Bandwidth prediction method based on buffer duration and stable segment segmentation

Abstract

The invention discloses a bandwidth prediction method based on buffer duration and stable segment segmentation. The bandwidth prediction accuracy is improved by helping a code rate adaptive algorithm in a live broadcast scene. According to the method, stable segment segmentation is carried out on a network bandwidth sequence, and bandwidth prediction is carried out by taking the average bandwidth within the duration of a buffer area as a target. In this way, a more accurate bandwidth prediction result can be provided for the code rate self-adaption algorithm of the live broadcast scene, the code rate self-adaption algorithm is helped to reduce the jamming duration ratio, and delay is reduced. Experimental results show that the bandwidth prediction model provided by the invention is used for replacing a bandwidth prediction scheme of a code rate adaptive algorithm ThroughputRule and MPC which are realized in Dash.js, root-mean-square errors of bandwidth prediction are respectively reduced by 39.1% and 40.6%, jamming duration ratios are respectively reduced by 15.94% and 21.41%, and average delays of video blocks are respectively reduced by 5.26% and 4.11%. In a word, the method can help a code rate adaptive algorithm to control the delay within an acceptable range of a live broadcast system, and effectively improves the user experience quality.

Description

Technical Field

[0001] The invention relates to the field of streaming media transmission, and in particular to a bandwidth prediction method based on buffering duration and stable segment segmentation. Background Art

[0002] Video traffic has become the largest component of Internet traffic. As of the third quarter of 2023, global live streaming accounts for 23% of viewing time and 17% of global Internet traffic. It is estimated that by 2029, the size of the global live streaming market will reach US$252.76 billion. Live streaming is one of the key applications of streaming technology, and platforms such as YouTube and TikTok are already in the leading position in the industry.

[0003] Compared with on-demand scenarios, live streaming has more stringent requirements on buffering and latency due to its interactive and real-time characteristics. Adaptive Bitrate Streaming (ABR) dynamically selects the appropriate video bitrate based on changing network conditions (such as bandwidth and buffer size), which is crucial to improving the user's Quality of Experience (QoE). However, the effectiveness of the ABR algorithm is highly dependent on the accuracy of bandwidth prediction. In on-demand scenarios, a larger buffer can tolerate a certain degree of bandwidth prediction error, but in live streaming, since the buffer is usually smaller, overestimation of bandwidth may lead to the selection of too high a bitrate, which in turn causes the download time to exceed the buffering time, resulting in video freezes. Therefore, a more robust and accurate bandwidth prediction strategy is needed to meet the needs of live streaming.

[0004] Bandwidth prediction is essentially a time series prediction problem, which relies on the bandwidth measurement values ​​of multiple historical video chunk downloads to predict the download bandwidth of the next video chunk, thereby guiding the bitrate selection. For example, the ThroughputRule algorithm in Dash.js uses the exponentially weighted moving average (EWMA) to predict the bandwidth of the next video chunk and selects a bitrate level that does not exceed the predicted bandwidth; the MPC algorithm uses the harmonic mean of the bandwidth measurement values ​​of the past 5 to 10 video chunks to predict the bandwidth of the next video chunk. However, these existing bandwidth prediction algorithms have two main problems:

[0005] First, the piecewise stable characteristics of network bandwidth are not considered. Network bandwidth behaves as a piecewise stable random process, that is, each stable segment follows a Gaussian distribution with the same parameters. In time series analysis, the stable state helps pattern recognition and feature extraction. If the input sequence is non-stationary and there are segmentation points, this will affect the model's extraction of useful features, leading to inaccurate predictions.

