Service flow off-peak scheduling methods and related equipment

By identifying and scheduling the burst traffic characteristics of real-time video streams at the business flow aggregation and forwarding nodes, constructing a scheduling model and increasing latency, the problem of network congestion in real-time video stream transmission is solved, peak scheduling of video streams is realized, and network transmission quality and real-time video decoding are improved.

CN114827041BActive Publication Date: 2026-11-10HUAWEI TECH SERVICE
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202110127349.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-01-29
Publication Date
2026-11-10
Estimated Expiration
2041-01-29

AI Technical Summary

Technical Problem

When multiple real-time video streams are transmitted simultaneously, the overlapping time periods of I-frames cause network congestion, affecting network experience. Existing technologies are unable to effectively control network traffic bursts, leading to a decline in network quality.

Method used

By using business flow aggregation and forwarding nodes, traffic is counted for each time period, characteristics of sudden traffic surges are identified, a scheduling model is built and scheduling latency is increased, and the scheduling scheme is optimized to avoid traffic peaks and achieve off-peak scheduling.

Benefits of technology

It reduces the peak traffic of multiple service flows, avoids video stream forwarding delay, improves network transmission quality and experience, and ensures full-frame transmission of I-frames to guarantee real-time video decoding.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114827041B_ABST
    Figure CN114827041B_ABST
Patent Text Reader

Abstract

This application provides a service flow peak-shifting scheduling method and related equipment. The method is applied to a service flow aggregation and forwarding node. The method includes: receiving multiple service flows; statistically analyzing the traffic of each service flow received in each time period according to a preset time interval; identifying burst traffic of each service flow based on the traffic of each service flow received in each time period; and determining the scheduling delay of each service flow based on the burst traffic of each service flow. This application adds a corresponding scheduling delay to multiple service flows, reduces the peak traffic of multiple service flows, and avoids forwarding time delays for all service flows.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a service flow staggered scheduling method and related equipment. Background Technology

[0002] With the continuous increase in data traffic and the rapid development of the real-time audio and video industry, the requirements for network transmission quality are becoming increasingly stringent. When traffic exceeds network transmission capacity, large latency, packet loss, and retransmissions occur, further deteriorating network transmission conditions and severely reducing network experience. This is particularly evident in real-time video services such as video surveillance, video conferencing, and virtual reality (VR) games. Real-time video services often employ real-time encoding and transmission, resulting in significant bursts of video traffic. The data volume of intra-frame coded frames (I-frames) is much larger than that of forward-predictive coded frames (P-frames), leading to a high peak-to-average power ratio (PAPR) in the video stream. When multiple video streams are transmitted simultaneously, if the transmission times of I-frames from different video streams overlap (i.e., I-frame collisions), extremely high instantaneous bursts of traffic occur, causing network congestion, packet loss, and retransmissions, impacting network experience. Therefore, controlling network traffic volume, reducing the impact of traffic bursts on the network, and ensuring that the amount of data transmitted matches network transmission capacity are crucial for guaranteeing and improving network transmission quality and network experience. Summary of the Invention

[0003] This application discloses a service flow off-peak scheduling method and related equipment, which can realize off-peak scheduling of instantaneous burst traffic.

[0004] The first aspect of this application discloses a service flow peak-shifting scheduling method, applied to a service flow aggregation and forwarding node, the method comprising:

[0005] Receive multiple service streams;

[0006] Based on preset time intervals, the traffic of each service stream received in each time period is counted;

[0007] Identify burst traffic for each service flow based on the traffic received for each service flow in each time period;

[0008] The scheduling delay for each service flow is determined based on the burst traffic of each service flow.

[0009] This application addresses the periodic traffic bursts characteristic of service flows (e.g., video streams) by adding corresponding scheduling delays to each service flow, reducing the cumulative traffic peaks of multiple service flows, and avoiding forwarding time delays for all service flows. This application improves transmission assurance capabilities by planning traffic shaping schemes and resource allocation. In real-time video service scenarios, using the multi-service flow staggered scheduling method disclosed in this application can enable the transmission of I-frames of video streams in their entirety, allowing some video streams to receive complete I-frames first and decode and play them.

[0010] In some optional implementations, determining the scheduling delay of each service flow based on the burst traffic of each service flow includes:

[0011] Extract burst traffic characteristics for each service flow based on the traffic received for each service flow in each time period;

[0012] Construct a burst flow model based on the burst flow characteristics;

[0013] By adding scheduling delay as a design variable to the aforementioned burst traffic model, a scheduled burst traffic model is obtained.

[0014] Establish an objective function for the scheduled burst traffic model;

[0015] The objective function is optimized to obtain the scheduling delay for each service flow.

[0016] In some optional implementations, the burst traffic characteristics include burst time phase, burst traffic magnitude, and burst duration, and the step of constructing a burst traffic model based on the burst traffic characteristics includes:

[0017] A burst flow function is constructed based on the burst time phase, burst flow magnitude, and burst duration.

[0018] In some optional implementations, constructing the burst flow function based on the burst time phase, burst flow magnitude, and burst duration includes:

[0019] For each business flow, the S-shaped function with time as the independent variable is shifted according to the burst duration and burst time phase of the business flow and scaled according to the first scaling factor to obtain the first function;

[0020] The second function is obtained by flipping the S-shaped function, shifting it according to the burst time phase of the service flow, and scaling it according to the second scaling factor.

[0021] Multiply the first function and the second function to obtain the third function;

[0022] The third function is scaled based on the burst traffic size of the business flow to obtain the burst traffic function.

[0023] In some alternative implementations, both the first scaling factor and the second scaling factor are 1.

[0024] In some alternative implementations, the objective function is a maximum value function or an entropy function.

[0025] In some optional implementations, the burst traffic characteristics include burst traffic magnitude, burst start time, and burst end time, and the step of constructing a burst traffic model based on the burst traffic characteristics includes:

[0026] A peak traffic collision matrix is ​​constructed based on the size of the burst traffic, the start time of the burst, and the end time of the burst.

[0027] In some optional implementations, constructing the peak traffic collision matrix based on the burst traffic size, burst start time, and burst end time includes:

[0028] Select the number of prediction time periods, where the product of the number of prediction time periods and the preset time interval is greater than the burst cycle of the business flow;

[0029] The peak traffic surge matrix is ​​constructed by using the number of the multiple service flows as the number of rows in the peak traffic surge matrix and the number of predicted time periods as the number of columns in the peak traffic surge matrix. If a predicted time period of one of the multiple service flows does not overlap with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic surge matrix is ​​0. If the predicted time period of that service flow overlaps with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic surge matrix is ​​the burst traffic size of that service flow. The burst duration is determined by the burst start time and the burst end time.

[0030] In some alternative implementations, the objective function is a maximum value function.

[0031] In some optional implementations, establishing the objective function for the scheduled burst traffic model includes:

[0032] Under the constraint of maximum scheduling delay, the objective function is established for the scheduled burst traffic model.

[0033] By establishing the objective function for the scheduled burst traffic model under the constraint of maximum scheduling delay, peak shaping under certain delay constraints can be achieved, making the increased delay of each service flow due to traffic shaping controllable. The delay constraint can be set according to actual service needs and the delay cost of packet loss retransmission.

[0034] In some optional implementations, before constructing the burst flow model based on the burst flow characteristics, the method further includes:

[0035] Determine whether the burst traffic of each of the multiple service flows clashes with the burst traffic of other service flows in the multiple service flows;

[0036] If the burst traffic of this service flow collides with the burst traffic of other service flows, then the burst traffic model is constructed for this service flow.

