary of the invention

[0005] The present invention provides a real-time data processing system and method for power transmission side based on a multi-level deployment architecture to solve the problems of poor real-time performance and low accuracy of load prediction data in the prior art.

[0006] According to one aspect of the present invention, there is provided a real-time data processing system for transmission side based on a multi-level deployment architecture, comprising: a load data acquisition module, an environmental data acquisition module, a service resource acquisition module, a power grid load prediction module and a communication module;

[0007] The load data acquisition module is used to acquire the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment, and transmit the historical power load data and the power demand data to the power grid load prediction module;

[0008] The environmental data acquisition module is used to acquire target environmental data associated with the target power grid at the current moment, and transmit the target environmental data to the power grid load prediction module;

[0009] The service resource acquisition module is used to acquire the power service acquisition resource of the target power grid at the current moment and the lowest power service acquisition resource within a preset time period, and transmit them to the power grid load prediction module;

[0010] The power grid load prediction module is used to receive the historical power load data and the power demand data transmitted by the load data acquisition module, the target environment data transmitted by the environment data acquisition module, and the power service acquisition resources at the current moment and the minimum power service acquisition resources sent by the service resource acquisition module, determine the predicted load data of the target power grid in a preset time period based on the historical power load data, the power demand data, the target environment data, the power service acquisition resources at the current moment and the minimum power service acquisition resources, and send the predicted load data to the distribution end through the communication module.

[0011] According to another aspect of the present invention, a method for processing real-time data on a power transmission side based on a multi-level deployment architecture is provided, which is applied to a real-time data processing system on a power transmission side based on a multi-level deployment architecture. The method comprises:

[0012] Acquire historical power load data of the target power grid at a preset historical moment and power demand data at the current moment, and transmit the historical power load data and the power demand data to a power grid load prediction module;

[0013] Acquire target environmental data associated with the target power grid at the current moment, and transmit the target environmental data to a power grid load prediction module; wherein the target environmental data includes solar radiation data, ambient temperature data, air quality data, and fine particulate matter concentration data;

[0014] Obtain the power service acquisition resources of the target power grid at the current moment and the minimum power service acquisition resources within a preset time period, and transmit them to the power grid load prediction module;

[0015] The predicted load data of the target power grid in a preset time period is determined based on the historical power load data, the power demand data, the target environment data, the power service acquisition resources at the current moment and the minimum power service acquisition resources, and the predicted load data is sent to the distribution end through the communication module.

[0016] The technical solution of the embodiment of the present invention is to obtain the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment through the load data acquisition module, the environment data acquisition module obtains the target environment data associated with the target power grid at the current moment, and the service resource acquisition module obtains the power service acquisition resources of the target power grid at the current moment and the lowest power service acquisition resources within a preset time period, and transmits the acquired data to the power grid load prediction module. The power grid load prediction module receives the data transmitted by each module, and determines the predicted load data of the target power grid in the preset time period based on the historical power load data, power demand data, target environment data, power service acquisition resources at the current moment and the lowest power service acquisition resources, and sends the predicted load data to the distribution end through the communication module. It can improve the timeliness of load prediction and the accuracy of load prediction.

[0017] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a structural schematic diagram of a real-time data processing system at the transmission side based on a multi-level deployment architecture provided according to Embodiment 1 of the present invention;

[0020] Figure 2 It is a structural schematic diagram of another transmission side real-time data processing system based on a multi-level deployment architecture provided according to Embodiment 2 of the present invention;

[0021] Figure 3 It is a flowchart of a real-time data processing method at the transmission side based on a multi-level deployment architecture provided according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] Embodiment 1

[0025] Figure 1 This is a schematic diagram of the structure of a real-time data processing system for transmission side based on a multi-level deployment architecture provided in the first embodiment of the present invention. This embodiment is applicable to the case of predicting load data of the power grid. The system can be implemented in the form of hardware and / or software. Figure 1 As shown, the real-time data processing system on the transmission side based on the multi-level deployment architecture includes: a load data acquisition module 100, an environmental data acquisition module 110, a service resource acquisition module 120, a power grid load prediction module 130, a communication module 140 and a distribution terminal 150.

[0026] The load data acquisition module 100 can be used to obtain the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment, and transmit the historical power load data and the power demand data to the power grid load prediction module 130 .