[0006] Second, existing bandwidth prediction methods usually only predict the bandwidth within the download time of a future video block. This short-term prediction target ignores the special requirements of live broadcast scenarios for less lag and low latency, resulting in large deviations in bandwidth prediction results. Using a single video block download bandwidth as a learning target is prone to overfitting the noise in the training data. The model is more inclined to capture short-term fluctuations rather than long-term stable trends, resulting in inaccurate bandwidth prediction. The bit rate selected by the ABR module does not match the actual network bandwidth conditions, which can easily cause video playback to freeze and affect user experience. Summary of the invention

[0007] In order to solve the problem of inaccurate prediction in existing bandwidth prediction methods, the present invention provides a bandwidth prediction method based on buffering duration and stable segment segmentation that can be applied in live broadcast scenarios.

[0008] In order to achieve the above technical objectives, the technical solution of the present invention is: a bandwidth prediction method based on buffer duration and stable segment segmentation, comprising the following steps:

[0009] Step 1: Record the network bandwidth when downloading each video block, so as to construct a bandwidth sequence; at the same time, record the buffer duration after each video block is downloaded, that is, the total future playback time of all video blocks downloaded in the buffer, so as to construct a buffer duration sequence;

[0010] Step 2: Calculate the probability of potential segmentation points in the bandwidth sequence, and then obtain segmentation points based on the potential segmentation points in combination with the buffer duration, so as to divide the bandwidth sequence into a stable segment set, and then unify the lengths of each stable segment in the stable segment set as training features; finally, calculate the average bandwidth within the buffer duration corresponding to the end time point of each bandwidth stable segment as a training label; thereby obtaining training samples;

[0011] Step 3, based on the training samples obtained in step 2, a bandwidth prediction model is constructed using a gated neural unit (GRU) and trained;

[0012] Step 4, obtain the stable segment according to the network bandwidth and buffer duration when downloading the current video block, and then divide the stable segment into sub-segments that meet the training feature length of the bandwidth prediction model, and input them into the bandwidth prediction model to obtain the bandwidth prediction result.

[0013] The method, in step 1, the bandwidth sequence is expressed as , , and represents the network bandwidth when downloading the tth video block, , n is the total number of video blocks counted in the bandwidth sequence; the corresponding buffer duration sequence is expressed as , , and Indicates the buffer length after the tth video chunk is downloaded.

[0014] The method described, It is calculated by the following formula:

[0015] .

[0016] Where q represents the bit rate of the video block, , Indicates the total number of optional bitrate levels for video blocks; represents the t-th video block with bit rate q, express The size of Indicates the downloading time of the tth video chunk.

[0017] The method, in step 2, calculating the probability of potential segmentation points in the bandwidth sequence includes the following steps:

[0018] Let the discrete random variable Indicates that until The length of the stable segment of the video block bandwidth; represent is a segmentation point of a bandwidth stability segment; otherwise, It is a continuation of the previous bandwidth stability period. ; In the acquired bandwidth sequence On the premise of The conditional probability distribution law of the value is ,in , p represents the probability, according to the Bayesian formula:

[0019] .

[0020] The molecular part in the above formula, i.e., up to The length of the stable bandwidth segment of the video block and the acquired bandwidth sequence The joint probability distribution of , is obtained by recursive calculation as follows:

[0021] .

[0022] in Represents a historical bandwidth sequence and Under the condition of The likelihood probability of ; is a predefined parameter, indicating that the bandwidth is The probability of a jump at , and set it as the probability of an abnormal point appearing, that is, ;in, and Respectively indicate the use Calculated mean and standard deviation; represents the inferred probability at the previous time point; and the initial condition of the recursive calculation is set to .

[0023] In the method, in step 2, the step of determining the segmentation point in combination with the buffer time comprises:

[0024] The buffer occupancy rate r is calculated by the following formula, that is, the ratio of the current buffer duration to the total duration of the video block that the buffer can accommodate:

[0025] .