[0037] By judging the peak collision situation of the video stream, modeling is not performed when the video stream does not experience peak collision, which can reduce the computational load of modeling and improve the efficiency of peak scheduling.

[0038] In some optional implementations, the method further includes:

[0039] The scheduling delay of each service flow is sent to the upstream node, so that the upstream node can add a corresponding scheduling delay to the service flow based on the scheduling delay of each service flow.

[0040] In some optional implementations, the method further includes:

[0041] Based on the scheduling delay of each service flow, add a corresponding scheduling delay to the scheduling delay of each service flow;

[0042] The multiple service flows with increased scheduling latency are sent to downstream nodes.

[0043] A second aspect of this application discloses a service flow peak-shifting scheduling device, applied to a service flow aggregation and forwarding node, the device comprising:

[0044] The business flow statistics module is used to receive multiple business flows and, based on a preset time interval, to count the traffic of each business flow received in each time period.

[0045] The off-peak scheduling algorithm module is used to identify the burst traffic of each service flow based on the traffic received for each service flow in each time period, and to determine the scheduling delay of each service flow based on the burst traffic of each service flow.

[0046] In some optional implementations, the off-peak scheduling algorithm module is used for:

[0047] Extract burst traffic characteristics for each service flow based on the traffic received for each service flow in each time period;

[0048] Construct a burst flow model based on the burst flow characteristics;

[0049] By adding scheduling delay as a design variable to the aforementioned burst traffic model, a scheduled burst traffic model is obtained.

[0050] Establish an objective function for the scheduled burst traffic model;

[0051] The objective function is optimized to obtain the scheduling delay for each service flow.

[0052] In some optional implementations, the burst traffic characteristics include burst time phase, burst traffic size, and burst duration, and the peak-shifting scheduling algorithm module is used for:

[0053] A burst flow function is constructed based on the burst time phase, burst flow magnitude, and burst duration.

[0054] In some optional implementations, the off-peak scheduling algorithm module is used for:

[0055] For each business flow, the S-shaped function with time as the independent variable is shifted according to the burst duration and burst time phase of the business flow and scaled according to the first scaling factor to obtain the first function;

[0056] The second function is obtained by flipping the S-shaped function, shifting it according to the burst time phase of the service flow, and scaling it according to the second scaling factor.

[0057] Multiply the first function and the second function to obtain the third function;

[0058] The third function is scaled based on the size of the burst traffic of the business flow to obtain the burst traffic function.

[0059] In some alternative implementations, both the first scaling factor and the second scaling factor are 1.

[0060] In some alternative implementations, the objective function is a maximum value function or an entropy function.

[0061] In some optional implementations, the burst traffic characteristics include burst traffic size, burst start time, and burst end time, and the peak-shifting scheduling algorithm module is used for:

[0062] A peak traffic collision matrix is ​​constructed based on the size of the burst traffic, the start time of the burst, and the end time of the burst.

[0063] In some optional implementations, the off-peak scheduling algorithm module is used for:

[0064] Select the number of prediction time periods, where the product of the number of prediction time periods and the preset time interval is greater than the burst cycle of the business flow;

[0065] The peak traffic surge matrix is ​​constructed by using the number of the multiple service flows as the number of rows in the peak traffic surge matrix and the number of predicted time periods as the number of columns in the peak traffic surge matrix. If a predicted time period of one of the multiple service flows does not overlap with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic surge matrix is ​​0. If the predicted time period of that service flow overlaps with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic surge matrix is ​​the burst traffic size of that service flow. The burst duration is determined by the burst start time and the burst end time.

[0066] In some alternative implementations, the objective function is a maximum value function.

[0067] In some optional implementations, the off-peak scheduling algorithm module is used for:

[0068] Under the constraint of maximum scheduling delay, the objective function is established for the scheduled burst traffic model.

[0069] In some alternative embodiments, the apparatus further includes:

[0070] The judgment module is used to determine whether the burst traffic of each of the multiple service flows overlaps with the burst traffic of other service flows in the multiple service flows.

[0071] In some alternative embodiments, the apparatus further includes:

[0072] The message sending module is used to send the scheduling delay of each service flow to the upstream node, so that the upstream node can add the corresponding scheduling delay to the service flow according to the scheduling delay of each service flow.

[0073] In some alternative embodiments, the apparatus further includes:

[0074] The off-peak scheduling module is used to add a corresponding scheduling delay to the scheduling delay of each service flow based on the scheduling delay of each service flow, and then send the multiple service flows with the increased scheduling delay to the downstream nodes.

[0075] A third aspect of this application discloses a computer-readable storage medium including computer instructions that, when executed on an electronic device, cause the electronic device to perform the service flow off-peak scheduling method as described in the first aspect.

[0076] The fourth aspect of this application discloses an electronic device, which includes a processor and a memory. The memory is used to store instructions, and the processor is used to call the instructions in the memory to cause the electronic device to execute the service flow peak scheduling method as described in the first aspect.

[0077] The fifth aspect of this application discloses a chip system applied to an electronic device; the chip system includes an interface circuit and a processor; the interface circuit and the processor are interconnected via a line; the interface circuit is used to receive signals from the memory of the electronic device and send signals to the processor, the signals including computer instructions stored in the memory; when the processor executes the computer instructions, the chip system executes the service flow peak scheduling method as described in the first aspect.

[0078] The sixth aspect of this application discloses a computer program product that, when run on a computer, causes the computer to execute the business flow off-peak scheduling method as described in the first aspect.

[0079] A seventh aspect of this application discloses an apparatus having the function of implementing the electronic device behavior described in the first aspect. The function can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the described function.

[0080] It should be understood that the business flow off-peak scheduling device described in the second aspect, the computer-readable storage medium described in the third aspect, the electronic device described in the fourth aspect, the chip system described in the fifth aspect, the computer program product described in the sixth aspect, and the device described in the seventh aspect all correspond to the method described in the first aspect. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here. Attached Figure Description

[0081] Figure 1 This is a schematic diagram illustrating an application scenario of the service flow off-peak scheduling method disclosed in the embodiments of this application.

[0082] Figure 2 This is a software block diagram of the service flow aggregation and forwarding node disclosed in the embodiments of this application.

[0083] Figure 3 This is a flowchart of the service flow staggered scheduling method disclosed in the embodiments of this application.

[0084] Figure 4This is a diagram illustrating sudden traffic spikes.

[0085] Figure 5 yes Figure 2 One implementation scheme of the peak-shifting scheduling algorithm module in [the system].

[0086] Figure 6 This is a schematic diagram of the burst flow function.

[0087] Figure 7 yes Figure 2 Another implementation scheme for the off-peak scheduling algorithm module in the model.

[0088] Figure 8 This is a schematic diagram of the peak flow collision matrix values.

[0089] Figure 9 This is a schematic diagram of the peak traffic collision matrix values ​​after scheduling.

[0090] Figure 10 This is a schematic diagram of deploying the off-peak scheduling module on the terminal.

[0091] Figure 11 This is a schematic diagram of the structure of the electronic device disclosed in the embodiments of this application. Detailed Implementation

[0092] For ease of understanding, exemplary descriptions of some concepts related to the embodiments of this application are provided for reference.

[0093] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0094] Group of pictures (GOP): A video encoder divides multiple encoded video frames into a group. The size of a GOP is the number of frames between two intra-coded frames (i.e., I-frames).

[0095] Intra-coded frame (I-frame, also known as an intra picture): A type of video frame, also called a keyframe. I-frames have a lower level of compression and a larger data size. Decoding an I-frame does not depend on other frames.

[0096] Forward predictive-frame (P-frame): A type of video frame with high compression and a much smaller data size than an I-frame. P-frame decoding relies on information from earlier I-frames and P-frames.

