CN119729058B - Network measurement methods and apparatus, electronic devices, storage media and computer program products - Google Patents
Network measurement methods and apparatus, electronic devices, storage media and computer program productsInfo
- Publication number
- CN119729058B CN119729058B CN202411918771.9A CN202411918771A CN119729058B CN 119729058 B CN119729058 B CN 119729058B CN 202411918771 A CN202411918771 A CN 202411918771A CN 119729058 B CN119729058 B CN 119729058B
- Authority
- CN
- China
- Prior art keywords
- network
- information
- time
- degradation
- observed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present disclosure relates to a network measurement method and apparatus, an electronic device, a storage medium, and a computer program product. The network measurement method comprises the steps of receiving view quality degradation information sent by a client, obtaining a network degradation time interval of a target network based on the view quality degradation information, obtaining network state information of the target network with round trip time of data packets as granularity by utilizing a congestion control model, obtaining data packet transmission information of the target network with round trip time of the data packets as granularity by monitoring the target network, determining the network state information and the data packet transmission information in the network degradation time interval as original information of a weak network part of the target network, extracting a plurality of key features with first preset duration as granularity from the original information of the weak network part, and determining the plurality of key features as network measurement data of the weak network part, wherein the key features are features representing real-time quality of the weak network part.
Description
Technical Field
The present disclosure relates to the field of communications, and in particular, to a network measurement method and apparatus, an electronic device, a storage medium, and a computer program product.
Background
In recent years, with the development of large-scale media services (such as short video, long video, live broadcast, etc.), a smooth and clear video viewing experience is becoming more important. In the process that the user watches the video, the watching experience of the user is reduced due to the fact that the video is blocked, the first screen is longer, the definition is lower and the like, watching of the user is influenced, and accordingly the watching duration of the user is reduced. The degradation of the network where the user is located is the most central factor causing the degradation of the user experience, so the research on the countermeasure strategy under the weak network is a central subject of increasing interest in industry.
The network infrastructure has been greatly developed, the network speed is gradually increased, but the network also has great fluctuation. To combat network fluctuations, the industry uses adaptive multi-rate algorithms, congestion control algorithms, preloading algorithms, etc. to combat network fluctuations. However, the fluctuation of the network is diversified, and the increase of latency, bandwidth reduction and packet loss of the underlying network all cause the decrease of available bandwidth of the user application layer. If the quantitative expression of the change of the weak network exists, and a rich online real weak network database can be established locally, the research and development efficiency of the weak network algorithm strategy is greatly improved, and the trial-and-error cost is greatly reduced.
Currently, the industry and academia mostly use network measurement and network loss instruments for recording and playback of weak networks. The existing network measurement method mainly comprises bandwidth measurement, delay measurement, maximum transmission unit (Maximum Transmission Unit, abbreviated as MTU) measurement, reachability measurement and the like. However, denser network measurement introduces a great deal of extra bandwidth cost, and can cause destructive influence on the experience of users, while thinner network measurement cannot reflect the change condition of a real network.
Disclosure of Invention
The disclosure provides a network measurement method and device, an electronic device, a storage medium and a computer program product, so as to at least solve the problems that the bandwidth consumed by the related technology is high in cost or the change situation of a real network cannot be reflected.
According to a first aspect of an embodiment of the present disclosure, there is provided a network measurement method, including receiving viewing quality degradation information sent by a client, acquiring a network degradation time interval of a target network based on the viewing quality degradation information, acquiring network state information of the target network with round trip time of a data packet as granularity, and acquiring data packet transmission information of the target network with round trip time of the data packet as granularity by monitoring the target network, determining the network state information and the data packet transmission information within the network degradation time interval as original information of a weak network part of the target network, extracting a plurality of key features with a first predetermined duration as granularity from the original information of the weak network part, and determining the plurality of key features as network measurement data of the weak network part, wherein the key features refer to features characterizing real-time quality of the weak network part.
Optionally, acquiring a network degradation time interval of the target network based on the viewing quality degradation information comprises acquiring degradation start time when viewing quality degradation occurs at the client and start downloading time of a video part when viewing quality degradation occurs at the client based on the viewing quality degradation information, determining degradation start time when viewing quality degradation occurs at the server and start downloading time of the video part at the server based on first time, second time, degradation start time and start downloading time of the client, wherein the first time is time when the transmission layer communicated with the client receives the viewing quality degradation information, the second time is time when the server receives the viewing quality degradation information, and determining the network degradation time interval of the target network by taking the start downloading time and the degradation start time of the server as boundaries.
Optionally, determining the network state information and the data packet transmission information in the network degradation time interval as the original information of the weak network portion of the target network includes expanding the network degradation time interval based on a second predetermined time length, and determining the network state information and the data packet transmission information in the expanded network degradation time interval as the original information of the weak network portion of the target network.
Optionally, under the condition that the key features comprise physical propagation delay, bottleneck routing bandwidth, random packet loss rate and maximum queue depth of bottleneck routing, extracting a plurality of key features taking first preset time as granularity from original information of a weak network part, wherein the key features comprise the physical propagation delay and the physical bandwidth in the original information which are respectively used as the physical propagation delay and the bottleneck routing bandwidth of the weak network part, determining correlation degree of observed round trip delay and observed packet loss rate in the original information, determining the random packet loss rate and the maximum queue depth of the bottleneck routing of the weak network part based on the correlation degree, and sampling the physical propagation delay, the bottleneck routing bandwidth, the random packet loss rate and the maximum queue depth of the bottleneck routing respectively with the first preset time as granularity to obtain a plurality of key features of each key feature.