[0026] in Indicates the total length of video chunks that the buffer can hold. Indicates the buffer length after the tth video chunk is downloaded;

[0027] Then, based on the recursive calculation formula, calculate S t The specific probability of taking each value, where the probability of the potential segmentation point is and the buffer occupancy For comparison, if , then it is believed that is a segmentation point of the bandwidth stability segment, starting from the previous segmentation point to Marked as a bandwidth stable segment, is the beginning of the next stable segment; otherwise, the current segmentation point is considered to be a continuation of the previous stable segment; after traversing all potential segmentation points, the bandwidth sequence Split into a set of stable segments , , i and j are the video block numbers, i.e., the i-th video block and the j-th video block, where Bandwidth sequence It is stable.

[0028] In the method, in step 2, the step of unifying the lengths of the various stable segments in the stable segment set includes:

[0029] Stable segment collection The length of the shortest stable segment As a uniform standard, the length greater than The stable phase The length of the window is , the sliding window method with a step size of 1 overlaps and intercepts sub-segments to generate a length of The sub-segment of And as training features, and Respectively represent the video block number as the starting point and the video block number as the end point in the sub-segment, and satisfy .

[0030] In the method, in step 2, the training labels are obtained by the following steps:

[0031] The average bandwidth corresponding to the buffer duration at the end of each bandwidth stabilization period is calculated by the following formula As training labels:

[0032] .

[0033] in Represents each sub-segment In download The buffer length after each video block, is the playback time of each video chunk.

[0034] In the method, in step 3, the bandwidth prediction model includes a first GRU layer, a first Dropout layer, a second GRU layer, a second Dropout layer and a Dense layer connected in sequence, the first GRU layer and the second GRU layer include 80 hidden units and 100 hidden units respectively, the first Dropout layer and the second Dropout layer are both set to a drop rate of 0.2, and the Dense layer is set to one neuron.

[0035] In the method, in step 4, the step of obtaining a stable segment according to the network bandwidth and buffer duration when the current video block is downloaded includes:

[0036] Get the Network bandwidth for downloading video chunks and buffer duration ,calculate The potential segmentation point probability value , and the current buffer occupancy , then use and determination Whether it corresponds to a segmentation point:

[0037] 1) If ,illustrate is a segmentation point, then Directly used as bandwidth prediction result;

[0038] 2) If ,illustrate is not a segmentation point, then based on The distribution law of , determine The maximum possible stable segment length at the end ,Right now .

[0039] In the method, in step 4, the step of constructing the stable segment into a sub-segment that meets the characteristic length of the bandwidth prediction model training includes:

[0040] The length of the input to the bandwidth prediction model is The stable segment is constructed as the input size of the bandwidth prediction model Subsection of:

[0041] ①If , then the intercept length is From arrive The sub-segment is , and then input the bandwidth prediction model;

[0042] ②If , then in the stable phase Before filling Bandwidth data: By constructing a length of , the mean is And the standard deviation is A sequence of random numbers, and After splicing, input the bandwidth prediction model.

[0043] The technical effect of the present invention is that the present invention can provide more accurate bandwidth prediction results for the bit rate adaptive algorithm of the live broadcast scene, helping the bit rate adaptive algorithm to reduce the stalling duration ratio and delay. Experimental results show that by replacing the bandwidth prediction scheme of the bit rate adaptive algorithm ThroughputRule and MPC implemented in Dash.js with the SSS-PBP provided by the present invention, the root mean square error of bandwidth prediction is reduced by 39.1% and 40.6% respectively, the stalling duration ratio is reduced by 15.94% and 21.41% respectively, and the average delay of video blocks is reduced by 5.26% and 4.11% respectively. In short, the present invention can help the bit rate adaptive algorithm to control the delay within the acceptable range of the live broadcast system, effectively improving the quality of user experience.

[0044] The present invention will be further described below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] FIG1 is a schematic diagram of the overall process framework of the present invention.

[0046] FIG. 2 is a schematic diagram of the process framework of segmentation point inference of the present invention.

[0047] FIG3 is a schematic diagram of a process framework of using average bandwidth as a prediction label in the present invention.