[0097] Bidirectional interpolated prediction frame (B-frame): A type of video frame with very high compression and less data size than a P-frame. Decoding a B-frame depends on both earlier and later video frames.

[0098] Traffic: The amount of data transmitted.

[0099] Upstream and downstream: Upstream and downstream are relative to the current node and the direction of data flow. The part from the data sending end to the current node is called upstream, and the part from the current node to the receiving end is called downstream.

[0100] Entry point and exit point: Entry point refers to the location where a message arrives at the current node, and exit point refers to the location where a message is sent from the current node.

[0101] Transmission bandwidth: refers to the amount of data that a network can transmit per unit of time.

[0102] Transmission rate: refers to the amount of data actually transmitted over the network per unit time. Since the demand for business data transmission may be less than the network's transmission capacity, the transmission rate may be less than the transmission bandwidth.

[0103] Peak-to-average power ratio (PAPR): This refers to the ratio of the maximum to the average amount of data transmitted per unit time in a service flow.

[0104] Burst traffic: Burst traffic refers to a sudden increase in the amount of data transmitted per unit time, which lasts for a short period of time before returning to the original level. This change presents a "peak shape" on the time-volume curve, hence it is also called peak traffic.

[0105] Queuing: During network transmission, messages need to be sent in a certain order. When there are too many messages, messages that cannot be sent in time need to be queued in the buffer and wait to be sent.

[0106] Network congestion refers to a situation where the amount of data to be sent per unit time exceeds the network bandwidth, causing packets to accumulate in the network, resulting in packet loss, retransmission, and other issues.

[0107] Congestion packet loss: When the network is congested, packets are dropped due to factors such as the number of packets waiting in the queue exceeding the network's buffer capacity or the packets waiting in the network for too long.

[0108] Retransmission: When the sender and receiver detect that a message is lost through message exchange, the sender retransmits the lost message.

[0109] Screen flickering: Due to data loss or errors, the decoded video frame image is severely damaged.

[0110] Stuttering: Video playback involves playing each video frame in a certain time sequence. When the video reaches a certain point in time but the video data corresponding to that point is not received, stuttering will occur in the playback effect.

[0111] Network experience: For services that require network transmission, the impact of network quality, such as packet loss, network latency, and network transmission rate, on the service.

[0112] Business flow: An ordered sequence of business data bytes (or messages) with a start and an end.

[0113] Traffic shaping: Changing the amount of data transmitted by a service flow at different times through control or scheduling.

[0114] The 5-tuple consists of the source Internet Protocol (IP) address, source port, destination IP address, destination port, and transport layer protocol number. In the IP protocol, the IP address and port uniquely identify the sender or receiver. The source IP address and source port form the sender's address, and the destination IP address and destination port form the receiver's address. The transport layer protocol number indicates the transport layer protocol carried in the IP packet, such as Transmission Control Protocol (TCP) or User Datagram Protocol (UDP). Each protocol is identified by a unique number (i.e., the transport layer protocol number), for example, 6 represents TCP, and 17 represents UDP.

[0115] To better understand the service flow off-peak scheduling method and related equipment disclosed in the embodiments of this application, the application scenarios of the service flow off-peak scheduling method of this application are described below.

[0116] Figure 1 This is a schematic diagram illustrating an application scenario of the service flow off-peak scheduling method disclosed in an embodiment of this application. Wherein, Figure 1 A illustrates a scenario where the service flow off-peak scheduling method provided in this application's embodiments is not applied to customer-premise equipment (CPE). Figure 1 B illustrates the application of the service flow peak-shifting scheduling method provided in this application's embodiments on a CPE. This service flow peak-shifting scheduling method is applied to application scenarios where multiple service flows experience periodic bursts of traffic peaks, for example... Figure 1 The example shown illustrates an application scenario for real-time monitoring of video upload services. Figure 1As shown, the network includes multiple cameras, CPEs, base stations, core network equipment, and servers. Cameras are the terminals, CPEs are service flow aggregation and forwarding nodes, and core network equipment is user data processing and forwarding equipment. Each camera can only monitor a localized area; multiple cameras need to operate simultaneously to achieve comprehensive monitoring. Multiple cameras transmit real-time captured video to the base station via the CPE. The base station then forwards the data to the server via the core network equipment, thus achieving comprehensive real-time video monitoring.

[0117] To ensure real-time video surveillance, the video frames encoded by the cameras need to be sent to the server in real time. The instantaneous traffic volume of the video stream is directly proportional to the data size of the video frames. The cameras encode multiple video frames and divide them into Groups of Pictures (GOPs). The encoded video frames include three types: I-frames, P-frames, and B-frames. Each GOP includes one I-frame and multiple P-frames, or one I-frame and multiple B-frames. In one embodiment of this application, to ensure real-time video decoding, a GOP of real-time video encoding contains one I-frame and multiple P-frames, but no B-frames. In another embodiment of this application, a GOP of real-time video encoding contains one I-frame and multiple B-frames. The compression level of I-frames is lower, and the data volume of an I-frame is several times that of a P-frame. Real-time video streams uploaded by multiple cameras converge at the CPE and are then sent to the base station. Real-time video streams have the characteristic of periodic traffic bursts. When the burst traffic of multiple video streams collides (i.e., a burst traffic peak), it causes an even larger burst traffic, resulting in instantaneous network congestion. Because real-time video streams have the characteristic of periodic traffic bursts, instantaneous network congestion will occur periodically (i.e., periodic bursts of traffic peaks).

[0118] See Figure 1 As shown in Figure 1A, when the service flow peak scheduling method provided in this application is not applied for peak scheduling, the burst times of traffic from different video streams output by the CPE overlap, thereby causing burst traffic peaks. See also Figure 1 As shown in Figure 1B, after applying the service flow staggered scheduling method provided in this application embodiment for staggered scheduling, the traffic burst times of different video streams output by CPE do not overlap, thus avoiding burst traffic collisions.

[0119] In other embodiments of this application, the service flow peak scheduling method can also be applied to other scenarios where there are periodic sudden traffic peaks in multiple service flows, such as video on demand (including virtual reality (VR) video on demand) and live video streaming.

[0120] Figure 2 This is a software block diagram of the service flow aggregation and forwarding node provided in the embodiments of this application.

[0121] The service flow peak scheduling method of this application can be applied to the service flow aggregation and forwarding node 20 in the network, for example... Figure 1 CPE in the middle. For example Figure 2 As shown, the service flow aggregation and forwarding node 20 includes a service flow peak-shaving scheduling device 200, which comprises a service flow statistics module 201, a peak-shaving scheduling algorithm module 202, and a peak-shaving scheduling module 203. The main functions of each module are described below.

[0122] The service flow statistics module 201 can be deployed at the entry point of the service flow aggregation and forwarding node 20. The service flow statistics module 201 is used to receive multiple service flows and, according to a preset time interval (e.g., 10 milliseconds), count the traffic of each service flow received in each time period.

[0123] In one embodiment of this application, the preset time interval is set to be less than the burst duration of each service flow.

[0124] For example, Figure 1 In the real-time monitoring video upload scenario shown, burst traffic is generated by I-frame data transmission, and the preset time interval can be set to be less than the I-frame transmission time. For example, if the I-frame transmission time is 20 milliseconds, the preset time interval can be set to 10 milliseconds.