The method comprises the steps of determining a random packet loss rate of a weak network part and a maximum queue depth of a bottleneck route based on correlation, wherein the method comprises the steps of taking an average value of all observed packet loss rates of all observed round trip delay intervals as the random packet loss rate of the weak network part in response to the correlation being smaller than a first threshold value, taking an average observed packet loss rate corresponding to a preset observed round trip delay interval as the random packet loss rate of the weak network part in response to the correlation being larger than a second threshold value, wherein the preset observed round trip delay interval is the interval with the minimum average observed round trip delay, and determining the maximum queue depth of the bottleneck route based on the maximum observed round trip delay, the bottleneck route bandwidth and the physical propagation delay in response to the correlation being larger than a third threshold value.
The method comprises the steps of dividing the observed round-trip delay in original information into a plurality of observed round-trip delay intervals, obtaining an average value of the observed round-trip delay and an average value of the observed round-trip delay for each observed round-trip delay interval, and determining the correlation degree of the observed round-trip delay and the observed packet loss rate based on the average value of the observed round-trip delay and the spearman correlation coefficient of the average value of the observed round-trip delay.
According to a second aspect of the embodiments of the present disclosure, there is provided a network measurement apparatus including a receiving unit configured to receive viewing quality degradation information transmitted by a client, a first acquiring unit configured to acquire a network degradation time interval of a target network based on the viewing quality degradation information, a second acquiring unit configured to acquire network state information of the target network with a round trip time of a packet as granularity using a congestion control model, and to acquire packet transmission information of the target network with the round trip time of the packet as granularity by monitoring the target network, a determining unit configured to determine the network state information and the packet transmission information within the network degradation time interval as original information of a weak network part of the target network, an extracting unit configured to extract a plurality of key features of a first predetermined length as granularity from the original information of the weak network part and determine the plurality of key features as network measurement data of the weak network part, wherein the key features refer to features characterizing real-time quality of the weak network part.
Optionally, the first obtaining unit is further configured to obtain, based on the viewing quality degradation information, a degradation start time when the viewing quality degradation occurs at the client and a start download time of the video portion when the viewing quality degradation occurs at the client, determine, based on the first time, the second time, the degradation start time of the client and the start download time of the video portion when the viewing quality degradation occurs at the server, wherein the first time is a time when the viewing quality degradation information is received by a transmission layer communicating with the client, the second time is a time when the viewing quality degradation information is received by the server, and determine a network degradation time interval of the target network with the start download time and the degradation start time of the server as boundaries.
Optionally, the determining unit is further configured to expand the network degradation time interval based on the second predetermined time length, and determine the network status information and the data packet transmission information within the expanded network degradation time interval as original information of the weak network portion of the target network.
Optionally, under the condition that the key features include physical propagation delay, bottleneck routing bandwidth, random packet loss rate and maximum queue depth of bottleneck routing, the extracting unit is further configured to respectively use the physical propagation delay and the physical bandwidth in the original information as the physical propagation delay and the bottleneck routing bandwidth of the weak network part, determine correlation between the observed round trip delay and the observed packet loss rate in the original information, determine the random packet loss rate and the maximum queue depth of bottleneck routing of the weak network part based on the correlation, and sample the physical propagation delay, the bottleneck routing bandwidth, the random packet loss rate and the maximum queue depth of the bottleneck routing with a first predetermined time length as granularity to obtain a plurality of key features of each key feature.
Optionally, the extracting unit is further configured to respond to the correlation being smaller than a first threshold, take an average value of the observed packet loss rates of all the observed round-trip delay intervals as a random packet loss rate of the weak network part, respond to the correlation being larger than a second threshold, take an average observed packet loss rate corresponding to a preset observed round-trip delay interval as a random packet loss rate of the weak network part, wherein the preset observed round-trip delay interval is a minimum interval of the average observed round-trip delay, and respond to the correlation being larger than a third threshold, and determine a maximum queue depth of the bottleneck routing based on the maximum observed round-trip delay, the bottleneck routing bandwidth and the physical propagation delay.
The extraction unit is further configured to partition the observed round trip delay in the original information to obtain a plurality of observed round trip delay intervals, obtain an average value of the observed packet loss rate and an average value of the observed round trip delay for each of the observed round trip delay intervals, and determine the correlation degree between the observed round trip delay and the observed packet loss rate based on the average value of the observed packet loss rate and the spearman correlation coefficient of the average value of the observed round trip delay for each of the observed round trip delay intervals.
According to a third aspect of embodiments of the present disclosure, there is provided an electronic device comprising a processor, a memory for storing processor-executable instructions, wherein the processor is configured to execute the instructions to implement the network measurement method of the present disclosure.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer readable storage medium, which when executed by at least one processor, causes the at least one processor to perform the network measurement method of the present disclosure as above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising computer instructions which, when executed by a processor, implement the network measurement method of the present disclosure.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
According to the network measurement method and device, the electronic equipment, the storage medium and the computer program product, when the viewing quality is degraded, the client sends the viewing quality degradation information to the server, namely the client can feed back the viewing quality degradation information in real time, and after receiving the information, the server can know a network degradation time interval according to the viewing quality degradation information, and further acquire network measurement data of a weak network part of a real network by combining the monitored data packet transmission information and network state information output by a congestion control model, so as to accelerate iteration of a local algorithm and improve the use quality of users on line. Accordingly, the present disclosure solves the problems that the related art consumes a high bandwidth cost or cannot reflect the change situation of the real network.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.
FIG. 1 is a schematic diagram of an implementation scenario of a network measurement method shown according to an exemplary embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a weak network measurement and full link optimization framework shown in accordance with an exemplary embodiment of the present disclosure;
FIG. 3 is a flow chart of a network measurement method shown in accordance with an exemplary embodiment of the present disclosure;
FIG. 4 is a block diagram of a network measurement device shown in accordance with an exemplary embodiment of the present disclosure;
Fig. 5 is a block diagram of an electronic device 500, shown in accordance with an exemplary embodiment of the present disclosure.