[0048] FIG4 is a diagram showing the effect of bandwidth sequence stable segment segmentation.

[0049] FIG5 is a diagram showing error curves for verifying a GRU using only stationary segment segmentation (SSS), a model using stationary segment segmentation and using average bandwidth as a prediction label (SSS-PBP), and training and testing using only GRU.

[0050] 6 is a comparison chart of the bandwidth prediction effects of the bandwidth prediction model adopted by the present invention (SSS-PBP) and the harmonic mean bandwidth prediction method (HM) used in MPC, the bandwidth prediction method (EWMA) used by ThroughputRule, and the moving average autoregression (ARMA) under the FCC data set.

[0051] FIG7 is a total QoE bar graph of all video blocks and a CDF curve of the average QoE of each video block after the bandwidth prediction model adopted by the present invention (SSS-PBP) replaces the original bandwidth prediction method of the ABR algorithm (MPC, Throughput Rule) based on bandwidth prediction; wherein (a) is a total QoE bar graph of all video blocks, and (b) is a CDF curve graph of the average QoE of each video block.

[0052] FIG8 is a histogram of the jamming duration ratio and a CDF curve of the delay after the bandwidth prediction model adopted by the present invention (SSS-PBP) replaces the original bandwidth prediction method of the ABR algorithm (MPC, Throughput Rule) based on bandwidth prediction; wherein (a) is a histogram of the jamming duration ratio and (b) is a CDF curve of the delay.

[0053] Fig. 9 The average bit rate of the video under three real network bandwidth data sets FCC, Oboe, Norway and synthetic data sets is shown after the bandwidth prediction model adopted by the present invention (SSS-PBP) replaces the original bandwidth prediction method of MPC and ThroughputRule. DETAILED DESCRIPTION

[0054] See also Figure 1, the bandwidth prediction method based on buffer duration and stable segment segmentation provided in this embodiment comprehensively considers the stability of bandwidth segmentation and the goal of less freezes and low playback delays in live broadcast scenarios. This embodiment divides the bandwidth sequence into stable segments and introduces the buffer duration to assist in the determination of segmentation points. Secondly, bandwidth prediction is performed based on the average bandwidth within the buffer duration when the last video block in each stable sub-segment is downloaded as a training label to obtain a prediction model, that is, a bandwidth prediction model that uses stable segment segmentation and uses the average bandwidth as a prediction label. Specifically, the following steps are included:

[0055] Step 1: Monitor the network bandwidth when downloading each video block and construct a bandwidth sequence: Indicates the bitrate level of the video block. represents the t-th video block with bit rate q, , the video block size is recorded as If the download time is , then the measured bandwidth value when downloading the video block is: .forward The bandwidth sequence composed of video chunk downloads is recorded as , and represents the network bandwidth when downloading the tth video block, . Record the buffer duration after each video chunk is downloaded, that is, the total future playback time of all downloaded video chunks in the buffer, and construct a buffer duration sequence: Indicates The buffer length after the video chunks are downloaded, that is, the playback time of the downloaded video chunks in the buffer. The buffer duration sequence consisting of video chunk downloads is recorded as , and Indicates the buffer length after the tth video chunk is downloaded.

[0056] Step 2: Construct training samples. First, divide the bandwidth sequence into a set of stable segments as training features: calculate the probability of potential segmentation points in the bandwidth sequence, combine the buffer duration, determine the segmentation points, and divide the bandwidth sequence into a set of stable segments as training features. Secondly, calculate the average bandwidth within the buffer duration corresponding to the end time point of each bandwidth stable segment as the training label: for each bandwidth stable segment, take the buffer duration corresponding to the end time point of the segment, and calculate the average network bandwidth of this duration in the future as the training label.