[0125] The peak-shifting scheduling algorithm module 202 is used to identify the burst traffic of each service flow based on the traffic received by each service flow in each time period, and to determine the scheduling delay of each service flow based on the burst traffic. In one embodiment of this application, the peak-shifting scheduling algorithm module 202 extracts the burst traffic characteristics of each service flow based on the traffic received by each service flow in each time period, models the burst traffic based on the burst traffic characteristics of each service flow, and obtains a burst traffic model. The peak-shifting scheduling algorithm module 202 adds scheduling delay as a design variable to the burst traffic model to obtain a scheduled burst traffic model, establishes an objective function for the scheduled burst traffic model, optimizes and solves the objective function to obtain the scheduling delay of each service flow, that is, to obtain the delay scheduling scheme that minimizes peak collision.

[0126] In one embodiment of this application, the off-peak scheduling algorithm module 202 optimizes the objective function under the constraint of maximum scheduling delay to ensure that the scheduled service flow meets the actual service requirements.

[0127] The peak-shifting scheduling module 203 can be deployed at the egress point of the service flow aggregation and forwarding node 20. Based on the delay scheduling scheme, the peak-shifting scheduling module 203 adds a corresponding scheduling delay to each service flow, thus staggering the burst traffic times of each service flow and achieving peak-shifting scheduling.

[0128] Figure 3 This is a flowchart of the service flow staggered scheduling method disclosed in the embodiments of this application.

[0129] The service flow peak-shifting scheduling method disclosed in this application can be applied to service flow aggregation and forwarding nodes, for example... Figure 1 The CPE shown is Figure 3 The illustrated embodiment uses Figure 1 The application scenario will be used as an example for illustration. CPE includes a business flow statistics module, a peak-shaving scheduling algorithm module, and a peak-shaving scheduling module (see [link]). Figure 2 As shown). The following is based on Figure 3 The implementation process of this application is described in detail.

[0130] 301. Multiple cameras send multiple real-time video streams to the CPE.

[0131] The camera sends the video stream to the CPE via messages.

[0132] In one embodiment of this application, the camera sends a video stream to the CPE via IP packets. The IP packet contains a five-tuple: source IP address, source port, destination IP address, destination port, and protocol number.

[0133] 302. The business flow statistics module counts the traffic of each video stream received by the CPE in each time period according to a preset time interval.

[0134] The length of each time period is equal to the preset time interval. For example, if the starting time is t0 and the preset time interval is Δt, then the Mth time period is t0 + M·Δt. <t<t0+(M+1)·Δt。

[0135] In one embodiment of this application, the camera sends a video stream to the CPE via IP packets, and the service flow statistics module can distinguish each video stream based on the five-tuple of the IP packets.

[0136] The traffic received by the CPE for each video stream in each time period can be counted based on the number of packets (e.g., IP packets) received for that video stream within that time period. In other words, the traffic received by the CPE for each video stream in each time period can be equal to the number of packets received for that video stream within that time period.

[0137] Alternatively, the traffic received by the CPE for each video stream in each time period can be calculated based on the size of the packets received for that video stream within that time period. In other words, the traffic received by the CPE for each video stream in each time period can be equal to the sum of the sizes of all packets received for that video stream within that time period.

[0138] 303, The business flow statistics module transmits the traffic of each video stream received in each time period to the peak scheduling algorithm module.

[0139] 304, the peak scheduling algorithm module identifies burst traffic based on the traffic of each service flow received in each time period.

[0140] Burst traffic refers to a sudden increase in the amount of data transmitted per unit of time, which lasts for a short period of time and then decreases.

[0141] Figure 4 It is a graph showing the traffic changes of a real-time video stream. The "peak-shaped" spikes in the graph represent sudden traffic surges.

[0142] The business flow statistics module can calculate the traffic for each time period based on the traffic received in each time period, and calculate the burst traffic threshold based on the mean and variance of the traffic. If the traffic in a certain time period exceeds the threshold, it is determined to be a burst traffic.

[0143] The transmission rate, or instantaneous rate, is the data rate during a given time period when the data volume is divided by the preset time interval.

[0144] The burst traffic threshold can be expressed as:

[0145] r threshold =f(r mean ,r var );

[0146] Where, r threshold Indicates the burst traffic threshold, r mean r represents the mean of the flow rate. var This represents the variance of the flow rate. mean and r var It can be calculated using exponential smoothing. In one embodiment of this application, r threshold =r mean +k·r var , where k is a constant, for example, k = 3.

[0147] 305, the off-peak scheduling algorithm module extracts the burst traffic characteristics of each business flow.

[0148] In one embodiment of this application, the extracted burst traffic features include burst time phase, burst traffic size, and burst duration.

[0149] In another embodiment of this application, the extracted burst traffic features include burst traffic size, burst start time, and burst end time.

[0150] The extracted burst traffic characteristics can also include burst cycles.

[0151] The moment of sudden onset (t)ps ): The moment when the flow rate changes from less than the burst flow threshold to greater than the burst flow threshold.

[0152] The sudden end time (t) pe ): The moment when the flow rate changes from being greater than the burst flow rate threshold to being less than the burst flow rate threshold.

[0153] Burst duration (w): The time from the start of the burst (i.e., the burst start time) to the end of the burst (i.e., the burst end time). In real-time video streams, it represents the duration of an I-frame (keyframe).

[0154] Burst Flow Size (r): The maximum flow rate of a burst or the average flow rate during the duration of the burst.

[0155] Burst period (T): The time interval between two consecutive bursts of traffic. In real-time video streams, it is the transmission time of one GOP (Group of Pictures) video frame.

[0156] Sudden time phase (θ) i ): Define an arbitrary time point t0, and the burst time phase θ of the i-th service stream (e.g., video stream). i This refers to the time difference between the start time of the first burst of the i-th service flow and t0. It utilizes the burst time phase θ. i t0 and the burst period T can be used to calculate the burst start time of any burst traffic in the i-th service flow. For example, the burst start time of the j-th burst traffic in the i-th service flow is: t0 + θ i +T·(j-1).

[0157] 306. The peak-shifting scheduling algorithm module constructs a peak-burst traffic model based on the characteristics of peak-burst traffic.

[0158] In one embodiment of this application, before modeling the burst traffic of each video stream, the peak scheduling algorithm module determines whether each video stream experiences a burst traffic collision with other video streams. If a video stream does not experience a burst traffic collision with other video streams, then the burst traffic of that video stream is not modeled. Otherwise, if the video stream experiences a burst traffic collision with other video streams, then the burst traffic of that video stream is modeled.

[0159] Traffic surge refers to the collision of sudden bursts of traffic from different service streams (such as video streams), resulting in a larger instantaneous surge in traffic. Traffic surges can occur between two service streams or between multiple service streams. The peak-shifting scheduling algorithm module can determine whether the duration of a video stream's burst overlaps with the duration of bursts from other video streams. If the duration of a video stream's burst overlaps with the duration of bursts from other video streams, it is determined that a traffic surge has occurred between that video stream and other video streams.

[0160] By judging the peak traffic situation of the video stream, we can reduce the computational burden of modeling and improve the efficiency of peak scheduling by not modeling the video stream when there is no sudden traffic peak.

[0161] 307. The peak-shifting scheduling algorithm module adds scheduling delay as a design variable to the burst traffic model to obtain the scheduled burst traffic model.

[0162] 308. The off-peak scheduling algorithm module establishes an objective function for the scheduled burst traffic model.

[0163] The objective function can be a maximum value function or an entropy function.

[0164] 309. The off-peak scheduling algorithm module optimizes the objective function to obtain a time-delay scheduling scheme (i.e., the scheduling delay of each video stream).

[0165] In one embodiment of this application, the peak-shifting scheduling algorithm module uses the maximum scheduling delay as a constraint on the objective function when optimizing the objective function of the scheduled burst traffic model. Therefore, the resulting delay scheduling scheme is the one that minimizes peak collisions while satisfying the maximum scheduling delay constraint.