Detailed Description
In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The embodiments described in the examples below are not representative of all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
It should be noted that, in this disclosure, "at least one of the items" refers to a case where three types of juxtaposition including "any one of the items", "a combination of any of the items", "an entirety of the items" are included. For example, "comprising at least one of A and B" includes the case of juxtaposition of three of (1) comprising A, (2) comprising B, and (3) comprising A and B. For example, "at least one of the first and second steps is executed", that is, three cases are shown in parallel, namely (1) execute the first step, (2) execute the second step, and (3) execute the first and second steps.
Currently, network measurement mainly includes bandwidth measurement, delay measurement, maximum transmission unit (Maximum Transmission Unit, abbreviated as MTU) measurement, reachability measurement, and the like, and the following two network measurement methods are briefly introduced:
1. The network bandwidth measurement method based on PathLoad is a typical method of active network measurement, namely, a packet sequence is actively transmitted according to a fixed rate, the arrival time and the receiving time of the packets are recorded, the arrival trend of packet intervals is analyzed, if the packet arrival interval has an increasing trend, the transmission rate is larger than the link bandwidth, the receiving rate at the moment is calculated as the link bandwidth, and if the packet arrival interval has no increasing trend, the transmission rate is increased by using a binary method until the packet arrival interval is observed to have an increasing trend.
However, the network bandwidth measurement method based on PathLoad has the following three disadvantages that 1) PathLoad needs to actively send packets to perform network measurement, which introduces a huge amount of bandwidth cost when the online streaming media application is actually deployed, 2) PathLoad uses a bipartite method to detect bandwidth, the bipartite boundary selection greatly influences the detection speed, the bandwidth measurement efficiency is lower, and 3) PathLoad can only reflect the network bandwidth level when the network bandwidth measurement method detects, cannot reflect the network characteristics of other dimensions, such as factors of delay, random packet loss, queue depth and the like, and cannot reflect the network characteristics when the streaming media application is degraded in quality.
In particular, numerous variant algorithms have emerged in recent years that use packet pairs, sequences of packets for bandwidth measurement, but introduce significant bandwidth costs and do not allow simultaneous observation of multi-dimensional network characteristics, only PathLoad being exemplified as a typical algorithm.
2. The network measurement method based on the ICMP packet is a typical method for measuring reachability, packet loss and delay, namely, periodically sending the ICMP packet at a client by using a ping command, measuring the network round-trip delay mean value and jitter level, and observing the packet loss rate and network reachability in a period of time.
But the ICMP packet-based network measurement method has the following two disadvantages that 1) delay measurement is generally sparse by using an IMCP packet, a typical interval is 1000ms, and the actual level of physical delay cannot be reflected if the delay measurement is dense, and 2) the bandwidth level of the network cannot be reflected by using the ICMP packet measurement, and the network characteristics of the streaming media application when quality degradation occurs cannot be reflected.
In order to solve the problems of high bandwidth cost, slower measurement speed and incomplete response network characteristics of a related network measurement method, the method disclosed by the invention obtains network measurement data of a weak network part conforming to a real user network by real-time feedback of application software (such as streaming media application on a client) and combining congestion control model and information required by network monitoring real-time statistics, and is used for accelerating iteration of a local algorithm and improving the use quality of online users.
Hereinafter, a network measurement method and apparatus, an electronic device, a storage medium, and a computer program product according to exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of an implementation scenario of a network measurement method according to an exemplary embodiment of the present disclosure, as shown in fig. 1, where the implementation scenario includes a server 100, a user terminal 110, and a user terminal 120, where the user terminals are not limited to 2, including devices such as a mobile phone, a personal computer, and the like, and the user terminal may install streaming media application software, and the server may be one server, or may be a server cluster formed by a plurality of servers, or may be a cloud computing platform or a virtualization center.
After the user terminals 110 and 120 access the target network, the user may watch the video through the streaming application software on the user terminal 110 or 120, and in case that the viewing quality is deteriorated during the video watching process, the viewing quality deterioration information is transmitted to the server 100. After receiving the viewing quality degradation information sent by the user terminals 110 and 120, the server 100 obtains a network degradation time interval of the target network based on the viewing quality degradation information, obtains network state information of the target network with the round trip time of the data packet as granularity by using a congestion control model, and obtains data packet transmission information of the target network with the round trip time of the data packet as granularity by monitoring the target network, determines the network state information and the data packet transmission information in the network degradation time interval as original information of a weak network part of the target network, and then extracts a plurality of key features with the first predetermined duration as granularity from the original information of the weak network part and determines the plurality of key features as network measurement data of the weak network part, wherein the key features refer to features representing real-time quality of the weak network part.
After the network measurement data of the weak network part is obtained, a large-scale network database of the weak network of the real user on line can be established by utilizing the network measurement data, and accelerated simulation playback is carried out locally, so that the research and development efficiency of weak network countermeasure is greatly improved. Fig. 2 illustrates a weak network measurement and full link optimization framework in the present disclosure, when a user views a video by using streaming media application software and the viewing quality is degraded, a network measurement unit will record network conditions, that is, network measurement data in real time, and then perform weak network playback and evaluation on line, so as to form a weak network database, and provide support for off-line policy optimization.
Fig. 3 is a flowchart illustrating a network measurement method according to an exemplary embodiment of the present disclosure, as shown in fig. 3, including the steps of:
in step S301, viewing quality degradation information transmitted by a client is received.
As an example, the client runs the application software (such as streaming media application software) using the target network, and when the situation that the viewing quality of the application software is degraded is monitored, the viewing quality degradation information may be sent to the server.