[0057] The overall process of step 2 is as follows Figure 2 As shown, the specific operations are as follows:

[0058] Step A1: Let the discrete random variable Indicates that until The length of the stable segment of video block bandwidth, All possible values ​​of .but show is a segmentation point of a bandwidth stability segment; otherwise, It is a continuation of the previous bandwidth stability period. . In the bandwidth measurement obtained On the premise of Conditional probability distribution law of values , according to the Bayesian formula:

[0059] .

[0060] The numerator part of the formula means that until the The length of the stable bandwidth segment of the video block and the bandwidth measurements obtained The joint probability distribution of , is obtained by recursive calculation as follows:

[0061] . .

[0062] in Indicates based on historical bandwidth information and Under the condition of The likelihood of In short, ; Indicates bandwidth in The probability of a jump at is a predefined parameter, which is usually set to the probability of an abnormal point appearing based on experience, that is, ,in, and Respectively represent the mean and standard deviation calculated using the original bandwidth dataset. In short, ; represents the inference probability at the previous time point. In particular, set the recursive initial condition .

[0063] Step A2, determine the segmentation point. Indicates the total duration of the video blocks that the buffer can accommodate. The ratio of the current buffer duration to the total duration of the video blocks that the buffer can accommodate is the buffer occupancy rate. In order to adapt the determination of bandwidth stable segment segmentation to different network environments, S is calculated based on the recursive calculation formula. t The specific probability of taking each value, where the potential segmentation point probability value is ,Will and buffer occupancy For comparison. is greater than the buffer occupancy, i.e. ,but is a segmentation point of the bandwidth stability segment, starting from the previous segmentation point to Marked as a bandwidth stable segment, is the beginning of the next stable segment; otherwise, the current point is considered to be the continuation of the previous stable segment. is divided into a set of stable segments, denoted as , i and j are the video block numbers, where Bandwidth sequence It is stable.

[0064] Step A3, due to the stable segment set The lengths of the various stable segments in may be different, so it is necessary to unify the input size of the SSS-PBP model. The length of the shortest stable segment , which is used as the input size of the bandwidth prediction model, and then the length is greater than The stable phase The length of the window is , the sliding window method with a step size of 1 is overlapped to generate a length of The sub-segment of , where the video block number and Respectively represent the starting point and end point of the segment, and satisfy , as training features. For each sub-segment , in the download The buffer length after video chunks is , is the playback time of each video block, calculating the buffer duration Average bandwidth within , as training labels. Finally, the training samples of the bandwidth prediction model are obtained. , >. The overall process of step A3 is as follows Figure 3 shown.

[0065] Step 3: Model training. Use GRU to train the bandwidth prediction model. Specifically, the first layer of the model is a GRU layer with 80 hidden units, followed by a Dropout layer with a dropout rate of 0.2, which is used to randomly drop 20% of neurons during training to prevent overfitting and improve the generalization ability of the model. The second layer is a GRU layer with 100 hidden units, followed by another Dropout layer with a dropout rate of 0.2 to further alleviate the risk of overfitting. Finally, the output is completed through a Dense layer, which has only one neuron for predicting scalar values. The entire model extracts the complex features of the time series by stacking two layers of GRU, and combines Dropout and fully connected layers to achieve efficient processing and prediction of input data.

[0066] Step 4: Bandwidth prediction based on the model. The trained SSS-PBP model is applied in the AITrans simulation environment. The AITrans simulation platform has simulated the download and playback process of video blocks and provided a QoE calculation module. The QoE of each video frame is And the QoE of each video block is The calculation formula is as follows:

[0067] .

[0068] .

[0069] in, For playback time; is the bit rate; The duration of the freeze; Delay for playback; The bitrate selected for the previous video. The available bitrate (bitrate) set for the simulation platform is {0.3, 0.6, 1.5, 2.5, 4, 6} Mbps.

