Data transmission optimization method and system based on energy big data center

Abstract

The invention relates to the technical field of data transmission, in particular to a data transmission optimization method and system based on an energy big data center, and the method comprises the steps: recognizing a bandwidth bottleneck in advance through a traffic prediction mode, avoiding the processing hysteresis caused by a manual intervention mode after a conventional passive alarm, and responding to the bandwidth bottleneck in advance. According to a data consumption information prediction result, a reference priority corresponding to each energy data type is determined, a data priority is determined in combination with a service demand, and when data is transmitted according to a priority hierarchical architecture, high-demand data is ensured to be transmitted preferentially, key service delay or interruption caused by insufficient bandwidth is avoided, and the data transmission efficiency is improved. In addition, the low-priority data share the residual bandwidth through time division multiplexing, the data transmission balance of each data source is improved, the data transmission optimization does not need to modify the device, and when a new data source is newly added or a new energy data type is entered, rapid adaptation can be achieved, and both expansibility and flexibility are high.

Description

Technical Field

[0001] The present invention relates to the field of data transmission technology, and in particular to a data transmission optimization method and system based on an energy big data center. Background Art

[0002] In order to strengthen the aggregation and management of energy big data and solve problems such as difficulty in data aggregation, decentralized management of data resources, poor timeliness of data access, and cross-regional network isolation, the existing method uses the energy big data center to realize the aggregation and fusion of multi-type energy indicator data, and completes the aggregation and access of energy data indicators such as electricity, coal, oil, and natural gas from multiple data sources, thereby providing a data foundation for application scenarios such as energy scenario construction and data services.

[0003] In the existing technology, energy big data centers are usually deployed with network security isolation devices, which only receive data of specific protocols and then forward them to the data center of the energy big data center to improve the security and reliability of data transmission and storage.

[0004] However, when data is transmitted through a network security isolation device, fluctuations in data traffic may cause transmission delays or interruptions, which in turn may cause business delays or interruptions, resulting in poor efficiency in data transmission required for the business. The existing method requires replacing the network security isolation device to provide higher data transmission bandwidth, and the simplicity and convenience of data transmission optimization are poor.

[0005] Therefore, how to improve the efficiency of business data transmission has become an urgent problem to be solved. Summary of the Invention

[0006] In response to the above technical problems, the technical solution adopted by the present invention is a data transmission optimization method based on an energy big data center, which includes: S101, predicting the reference traffic of the network isolation device obtained at I preset time points to obtain the predicted traffic corresponding to the target time point, where I is a positive integer.

[0007] S102: If the predicted traffic volume is greater than the preset traffic volume threshold, a prediction is performed based on the data consumption information of N data consumption terminals obtained at I preset time points to obtain the predicted consumption information corresponding to the target time point. The predicted consumption information includes the predicted consumption data volumes corresponding to J energy data types, where N and J are positive integers.

[0008] S103: Determine reference priorities corresponding to respective energy data types according to the predicted consumption information.

[0009] S104, obtaining data generation distribution information corresponding to M data sources, and determining a target priority threshold according to the data generation distribution information corresponding to each data source and the reference priority corresponding to each energy data type, where M is a positive integer.

[0010] S105. For any data source, after the target time point, if the reference priority of the energy data type to which the collected data sent by the data source to the network isolation device belongs is greater than the target priority threshold, the collected data is directly sent to the network isolation device; otherwise, the collected data is sent to the network isolation device using time division multiplexing.

[0011] The present invention also provides a data transmission optimization system based on an energy big data center, the data transmission optimization system based on an energy big data center includes: A traffic prediction module is used to predict the reference traffic of the network isolation device obtained at I preset time points, and obtain the predicted traffic corresponding to the target time point, where I is a positive integer; a consumption prediction module configured to, if the predicted flow rate is greater than a preset flow rate threshold, perform a prediction based on the data consumption information of N data consumers obtained at I preset time points to obtain predicted consumption information corresponding to a target time point, wherein the predicted consumption information includes predicted consumption data volumes corresponding to J energy data types, where N and J are positive integers; a priority determination module, configured to determine reference priorities corresponding to respective energy data types based on the predicted consumption information; a threshold determination module, configured to obtain data generation distribution information corresponding to M data sources, and determine a target priority threshold based on the data generation distribution information corresponding to each data source and the reference priority corresponding to each energy data type, where M is a positive integer; The data transmission module is used for sending the collected data to the network isolation device directly to the network isolation device after the target time point if the reference priority of the energy data type to which the collected data sent by the data source to the network isolation device belongs is greater than the target priority threshold; otherwise, the collected data is sent to the network isolation device using time division multiplexing.

