Dynamic bandwidth resource management method and device

Abstract

The present application provides a dynamic bandwidth resource management method and device, an electronic device and a storage medium, the method comprising: using a pre-trained bandwidth demand prediction model to predict the bandwidth demand of a cloud application user; when the bandwidth demand is greater than a first value, adjusting the encoding parameters of the cloud application screen to reduce the data volume of the encoded cloud application screen; or when at least two consecutive predicted bandwidth demands are less than a second value, adjusting the encoding parameters of the cloud application screen to increase the data volume of the encoded cloud application screen, wherein the first value is greater than or equal to the second value, which can effectively manage bandwidth resources, improve bandwidth resource utilization efficiency, and reduce overall bandwidth costs, while ensuring a high-quality user experience.

Description

Technical Field

[0001] The present invention relates to the field of cloud applications, and in particular to a dynamic bandwidth resource management method and device, electronic equipment and storage medium. Background Art

[0002] With the popularity and development of cloud application services (such as cloud gaming services), cloud application service providers are facing more and more challenges, especially in bandwidth management and cost control. As a service with high bandwidth requirements, cloud application services rely on stable and fast network connections to ensure a smooth application experience. However, since cloud application customers are usually active during specific time periods (such as evenings or weekends), cloud application service providers face a high peak superposition effect of bandwidth usage during peak hours. This superposition effect causes extreme bandwidth demand peaks, resulting in high bandwidth costs for cloud application service providers. At the same time, during non-peak hours, a large amount of bandwidth resources are not fully utilized, resulting in resource waste.

[0003] Therefore, how to provide a solution to effectively manage bandwidth resources, improve bandwidth resource utilization efficiency, and reduce overall bandwidth costs while ensuring high-quality user experience has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the embodiments of the present application provide a dynamic bandwidth resource management method and device, an electronic device and a storage medium.

[0005] In a first aspect, an embodiment of the present application provides a dynamic bandwidth resource management method, which is applied to a cloud server, including:

[0006] Use the pre-trained bandwidth demand prediction model to predict the bandwidth demand of cloud application users;

[0007] When the bandwidth requirement is greater than a first value, adjust the encoding parameters of the cloud application screen to reduce the amount of data of the encoded cloud application screen; or when at least two consecutive predicted bandwidth requirements are less than a second value, adjust the encoding parameters of the cloud application screen to increase the amount of data of the encoded cloud application screen, wherein the first value is greater than or equal to the second value.

[0008] In a second aspect, the embodiment of the present application further provides a dynamic bandwidth resource management device, which is applied to a cloud server, including:

[0009] A prediction unit, used to predict the bandwidth demand of cloud application users by using a pre-trained bandwidth demand prediction model;

[0010] An adjustment unit is used to adjust the encoding parameters of the cloud application screen to reduce the data volume of the encoded cloud application screen when the bandwidth demand is greater than a first value; or to adjust the encoding parameters of the cloud application screen to increase the data volume of the encoded cloud application screen when at least two consecutive predicted bandwidth demands are less than a second value, wherein the first value is greater than or equal to the second value.

[0011] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the dynamic bandwidth resource management method described in the first aspect are executed.

[0012] In a fourth aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the dynamic bandwidth resource management method as described in the first aspect.

[0013] In summary, the dynamic bandwidth resource management method and device, electronic device and storage medium provided in the embodiments of the present application use a pre-trained bandwidth demand prediction model to predict the bandwidth demand of cloud application users; when the bandwidth demand is greater than a first value, adjust the encoding parameters of the cloud application screen to reduce the data volume of the encoded cloud application screen; or when at least two consecutive predicted bandwidth demands are less than a second value, adjust the encoding parameters of the cloud application screen to increase the data volume of the encoded cloud application screen. That is to say, during peak periods, the bandwidth demand peak is smoothed by adjusting the encoding parameters of the cloud application screen, and during non-peak periods, the quality of the cloud application screen is improved by adjusting the encoding parameters of the cloud application screen. The entire solution can effectively manage bandwidth resources, improve the efficiency of bandwidth resource utilization, and reduce overall bandwidth costs, while ensuring a high-quality user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart of an embodiment of a dynamic bandwidth resource management method provided in an embodiment of the present application;

[0015] Figure 2 A structural diagram of an embodiment of a dynamic bandwidth resource management device provided in an embodiment of the present application;

[0016] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0018] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0019] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0020] Reference Figure 1 As shown, it is a flow chart of a dynamic bandwidth resource management method provided in an embodiment of the present application. The dynamic bandwidth resource management method is applied to a cloud server, including:

[0021] S10, predicting the bandwidth demand of cloud application users using a pre-trained bandwidth demand prediction model;