[0166] The maximum scheduling latency is the maximum increase in latency that the business can tolerate. The maximum scheduling latency can be set according to business requirements. Using the maximum scheduling latency as a constraint on the objective function can yield a more reasonable scheduling scheme, ensuring that the scheduling result meets actual business needs.

[0167] The specific implementation process of 306-309 is as follows: Figure 5 , Figure 6 The description is in the middle.

[0168] 310. The peak-shifting scheduling algorithm module transmits the delay scheduling scheme to the peak-shifting scheduling module.

[0169] 311. The off-peak scheduling module adds corresponding scheduling delays to each video stream according to the delay scheduling scheme.

[0170] 312, the off-peak scheduling module will send the video stream with increased scheduling delay to the base station.

[0171] If the scheduling latency is 0, the off-peak scheduling module directly sends the video stream to the base station.

[0172] Adding scheduling latency to a video stream means adding scheduling latency to the packets of that video stream.

[0173] The peak-shifting scheduling module adds corresponding scheduling delays to the packets of each video stream according to the delay scheduling scheme, and sends the video stream with the added scheduling delay to the base station, thereby realizing peak-shifting scheduling of video streams and reducing the peak-to-average ratio of the total traffic forwarded by CPE to the base station.

[0174] It should be noted that if the video stream sent by the camera to the CPE changes (e.g., a video stream is added or a video stream is removed), the service flow staggered scheduling method of this application embodiment determines a new delay scheduling scheme based on the changed video stream, and performs staggered scheduling of the video stream according to the new delay scheduling scheme.

[0175] For example, the service flow statistics module distinguishes each video stream based on the five-tuple of the IP packet. When the number of service streams changes, the service flow statistics module passes the traffic of each video stream received in each time period after the change to the peak scheduling algorithm module (i.e., step 303). The peak scheduling module re-executes steps 304-309 to obtain a new delay scheduling scheme.

[0176] Traffic shaping is an effective method to address congestion caused by data volume exceeding network capacity. Traffic shaping methods can be deployed on packet forwarding devices (i.e., service flow aggregation and forwarding nodes) along the network transmission path. By changing the amount of data transmitted per unit time, they prevent network congestion caused by excessive data sent to downstream nodes. Existing traffic shaping methods use rate limiting (e.g., token bucket, leaky bucket, and combinations thereof) to control the amount of data sent from the current node to downstream nodes, thereby reducing traffic bursts and network congestion.

[0177] Existing flow shaping methods have the following shortcomings:

[0178] (1) For real-time video services, a video frame needs to be split into multiple packets for transmission. The receiving end needs to receive all packets of the same video frame in order to successfully decode the video frame. Existing traffic shaping methods simply limit the forwarding rate of all video streams based on a preset transmission rate threshold, which leads to an increase in the latency of all video streams and a delay in the decoding time of all video streams.

[0179] (2) Existing traffic shaping algorithms essentially use a set rate threshold for rate control. This method works well in wired transmission scenarios with relatively stable bandwidth. However, in wireless transmission scenarios, bandwidth (the maximum network transmission rate, i.e., network transmission capacity) is constantly changing and fluctuates significantly, and the pre-set rate threshold cannot match the changing bandwidth in all situations. This leads to the following two problems: when bandwidth is sufficient, the rate threshold set by the shaping algorithm limits the transmission rate, resulting in a low message transmission rate; when bandwidth is insufficient, the rate threshold set by the shaping algorithm is too high, causing excessive data to be sent to the downstream network, leading to network congestion.

[0180] This application addresses the periodic traffic bursts characteristic of service flows (e.g., video streams) by adding corresponding scheduling delays to each service flow, reducing the cumulative traffic peaks of multiple service flows, and avoiding forwarding time delays for all service flows. This application improves transmission assurance capabilities by predicting peak traffic and planning traffic shaping schemes and resource allocation in advance. This application implements peak-shifting shaping under certain delay constraints, making the increased delay of each service flow due to traffic shaping controllable. The delay constraints can be set according to actual business needs and the delay cost of packet loss retransmission. In real-time video service scenarios, peak-shifting scheduling using the multi-service flow peak-shifting scheduling method disclosed in this application can enable the transmission of I-frames of video streams in whole frames, allowing some video streams to receive complete I-frames first and decode and play them.

[0181] In the embodiments provided in this application, the peak-shaving scheduling algorithm module models the burst traffic based on the characteristics of the burst traffic, obtaining a burst traffic model. The peak-shaving scheduling algorithm module adds scheduling delay as a design variable to the burst traffic model, obtaining a scheduled burst traffic model, and then optimizes and solves the scheduled burst traffic model to obtain a delay-based scheduling scheme. The embodiments of this application provide two modeling and optimization solutions.

[0182] Option 1

[0183] Option 1 describes the traffic characteristics of each service flow by constructing a constructor (i.e., a burst traffic function).

[0184] For the detailed implementation process of Option 1, please refer to [link / reference]. Figure 5 As shown.

[0185] 501, the peak-shifting scheduling algorithm module constructs a burst flow function based on the burst time phase, burst flow size, and burst duration.

[0186] The burst flow function is the relationship between time and flow, representing the change in business flow flow over time.

[0187] In one embodiment of this application, the burst flow function is constructed based on a sigmoid function with time as the independent variable. The sigmoid function, also called the Sigmoid function, has the following sigmoid function Z0(t) with time t as the independent variable:

[0188]

[0189] For each service flow, the off-peak scheduling algorithm module shifts the S-shaped function based on the burst duration and burst phase of the service flow, and scales it according to the first scaling factor, to obtain the first function of the service flow. The first function Z of the i-th service flow... 1,i (t) can be represented as:

[0190]

[0191] Where, θ i For the burst time phase of the i-th service flow, w i Let α be the burst duration of the i-th service flow, and let α be the first scaling factor.

[0192] The off-peak scheduling algorithm module reverses the S-shaped function, shifts it according to the burst time phase of the service flow, and scales it according to the second scaling factor to obtain the second function. The second function Z for the i-th service flow is... 2,i (t) can be represented as:

[0193]

[0194] Where β is the second scaling factor.

[0195] In one embodiment of this application, both the first scaling factor and the second scaling factor are 1.

[0196] The first and second scaling factors can be other values. For example, the first scaling factor is 1 and the second scaling factor is 3.

[0197] The off-peak scheduling algorithm module multiplies the first and second functions to obtain the third function. The third function Z for the i-th service flow is... 3,i (t) can be represented as:

[0198]

[0199] The off-peak scheduling algorithm module scales the third function based on the magnitude of the burst traffic to obtain the burst traffic function. The burst traffic function X for the i-th service flow is... i (t|θ i ,r i ,w i (α,β) can be represented as:

[0200]

[0201] Among them, X i It is the traffic of the i-th business flow, r i Let be the burst traffic size of the i-th business flow.

[0202] Figure 6 This is a schematic diagram of the burst flow function, where 60 is the burst flow function curve and 61 is the time-flow curve obtained from the statistical flow.

[0203] 502, the peak-shifting scheduling algorithm module adds scheduling delay as a design variable to the burst flow function to obtain the scheduled burst flow function.

[0204] For example, for the burst flow function X i (t|θ i ,r i ,w i The scheduled burst flow function can be expressed as:

[0205]

[0206] t i This indicates that a scheduling delay t is added to the i-th service flow. i The scheduling latency of each service flow can be represented by the scheduling vector S1.

[0207] 503, the peak-shifting scheduling algorithm module establishes the objective function for the scheduled burst traffic function.

[0208] The objective function is the scheduling delay t. i The mathematical function is used to reflect the goal of staggered scheduling.