[0012] The present invention has at least the following beneficial effects: identifying bandwidth bottlenecks in advance through traffic prediction, avoiding processing lags caused by traditional passive alarm followed by manual intervention, responding to bandwidth bottlenecks in advance, determining the reference priority corresponding to each energy data type based on the data consumption information prediction results, determining data priority in combination with business needs, and ensuring that high-demand data is transmitted first when transmitting data according to the priority hierarchical architecture, avoiding delays or interruptions in critical business due to insufficient bandwidth, and improving the efficiency of business data transmission. In addition, low-priority data shares the remaining bandwidth through time division multiplexing, improving the balance of data transmission of each data source, and avoiding data loss caused by local data accumulation of the data source. In addition, data transmission optimization does not require modification of the device itself, and can quickly adapt when adding new data sources or entering new energy data types, with strong scalability and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] 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.

[0014] Figure 1 This is a flow chart of a data transmission optimization method based on an energy big data center provided in Example 1 of the present invention; Figure 2 This is a schematic diagram of a data transmission optimization system based on an energy big data center provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first", "second", etc. in the description 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 is understood that, where appropriate, the above-mentioned terms used to distinguish similar objects can be interchanged so that the present invention can also implement other embodiments other than the above-mentioned illustrated embodiments or described embodiments. 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 server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] Example 1 This embodiment provides a data transmission optimization method based on energy big data center, such as Figure 1 FIG. 1 is a flowchart of a data transmission optimization method based on an energy big data center provided by an embodiment of the present invention. The data transmission optimization method based on an energy big data center includes: S101, predicting the reference traffic of the network isolation device obtained at I preset time points to obtain the predicted traffic corresponding to the target time point, where I is a positive integer; S102: If the predicted flow rate is greater than a preset flow rate threshold, a prediction is performed based on the data consumption information of N data consumers obtained at I preset time points to obtain predicted consumption information corresponding to the target time point, wherein the predicted consumption information includes predicted consumption data volumes corresponding to J energy data types, where N and J are positive integers. S103, determining reference priorities corresponding to respective energy data types based on the predicted consumption information; S104, obtaining data generation distribution information corresponding to M data sources, and determining a target priority threshold based on the data generation distribution information corresponding to each data source and the reference priority corresponding to each energy data type, where M is a positive integer; S105. For any data source, after the target time point, if the reference priority of the energy data type to which the collected data sent by the data source to the network isolation device belongs is greater than the target priority threshold, the collected data is directly sent to the network isolation device; otherwise, the collected data is sent to the network isolation device using time division multiplexing.

[0018] Among them, the data source can refer to edge-side devices, including sensors, edge-side terminals, etc. The data consumption end can correspond to different business types, and the data consumption end can be used to use data.

[0019] Network isolation devices can be used to improve the security of data transmission, and the data middle platform can be used to distribute, store and perform real-time calculations on data.

[0020] The time interval between adjacent preset time points can be a fixed value. The preset traffic threshold can be calculated based on the maximum bandwidth of the network isolation device, the preset bandwidth ratio and the time interval between adjacent preset time points. The preset traffic threshold is obtained by multiplying the maximum bandwidth, the preset bandwidth ratio and the time interval between adjacent preset time points. In this embodiment, the preset bandwidth ratio can be set to 0.9.

[0021] Energy data types may include electricity, coal, natural gas, etc. Furthermore, under the electricity type, it can be divided into power generation, load, electricity price, etc. Under the coal type, it can include calorific value, output, inventory, etc. Implementers can determine the energy data type according to actual needs.

[0022] The data consumption information may include actual consumption data volumes corresponding to the J energy data types. The actual consumption data volume may refer to the consumption data volume from a preset time point before the corresponding preset time point to the corresponding preset time point.

[0023] The reference priority can be used to represent the transmission priority of data of different energy data types.

[0024] In a specific embodiment, the energy big data center includes a data middle platform, which includes a public library and a Datahub message queue. The network isolation device is used to receive collected data that complies with a preset protocol, and then send the received collected data to the public library. The public library is used to push the received collected data to the Datahub message queue. The Datahub message queue is used to distribute the received collected data to N data consumption terminals for data consumption.