[0022] In this embodiment, it should be noted that the input of the bandwidth demand prediction model can be the actual bandwidth usage of cloud application users in multiple historical time periods, and the output can be the bandwidth demand of cloud application users in the current time period. For example, the actual bandwidth usage of cloud application users in each hour in the past 5 hours, then the actual bandwidth usage of cloud application users in each hour in the past 5 hours is input into the bandwidth demand prediction model, and the bandwidth demand of cloud application users in the current hour can be predicted. Cloud application users can be users who access the same IDC (Internet Data Center) computer room instance to play in the cloud. In the prediction of the bandwidth demand of cloud application users and the subsequent processing measures in step S11, network operators can be distinguished or not.

[0023] S11. When the bandwidth demand is greater than a first value, adjust the encoding parameters of the cloud application screen to reduce the amount of data of the encoded cloud application screen; or when at least two consecutive predicted bandwidth demands are less than a second value, adjust the encoding parameters of the cloud application screen to increase the amount of data of the encoded cloud application screen, wherein the first value is greater than or equal to the second value.

[0024] In this embodiment, it should be noted that the first value and the second value can be set as needed. When the bandwidth demand is greater than the first value, reducing the amount of data of the encoded cloud application screen can reduce the bandwidth usage; when at least two consecutive predicted bandwidth demands are less than the second value, increasing the amount of data of the encoded cloud application screen can increase the bandwidth usage. By reducing the bandwidth usage during peak hours and increasing the bandwidth usage during non-peak hours, the gap between the bandwidth peak and the bandwidth valley can be reduced, the efficiency of bandwidth resource utilization can be improved, user experience can be guaranteed, and bandwidth costs can be reduced.

[0025] The dynamic bandwidth resource management method provided in the embodiment of the present application uses a pre-trained bandwidth demand prediction model to predict the bandwidth demand of cloud application users; when the bandwidth demand is greater than a first value, the encoding parameters of the cloud application screen are adjusted to reduce the data volume of the encoded cloud application screen; or when at least two consecutive predicted bandwidth demands are less than a second value, the encoding parameters of the cloud application screen are adjusted to increase the data volume of the encoded cloud application screen. That is to say, during peak periods, the bandwidth demand peak is smoothed by adjusting the encoding parameters of the cloud application screen, and during non-peak periods, the quality of the cloud application screen is improved by adjusting the encoding parameters of the cloud application screen. The entire solution can effectively manage bandwidth resources, improve the efficiency of bandwidth resource utilization, and reduce overall bandwidth costs, while ensuring a high-quality user experience.

[0026] Based on the above method embodiment, the bandwidth demand prediction model is an ARIMA model (Autoregressive Integrated Moving Average Model).

[0027] Before predicting the bandwidth demand of cloud application users by using the pre-trained bandwidth demand prediction model, the following method may also be included:

[0028] Perform at least one difference processing on the historical bandwidth usage of multiple cloud application users, and use the bandwidth usage after the difference processing to train the ARIMA model.

[0029] In this embodiment, it should be noted that performing at least one differential processing on the bandwidth usage of multiple historical cloud application users is to transform the original sequence composed of the bandwidth usage of multiple historical cloud application users into a stable sequence.

[0030] Based on the foregoing method embodiment, the step of adjusting the encoding parameters of the cloud application screen to reduce the data volume of the encoded cloud application screen may include:

[0031] Increasing the encoding ratio of non-I frames; and / or

[0032] The bit rate and / or resolution for encoding the first designated area in the cloud application screen is reduced.

[0033] In this embodiment, it should be noted that in order to reduce the peak bandwidth usage during the predicted peak period of bandwidth usage, the amount of data sent by the cloud server to the terminal can be reduced. The specific measures include increasing the encoding ratio of the non-I frame picture frame, reducing the bit rate for encoding the first designated area in the cloud application screen, and reducing the resolution of encoding the first designated area in the cloud application screen. I frame is also called intra picture or key frame. It is a full-frame compressed coded frame. It does not need to refer to other pictures during decoding, and the complete image can be reconstructed using only the data of I frame. Increasing the encoding ratio of the non-I frame picture frame means that the proportion of the encoded non-I frame has increased, and the non-I frame is not a complete image frame, and the amount of data is small, so the amount of data sent to the terminal can be reduced. The first designated area can be a full-frame cloud application screen area, or a non-user-focused area (such as a background area) and / or a partial area such as a dark scene area. The identification of non-user-focused areas and dark scene areas in the cloud application screen can adopt existing technologies. This content is not the core of this application and will not be repeated here. Reducing the bit rate and / or resolution for encoding the first designated area in the cloud application screen means that the amount of encoded data obtained by the cloud server's encoder for encoding the cloud application screen is reduced, so the amount of data sent to the terminal is naturally reduced. The adjustment amount of the processing measures in this embodiment can be determined by referring to the encoding parameters with better user experience under a certain historical bandwidth usage (such as 80% of the peak bandwidth in the past month). When adjusting the bit rate and resolution, the bit rate and resolution can be alternately reduced according to their corresponding specified step sizes. The processing measures in this embodiment can be subject to additional restrictions, such as for low-priority users or non-critical cloud applications.