[0070] When the bandwidth prediction model provided by the present invention is used to predict the bandwidth, the specific process is as follows: Bandwidth measurements for video chunks and buffer duration ,calculate The distribution law of the buffer and the current buffer occupancy rate . Reuse and determination Whether it corresponds to a segmentation point: (1) If is a segmentation point, indicating that the bandwidth has changed significantly. It is directly used as the predicted bandwidth and handed over to the ABR algorithm to make the bitrate decision. (2) If is not a segmentation point, it is considered to be part of the previous stable segment. The distribution law of , determine The maximum possible stable segment length at the end ,Right now In order to make the length The stable segment input bandwidth prediction model predicts that the input size of the model needs to be adapted ①If , then the intercept length is From arrive The sub-segment is , input SSS-PBP inference to get the predicted value; ② If , that is, the current stable segment length is smaller than the input size of the bandwidth prediction model, and it is necessary to Before filling bandwidth data. Specifically, the construction length is , the mean is And the standard deviation is A sequence of random numbers, and After splicing, the bandwidth prediction model is input to obtain the predicted value of the bandwidth, which can then be handed over to the ABR algorithm to make a bit rate decision.

[0071] Figure 4 The bandwidth stable segment segmentation effect of SSS-PBP provided in this example is shown. The figure shows that these segmentation points can be responded quickly, especially when the bandwidth drops suddenly. For example, between video block numbers 352-353 in the figure, the bandwidth drops from 2.5Mbps to 1.3Mbps, and between video block numbers 379-382, the bandwidth drops from 2.46Mbps to 0.83Mbps. SSS-PBP can effectively identify these segmentation points, marked with dotted lines in the figure, so as to provide accurate bandwidth values ​​for the ABR algorithm.

[0072] Figure 5 The training and testing effects of the model using only GRU training, only stationary segment segmentation (SSS) GRU, and the SSS-PBP of the present invention using stationary segmentation and average bandwidth as the prediction label are progressively demonstrated. Whether it is the training error or the test error, it can be seen that the role of stationary segmentation in the predicted model, segmenting the bandwidth and predicting the average bandwidth within the buffer duration brings better model convergence performance.

[0073] Figure 6The bandwidth prediction effect comparison chart of the bandwidth prediction model provided by the SSS-PBP of the present invention and the harmonic mean bandwidth prediction method (HM) used in MPC, the bandwidth prediction method (TR) used by ThroughputRule, and the moving average autoregression (ARMA) under the FCC data set is shown. Figure 6 In the example, the bandwidth drops at video blocks 47 and 83. SSS-PBP identifies them as segmentation points, and its prediction value quickly responds to the sudden change in bandwidth. In particular, at the 47th video block, the prediction values ​​of other bandwidth prediction algorithms such as TR, HM, and ARMA need to go through about 4 video blocks to gradually converge to the actual bandwidth in the face of the sudden drop in bandwidth. The prediction values ​​between 47 and 50 overestimate the actual bandwidth, which will lead to incorrect bitrate decisions and easily cause video freezes.

[0074] Figure 7 The total QoE histogram of all video blocks and the CDF curve of the average QoE of each video block are shown after the bandwidth prediction model of the SSS-PBP of the present invention replaces the original bandwidth prediction method of the ABR algorithm (MPC, ThroughputRule) based on bandwidth prediction. (a) is the total QoE histogram of all video blocks, and (b) is the CDF curve of the average QoE of each video block. Under the synthetic data set and the public network bandwidth data set FCC, MPC, ThroughputRule, and ThroughputRule replaced by SSS-PBP (TR with SSS-PBP in the figure) and MPC (MPC with SSS-PBP in the figure) are compared. The results show that in the synthetic data set, the total QoE of the MPC video block using the SSS-PBP model is improved by 0.56%, and the total QoE of the ThroughputRule video block using the SSS-PBP model is improved by 6.13%. Under the FCC data set, the same performance is also shown through the CDF curve. However, the overall QoE of ThroughputRule combined with the bandwidth prediction model of the present invention is slightly lower than that of the pure MPC algorithm. This is because the present invention only focuses on accurate bandwidth prediction, while MPC also considers factors such as buffer occupancy and bit rate switching.