[0025] Among them, the preset protocol can refer to the JDBC (Java Database Connectivity) protocol. The data center (Datahub) message queue supports high-throughput, low-latency, and elastically scalable data flow requirements. It can be responsible for real-time reception, buffering, and distribution of massive data, solving the speed matching problem between data sources and computing / storage systems.

[0026] Specifically, the data center can also include a stream computing engine to support the cleaning, conversion, aggregation, and analysis of real-time data in the Datahub message queue, and output results that can be directly used for business decision-making.

[0027] The data center can also include a storage database, which is used to store data in the Datahub message queue for a long time.

[0028] In a specific embodiment, the prediction is performed based on the reference traffic of the network isolation device obtained at each preset time point to obtain the predicted traffic corresponding to the target time point, including: The reference traffic of the network isolation device obtained at I preset time points is input into the trained traffic prediction model for prediction to obtain the predicted traffic corresponding to the target time point.

[0029] Among them, the traffic prediction model can adopt a time series prediction model, and the time series prediction model can use a recurrent neural network model, a long short-term memory network model, a time domain convolution model, etc. The architecture and training of the time series prediction model are existing technologies and will not be repeated here.

[0030] Specifically, the target time point can be the I+Kth preset time point. The reference flow obtained from the 1st preset time point to the Ith preset time point is input into the trained flow prediction model for prediction to obtain the predicted flow at the I+1th preset time point. Then, the reference flow obtained from the 2nd preset time point to the Ith preset time point and the predicted flow at the I+1th preset time point are input into the trained flow prediction model for prediction to obtain the predicted flow at the I+2th preset time point. And so on, until the predicted flow corresponding to the I+Kth preset time point is obtained, where K is a positive integer. In this embodiment, K can be set to 5.

[0031] In a specific embodiment, the step of performing prediction based on the data consumption information of N data consumers respectively obtained at one preset time point to obtain the predicted consumption information corresponding to the target time point includes: For any preset time point, the data consumption information corresponding to each data consumption terminal obtained at the preset time point is added together, and the sum is used as the comprehensive consumption information corresponding to the preset time point; The comprehensive consumption information corresponding to each of the I preset time points is input into the trained consumption information prediction model for prediction to obtain the predicted consumption information corresponding to the target time point.

[0032] Among them, the data consumption information may include the actual consumption data volume corresponding to the corresponding data consumption end under J energy data types, and the comprehensive consumption information may include the comprehensive consumption data volume corresponding to all data consumption ends under J energy data types.

[0033] The consumption information prediction model can adopt a time series prediction model. The architecture and training of the time series prediction model are both existing technologies. The reasoning process of the time series prediction model refers to the reasoning process of the traffic prediction model, which will not be repeated here.

[0034] In a specific embodiment, determining the reference priority corresponding to each energy data type according to the predicted consumption information includes: Sort each energy data type according to the predicted consumption data amount corresponding to each energy data type to obtain a first type sequence; For any energy data type, determining an initial priority corresponding to the energy data type according to the position of the energy data type in the first type sequence; Determine a consumption data volume change value corresponding to the energy data type based on the predicted consumption data volume corresponding to the energy data type and the comprehensive consumption data volume corresponding to the comprehensive consumption information corresponding to the energy data type at the first preset time point; Using a preset mapping function, the consumption data amount change value is mapped to a priority offset value corresponding to the energy data type; A reference priority corresponding to the energy data type is determined according to the initial priority and the priority offset value corresponding to the energy data type.

[0035] Among them, in the first type sequence, the energy data type with a higher predicted consumption data volume is ranked lower. It is easy to know that the value range of the initial priority is an integer in [1, J].

[0036] Specifically, the predicted consumption data volume corresponding to the energy data type is subtracted from the comprehensive consumption data volume corresponding to the comprehensive consumption information corresponding to the energy data type at the first preset time point to obtain the consumption data volume change value corresponding to the energy data type.

[0037] The default mapping function can be y=0.5tan -1 (p×x), where x is the change in the amount of consumed data, y is the priority offset value, and p is the adjustment coefficient. The adjustment coefficient can be used to support different data volume levels in different scenarios. In this embodiment, p can be set to 1 / 1000, and the priority offset value range is (-1,1). The priority offset value can represent the change in the degree of data demand. When the priority offset value corresponding to a certain energy data type is close to -1, it can indicate that the data demand degree of the energy data type has been greatly reduced, and its reference priority should also be reduced accordingly.