[0034] Based on the foregoing method embodiment, the step of adjusting the encoding parameters of the cloud application screen to increase the data volume of the encoded cloud application screen may include:

[0035] Reducing the encoding ratio of non-I frames; and / or

[0036] The bit rate and / or resolution and / or frame rate for encoding the second designated area in the cloud application screen is increased.

[0037] In this embodiment, it should be noted that, corresponding to the previous embodiment in which the amount of data sent by the cloud server to the terminal needs to be reduced, this embodiment needs to increase the amount of data sent by the cloud server to the terminal. Specifically, the encoding ratio of the non-I frame frame can be reduced, that is, the encoded I frame is increased, and the amount of data of the I frame is large, so the amount of data sent to the terminal can be increased. The second designated area can be a whole frame cloud application screen area, or a user focus area and / or other partial areas (dark scene area, background area, etc.). Increasing the bit rate and / or resolution for encoding the second designated area in the cloud application screen can increase the amount of data of the encoded data obtained after encoding the cloud application screen, so that the amount of data sent to the terminal can be increased. In addition to increasing the bit rate and / or resolution and / or frame rate for encoding the second designated area in the cloud application screen, the FEC (Forward Error Correction) redundancy ratio and the transmission speed of the encoded data can be increased to make full use of bandwidth resources and improve user experience. Specifically, increasing the FEC redundancy ratio can reduce the packet loss rate under weak network conditions; increasing the data transmission speed can increase the smoothness of the cloud application screen display.

[0038] Reference Figure 2 FIG. 1 is a schematic diagram of a structure of a dynamic bandwidth resource management device provided in an embodiment of the present application, and the device is applied to a cloud server, including:

[0039] A prediction unit 20, configured to predict the bandwidth demand of cloud application users using a pre-trained bandwidth demand prediction model;

[0040] The adjustment unit 21 is used to adjust the encoding parameters of the cloud application screen to reduce the data volume of the encoded cloud application screen when the bandwidth demand is greater than a first value; or to adjust the encoding parameters of the cloud application screen to increase the data volume of the encoded cloud application screen when at least two consecutive predicted bandwidth demands are less than a second value, wherein the first value is greater than or equal to the second value.

[0041] The dynamic bandwidth resource management device provided in the embodiment of the present application predicts the bandwidth demand of cloud application users by means of a prediction unit 20 using a pre-trained bandwidth demand prediction model; adjusts the encoding parameters of the cloud application screen by means of an adjustment unit 21 when the bandwidth demand is greater than a first value to reduce the data volume of the encoded cloud application screen; or adjusts the encoding parameters of the cloud application screen when at least two consecutive predicted bandwidth demands are less than a second value to increase the data volume of the encoded cloud application screen. That is to say, during peak periods, the bandwidth demand peak is smoothed by adjusting the encoding parameters of the cloud application screen, and during non-peak periods, the quality of the cloud application screen is improved by adjusting the encoding parameters of the cloud application screen. The entire solution can effectively manage bandwidth resources, improve the efficiency of bandwidth resource utilization, and reduce overall bandwidth costs, while ensuring a high-quality user experience.

[0042] Based on the above device embodiment, the bandwidth demand prediction model is an ARIMA model, and the device may further include:

[0043] The training unit is used to perform at least one differential processing on the bandwidth usage of multiple historical cloud application users before the prediction unit works, and train the ARIMA model by using the bandwidth usage after the differential processing.

[0044] Based on the above device embodiment, the adjustment unit may be used for:

[0045] When the bandwidth requirement is greater than the first value, increasing the encoding ratio of non-I-frame picture frames; and / or

[0046] The bit rate and / or resolution for encoding the first designated area in the cloud application screen is reduced.

[0047] Based on the above device embodiment, the adjustment unit may be used for:

[0048] When at least two consecutive predicted bandwidth requirements are both less than a second value, reducing the coding ratio of non-I-frame picture frames; and / or

[0049] The bit rate and / or resolution and / or frame rate for encoding the second designated area in the cloud application screen is increased.