[0075] Figure 8 The CDF curves of the freeze duration ratio and playback delay are shown after the bandwidth prediction model SSS-PBP replaces the original bandwidth prediction methods of MPC and ThroughputRule, both using the FCC dataset. Figure 8Figure (a) shows that the ThroughputRule and MPC models using SSS-PBP bandwidth prediction have lower stall duration ratios, which are reduced by 15.94% and 21.41% respectively. Figure 8 Figure (b) shows that ThroughputRule with SSS-PBP reduces the average playback delay to 1.567 seconds, which meets the low delay (2 seconds) requirement of live streaming. In contrast, the delays of MPC and ThroughputRule are 2.425 seconds and 1.654 seconds, respectively. Compared with ThroughputRule and MPC, SSS-PBP reduces the delay by 5.26% and 4.11%, respectively, keeping the average delay within the acceptable range for live streaming. Although MPC with SSS-PBP does not fully meet the delay tolerance (less than 2 seconds), it still reduces the delay by 4.11% compared to the original MPC, showing some improvement.

[0076] Fig. 9 The average bit rate of videos in three real network bandwidth datasets, FCC, Oboe, and Norway, as well as synthetic datasets, is shown after the bandwidth prediction model SSS-PBP replaces the original bandwidth prediction methods of MPC and ThroughputRule. The bit rate improvement achieved by MPC combined with SSS-PBP is 8.26% to 9.94% higher than the baseline MPC, while TR combined with SSS-PBP shows more significant improvements, with the average bit rate increased by 11.32% to 30.11% compared to TR.

[0077] The above experimental results effectively confirm the excellent performance of SSS-PBP under different network bandwidth environments in live broadcast scenarios.

Claims

1. A bandwidth prediction method based on buffer duration and stable segment segmentation, characterized in that: The following steps are involved: Step 1: Record the network bandwidth when downloading each video block, so as to construct a bandwidth sequence; at the same time, record the buffer duration after each video block is downloaded, that is, the total future playback time of all video blocks downloaded in the buffer, so as to construct a buffer duration sequence; Step 2: Calculate the probability of potential segmentation points in the bandwidth sequence, and then obtain segmentation points based on the potential segmentation points in combination with the buffer duration, so as to divide the bandwidth sequence into a stable segment set, and then unify the lengths of each stable segment in the stable segment set as training features; Finally, the average bandwidth corresponding to the buffer duration at the end of each bandwidth stabilization period is calculated as a training label, thereby obtaining training samples. Step 3, based on the training samples obtained in step 2, a bandwidth prediction model is constructed using a gated neural unit (GRU) and trained; Step 4, obtain the stable segment according to the network bandwidth and buffer duration when downloading the current video block, and then divide the stable segment into sub-segments that meet the training feature length of the bandwidth prediction model, and input them into the bandwidth prediction model to obtain the bandwidth prediction result.

2. The method according to claim 1, characterized in that: In step 1, the bandwidth sequence is expressed as , , and represents the network bandwidth when downloading the tth video chunk, , n is the total number of video blocks counted in the bandwidth sequence; the corresponding buffer duration sequence is expressed as , , and Indicates the buffer length after the tth video chunk is downloaded.

3. The method according to claim 2, characterized in that It is calculated by the following formula: ； Where q represents the bit rate of the video block, , Indicates the total number of optional bitrate levels for video blocks; represents the t-th video block with bit rate q, express The size of Indicates the downloading time of the tth video chunk.