[0209] In one embodiment of this application, the objective function of the scheduled burst flow function can be a function for maximizing the superimposed flow or an entropy function, i.e. or Where f1(·) represents the objective function of the burst traffic function after scheduling, and g1(t) is the superimposed traffic of all service flows at time t, which can be expressed as:

[0210]

[0211] 504. Under the constraint of maximum scheduling delay, the peak-shifting scheduling algorithm module optimizes the objective function of the scheduled burst traffic function to obtain a delay scheduling scheme.

[0212] Under the constraint of maximum scheduling delay, the objective function of the scheduled burst flow function can be optimized as follows:

[0213]

[0214] Among them, t max Indicates the maximum scheduling delay; For constraints, i.e., satisfying

[0215] The optimization objective is to optimize within the constraint of maximum scheduling delay (i.e.) Under these conditions, the peak-to-average power ratio (PAPR) of the combined traffic (i.e., the combined traffic) of all service flows is reduced through orchestration and scheduling. For example, if the objective function is an entropy function, the optimization objective is:

[0216]

[0217] The above optimization objective represents maximizing entropy, that is, the more evenly the superimposed traffic of each business flow is distributed in each time period and the smaller the peak traffic is, the better.

[0218] To solve this optimization problem, a gradient descent-based heuristic optimization algorithm (such as the quasi-Newton iteration method) can be used to find the local optimum and obtain the final time delay scheduling scheme.

[0219] Option 1 describes the traffic characteristics of each service flow by constructing a function (i.e., a burst traffic function), and optimizes the target based on the burst traffic function, thereby realizing the planning and allocation of resources and improving the network transmission guarantee capability.

[0220] Option 2

[0221] Option 2 uses a traffic matrix to describe the traffic characteristics of each service flow. For details on the implementation of Option 2, please refer to [link / reference needed]. Figure 7 As shown.

[0222] 701, the peak scheduling algorithm module constructs a peak traffic collision matrix based on the size of the sudden traffic flow, the start time of the sudden traffic flow, and the end time of the sudden traffic flow.

[0223] The peak flow collision matrix is ​​used to represent the sudden flow that occurs in each predicted time period.

[0224] In one embodiment of this application, the peak-shifting scheduling algorithm module selects the number of predicted time periods, and the product of the number of predicted time periods and the preset time interval is greater than the burst cycle of the business flow.

[0225] The peak traffic collision matrix is ​​constructed using the number of service flows as the number of rows and the number of predicted time periods as the number of columns. Each row of the peak traffic collision matrix represents the traffic of a service flow in different predicted time periods. If a predicted time period of a service flow does not overlap with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic collision matrix is ​​0. If the predicted time period of a service flow overlaps with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic collision matrix is ​​the burst traffic size of that service flow.

[0226] The duration of a business flow is the time from the start of the flow to its end.

[0227] Assume there are N business flows and n prediction time periods. ken n ken satisfy:

[0228] n ken ×Δt>T

[0229] Where Δt is the preset time interval and T is the burst period.

[0230] The peak traffic collision matrix is ​​Y, and the elements of Y are Y(i,j), i∈[1,N],j∈[1,n]. Len Each row of Y represents the traffic of a business flow at different time periods. Y(i,j) is defined as follows:

[0231]

[0232] The above formula indicates that when t is satisfied pe ≤t j- Or t j+ ≤t ps When, Y(i,j) takes the value r i When t is not satisfied pe ≤t j- and t j+ ≤t ps When r is zero, Y(i,j) takes the value 0. i Let t be the burst traffic size of the i-th business flow. ps Indicates the start time of the emergency, t pe Indicates the end time of the emergency, t j- ,t j+ Indicates the j-th time period n j The start and end times, i.e., n j =[t j- ,t j+ ].

[0233] Figure 8 This is a schematic diagram of the peak flow collision matrix values. Figure 8 This shows the values ​​of the elements in the peak traffic collision matrix.

[0234] 702, the peak-shifting scheduling algorithm module adds scheduling delay as a design variable to the peak traffic collision matrix to obtain the peak traffic collision matrix after scheduling.

[0235] The number of scheduling windows for the i-th service flow is n. i That is, the scheduling delay t of the i-th service flow. i For n i ·Δt, where Δt is a preset time interval, the scheduling vector can be represented as

[0236] The peak traffic collision matrix after scheduling can be represented as:

[0237]

[0238] The above formula indicates that when t is satisfied ps +n i ·Δt <j<t pe +n i At time Δt, The value is Y(i,jn) i When t is not satisfied ps +n i ·Δt <j<t pe +n i At time Δt, The value is 0.

[0239] Figure 9 This is a schematic diagram of the peak traffic collision matrix values ​​after scheduling. Figure 9 This demonstrates that the i-th business flow increases by n. i After a scheduling delay of 2 (i.e., two preset time intervals), the elements in the peak traffic collision matrix after scheduling (i.e., The value of ).

[0240] 703, the peak-shifting scheduling algorithm module establishes an objective function for the peak traffic collision matrix after scheduling.

[0241] In one embodiment of this application, the objective function of the scheduled peak traffic collision matrix can be the maximum value function of the superimposed traffic of all service flows, i.e. f2(·) represents the objective function of the peak traffic collision matrix after scheduling, and g2(j) is the superimposed traffic of all service flows. g2(j) can be expressed as:

[0242]

[0243] 704. Under the constraint of maximum scheduling delay, the peak-shifting scheduling algorithm module optimizes the objective function of the peak traffic collision matrix after scheduling to obtain a delay scheduling scheme.

[0244] Under the constraint of maximum scheduling delay, the objective function of optimizing the peak traffic collision matrix after scheduling can be expressed as:

[0245]

[0246] stn i ≤n max For constraints, i.e., satisfying n i ≤n max .

[0247] The maximum number of scheduling windows is in Indicates rounding down, t max It is the maximum scheduling delay.

[0248] This approach directly aims to minimize the maximum value of the superimposed flow, i.e., to minimize the peak flow of the superimposed flow.

[0249] Since Scheme 2's modeling method lacks an explicit functional expression, it cannot be solved using gradient descent optimization algorithms (such as quasi-Newton iteration methods). Scheme 2 can employ heuristic optimization algorithms such as genetic algorithms and particle swarm optimization to solve the objective function and obtain the scheduling delays of each service flow.

[0250] This application implements multi-service flow staggered scheduling through a service flow statistics module, a staggered scheduling algorithm module, and a staggered scheduling module. In the above embodiments, the service flow statistics module, the staggered scheduling algorithm module, and the staggered scheduling module are deployed at the service flow aggregation and forwarding node (e.g., CPE). The staggered scheduling module adds scheduling latency to each service flow to achieve staggered scheduling. In other embodiments of this application, the staggered scheduling module can be deployed at any upstream node with service flow control capabilities. For example, in a video surveillance scenario, the staggered scheduling module can be deployed in the camera (terminal).

[0251] Figure 10 This is a schematic diagram of deploying the off-peak scheduling module on the terminal.

[0252] like Figure 10As shown, the terminals (e.g., terminal 1 and terminal 2) include a peak-shaving scheduling module, and the service flow aggregation and forwarding node includes a service flow statistics module, a peak-shaving scheduling algorithm module, and a message sending module. In 10A, the peak-shaving scheduling module sends service flows to the service flow aggregation and forwarding node according to the original time sequence. The peak-shaving scheduling algorithm module solves the delay scheduling scheme and sends the scheduling delay of each service flow to the corresponding terminal through the message sending module. In 10B, the peak-shaving scheduling module adjusts the service flows according to the scheduling delay to adjust the timing of sudden traffic spikes in the service flows.