Taking as an example the viewing quality degradation as the viewing video clip, at this time, the viewing quality degradation information (QoS info) may include, but is not limited to, a viewing video clip duration (block dur), a viewing video clip number (block count), a viewing video clip time (block ts), an application layer video code rate (bitrate), and a start download time (download start) of a video portion where the clip is located.
It should be noted that the degradation of viewing quality is not limited to video clip, but may be degradation of viewing quality of various types of streaming media, such as degradation of definition of a viewing video, a first screen time period of the viewing video, etc., and this disclosure only exemplifies video clip.
In step S302, a network degradation time zone of the target network is acquired based on the viewing quality degradation information.
As an example, the corresponding time information of the server may be obtained based on the time information corresponding to the click in the viewing quality degradation information sent by the client, and then the network degradation time interval may be determined based on the corresponding time information of the server.
According to an exemplary embodiment of the present disclosure, a network degradation time interval of a target network may be determined by acquiring a degradation start time at which viewing quality degradation occurs at a client and a start download time at the client for a video portion at which viewing quality degradation occurs based on viewing quality degradation information, determining a degradation start time at which viewing quality degradation occurs at a server and a start download time at the server based on a first time, a second time, and the degradation start time and the start download time of the client, wherein the first time is a time at which a transmission layer in communication with the client receives the viewing quality degradation information, the second time is a time at which the server receives the viewing quality degradation information, and determining the network degradation time interval of the target network with the start download time and the degradation start time of the server as boundaries.
According to the embodiment, the time of the server and the time of the client are aligned based on the time of the transmission layer communicated with the client receiving the viewing quality degradation information and the time of the server receiving the viewing quality degradation information, so that the server can determine a relatively accurate network degradation time interval based on the aligned time.
As an example, the present disclosure communicates information between a transmission layer and application software of a client, and when the application software experiences degradation of viewing quality, the application software transparently transmits the degradation information of viewing quality to the communicated transmission layer, which transmits the degradation information of viewing quality to a server through a streaming media information frame. The server receives the viewing quality degradation information, starts a network measurement flow, records the measured information to the local of the server, and transmits the information recorded by the network measurement to a weak network database for storage in a non-network peak period.
As an example, when the application software has a degradation of viewing quality, the viewing quality degradation information QoS info may be delivered to the transport layer, and when the client transport layer receives the viewing quality degradation information QoS info, it records that the time is t c, and the transport layer combines t c and QoS info into a streaming media information frame and sends the streaming media information frame to the server. When the service end receives the viewing quality degradation information QoS info, the time is recorded as t s, and then the timestamp block ts and the downlink start of the client end in the QoS info are analyzed, so that the timestamp corresponding to the service end can be converted according to the following formula:
blocktsserver＝blockts-tc+ts-srtt
=downloadstart-tc+ts-srtt
wherein srtt is a smooth rtt calculated by the server, which is not discussed in this disclosure.
After obtaining the corresponding time stamps block ts_server and download start_server of the server, the network degradation time interval, i.e., [ download start_server,blockts_server ], can be further obtained.
In step S303, using the congestion control model, network state information of the destination network with the round trip time of the data packet as granularity is obtained, and by monitoring the destination network, data packet transmission information of the destination network with the round trip time of the data packet as granularity is obtained.
As an example, an acknowledgement message of a data packet transmitted through the target network may be acquired, and the acknowledgement message is input into the congestion control model, so that network state information, such as physical propagation delay and physical bandwidth, corresponding to the round trip time of the target network in the data packet may be obtained.
As an example, in the operation process of the target network, the target network is monitored, that is, corresponding data packet transmission information, such as round trip delay, packet loss rate, etc., can be observed.
As an example, the server may record network state information and packet transmission information up to T seconds (e.g., 600 seconds) with Round Trip Time (RTT) as granularity, where the network state information may include physical bandwidth bw i output by the plug control model and physical propagation time d i output by the congestion control model, and the packet transmission information may include observed packet loss rate l i and current observed round trip time RTT i, where i represents the ith RTT.
In step S304, the network state information and the packet transmission information in the network degradation time interval are determined as the original information of the weak network part of the target network.
As an example, the network state information and the packet transmission information in the network degradation time interval may be acquired and stored in separate local files on the server, and the corresponding file name may use the md5 code of the piece of information, and the file may be used as an original file of the weak network part, which is equivalent to the original information of the weak network part.
According to an exemplary embodiment of the present disclosure, network state information and packet transmission information within a network degradation time interval may be determined as original information of a weak network portion of a target network by expanding the network degradation time interval based on a second predetermined time length and determining the network state information and the packet transmission information within the expanded network degradation time interval as original information of the weak network portion of the target network. By this embodiment, the network degradation time interval is enlarged, and the time when the network degradation is not completely covered is avoided.
As an example, after the network degradation time interval [ download start_server,blockts_server ] is obtained, the network degradation time interval may be expanded by a second predetermined length of time, resulting in an expanded network degradation time interval t i:
ti∈[downloadstart_server-α×srtt,blockts_server+α×srtt]
where α× srtt is a second predetermined time period, it may take between 30 seconds and 40 seconds, which is not limited to this disclosure.
Then, the network state information and the data packet transmission information in t i can be acquired and stored in independent local files on the server, the corresponding file name can adopt the md5 code of the information, and the file is taken as the original file of the weak network part and is equivalent to the original information of the weak network part.
In step S305, a plurality of key features with granularity of a first predetermined time length are extracted from the original information of the weak network part and are determined as network measurement data of the weak network part, wherein the key features are features characterizing real-time quality of the weak network part.