[0050] The implementation process of the dynamic bandwidth resource management device provided in the embodiment of the present application is consistent with the dynamic bandwidth resource management method provided in the embodiment of the present application, and the effect that can be achieved is also the same as the dynamic bandwidth resource management method provided in the embodiment of the present application, which will not be repeated here.

[0051] The above solution adaptively adjusts the encoding strategy of the cloud application screen according to the predicted bandwidth demand, which can maximize the utilization efficiency of bandwidth resources, avoid resource overload during peak hours and resource idleness during non-peak hours, and maintain or improve user experience while reducing costs. This enables cloud application service providers to effectively manage and optimize bandwidth usage while ensuring good user experience quality, thereby achieving dual optimization of service quality and cost-effectiveness.

[0052] like Figure 3 As shown, an electronic device provided by an embodiment of the present application includes: a processor 30, a memory 31 and a bus 32, wherein the memory 31 stores machine-readable instructions executable by the processor 30, and when the electronic device is running, the processor 30 communicates with the memory 31 through the bus 32, and the processor 30 executes the machine-readable instructions to perform the steps of the dynamic bandwidth resource management method as described above.

[0053] Specifically, the memory 31 and the processor 30 can be general-purpose memories and processors, which are not specifically limited here. When the processor 30 runs the computer program stored in the memory 31, the dynamic bandwidth resource management method can be executed.

[0054] Corresponding to the above-mentioned dynamic bandwidth resource management method, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned dynamic bandwidth resource management method are executed.

[0055] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A dynamic bandwidth resource management method, applied to a cloud server, characterized in that: include: Use the pre-trained bandwidth demand prediction model to predict the bandwidth demand of cloud application users under the bandwidth billing dimension; When the bandwidth requirement is greater than a first value, adjust the encoding parameters of the cloud application screen to reduce the amount of data of the encoded cloud application screen; or when at least two consecutive predicted bandwidth requirements are less than a second value, adjust the encoding parameters of the cloud application screen to increase the amount of data of the encoded cloud application screen, wherein the first value is greater than or equal to the second value.

2. The method according to claim 1, characterized in that The bandwidth demand prediction model is the ARIMA model. Before predicting the bandwidth demand of cloud application users by using the pre-trained bandwidth demand prediction model, the method further includes: Perform at least one difference processing on the historical bandwidth usage of multiple cloud application users, and use the bandwidth usage after the difference processing to train the ARIMA model.

3. The method according to claim 1 or 2, characterized in that The adjusting the encoding parameters of the cloud application screen to reduce the data volume of the encoded cloud application screen includes: Increasing the encoding ratio of non-I frames; and / or The bit rate and / or resolution for encoding the first designated area in the cloud application screen is reduced.

4. The method according to claim 1 or 2, characterized in that: The adjusting the encoding parameters of the cloud application screen to increase the data volume of the encoded cloud application screen includes: Reducing the encoding ratio of non-I frames; and / or The bit rate and / or resolution and / or frame rate for encoding the second designated area in the cloud application screen is increased.

5. A dynamic bandwidth resource management device, applied to a cloud server, characterized in that: include: A prediction unit, used to predict the bandwidth demand of cloud application users under the bandwidth billing dimension by using a pre-trained bandwidth demand prediction model; An adjustment unit is used to adjust the encoding parameters of the cloud application screen to reduce the data volume of the encoded cloud application screen when the bandwidth demand is greater than a first value; or to adjust the encoding parameters of the cloud application screen to increase the data volume of the encoded cloud application screen when at least two consecutive predicted bandwidth demands are less than a second value, wherein the first value is greater than or equal to the second value.

6. The device according to claim 5, characterized in that The bandwidth demand prediction model is an ARIMA model, and the device further includes: The training unit is used to perform at least one differential processing on the bandwidth usage of multiple historical cloud application users before the prediction unit works, and train the ARIMA model by using the bandwidth usage after the differential processing.

7. The device according to claim 5 or 6, characterized in that The adjustment unit is used for: When the bandwidth requirement is greater than the first value, increasing the encoding ratio of non-I-frame picture frames; and / or The bit rate and / or resolution for encoding the first designated area in the cloud application screen is reduced.

8. The device according to claim 5 or 6, characterized in that The adjustment unit is used for: When at least two consecutive predicted bandwidth requirements are both less than a second value, reducing the coding ratio of non-I-frame picture frames; and / or The bit rate and / or resolution and / or frame rate for encoding the second designated area in the cloud application screen is increased.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the dynamic bandwidth resource management method according to any one of claims 1 to 4 are executed.

10. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the dynamic bandwidth resource management method as described in any one of claims 1 to 4.

Images