[0253] Deploying peak-shaving scheduling modules on terminals allows for adjustments to the timing of sudden large data surges, such as adjusting the timing of I-frame encoding in real-time video streams. This approach addresses the issue of traffic spikes at aggregation nodes during network transmission at the data source without introducing additional latency.

[0254] Figure 11 This is a schematic diagram of the structure of an electronic device (service flow aggregation and forwarding node or terminal) disclosed in an embodiment of this application. Figure 11 As shown, the electronic device 110 may include components such as a radio frequency (RF) circuit 1101, a memory 1102, an input unit 1103, a display unit 1104, a sensor 1105, an audio circuit 1106, a Wi-Fi module 1107, a processor 1108, and a power supply 1109. Those skilled in the art will understand that... Figure 11 The structure shown does not constitute a limitation on the service flow aggregation and forwarding node, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0255] RF circuit 1101 can be used to send and receive information or, during a call, to receive and transmit signals. Specifically, after receiving downlink information from the base station, it forwards it to processor 1108 for processing; additionally, it transmits uplink data to the base station. Typically, RF circuit 1101 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low-noise amplifier (LNA), a duplexer, etc.

[0256] The memory 1102 can be used to store software programs and modules. The processor 1108 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 1102. The memory 1102 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as audio data, telephone book, etc.). In addition, the memory 1102 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0257] The input unit 1103 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the electronic device. Specifically, the input unit 1103 may include a touch panel 11031 and other input devices 11032. The touch panel 11031, also known as a touch screen, can collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 11031), and drive the corresponding connection devices according to a pre-set program. Optionally, the touch panel 11031 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device, converts it into touch point coordinates, sends it to the processor 1108, and receives and executes commands from the processor 1108. In addition, the touch panel 11031 can be implemented using various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 11031, the input unit 1103 may also include other input devices 11032. Specifically, other input devices 11032 may include, but are not limited to, one or more of the following: physical keyboard, function keys (such as volume control buttons, power buttons, etc.), trackball, mouse, joystick, etc.

[0258] Display unit 1104 can be used to display information input by the user or information provided to the user, as well as various menus of the electronic device. Display unit 1104 may include display panel 11041, optionally configured as a Liquid Crystal Display (LCD), Organic Light-Emitting Diode (OLED), or similar display panel 11041. Further, touch panel 11031 may cover display panel 11041. When touch panel 11031 detects a touch operation on or near it, it transmits the information to processor 1108 to determine the type of touch event. Subsequently, processor 1108 provides corresponding visual output on display panel 11041 based on the type of touch event. Although in Figure 11 In this embodiment, the touch panel 11031 and the display panel 11041 are two separate components to realize the input and output functions of the electronic device. However, in some embodiments, the touch panel 11031 and the display panel 11041 can be integrated to realize the input and output functions of the electronic device.

[0259] The electronic device may also include at least one sensor 1105, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 11041 according to the ambient light level, and the proximity sensor can turn off the display panel 11041 and / or the backlight when the electronic device is moved to the ear. As a type of motion sensor, an accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the electronic device (such as landscape / portrait switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometers, taps), etc. In addition, the electronic device may also be equipped with other sensors such as gyroscopes, barometers, hygrometers, thermometers, and infrared sensors, which will not be described in detail here.

[0260] Audio circuit 1106, speaker 11061, and microphone 11062 provide an audio interface between the user and the electronic device. Audio circuit 1106 converts received audio data into electrical signals and transmits them to speaker 11061, where speaker 11061 converts them into sound signals for output. On the other hand, microphone 11062 converts collected sound signals into electrical signals, which are received by audio circuit 1106, converted into audio data, and then processed by processor 1108 before being sent to another electronic device via RF circuit 1101, or the audio data can be output to memory 1102 for further processing.

[0261] Wi-Fi is a short-range wireless transmission technology. Electronic devices using the Wi-Fi module 1107 can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 11 Wi-Fi module 1107 is shown, but it is understood that it is not an essential component of the electronic device and can be omitted as needed without changing the nature of the invention.

[0262] The processor 1108 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 1102, and by calling data stored in the memory 1102, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, the processor 1108 may include one or more processing units; preferably, the processor 1108 may integrate an application processor and a modem, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem mainly handles wireless communication. It is understood that the aforementioned modem processor may not be integrated into the processor 1108.

[0263] The electronic device also includes a power supply 1109 (such as a battery) that supplies power to various components. Optionally, the power supply can be logically connected to the processor 1108 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0264] Although not shown, electronic devices may also include cameras, Bluetooth modules, etc., which will not be described in detail here.

[0265] Figure 11 The electronic equipment described herein can be used to implement this application. Figure 3 For some or all of the processes described in the method embodiments, please refer to the foregoing. Figure 3 The relevant descriptions in the embodiments will not be repeated here.

[0266] This embodiment also provides a computer storage medium storing computer instructions. When the computer instructions are executed on an electronic device, the electronic device performs the aforementioned method steps to implement the blockchain signature verification method in the above embodiment.

[0267] This embodiment also provides a computer program product that, when run on an electronic device, causes the electronic device to perform the aforementioned steps to implement the blockchain signature verification method described in the above embodiment.

[0268] In addition, embodiments of this application also provide an apparatus, which may specifically be a chip, component or module. The apparatus may include a connected processor and a memory; wherein the memory is used to store computer execution instructions, and when the apparatus is running, the processor may execute the computer execution instructions stored in the memory to cause the chip to execute the blockchain signature verification method in the above method embodiments.

[0269] In this embodiment, the electronic device, computer storage medium, computer program product or chip are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding method provided above, and will not be repeated here.

[0270] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0271] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0272] The unit described as a separate component may or may not be physically separate. The component shown as a unit can be one physical unit or multiple physical units, that is, it can be located in one place or distributed in multiple different places. Some or all of the units can be selected to achieve the purpose of the solution in this embodiment according to actual needs.

[0273] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0274] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0275] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A service flow peak-shifting scheduling method, applied to a service flow aggregation and forwarding node, characterized in that, The method includes: Receive multiple service streams; Based on preset time intervals, the traffic of each service stream received in each time period is counted; Identify burst traffic for each service flow based on the traffic received for each service flow in each time period; The scheduling latency for each service flow is determined based on the burst traffic of each service flow, including: Extract burst traffic characteristics for each service flow based on the traffic received for each service flow in each time period; Construct a burst flow model based on the burst flow characteristics; By adding scheduling delay as a design variable to the aforementioned burst traffic model, a scheduled burst traffic model is obtained. Based on the superimposed traffic of the multiple service flows after scheduling, an objective function is established for the burst traffic model after scheduling; Under the constraint of maximum scheduling delay, the objective function is optimized to reduce the peak traffic of the multiple service flows and obtain the scheduling delay of each service flow.

2. The service flow off-peak scheduling method as described in claim 1, characterized in that, The burst flow characteristics include burst time phase, burst flow magnitude, and burst duration. Constructing a burst flow model based on these characteristics includes: A burst flow function is constructed based on the burst time phase, burst flow magnitude, and burst duration.

3. The service flow off-peak scheduling method as described in claim 2, characterized in that, The step of constructing the burst flow function based on the burst time phase, burst flow magnitude, and burst duration includes: For each business flow, the S-shaped function with time as the independent variable is shifted according to the burst duration and burst time phase of the business flow and scaled according to the first scaling factor to obtain the first function; The second function is obtained by flipping the S-shaped function, shifting it according to the burst time phase of the service flow, and scaling it according to the second scaling factor. Multiply the first function and the second function to obtain the third function; The third function is scaled based on the size of the burst traffic of the business flow to obtain the burst traffic function.