As an example, in this embodiment, from the above original information, network measurement data that can be used for local weak network restoration may be extracted with the first predetermined duration as granularity, so as to improve the iteration efficiency of the local algorithm policy. The first predetermined period of time described above is set as needed, and may be set to 1 millisecond, for example.
By way of example, to obtain relatively accurate network measurement data for the weak network portion, the key features described above include, but are not limited to, random packet loss rate l r, physical propagation delay d p, bottleneck routing bandwidth b, and bottleneck routing maximum queue depth d q. In this embodiment, with granularity of 1 ms, the bottleneck routing bandwidth b and the maximum queue depth d q of the bottleneck routing are extracted, while the random packet loss rate l r and the physical propagation delay d p may still be granularity of RTT, and the following form is adopted to record network measurement data in RTT, which is used as a corresponding weak network track (trace) for simulation and restoration of the subsequent local weak network:
<lr,dp,<dq1,b1>,<dq2,b2>…<dqn,bn>>
It should be noted that, assuming that there are a plurality of network degradation time intervals, if the interval between two network degradation time intervals does not exceed a predetermined time (e.g., 30 seconds), the network measurement data of the two network degradation time intervals may be merged together as a weak network track.
According to the exemplary embodiment of the disclosure, under the condition that key features comprise physical propagation delay, bottleneck routing bandwidth, random packet loss rate and maximum queue depth of bottleneck routing, extracting a plurality of key features taking a first preset time length as granularity from original information of a weak network part can comprise taking the physical propagation delay and the physical bandwidth in the original information as the physical propagation delay and the bottleneck routing bandwidth of the weak network part respectively, determining correlation degree between observed round trip delay and observed packet loss rate in the original information, determining the random packet loss rate and the maximum queue depth of the bottleneck routing of the weak network part based on the correlation degree, and taking the first preset time length as granularity to sample the physical propagation delay, the bottleneck routing bandwidth, the random packet loss rate and the maximum queue depth of the bottleneck routing respectively to obtain a plurality of key features of each key feature.
By adopting the four key features, the embodiment can better describe the actual quality of the weak network part so as to facilitate the subsequent use of the network measurement data of the weak network part to improve the iteration efficiency of the local algorithm strategy.
As an example, the present embodiment directly adopts the physical propagation delay d output in real time by the congestion control model as the physical propagation delay d p, and directly adopts the physical bandwidth bw i output in real time by the congestion control model as the bottleneck routing bandwidth b. The random packet loss rate and the maximum queue depth of the bottleneck route can be determined based on the correlation degree between the observed round trip delay and the observed packet loss rate in the original information. After the four key features are obtained, sampling can be performed according to the first preset time length as required, so that a plurality of key features meeting the requirements are obtained.
As an example, the congestion control model may use BBR (Bottleneck Bandwidth and Round-trip Propagation Time) V3, and may also use other congestion control models, for example, bandwidth detection speed may be improved by improving a bandwidth detection mechanism of the congestion control model, and when a network bandwidth is greatly changed and application layer data is limited, the bandwidth may still be accurately measured, and more accurate network measurement raw data may be obtained.
It should be noted that the key features are not limited to physical propagation delay, bottleneck routing bandwidth, random packet loss rate and maximum queue depth of bottleneck routing, but may be other features, and the disclosure is not limited thereto.
According to an exemplary embodiment of the disclosure, determining a random packet loss rate of a weak network portion and a bottleneck routing maximum queue depth based on a correlation may include taking an average value of observed packet loss rates of all observed round trip delay intervals as the random packet loss rate of the weak network portion in response to the correlation being smaller than a first threshold, taking an average observed packet loss rate corresponding to a predetermined observed round trip delay interval as the random packet loss rate of the weak network portion in response to the correlation being larger than a second threshold, wherein the predetermined observed round trip delay interval is a minimum interval of the average observed round trip delay, and determining the bottleneck routing maximum queue depth based on the maximum observed round trip delay, the bottleneck routing bandwidth and the physical propagation delay in response to the correlation being larger than a third threshold. According to the embodiment, based on the similarity information, the relatively accurate random packet loss rate and the maximum queue depth of the bottleneck route can be determined.
As an example, the first threshold, the second threshold, and the third threshold may be set as needed, which is not limited to this disclosure.
Taking the first threshold value of 0.25 and the second threshold value of 0.75 as an example, if the similarity is smaller than 0.25, calculating the average value of all the observed packet loss rates as the random packet loss rate l r of the weak network part, and if the correlation is larger than 0.75, determining the interval in which the average value of the observed round trip delay is minimum, and taking the average value of the observed packet loss rates in the interval as the random packet loss rate l r of the weak network part.
By way of example, taking a third threshold of 0.75 as an example, if the similarity is greater than 0.75, then the maximum round trip delay rtt max is determined and the bottleneck routing maximum queue depth d q may be derived as follows:
dq＝(rttmax-dp)×b
According to the exemplary embodiment of the disclosure, determining the correlation between the observed round trip delay and the observed packet loss rate in the original information can include partitioning the observed round trip delay in the original information to obtain a plurality of observed round trip delay intervals, acquiring an average value of the observed packet loss rate and an average value of the observed round trip delay for each of the observed round trip delay intervals, and determining the correlation between the observed round trip delay and the observed packet loss rate based on the spearman correlation coefficient of the average value of the observed packet loss rate and the average value of the observed round trip delay for each of the observed round trip delay intervals. According to the embodiment, the similarity is calculated through the partition, the average value of the observed packet loss rate in each interval and the average value of the observed delay, so that the calculation complexity can be reduced, and the accuracy can be ensured.