[0038] The initial priority and priority offset value corresponding to the energy data type are added together, and the result of the addition is used as the temporary priority corresponding to the energy data type. According to the temporary priorities corresponding to each energy data type, each energy data type is reordered to obtain a second type sequence. For any energy data type, the reference priority corresponding to the energy data type is determined according to the position of the energy data type in the second type sequence, thereby ensuring that the reference priorities are all integers, which is convenient for subsequent processing.

[0039] In a specific embodiment, determining the target priority threshold according to the data generation distribution information corresponding to each data source and the reference priority corresponding to each energy data type includes: Add the data generation distribution information corresponding to each data source obtained, and use the added result as the overall distribution information; The target priority threshold is determined according to the overall distribution information and the reference priorities corresponding to each energy data type.

[0040] Among them, the data generation distribution information may include the data increments corresponding to each energy data type of the corresponding data source between the previous preset time point and the current preset time point. Correspondingly, the overall distribution information may include the data increments corresponding to each energy data type of all data sources between the previous preset time point and the current preset time point.

[0041] In a specific embodiment, determining the target priority threshold according to the overall distribution information and the reference priorities corresponding to each energy data type includes: Adjusting the overall distribution information according to the reference priorities corresponding to the various energy data types to obtain target distribution information; Obtain a preset traffic ratio, and determine the target priority threshold based on the target distribution information, the predicted traffic corresponding to the target time point, and the preset traffic ratio.

[0042] The target distribution information identifies the energy data type with the corresponding reference priority, that is, the target distribution information includes the data increment corresponding to each reference priority.

[0043] Specifically, the predicted traffic corresponding to the target time point is multiplied by the preset traffic ratio to obtain the multiplication result, and each reference priority is traversed from large to small. If a reference priority meets the conditions: calculate the sum of the data increments corresponding to each reference priority that is greater than the reference priority. If the calculated sum of the data increments is greater than the multiplication result, then the reference priority is used as the target priority threshold.

[0044] In a specific embodiment, the preset flow threshold is initially a basic flow value; After step S104, the following steps are also included: The preset flow threshold is updated according to the predicted flow corresponding to the target time point.

[0045] Among them, in order to avoid frequent updates of the reference priority and target priority thresholds, which would lead to a waste of computing resources, this embodiment updates the preset traffic threshold after determining the target priority threshold. The specific updating method can be to compare the predicted traffic with the preset bandwidth ratio, and update the preset traffic threshold with the ratio calculation result. In this way, when the predicted traffic does not change much, the reference priority and target priority thresholds do not need to be updated. When the predicted traffic changes greatly, the reference priority and target priority thresholds are updated.

[0046] In a specific embodiment, after step S102, the following steps are further included: If the predicted traffic is less than or equal to the basic traffic value, the target priority threshold is set to a first preset value, the preset traffic threshold is reset to the basic traffic value, and the process jumps to step S105.

[0047] Among them, if the predicted flow is less than or equal to the basic flow value, it means that the corresponding target time point is no longer a situation of insufficient data transmission bandwidth, and the target priority threshold is set to the first preset value, which can be 0, and the process jumps to step S105. At this time, the reference priority of the collected data of any energy data type is greater than the target priority threshold, that is, all collected data are directly sent to the network isolation device.

[0048] In a specific embodiment, the network isolation device is used to determine a target source corresponding to a target time slice from M data sources according to a preset arbitration method, and send a receive signal to the target source corresponding to the target time slice at a starting time point of the target time slice, wherein the starting time point of the target time slice is greater than the target time point; The step of sending the collected data to the network isolation device in a time division multiplexing manner includes: When the data source receives the receiving signal, it sends the collected data to the network isolation device.

[0049] Among them, the starting time point of the target time slice can be the I+K+Qth preset time point, and the ending time point of the target time slice can be the I+K+Rth preset time point, Q is an integer greater than or equal to zero, and R is an integer greater than Q.

[0050] The preset arbitration method may adopt round-robin arbitration, priority arbitration based on the priority of data sources determined based on the amount of non-high-demand data, and the like.

[0051] Specifically, several target time slices are divided from the target time point. The network isolation device selects the target source corresponding to each target time slice through polling arbitration, and only receives the collected data sent by the target source in the corresponding time slice, realizing time-division multiplexing of the bandwidth. Under the premise of unchanged overall transmission efficiency, the balance of transmission efficiency of each data source is improved, and the bandwidth is avoided from being occupied by high-demand data, resulting in data accumulation in the local data source and causing data loss.