4. The service flow off-peak scheduling method as described in claim 3, characterized in that, Both the first scaling factor and the second scaling factor are 1.

5. The service flow off-peak scheduling method as described in claim 3, characterized in that, The objective function is either a maximum value function or an entropy function.

6. The service flow off-peak scheduling method as described in claim 1, characterized in that, The burst traffic characteristics include burst traffic magnitude, burst start time, and burst end time. Constructing a burst traffic model based on these characteristics includes: A peak traffic collision matrix is ​​constructed based on the size of the burst traffic, the start time of the burst, and the end time of the burst.

7. The service flow off-peak scheduling method as described in claim 6, characterized in that, The step of constructing the peak traffic collision matrix based on the burst traffic size, burst start time, and burst end time includes: Select the number of prediction time periods, where the product of the number of prediction time periods and the preset time interval is greater than the burst cycle of the business flow; The peak traffic surge matrix is ​​constructed by using the number of the multiple service flows as the number of rows in the peak traffic surge matrix and the number of predicted time periods as the number of columns in the peak traffic surge matrix. If a predicted time period of one of the multiple service flows does not overlap with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic surge matrix is ​​0. If the predicted time period of that service flow overlaps with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic surge matrix is ​​the burst traffic size of that service flow. The burst duration is determined by the burst start time and the burst end time.

8. The service flow off-peak scheduling method as described in claim 7, characterized in that, The objective function is a maximum value function.

9. The service flow off-peak scheduling method as described in claim 8, characterized in that, The objective function for establishing the scheduled burst traffic model includes: Under the constraint of maximum scheduling delay, the objective function is established for the scheduled burst traffic model.

10. The service flow off-peak scheduling method as described in any one of claims 1 to 9, characterized in that, Before constructing the burst flow model based on the burst flow characteristics, the method further includes: Determine whether the burst traffic of each of the multiple service flows clashes with the burst traffic of other service flows in the multiple service flows; If the burst traffic of this service flow collides with the burst traffic of other service flows, then the burst traffic model is constructed for this service flow.

11. The service flow off-peak scheduling method as described in any one of claims 1 to 9, characterized in that, The method further includes: The scheduling delay of each service flow is sent to the upstream node, so that the upstream node can add a corresponding scheduling delay to the service flow based on the scheduling delay of each service flow.

12. The service flow off-peak scheduling method as described in any one of claims 1 to 9, characterized in that, The method further includes: Based on the scheduling delay of each service flow, add a corresponding scheduling delay to each service flow; The multiple service flows with increased scheduling latency are sent to downstream nodes.

13. A service flow peak-shifting scheduling device, applied to a service flow aggregation and forwarding node, characterized in that, The device includes: The business flow statistics module is used to receive multiple business flows and, based on a preset time interval, to count the traffic of each business flow received in each time period. The peak-shifting scheduling algorithm module is used to identify burst traffic of each service flow based on the traffic received from each service flow in each time period, and to determine the scheduling delay of each service flow based on the burst traffic of each service flow. This includes: extracting burst traffic features of each service flow based on the traffic received from each service flow in each time period; constructing a burst traffic model based on the burst traffic features; adding scheduling delay as a design variable to the burst traffic model to obtain a scheduled burst traffic model; establishing an objective function for the superimposed traffic of the multiple service flows based on the scheduled burst traffic model; and optimizing the objective function under the constraint of maximum scheduling delay to reduce the peak value of the superimposed traffic of the multiple service flows, thereby obtaining the scheduling delay of each service flow.

14. The service flow off-peak scheduling device as described in claim 13, characterized in that, The burst traffic characteristics include burst time phase, burst traffic magnitude, and burst duration. The peak-shifting scheduling algorithm module is used for: A burst flow function is constructed based on the burst time phase, burst flow magnitude, and burst duration.

15. The service flow off-peak scheduling device as described in claim 14, characterized in that, The peak-shifting scheduling algorithm module is used for: For each business flow, the S-shaped function with time as the independent variable is shifted according to the burst duration and burst time phase of the business flow and scaled according to the first scaling factor to obtain the first function; The second function is obtained by flipping the S-shaped function, shifting it according to the burst time phase of the service flow, and scaling it according to the second scaling factor. Multiply the first function and the second function to obtain the third function; The third function is scaled based on the size of the burst traffic of the business flow to obtain the burst traffic function.

16. The service flow off-peak scheduling device as described in claim 15, characterized in that, Both the first scaling factor and the second scaling factor are 1.

17. The service flow off-peak scheduling device as described in claim 15, characterized in that, The objective function is either a maximum value function or an entropy function.

18. The service flow off-peak scheduling device as described in claim 13, characterized in that, The burst traffic characteristics include burst traffic size, burst start time, and burst end time. The peak-shifting scheduling algorithm module is used for: A peak traffic collision matrix is ​​constructed based on the size of the burst traffic, the start time of the burst, and the end time of the burst.

19. The service flow off-peak scheduling device as described in claim 18, characterized in that, The peak-shifting scheduling algorithm module is used for: Select the number of prediction time periods, where the product of the number of prediction time periods and the preset time interval is greater than the burst cycle of the business flow; The peak traffic surge matrix is ​​constructed by using the number of the multiple service flows as the number of rows in the peak traffic surge matrix and the number of predicted time periods as the number of columns in the peak traffic surge matrix. If a predicted time period of one of the multiple service flows does not overlap with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic surge matrix is ​​0. If the predicted time period of that service flow overlaps with the burst duration of that service flow, the value of the element corresponding to that predicted time period in the peak traffic surge matrix is ​​the burst traffic size of that service flow. The burst duration is determined by the burst start time and the burst end time.

20. The service flow off-peak scheduling device as described in claim 19, characterized in that, The objective function is a maximum value function.

21. The service flow off-peak scheduling device as described in any one of claims 13 to 20, characterized in that, The peak-shifting scheduling algorithm module is used for: Under the constraint of maximum scheduling delay, the objective function is established for the scheduled burst traffic model.

22. The service flow off-peak scheduling device as described in any one of claims 13 to 20, characterized in that, The device further includes: The judgment module is used to determine whether the burst traffic of each of the multiple service flows overlaps with the burst traffic of other service flows in the multiple service flows.

23. The service flow off-peak scheduling device as described in any one of claims 13 to 21, characterized in that, The device further includes: The message sending module is used to send the scheduling delay of each service flow to the upstream node, so that the upstream node can add the corresponding scheduling delay to the service flow according to the scheduling delay of each service flow.

24. The service flow off-peak scheduling device as described in any one of claims 13 to 21, characterized in that, The device further includes: The off-peak scheduling module is used to add a corresponding scheduling delay to each service flow based on the scheduling delay of each service flow, and then send the multiple service flows with the added scheduling delay to the downstream nodes.

25. A computer-readable storage medium, characterized in that, It includes computer instructions that, when executed on an electronic device, cause the electronic device to perform the service flow off-peak scheduling method as described in any one of claims 1 to 12.

26. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory being used to store instructions, and the processor being used to invoke the instructions in the memory, causing the electronic device to execute the service flow peak scheduling method as described in any one of claims 1 to 12.

27. A chip system applied to an electronic device; the chip system includes an interface circuit and a processor; the interface circuit and the processor are interconnected via a line; the interface circuit is configured to receive signals from a memory of the electronic device and send signals to the processor, the signals including computer instructions stored in the memory; when the processor executes the computer instructions, the chip system performs a service flow peak-shifting scheduling method as described in any one of claims 1 to 12.

Citation Information

Patent Citations

  • Burst correlation dispersion mechanism for a packet switched communications system

    US6094420A