As an example, taking network state information including physical propagation delay and physical bandwidth, and data packet transmission information including observed round trip delay and observed packet loss rate as an example, for each piece of original information, the observed packet loss rate l i and the observed round trip delay rtt i in the original information may form an observed pair < rtt i,li >, and the maximum value rtt max and the minimum value rtt min of the statistics rtt i are divided into n intervals (k e [1, n ]) on average according to the following rule.
[rttmin+(k-1)*(rttmax-rttmin)/n,rttmin+k*(rttmax-rttmin)/n]
For each observed round-trip delay interval, an average of the internal observed packet loss rate and an average of the observed round-trip delay can be calculated to obtain < l k,rttk >, where k represents the kth observed round-trip delay interval. Based on the average value of the observed packet loss rate and the average value of the observed round-trip delay of each interval, the spearman correlation coefficient is calculated, and the correlation degree between the observed round-trip delay and the observed packet loss rate is determined.
In summary, the present disclosure combines the real-time feedback of application software (i.e., a client) with congestion control model and network monitoring to calculate the required information in real time, so as to obtain the original information of the weak network part in the network, and effectively convert the original data into the weak network trace while removing the noise data, so as to obtain the weak network large database conforming to the real user network, so that the multi-dimensional network characteristics can be measured while no extra bandwidth is introduced, and thus the possibility of large-scale industrial landing is provided.
According to the method, the weak network trace of about 500 ten thousand is obtained by carrying out network measurement in live broadcast and pull stream services of some occasions of application software, and the live broadcast and pull stream hundred second katon time length of the occasions is reduced by about 10% by carrying out targeted optimization locally by using the weak network trace.
Fig. 4 is a block diagram of a network measurement device shown according to an exemplary embodiment of the present disclosure. Referring to fig. 4, the apparatus includes a receiving unit 40, a first acquiring unit 42, a second acquiring unit 44, a determining unit 46, and an extracting unit 48.
The network quality degradation processing device comprises a receiving unit 40 configured to receive viewing quality degradation information sent by a client, a first obtaining unit 42 configured to obtain a network degradation time interval of a target network based on the viewing quality degradation information, a second obtaining unit 44 configured to obtain network state information of the target network with a round trip time of a data packet as granularity by using a congestion control model, and obtain data packet transmission information of the target network with the round trip time of the data packet as granularity by monitoring the target network, a determining unit 46 configured to determine the network state information and the data packet transmission information in the network degradation time interval as original information of a weak network part of the target network, and an extracting unit 48 configured to extract a plurality of key features with a first predetermined time length as granularity from the original information of the weak network part and determine the plurality of key features as network measurement data of the weak network part, wherein the key features refer to features representing real-time quality of the weak network part.
According to an exemplary embodiment of the present disclosure, the first obtaining unit 42 is further configured to obtain, based on the viewing quality degradation information, a degradation start time at which the viewing quality degradation occurs at the client and a start download time at which the video portion of the viewing quality degradation occurs at the client, determine, based on the first time, the degradation start time and the start download time at which the viewing quality degradation occurs at the server, a degradation start time at which the transmission layer communicating with the client receives the viewing quality degradation information, and a video portion start download time at the server, wherein the first time is a time at which the viewing quality degradation information is received by the transmission layer, and the second time is a time at which the viewing quality degradation information is received by the server, and determine a network degradation time interval of the target network with the start download time and the degradation start time at the server as boundaries.
According to an exemplary embodiment of the present disclosure, the determining unit 46 is further configured to expand the network degradation time interval based on the second predetermined length of time, and determine the network status information and the packet transmission information within the expanded network degradation time interval as the original information of the weak network portion of the target network.
According to an exemplary embodiment of the present disclosure, in the case that the key features include a physical propagation delay, a bottleneck routing bandwidth, a random packet loss rate, and a bottleneck routing maximum queue depth, the extracting unit 48 is further configured to use the physical propagation delay and the physical bandwidth in the original information as the physical propagation delay and the bottleneck routing bandwidth of the weak network portion, respectively, determine a correlation between the observed round trip delay and the observed packet loss rate in the original information, determine the random packet loss rate and the bottleneck routing maximum queue depth of the weak network portion based on the correlation, and sample the physical propagation delay, the bottleneck routing bandwidth, the random packet loss rate, and the bottleneck routing maximum queue depth with a first predetermined time length as granularity, to obtain a plurality of key features of each key feature.
According to an exemplary embodiment of the present disclosure, the extracting unit 48 is further configured to, in response to the correlation being smaller than the first threshold, take an average value of the observed packet loss rates of all the observed round trip delay intervals as a random packet loss rate of the weak network portion, in response to the correlation being larger than the second threshold, take an average observed packet loss rate corresponding to a predetermined observed round trip delay interval as a random packet loss rate of the weak network portion, wherein the predetermined observed round trip delay interval is a minimum interval of the average observed round trip delay, and in response to the correlation being larger than the third threshold, determine a bottleneck routing maximum queue depth based on the maximum observed round trip delay, the bottleneck routing bandwidth and the physical propagation delay.
According to an exemplary embodiment of the present disclosure, the extracting unit 48 is further configured to partition the observed round trip delay in the original information to obtain a plurality of observed round trip delay intervals, obtain an average value of the observed packet loss rate and an average value of the observed round trip delay for each of the observed round trip delay intervals, and determine a correlation of the observed round trip delay and the observed packet loss rate based on a spearman correlation coefficient of the average value of the observed packet loss rate and the average value of the observed round trip delay for each of the observed round trip delay intervals.
According to embodiments of the present disclosure, an electronic device may be provided. Fig. 5 is a block diagram of an electronic device 500 including at least one memory 501 having a set of computer-executable instructions stored therein and at least one processor 502, which when executed by the at least one processor, performs a network measurement method according to an embodiment of the present disclosure, according to an exemplary embodiment of the present disclosure.