4. The method according to claim 3, characterized in that In step 2, calculating the probability of potential segmentation points in the bandwidth sequence includes the following steps: Let the discrete random variable Indicates that until The length of the stable segment of the video block bandwidth; Represents then based on the recursive calculation formula, is a segmentation point of a bandwidth stability segment; otherwise, It is a continuation of the previous bandwidth stability period. ; In the acquired bandwidth sequence On the premise of The conditional probability distribution law of the value is ,in , p represents the probability, according to the Bayesian formula: ； In the above formula, the molecular part, i.e., up to The length of the stable segment of video block bandwidth and the acquired bandwidth sequence The joint probability distribution of , is obtained by recursive calculation as follows: ； in Represents a historical bandwidth sequence and Under the condition of The likelihood probability of ; is a predefined parameter, indicating that the bandwidth is The probability of a jump at , and set it as the probability of an abnormal point appearing, that is, ;in, and Respectively indicate the use Calculated mean and standard deviation; represents the inferred probability at the previous time point; and the initial condition of the recursive calculation is set to .

5. The method according to claim 4, characterized in that In step 2, the step of determining the segmentation point in combination with the buffer time includes: The buffer occupancy rate r is calculated by the following formula, that is, the ratio of the current buffer duration to the total duration of the video block that the buffer can accommodate: ； in Indicates the total length of video chunks that the buffer can hold. Indicates the buffer length after the tth video chunk is downloaded; Then, based on the recursive calculation formula, calculate S t The specific probability of taking each value, where the potential segmentation point probability value is and the buffer occupancy For comparison, if , then it is believed that is a segmentation point of the bandwidth stability segment, starting from the previous segmentation point to Marked as a bandwidth stable segment, is the beginning of the next stable segment; otherwise, the current segmentation point is considered to be a continuation of the previous stable segment; after traversing all potential segmentation points, the bandwidth sequence Split into a set of stable segments , , i and j are the video block numbers, i.e., the i-th video block and the j-th video block, where Bandwidth sequence It is stable.

6. The method according to claim 5, characterized in that In step 2, the step of unifying the lengths of the various stable segments in the stable segment set includes: Stable segment collection The length of the shortest stable segment As a uniform standard, the length greater than The stable phase The length of the window is , the sliding window method with a step size of 1 overlaps and intercepts sub-segments to generate a length of The sub-segment of And as training features, and Respectively represent the video block number as the starting point and the video block number as the end point in the sub-segment, and satisfy .

7. The method according to claim 6, characterized in that In step 2, the training labels are obtained by the following steps: The average bandwidth corresponding to the buffer duration at the end of each bandwidth stabilization period is calculated by the following formula As training labels: ； in Represents each sub-segment In download The buffer length after each video block, is the playback time of each video chunk.

8. The method according to claim 1, characterized in that In the step 3, the bandwidth prediction model includes a first GRU layer, a first Dropout layer, a second GRU layer, a second Dropout layer and a Dense layer connected in sequence, the first GRU layer and the second GRU layer include 80 hidden units and 100 hidden units respectively, the first Dropout layer and the second Dropout layer are both set to a drop rate of 0.2, and the Dense layer is set to one neuron.

9. The method according to claim 7, characterized in that: In step 4, the step of obtaining a stable segment according to the network bandwidth and buffer duration when downloading the current video block includes: Get the Network bandwidth for downloading video chunks and buffer duration ,calculate The potential segmentation point probability value , and the current buffer occupancy , then use and determination Whether it corresponds to a segmentation point: 1) If ,illustrate is a segmentation point, then Directly used as bandwidth prediction result; 2) If ,illustrate is not a segmentation point, then based on The distribution law of , determine The maximum possible stable segment length at the end ,Right now .

10. The method according to claim 9, characterized in that In step 4, the step of constructing the stable segment into a sub-segment that meets the characteristic length of the bandwidth prediction model training includes: The length of the input to the bandwidth prediction model is The stable segment is constructed as the input size of the bandwidth prediction model Subsection of: ①If , then the intercept length is From arrive The sub-segment is , and then input the bandwidth prediction model; ②If , then in the stable phase Before filling Bandwidth data: By constructing a length of , the mean is And the standard deviation is A sequence of random numbers, and After splicing, input the bandwidth prediction model.

Images