[0052] In the first embodiment of the present invention, bandwidth bottlenecks are identified in advance through traffic prediction, avoiding processing delays caused by manual intervention after traditional passive alarms, responding to bandwidth bottlenecks in advance, determining the reference priority corresponding to each energy data type based on the data consumption information prediction results, determining data priority in combination with business needs, and ensuring that high-demand data is transmitted first when transmitting data according to the priority layered architecture, avoiding delays or interruptions in critical business due to insufficient bandwidth, and improving the efficiency of business data transmission. In addition, low-priority data shares the remaining bandwidth through time division multiplexing, improving the balance of data transmission of each data source, and avoiding data loss caused by local data accumulation of the data source. In addition, data transmission optimization does not require modification of the device itself, and can quickly adapt when adding new data sources or entering new energy data types, with strong scalability and flexibility.

[0053] Example 2 This embodiment 2 provides a data transmission optimization system based on energy big data center, such as Figure 2 FIG. 1 is a schematic diagram of a data transmission optimization system based on an energy big data center provided in a second embodiment of the present invention. The data transmission optimization system based on an energy big data center includes: The traffic prediction module 201 is used to predict the reference traffic of the network isolation device obtained at I preset time points, and obtain the predicted traffic corresponding to the target time point, where I is a positive integer; The consumption prediction module 202 is configured to, if the predicted flow rate is greater than a preset flow rate threshold, perform a prediction based on the data consumption information of N data consumers obtained at I preset time points to obtain predicted consumption information corresponding to a target time point, wherein the predicted consumption information includes predicted consumption data volumes corresponding to J energy data types, where N and J are positive integers; A priority determination module 203 is configured to determine the reference priority corresponding to each energy data type according to the predicted consumption information; A threshold determination module 204 is configured to obtain data generation distribution information corresponding to M data sources, and determine a target priority threshold based on the data generation distribution information corresponding to each data source and the reference priority corresponding to each energy data type, where M is a positive integer. The data transmission module 205 is used for sending the collected data to the network isolation device directly to the network isolation device after the target time point if the reference priority of the energy data type to which the collected data sent by the data source to the network isolation device belongs is greater than the target priority threshold; otherwise, the collected data is sent to the network isolation device using time division multiplexing.

[0054] It should be noted that the specific limitations of the data transmission optimization system based on the energy big data center can be found in the limitations of the data transmission optimization method based on the energy big data center mentioned above, and will not be repeated here. The information interaction and execution process between the above modules, etc., are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the embodiment of the method, and will not be repeated here.

[0055] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any form. Although the present invention has been disclosed as above in terms of preferred embodiments, they are not intended to limit the present invention. Any technician familiar with this profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A data transmission optimization method based on energy big data center, characterized in that: The data transmission optimization method comprises: S101, predicting the reference traffic of the network isolation device obtained at I preset time points to obtain the predicted traffic corresponding to the target time point, where I is a positive integer; S102: If the predicted flow rate is greater than a preset flow rate threshold, a prediction is performed based on the data consumption information of N data consumers obtained at I preset time points to obtain predicted consumption information corresponding to the target time point, wherein the predicted consumption information includes predicted consumption data volumes corresponding to J energy data types, where N and J are positive integers. S103, determining reference priorities corresponding to respective energy data types based on the predicted consumption information; S104, obtaining data generation distribution information corresponding to M data sources, and determining a target priority threshold based on the data generation distribution information corresponding to each data source and the reference priority corresponding to each energy data type, where M is a positive integer; S105. For any data source, after the target time point, if the reference priority of the energy data type to which the collected data sent by the data source to the network isolation device belongs is greater than the target priority threshold, the collected data is directly sent to the network isolation device; otherwise, the collected data is sent to the network isolation device using time division multiplexing.

2. The data transmission optimization method based on the energy big data center according to claim 1 is characterized in that: The energy big data center includes a data middle platform, which includes a public library and a Datahub message queue. The network isolation device is used to receive collected data that complies with the preset protocol, and then send the received collected data to the public library. The public library is used to push the received collected data to the Datahub message queue. The Datahub message queue is used to distribute the received collected data to N data consumption terminals for data consumption.

3. The data transmission optimization method based on the energy big data center according to claim 1 is characterized in that: The method of predicting the reference traffic of the network isolation device obtained at each preset time point to obtain the predicted traffic corresponding to the target time point includes: The reference traffic of the network isolation device obtained at I preset time points is input into the trained traffic prediction model for prediction to obtain the predicted traffic corresponding to the target time point.