By way of example, electronic device 500 may be a PC computer, tablet device, personal digital assistant, smart phone, or other device capable of executing the above-described set of instructions. Here, the electronic device 1000 is not necessarily a single electronic device, but may be any apparatus or a collection of circuits capable of executing the above-described instructions (or instruction sets) individually or in combination. The electronic device 500 may also be part of an integrated control system or system manager, or may be configured as a portable electronic device that interfaces with either locally or remotely (e.g., via wireless transmission).
In electronic device 500, processor 502 may include a Central Processing Unit (CPU), a Graphics Processor (GPU), a programmable logic device, a special purpose processor system, a microcontroller, or a microprocessor. By way of example, and not limitation, processor 502 may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, and the like.
The processor 502 may execute instructions or code stored in a memory, wherein the memory 501 may also store data. The instructions and data may also be transmitted and received over a network via a network interface device, which may employ any known transmission protocol.
The memory 501 may be integrated with the processor 502, for example, RAM or flash memory disposed within an integrated circuit microprocessor or the like. In addition, memory 501 may include a stand-alone device, such as an external disk drive, a storage array, or other storage device usable by any database system. The memory 501 and the processor 502 may be operatively coupled or may communicate with each other, for example, through an I/O port, network connection, etc., such that the processor 502 is able to read files stored in the memory 501.
In addition, the electronic device 500 may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the electronic device may be connected to each other via a bus and/or a network.
According to an embodiment of the present disclosure, there may also be provided a computer-readable storage medium, wherein the instructions in the computer-readable storage medium, when executed by at least one processor, cause the at least one processor to perform the network measurement method of the embodiments of the present disclosure. Examples of computer readable storage media herein include read-only memory (ROM), random-access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random-access memory (RAM), dynamic random-access memory (DRAM), static random-access memory (SRAM), flash memory, nonvolatile memory, CD-ROM, CD-R, CD + R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD + R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, blu-ray or optical disk memory, hard Disk Drive (HDD), solid State Disk (SSD), card memory (such as a multimedia card, secure Digital (SD) card or ultra-fast digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, hard disk, solid state disk, and any other device configured to non-temporarily store a computer program and any associated data, data files and data structures and to cause the computer program and any associated data, data file and data structures to be provided to a processor or processor to execute the computer program. The computer programs in the computer readable storage media described above can be run in an environment deployed in a computer device, such as a client, host, proxy device, server, etc., and further, in one example, the computer programs and any associated data, data files, and data structures are distributed across networked computer systems such that the computer programs and any associated data, data files, and data structures are stored, accessed, and executed in a distributed fashion by one or more processors or computers.
According to an embodiment of the present disclosure, there is provided a computer program product comprising computer instructions which, when executed by a processor, implement a network measurement method of an embodiment of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A network measurement method, comprising:
receiving viewing quality degradation information sent by a client;
Acquiring a network degradation time interval of a target network based on the viewing quality degradation information;
acquiring network state information of the target network with the round trip time of the data packet as granularity by using a congestion control model, and acquiring data packet transmission information of the target network with the round trip time of the data packet as granularity by monitoring the target network;
Determining the network state information and the data packet transmission information in the network degradation time interval as original information of a weak network part of the target network;
extracting a plurality of key features with a first preset time length as granularity from the original information of the weak network part, and determining the key features as network measurement data of the weak network part, wherein the key features are features representing real-time quality of the weak network part.
2. The network measurement method according to claim 1, wherein the acquiring the network degradation time interval of the target network based on the viewing quality degradation information includes:
Acquiring, based on the viewing quality degradation information, a degradation start time at which viewing quality degradation occurs at the client and a start download time at the client of a video portion at which viewing quality degradation occurs;
Determining a degradation start time when viewing quality degradation occurs at a server and a start download time of the video portion at the server based on a first time when the viewing quality degradation information is received by a transport layer in communication with the client, a second time when the viewing quality degradation information is received by the server, and the start download time;
and determining a network degradation time interval of the target network by taking the starting download time and the degradation starting time of the server side as boundaries.
3. The network measurement method of claim 1, wherein determining the network state information and the packet transmission information within the network degradation time interval as original information of a weak network portion of the target network comprises:
expanding the network degradation time interval based on a second predetermined length of time;
And determining the network state information and the data packet transmission information in the expanded network degradation time interval as original information of a weak network part of the target network.
4. The network measurement method of claim 1 wherein, in the case where the key features include physical propagation delay, bottleneck routing bandwidth, random packet loss rate and bottleneck routing maximum queue depth,
Wherein the extracting a plurality of key features with a first predetermined duration as granularity from the original information of the weak network part includes:
Respectively taking the physical propagation delay and the physical bandwidth in the original information as the physical propagation delay and the bottleneck routing bandwidth of the weak network part;
Determining the correlation degree between the observed round trip delay and the observed packet loss rate in the original information, and determining the random packet loss rate of the weak network part and the maximum queue depth of the bottleneck route based on the correlation degree;
And taking the first preset time length as granularity to sample the physical propagation delay, the bottleneck routing bandwidth, the random packet loss rate and the maximum queue depth of the bottleneck routing respectively, so as to obtain a plurality of key features of each key feature.
5. The network measurement method of claim 4, wherein the determining the random packet loss rate and the bottleneck routing maximum queue depth for the weak network portion based on the correlation comprises:
The average observed packet loss rate corresponding to a preset observed round-trip delay interval is used as the random packet loss rate of the weak network part, and the preset observed round-trip delay interval is used as the interval with the minimum average observed round-trip delay;
And determining a bottleneck routing maximum queue depth based on a maximum observed round trip delay, the bottleneck routing bandwidth, and the physical propagation delay in response to the correlation being greater than a third threshold.