[0027] Among them, the target power grid may be a specific power grid area that needs to predict load data through a real-time data processing system on the transmission side based on a multi-level deployment architecture. For example, an urban power grid, an industrial area power grid, or any other specific geographical or functionally divided power grid area. The preset historical moment may be a moment preset before predicting the load of the power grid. The historical power load data may be a record of the power load borne by the target power grid within the preset historical moment period. For example, the preset historical moment may be the moment before the current moment, and the corresponding historical power load data may be a record of the power load borne by the target power grid from the previous moment to the current moment. The power demand data at the current moment may be the power demand information recorded by the target power grid at a real-time or near real-time time point. The power demand data may include data such as the current total power consumption, the power demand distribution of different users or regions, etc. The power demand data may be obtained by sorting out the power demand data fed back in advance by the user, or may be obtained by other means. The embodiment of the present invention does not specifically limit the method for determining the power demand data,

[0028] The environment data acquisition module 110 is used to acquire target environment data associated with the target power grid at the current moment, and transmit the target environment data to the power grid load prediction module 130 .

[0029] Among them, the target environmental data can be the real-time environmental data of the target power grid at the current moment, which is collected in real time by the environmental data acquisition module. The target environmental data may include solar radiation data, ambient temperature data, air quality data, and fine particulate matter concentration data. Solar radiation data may be the radiation energy intensity and distribution data from the sun received by the clean power generation equipment in the target power grid on the surface. The ambient temperature data may be the current temperature in the area where the target power grid is located. The air quality data may be the concentration and type data of pollutants in the air. The fine particulate matter concentration data may be the particle concentration of PM2.5 (particles with a diameter less than or equal to 2.5 microns) in the air. Collecting the target environmental data through the environmental data acquisition module can provide rich input information for the power grid load prediction module, enabling it to more comprehensively consider the various factors affecting power demand, thereby improving the accuracy of the prediction.

[0030] The service resource acquisition module 120 is used to acquire the power service acquisition resources of the target power grid at the current moment and the lowest power service acquisition resources within a preset time period, and transmit them to the power grid load prediction module 130 .

[0031] Among them, the power service acquisition resource can be the corresponding resource that needs to be paid when the current time node is used to acquire power resources. The lowest power service acquisition resource within the preset time period can be the power service acquisition resource when the power service acquisition resource is the lowest within the preset time period. For example, when acquiring power resources, it is necessary to pay the resource value corresponding to the power resources according to the current electricity price, such as the current electricity price value. The lowest power service acquisition resource within the preset time period can be the minimum value of the corresponding resource value that needs to be paid when acquiring power resources within the preset time period, such as the lowest electricity price value within the preset time period.

[0032] The power grid load prediction module 130 is used to receive the historical power load data and power demand data transmitted by the load data acquisition module, the target environment data transmitted by the environment data acquisition module, and the power service acquisition resources at the current moment and the minimum power service acquisition resources sent by the service resource acquisition module, determine the predicted load data of the target power grid in a preset time period based on the historical power load data, power demand data, target environment data, the power service acquisition resources at the current moment and the minimum power service acquisition resources, and send the predicted load data to the distribution terminal 140 through the communication module 150.

[0033] The preset time period may be a certain time range in the future for which the power grid load prediction module performs load prediction. The preset time period may be a longer or shorter time period such as a few hours, a day, a week or a month. The predicted load data may be the predicted power load value of the target power grid within the preset time period calculated by the power grid load prediction module through a prediction model based on historical power load data, power demand data, target environment data, power service acquisition resources at the current moment and the minimum power service acquisition resources. The prediction model may be a pre-built model for calculating the predicted power load value of the target power grid within the preset time period.

[0034] Optionally, the environmental data acquisition module may include a solar radiation data acquisition unit 111, wherein the solar radiation data acquisition unit may be used to acquire a preset radiation value and a current radiation value at the current moment, and transmit the preset radiation value and the current radiation value to the power grid load prediction module. The power grid load prediction module includes: a solar radiation processing unit 131, which is used to determine a radiation impact index according to a preset radiation value and a current radiation value.

[0035] Among them, the preset radiation value can be a preset expected value or standard value of solar radiation. The preset radiation value can be an average value, median or other statistic calculated based on historical data, or it can be a preset reference value preset based on factors such as geographical location, season, weather type, etc. The current radiation value can be the actual measured value of solar radiation in real time or at the current moment. The current radiation value can be obtained in real time through a solar radiation sensor installed on the ground or on the roof, or it can be obtained by other means. The radiation impact index can be an index value used to characterize the impact of changes in solar radiation on the grid load. The radiation impact index can be determined by the solar radiation processing unit based on the preset radiation value and the current radiation value through a pre-constructed radiation impact index calculation model.

[0036] Optionally, the radiation impact index calculation model can be expressed as:

[0037]

[0038] Among them, S is the calculation model of radiation impact index, s(t) is the current radiation value at time t, and s ref is the preset radiation value.

[0039] The environmental data acquisition module includes an environmental temperature data acquisition unit 112, wherein the environmental temperature data acquisition unit is used to obtain the preset maximum environmental temperature, the preset minimum environmental temperature and the current environmental temperature value at the current moment, and transmit the preset maximum environmental temperature, the preset minimum environmental temperature and the current environmental temperature value to the power grid load prediction module. The power grid load prediction module also includes: an environmental temperature processing unit 132, which is used to determine the environmental temperature impact index according to the preset maximum environmental temperature, the preset minimum environmental temperature and the current environmental temperature value.

[0040] Among them, the preset maximum value of the ambient temperature may be the highest expected standard value that the preset ambient temperature may reach. The preset ambient temperature may be the highest temperature value calculated based on historical data, or a preset maximum temperature reference value based on factors such as geographical location, season, and weather type. The preset minimum value of the ambient temperature may be the lowest temperature reference value that the preset ambient temperature may reach. The preset minimum value of the ambient temperature may be the lowest temperature value obtained based on historical data, or a preset minimum temperature reference value based on factors such as geographical location, season, and weather type. The current ambient temperature value may be the actual measured value of the ambient temperature obtained in real time at the current moment. The current ambient temperature value may be temperature data obtained in real time by a temperature sensor installed on the ground, a building, or other suitable locations. The ambient temperature impact index may be an index used to characterize the impact of ambient temperature changes on the power grid load. The ambient temperature impact index may be determined by the ambient temperature processing unit through a pre-constructed ambient temperature index calculation model based on the preset maximum value of the ambient temperature, the preset minimum value of the ambient temperature, and the current ambient temperature value.

[0041] Optionally, the ambient temperature index calculation model can be expressed as:

[0042]

[0043] Where T is the ambient temperature index calculation model, temp(t) is the current ambient temperature value, and temp max is the preset maximum ambient temperature, temp min It is the preset minimum ambient temperature.

[0044] The environmental data acquisition module includes an air quality data acquisition unit 113, wherein the air quality data acquisition unit 113 is used to obtain a preset air quality value and a current air quality value at the current moment, and transmit the preset air quality value and the current air quality value to the power grid load prediction module. The power grid load prediction module also includes: an air quality processing unit 133, which is used to determine an air quality impact index according to the preset air quality value and the current air quality value.

[0045] Among them, the preset air quality value may be a preset expected air quality level. The preset air quality value may be an air quality value preset based on historical data or other data. The current air quality value may be air quality data monitored in real time or at the current moment. The current air quality value may be obtained in real time through air quality monitoring stations installed at various monitoring points, or may be obtained in other ways. The air quality impact index may be an index value used to characterize the impact of air quality changes on the grid load. The air quality impact index may be determined by the air quality processing unit through a pre-constructed air quality index calculation model based on the preset air quality value and the current air quality value.

[0046] Optionally, the air quality index calculation model can be expressed as:

[0047]

[0048] Among them, A is the air quality index calculation model, a(t) is the current air quality value, and a ref is the preset air quality value.

[0049] The environmental data acquisition module includes a fine particle concentration data acquisition unit 114; the power grid load prediction module includes a fine particle concentration data processing unit 134; wherein the particle concentration data acquisition unit 114 is used to obtain a preset fine particle concentration and a current fine particle concentration at the current moment, and transmit the preset fine particle concentration and the current fine particle concentration to the power grid load prediction module. The fine particle concentration data processing unit 134 is used to determine a fine particle impact index according to the preset fine particle concentration and the current fine particle concentration.

[0050] The preset fine particle concentration may be a standard value of a preset fine particle concentration. The current fine particle concentration may be fine particle concentration data monitored in real time or at the current moment. The fine particle impact index may be an index value used to characterize the impact of changes in fine particle concentration on the grid load. The fine particle impact index may be determined by the fine particle processing unit through a pre-built fine particle index calculation model according to the preset fine particle concentration and the current fine particle concentration.

[0051] Optionally, the fine particulate matter index calculation model can be expressed as:

[0052]

[0053] Among them, K is the fine particle index calculation model, k(t) is the current fine particle concentration, k ref The preset fine particle concentration.

[0054] The power grid load prediction module 130 includes: a resource sensitivity index determination unit 135 and a load data prediction unit 136; wherein the resource sensitivity index determination unit 135 is used to determine the resource sensitivity index according to the power service acquisition resource and the lowest power service acquisition resource within a preset time period.

[0055] The resource sensitivity index may be an index value used to characterize the impact of power service acquisition resources on power grid load. The resource sensitivity index may be determined by a resource sensitivity index determination unit through a pre-built resource sensitivity index calculation model according to the power service acquisition resources and the lowest power service acquisition resources in a preset time period.

[0056] Optionally, the resource sensitivity index calculation model can be expressed as:

[0057]

[0058] Among them, P is the resource sensitivity index calculation model, p(t) is the power service acquisition resource, and p min Acquire resources for the lowest electricity service for a preset time period.

[0059] Optionally, the load data prediction unit 136 is specifically used to determine the predicted load data of the target power grid during a preset time period based on historical power load data, power demand data, a preset radiation value, a preset maximum ambient temperature, a preset minimum ambient temperature and a target impact index, wherein the target impact index includes at least one of a radiation impact index, an ambient temperature impact index, an air quality impact index, a fine particulate matter impact index and a resource sensitivity index.

[0060] Optionally, the load data prediction unit 136 can be used to determine the predicted load data of the target power grid in a preset period of time according to historical power load data, power demand data, preset radiation value, preset maximum ambient temperature, preset minimum ambient temperature, and at least one of the radiation impact index, ambient temperature impact index, air quality impact index, fine particulate matter impact index, and resource sensitivity index included in the target impact index. When determining the predicted load data of the target power grid in a preset period of time according to the historical power load data, power demand data, preset radiation value, preset maximum ambient temperature, preset minimum ambient temperature, and one or more of the radiation impact index, ambient temperature impact index, air quality impact index, fine particulate matter impact index, and resource sensitivity index included in the target impact index, the index used in the target impact index can be calculated by the corresponding model, and the unused index in the target impact index can be set to a default value, that is, the index is set to a default normal value.

[0061] Exemplarily, when the predicted load data of the target power grid in a preset period is determined based on the historical power load data, power demand data, preset radiation value, preset maximum ambient temperature, preset minimum ambient temperature, and the radiation impact index included in the target impact index, the ambient temperature impact index, air quality impact index, fine particulate matter impact index, and resource sensitivity index in the target impact index can be set to default values, that is, the impact of the ambient temperature impact index, air quality impact index, fine particulate matter impact index, and resource sensitivity index on the predicted load data is not considered. When the predicted load data of the target power grid in a preset period is determined based on the historical power load data, power demand data, preset radiation value, preset maximum ambient temperature, preset minimum ambient temperature, and the ambient temperature impact index and radiation impact index included in the target impact index, the air quality impact index, fine particulate matter impact index, and resource sensitivity index in the target impact index can be set to default values, that is, the impact of the air quality impact index, fine particulate matter impact index, and resource sensitivity index on the predicted load data is not considered.

[0062] Optionally, the power grid load prediction module 130 is further used to determine the predicted load data of the target power grid in a preset period of time according to historical power load data, power demand data, preset radiation value, preset maximum ambient temperature value, preset minimum ambient temperature value and target impact index through a pre-constructed load data prediction model when the target impact index includes a radiation impact index, an ambient temperature impact index, an air quality impact index, a fine particulate matter impact index and a resource sensitivity index; wherein the load data prediction model is expressed as:

[0063]

[0064] Where L(t) is the predicted load data at time t, L(t-1) is the historical power load data at time t-1, d(t) is the power demand data at time t, P is the resource sensitivity index at time t, S is the radiation impact index at time t, and S ref is the preset radiation value, T is the ambient temperature impact index at time t, temp ma is the preset maximum ambient temperature, temp min is the preset minimum ambient temperature, A is the air quality impact index at time t, and K is the fine particulate matter impact index at time t.

[0065] The technical solution of the embodiment of the present invention is to obtain the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment through the load data acquisition module, determine the corresponding target impact index through the target environment data associated with the target power grid at the current moment obtained by the environment data acquisition module, and determine the resource sensitivity index through the power service acquisition resources of the target power grid at the current moment obtained by the service resource acquisition module and the lowest power service acquisition resources within a preset time period. It is possible to obtain data related to the load in the power grid and provide data with high accuracy for the prediction of power grid load data. The power grid load prediction module determines the predicted load data of the target power grid in the preset time period based on the historical power load data, power demand data, preset radiation value, preset maximum ambient temperature, preset minimum ambient temperature, and at least one of the radiation impact index, ambient temperature impact index, air quality impact index, fine particulate matter impact index and resource sensitivity index. It is possible to improve the timeliness of load prediction and the accuracy of load prediction.

[0066] Embodiment 2

[0067] Figure 2 A schematic diagram of a real-time data processing system for transmission side based on a multi-level deployment architecture is provided in the second embodiment of the present invention, such as Figure 2 As shown, the real-time data processing system on the transmission side based on the multi-level deployment architecture also includes: a data comparison module 160, a startup module 170, a power generation fluctuation detection module 180 and a stability analysis module 190.

[0068] The load prediction module 130 is also used to transmit the predicted load data to the data comparison module 160 through the communication module 140 .

[0069] The data comparison module 160 is used to receive the predicted load data, compare the predicted load data with a preset load threshold, and send a start instruction for the power generation fluctuation detection module to the start module 170 when the predicted load data is greater than or equal to the preset load threshold.

[0070] The preset load threshold may be a preset value or value range, which is used to characterize whether the current grid load of the target grid has reached the value or value range for starting the power generation fluctuation detection module. The start instruction may be an instruction for triggering the start of the power generation fluctuation detection module.

[0071] The starting module 170 is used to receive a starting instruction for the power generation fluctuation detection module and start the power generation fluctuation detection module according to the starting instruction.

[0072] The power generation fluctuation detection module 180 is used to detect the clean energy illumination data in the target power grid, determine the clean energy power generation fluctuation factor according to the detection result, and transmit the clean energy power generation fluctuation factor to the stability analysis module 190.

[0073] Among them, the clean energy power generation fluctuation factor can be used to characterize the fluctuation of the output power during the clean energy power generation process in the target power grid. The clean energy power generation fluctuation factor is affected by many factors, such as weather conditions or equipment performance. The clean energy power generation fluctuation factor can be determined by the fluctuation factor calculation model according to the standard deviation of the fluctuation of the new energy power generation in the target power grid within a preset time interval and the average value of the fluctuation of the new energy power generation.

[0074] Optionally, the volatility factor calculation model can be expressed as:

[0075]

[0076] Among them, BD is the clean energy power generation fluctuation factor, β is the standard deviation of the new energy power generation fluctuation, and μ is the average value of the new energy power generation fluctuation.

[0077] Optionally, the fluctuation factor calculation model may include a standard deviation calculation submodel and an average value calculation submodel. The standard deviation of the fluctuation of the renewable energy power generation may be determined by the standard deviation calculation submodel, and the average value of the fluctuation of the renewable energy power generation may be determined by the average value calculation submodel.

[0078] Among them, the standard deviation calculation sub-model can be expressed as:

[0079]

[0080] Among them, β is the standard deviation of the fluctuation of renewable energy power generation, N is the number of detections of renewable energy power generation indicators within the preset time interval, and each detection corresponds to a preset time subinterval within the preset time interval. E n It is the renewable energy power generation indicator within the nth preset time sub-interval obtained during the nth detection within the preset time interval.

[0081] Among them, the average value calculation sub-model can be expressed as:

[0082]

[0083] Among them, μ is the average value of the fluctuation of renewable energy power generation.

[0084] Optionally, the renewable energy power generation index within the nth preset time sub-interval within the preset time interval may be determined by the following model:

[0085] E n =mj×qd n×η×(jd n +sj n )

[0086] Among them, mj is the total area of ​​photovoltaic panels of new energy in the target power grid, qd n is the average light intensity in the nth preset time subinterval, η is the energy efficiency of the new energy in the target power grid, jd n is the illumination angle index within the nth preset time subinterval, sj n It is the total effective sunshine duration in the nth preset time sub-interval.

[0087] Optionally, the illumination angle index at the nth detection within a preset time interval may be determined by the following model:

[0088]

[0089] Among them, maxθ n is the maximum illumination angle within the nth preset time subinterval, minθ n is the minimum illumination angle within the nth preset time subinterval.

[0090] The stability analysis module 190 is used to determine the stability index of the clean energy of the target power grid according to the clean energy generation fluctuation factor, and transmit the current stable state to the distribution end, wherein the stability index is used to characterize the stability of the clean energy.

[0091] The stability index may be an index determined according to the clean energy power generation fluctuation factor and used to characterize the stability of clean energy power generation. The stability of clean energy may be the stability and reliability of the output power during the clean energy power generation process. If the clean energy power generation stability of the target power grid is high, it means that its output power fluctuation is small and it can stably provide power to the target power grid.

[0092] Optionally, the stability analysis module 190 is specifically used for:

[0093] Under the condition that the clean energy power generation fluctuation factor is greater than or equal to the preset fluctuation factor threshold, the current stable state of the clean energy of the target power grid is determined to be an unstable state; and under the condition that the clean energy power generation fluctuation factor is less than the preset fluctuation factor threshold, the current stable state of the clean energy of the target power grid is determined to be a stable state.

[0094] The preset fluctuation factor threshold may be a pre-set threshold used to measure whether the clean energy power generation fluctuation factor is in a stable state. The preset fluctuation factor threshold may be a pre-set threshold based on various factors such as historical data of clean energy power generation of the target power grid or the experience judgment of the power grid manager.

[0095] Exemplarily, when the clean energy power generation fluctuation factor is greater than or equal to the preset fluctuation factor threshold, it means that the output power fluctuation of clean energy power generation is large, which may have an adverse effect on the stable operation of the power grid. At this time, the current stable state of the clean energy of the target power grid will be judged as an unstable state, and corresponding measures will be taken to deal with this unstable state, such as generating response operations such as adjusting the power dispatching strategy or increasing the backup power supply strategy. Conversely, when the clean energy power generation fluctuation factor is less than the preset fluctuation factor threshold, it means that the output power fluctuation of clean energy power generation is small, and the impact on the stable operation of the power grid is small. Therefore, the system will judge the current stable state of the clean energy of the target power grid as a stable state, and continue to maintain the current power dispatching and operation and maintenance strategy.

[0096] The technical solution of the embodiment of the present invention is that the load prediction module transmits the predicted load data to the data comparison module through the communication module. After receiving the predicted load data, the data comparison module compares the predicted load data with the preset load threshold. When the predicted load data is greater than or equal to the preset load threshold, the startup instruction for the power generation fluctuation detection module is sent to the startup module. It can reduce the energy consumption of running the power generation fluctuation detection module. The startup module receives the startup instruction for the power generation fluctuation detection module and starts the power generation fluctuation detection module according to the startup instruction. After receiving the startup command, the power generation fluctuation detection module detects the clean energy illumination data in the target power grid, determines the clean energy power generation fluctuation factor according to the detection result, and transmits the clean energy power generation fluctuation factor to the stability analysis module. The stability analysis module determines the stability index of the clean energy of the target power grid according to the clean energy power generation fluctuation factor, and transmits the current stable state to the distribution end. It can quickly respond according to the determined load prediction data to improve the stability and safety of the power grid operation.

[0097] Embodiment 3

[0098] Figure 3 The flowchart of a method for processing real-time data on the transmission side based on a multi-level deployment architecture is provided in the third embodiment of the present invention. Figure 3 As shown, the method includes:

[0099] S110, obtaining the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment through the load data acquisition module, and transmitting the historical power load data and the power demand data to the power grid load prediction module.

[0100] S120, acquiring target environmental data associated with the target power grid at the current moment through the environmental data acquisition module, and transmitting the target environmental data to the power grid load prediction module.

[0101] S130. Obtain the power service acquisition resources of the target power grid at the current moment and the lowest power service acquisition resources within a preset time period through a service resource acquisition module, and transmit them to the power grid load prediction module.

[0102] S140. Determine the predicted load data of the target power grid in a preset period of time through the power grid load prediction module according to historical power load data, power demand data, target environment data, current power service acquisition resources and minimum power service acquisition resources, and send the predicted load data to the distribution end through the communication module.

[0103] The technical solution of the embodiment of the present invention is to obtain the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment through the load data acquisition module, the environment data acquisition module obtains the target environment data associated with the target power grid at the current moment, and the service resource acquisition module obtains the power service acquisition resources of the target power grid at the current moment and the lowest power service acquisition resources within a preset time period, and transmits the acquired data to the power grid load prediction module. The power grid load prediction module receives the data transmitted by each module, and determines the predicted load data of the target power grid in the preset time period based on the historical power load data, power demand data, target environment data, power service acquisition resources at the current moment and the lowest power service acquisition resources, and sends the predicted load data to the distribution end through the communication module. It can improve the timeliness of load prediction and the accuracy of load prediction.

[0104] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0105] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time data processing system for transmission side based on a multi-level deployment architecture, characterized in that: include: Load data acquisition module, environmental data acquisition module, service resource acquisition module, power grid load prediction module and communication module; The load data acquisition module is used to acquire the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment, and transmit the historical power load data and the power demand data to the power grid load prediction module; The environmental data acquisition module is used to acquire target environmental data associated with the target power grid at the current moment, and transmit the target environmental data to the power grid load prediction module; The service resource acquisition module is used to acquire the power service acquisition resource of the target power grid at the current moment and the lowest power service acquisition resource within a preset time period, and transmit them to the power grid load prediction module; The power grid load prediction module is used to receive the historical power load data and the power demand data transmitted by the load data acquisition module, the target environment data transmitted by the environment data acquisition module, and the power service acquisition resources at the current moment and the minimum power service acquisition resources sent by the service resource acquisition module, determine the predicted load data of the target power grid in a preset time period based on the historical power load data, the power demand data, the target environment data, the power service acquisition resources at the current moment and the minimum power service acquisition resources, and send the predicted load data to the distribution end through the communication module.

2. The real-time data processing system for transmission side based on multi-level deployment architecture according to claim 1 is characterized in that: The environmental data acquisition module includes a solar radiation data acquisition unit; wherein, The solar radiation data acquisition unit is used to acquire a preset radiation value and a current radiation value at a current moment, and transmit the preset radiation value and the current radiation value to a power grid load prediction module; The power grid load prediction module includes: a solar radiation processing unit, which is used to determine a radiation impact index according to the preset radiation value and the current radiation value.

3. The real-time data processing system for transmission side based on multi-level deployment architecture according to claim 1 is characterized in that: The environmental data acquisition module includes an environmental temperature data acquisition unit; wherein, The ambient temperature data acquisition unit is used to acquire a preset maximum ambient temperature, a preset minimum ambient temperature and a current ambient temperature value at a current moment, and transmit the preset maximum ambient temperature, the preset minimum ambient temperature and the current ambient temperature value to a power grid load prediction module; The power grid load prediction module further includes: an ambient temperature processing unit, which is used to determine an ambient temperature impact index according to the preset maximum ambient temperature value, the preset minimum ambient temperature value and the current ambient temperature value.

4. The real-time data processing system for transmission side based on multi-level deployment architecture according to claim 1 is characterized in that: The environmental data acquisition module includes an air quality data acquisition unit; wherein, The air quality data acquisition unit is used to acquire a preset air quality value and a current air quality value at a current moment, and transmit the preset air quality value and the current air quality value to a power grid load prediction module; The power grid load prediction module further includes: an air quality processing unit, which is used to determine an air quality impact index according to the preset air quality value and the current air quality value.

5. The real-time data processing system for transmission side based on multi-level deployment architecture according to claim 1 is characterized in that: The environmental data acquisition module includes a fine particle concentration data acquisition unit; the power grid load prediction module includes a fine particle concentration data processing unit; wherein, The particle concentration data acquisition unit is used to acquire a preset fine particle concentration and a current fine particle concentration at a current moment, and transmit the preset fine particle concentration and the current fine particle concentration to the power grid load prediction module; The fine particle concentration data processing unit is used to determine the fine particle impact index according to the preset fine particle concentration and the current fine particle concentration.

6. The real-time data processing system for transmission side based on multi-level deployment architecture according to claim 1 is characterized in that: The power grid load prediction module includes: a resource sensitivity index determination unit and a load data prediction unit; wherein, The resource sensitivity index determination unit is used to determine a resource sensitivity index according to the power service acquisition resource and the lowest power service acquisition resource within a preset time period; The load data prediction unit is used to determine the predicted load data of the target power grid in a preset time period based on the historical power load data, the power demand data, the preset radiation value, the preset maximum ambient temperature, the preset minimum ambient temperature and the target impact index, wherein the target impact index includes at least one of a radiation impact index, an ambient temperature impact index, an air quality impact index, a fine particulate matter impact index and a resource sensitivity index.

7. The real-time data processing system for transmission side based on multi-level deployment architecture according to claim 6 is characterized in that: The power grid load prediction module is used to determine the predicted load data of the target power grid in a preset period of time according to the historical power load data, the power demand data, the preset radiation value, the preset maximum ambient temperature, the preset minimum ambient temperature and the target impact index through a pre-constructed load data prediction model when the target impact index includes the radiation impact index, the ambient temperature impact index, the air quality impact index, the fine particulate matter impact index and the resource sensitivity index; wherein the load data prediction model is expressed as: Wherein, L(t) is the predicted load data at time t, L(t-1) is the historical power load data at time t-1, d(t) is the power demand data at time t, P is the resource sensitivity index at time t, S is the radiation impact index at time t, S ref is the preset radiation value, T is the ambient temperature impact index at time t, temp max is the preset maximum ambient temperature, temp min is the preset minimum ambient temperature, A is the air quality impact index at time t, and K is the fine particulate matter impact index at time t.

8. The real-time data processing system for transmission side based on multi-level deployment architecture according to claim 1 is characterized in that: The system also includes: a data comparison module, a startup module, a power generation fluctuation detection module and a stability analysis module; wherein, The load prediction module is further used to transmit the predicted load data to the data comparison module through the communication module; The data comparison module is used to receive the predicted load data, compare the predicted load data with a preset load threshold, and send a start instruction for the power generation fluctuation detection module to a start module when the predicted load data is greater than or equal to the preset load threshold; The starting module is used to receive a starting instruction for the power generation fluctuation detection module, and start the power generation fluctuation detection module according to the starting instruction; The power generation fluctuation detection module is used to detect the clean energy illumination data in the target power grid, determine the clean energy power generation fluctuation factor according to the detection result, and transmit the clean energy power generation fluctuation factor to the stability analysis module; The stability analysis module is used to determine the stability index of the clean energy of the target power grid according to the clean energy power generation fluctuation factor, and transmit the current stable state to the distribution end, wherein the stability index is used to characterize the stability of the clean energy.

9. The real-time data processing system for transmission side based on multi-level deployment architecture according to claim 7, characterized in that: The stability analysis module is specifically used for: Under the condition that the clean energy power generation fluctuation factor is greater than or equal to a preset fluctuation factor threshold, determining that the current stable state of the clean energy of the target power grid is an unstable state; as well as, Under the condition that the clean energy power generation fluctuation factor is less than the preset fluctuation factor threshold, it is determined that the current stable state of the clean energy of the target power grid is a stable state.

10. A real-time data processing method for transmission side based on a multi-level deployment architecture, characterized in that: Applied to the real-time data processing system for transmission side based on the multi-stage deployment architecture as described in any one of claims 1 to 9, the method comprising: The load data acquisition module acquires the historical power load data of the target power grid at a preset historical moment and the power demand data at the current moment, and transmits the historical power load data and the power demand data to the power grid load prediction module; Acquire target environmental data associated with the target power grid at the current moment through an environmental data acquisition module, and transmit the target environmental data to a power grid load prediction module; The service resource acquisition module acquires the power service acquisition resources of the target power grid at the current moment and the lowest power service acquisition resources within a preset time period, and transmits them to the power grid load prediction module; The power grid load prediction module determines the predicted load data of the target power grid in a preset period according to the historical power load data, the power demand data, the target environment data, the power service acquisition resources at the current moment and the minimum power service acquisition resources, and sends the predicted load data to the distribution end through the communication module.

Images