4. The data transmission optimization method based on the energy big data center according to claim 1 is characterized in that: The step of predicting the data consumption information of N data consumption terminals respectively obtained at one preset time point to obtain the predicted consumption information corresponding to the target time point includes: For any preset time point, the data consumption information corresponding to each data consumption terminal obtained at the preset time point is added together, and the sum is used as the comprehensive consumption information corresponding to the preset time point; The comprehensive consumption information corresponding to each of the I preset time points is input into the trained consumption information prediction model for prediction to obtain the predicted consumption information corresponding to the target time point.

5. The data transmission optimization method based on the energy big data center according to claim 4 is characterized in that: Determining reference priorities corresponding to respective energy data types based on the predicted consumption information includes: Sort each energy data type according to the predicted consumption data amount corresponding to each energy data type to obtain a first type sequence; For any energy data type, determining an initial priority corresponding to the energy data type according to the position of the energy data type in the first type sequence; Determine a consumption data volume change value corresponding to the energy data type based on the predicted consumption data volume corresponding to the energy data type and the comprehensive consumption data volume corresponding to the comprehensive consumption information corresponding to the energy data type at the first preset time point; Using a preset mapping function, the consumption data amount change value is mapped to a priority offset value corresponding to the energy data type; A reference priority corresponding to the energy data type is determined according to the initial priority and the priority offset value corresponding to the energy data type.

6. The data transmission optimization method based on energy big data center according to claim 1 is characterized in that: Determining the target priority threshold according to the data generation distribution information corresponding to each data source and the reference priority corresponding to each energy data type includes: Add the data generation distribution information corresponding to each data source obtained, and use the added result as the overall distribution information; The target priority threshold is determined according to the overall distribution information and the reference priorities corresponding to each energy data type.

7. The data transmission optimization method based on the energy big data center according to claim 6 is characterized in that: The determining the target priority threshold according to the overall distribution information and the reference priorities corresponding to each energy data type includes: Adjusting the overall distribution information according to the reference priorities corresponding to the various energy data types to obtain target distribution information; Obtain a preset traffic ratio, and determine the target priority threshold based on the target distribution information, the predicted traffic corresponding to the target time point, and the preset traffic ratio.

8. The data transmission optimization method based on energy big data center according to claim 1 is characterized in that: The preset flow threshold is initially a basic flow value; After step S104, the following steps are also included: The preset flow threshold is updated according to the predicted flow corresponding to the target time point.

9. The data transmission optimization method based on energy big data center according to claim 8 is characterized in that: After step S102, the following steps are also included: If the predicted traffic is less than or equal to the basic traffic value, the target priority threshold is set to a first preset value, the preset traffic threshold is reset to the basic traffic value, and the process jumps to step S105.

10. The data transmission optimization method based on energy big data center according to claim 1 is characterized in that: The network isolation device is used to determine a target source corresponding to a target time slice from M data sources according to a preset arbitration method, and send a receive signal to the target source corresponding to the target time slice at a starting time point of the target time slice, wherein the starting time point of the target time slice is greater than the target time point; The step of sending the collected data to the network isolation device in a time division multiplexing manner includes: When the data source receives the receiving signal, it sends the collected data to the network isolation device.

11. A data transmission optimization system based on energy big data center, characterized in that: The data transmission optimization system based on the energy big data center includes: A traffic prediction module is used to predict the reference traffic of the network isolation device obtained at I preset time points, and obtain the predicted traffic corresponding to the target time point, where I is a positive integer; a consumption prediction module configured to, if the predicted flow rate is greater than a preset flow rate threshold, perform a prediction based on the data consumption information of N data consumers obtained at I preset time points to obtain predicted consumption information corresponding to a target time point, wherein the predicted consumption information includes predicted consumption data volumes corresponding to J energy data types, where N and J are positive integers; a priority determination module, configured to determine reference priorities corresponding to respective energy data types based on the predicted consumption information; a threshold determination module, configured to obtain data generation distribution information corresponding to M data sources, and determine a target priority threshold based on the data generation distribution information corresponding to each data source and the reference priority corresponding to each energy data type, where M is a positive integer; The data transmission module is used for sending the collected data to the network isolation device directly to the network isolation device after the target time point if the reference priority of the energy data type to which the collected data sent by the data source to the network isolation device belongs is greater than the target priority threshold; otherwise, the collected data is sent to the network isolation device using time division multiplexing.

Images