6. The network measurement method of claim 4, wherein determining the correlation between the observed round trip delay and the observed packet loss rate in the original information comprises:
partitioning the observed round trip delay in the original information to obtain a plurality of observed round trip delay intervals;
for each observation round-trip delay interval, obtaining an observation packet loss rate average value and an observation round-trip delay average value;
and determining the correlation degree between the observed round-trip delay and the observed packet loss rate based on the average value of the observed packet loss rate and the spearman correlation coefficient of the average value of the observed round-trip delay in each observed round-trip delay interval.
7. A network measurement device, comprising:
a receiving unit configured to receive viewing quality degradation information transmitted by a client;
A first acquisition unit configured to acquire a network degradation time zone of a target network based on the viewing quality degradation information;
A second obtaining unit, configured to obtain, by using a congestion control model, network state information of the target network with the round trip time of the data packet as granularity, and obtain, by monitoring the target network, data packet transmission information of the target network with the round trip time of the data packet as granularity;
A determining unit configured to determine the network state information and the packet transmission information within the network degradation time interval as original information of a weak network portion of the target network;
an extracting unit configured to extract, from original information of the weak network part, a plurality of key features with a first predetermined time length as granularity and determine the plurality of key features as network measurement data of the weak network part, wherein the key features are features characterizing real-time quality of the weak network part.
8. An electronic device, comprising:
At least one processor;
at least one memory storing computer-executable instructions,
Wherein the computer executable instructions, when executed by the at least one processor, cause the at least one processor to perform the network measurement method of any one of claims 1 to 6.
9. A computer readable storage medium, characterized in that instructions in the computer readable storage medium, when executed by at least one processor, cause the at least one processor to perform the network measurement method of any of claims 1 to 6.
10. A computer program product comprising computer instructions which, when executed by a processor, implement the network measurement method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411918771.9A CN119729058B (en) | 2024-12-24 | 2024-12-24 | Network measurement methods and apparatus, electronic devices, storage media and computer program products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411918771.9A CN119729058B (en) | 2024-12-24 | 2024-12-24 | Network measurement methods and apparatus, electronic devices, storage media and computer program products |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119729058A CN119729058A (en) | 2025-03-28 |
| CN119729058B true CN119729058B (en) | 2025-11-04 |
Family
ID=95099586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411918771.9A Active CN119729058B (en) | 2024-12-24 | 2024-12-24 | Network measurement methods and apparatus, electronic devices, storage media and computer program products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119729058B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118175112A (en) * | 2022-12-02 | 2024-06-11 | 深圳市腾讯计算机系统有限公司 | Data transmission control method, device, electronic device and storage medium |
| CN118433084A (en) * | 2023-02-01 | 2024-08-02 | 腾讯科技（深圳）有限公司 | Network parameter detection method and related device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10637788B2 (en) * | 2018-06-26 | 2020-04-28 | International Business Machines Corporation | Stability of delay-based congestion control in a computer network using an alpha-beta filter and round-trip-time predictor |
-
2024
- 2024-12-24 CN CN202411918771.9A patent/CN119729058B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118175112A (en) * | 2022-12-02 | 2024-06-11 | 深圳市腾讯计算机系统有限公司 | Data transmission control method, device, electronic device and storage medium |
| CN118433084A (en) * | 2023-02-01 | 2024-08-02 | 腾讯科技（深圳）有限公司 | Network parameter detection method and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119729058A (en) | 2025-03-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115499230B (en) | Network attack detection method and device, equipment and storage medium | |
| US10230602B2 (en) | Endpoint web monitoring system and method for measuring popularity of a service or application on a web server | |
| US10432652B1 (en) | Methods for detecting and mitigating malicious network behavior and devices thereof | |
| CN101044463B (en) | Method and system for monitoring performance of a client-server architecture | |
| US9503506B2 (en) | Transit-mode-based webpage accessing method, system, and crawler route server | |
| US8639796B2 (en) | Monitoring the performance of a streaming media server using server-side and client-side measurements | |
| CN113169896A (en) | Continuous calibration of network metrics | |
| CN113163002B (en) | Server switching method and device and storage medium | |
| JP2005506605A (en) | Calculating response time at the server site for any application | |
| CN114866489A (en) | Congestion control method and device and training method and device of congestion control model | |
| CN106911927B (en) | Method and device for evaluating experience quality of network video user and DPI equipment | |
| US20120072544A1 (en) | Estimating application performance in a networked environment | |
| WO2013029214A1 (en) | Video quality monitor and method for determining a network video quality measure in a communication network | |
| CN111327964B (en) | A method and device for locating stuck video playback | |
| CN108702302A (en) | Calculate service performance index | |
| CN119728479A (en) | Network measurement model training method and device, network measurement method and device, electronic device, storage medium, computer program product | |
| CN119729058B (en) | Network measurement methods and apparatus, electronic devices, storage media and computer program products | |
| US20060168288A1 (en) | Identifying failure of a streaming media server to satisfy quality-of-service criteria | |
| US12238386B2 (en) | Identification of session boundaries in encrypted video streams | |
| Zheng et al. | A Mobile Fog Computing‐Assisted DASH QoE Prediction Scheme | |
| CN114124754B (en) | Method for processing media data packets in a multimedia network and related products | |
| US20060136927A1 (en) | Models for monitoring of streaming server performance | |
| CN112242937B (en) | Network speed measuring method and device, electronic equipment and computer readable medium | |
| Tang et al. | Stalling assessment for wireless online video streams via ISP traffic monitoring | |
| JPWO2011048740A1 (en) | Data transmission system, transmission speed control method, receiving terminal, transmitting terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |