CN115277497A - Transmission delay time measuring method, device, electronic equipment and storage medium - Google Patents
Transmission delay time measuring method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115277497A CN115277497A CN202210716495.2A CN202210716495A CN115277497A CN 115277497 A CN115277497 A CN 115277497A CN 202210716495 A CN202210716495 A CN 202210716495A CN 115277497 A CN115277497 A CN 115277497A
- Authority
- CN
- China
- Prior art keywords
- data packet
- time interval
- historical
- transmission delay
- frame
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a method and a device for measuring transmission delay time, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring historical time intervals corresponding to historical data packets transmitted frame by a server; inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to a current data packet transmitted frame by frame, wherein the preset delay prediction model is a model obtained by training an LSTM model based on the sample historical time interval; and outputting the transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end. The data transmission delay is reduced by combining a frame-by-frame transmission mode, and the purposes of considering both the real-time performance and the bandwidth utilization rate of the whole transmission system are achieved; time synchronization of a sending end and a client is not needed, and the applicability of transmission delay measurement is improved; the method combines the mode of training the recurrent neural network, improves the accuracy of predicting the time interval, and also improves the accuracy and reliability of transmission delay measurement.
Description
Technical Field
The present invention relates to the field of network communication technologies, and in particular, to a method and an apparatus for measuring transmission delay time, an electronic device, and a storage medium.
Background
The transmission delay is an important technical index in a video monitoring system, and generally indicates that encoding delay, transmission delay and decoding display delay exist in an end-to-end transmission process, which affects not only user experience but also communication quality; for example, if there is transmission delay when a user uses a terminal to view a video, subjective experience of the user may be affected, and if there is transmission delay in a closed-loop video monitoring process, real-time performance of video information may be affected, and a judgment analysis and decision result may be affected. Therefore, it is important how to accurately measure the transmission delay.
In the related art, the delay time of the monitoring system is usually measured in a direct connection manner in a laboratory environment, that is, a sending end and a client are directly connected, and the transmission delay time is calculated by calculating the time difference of the same frame of video image.
However, the laboratory environment is simple and not suitable for the actual application environment, and meanwhile, the sending end and the client end are required to have the same time reference in the measurement process, so that the applicability and the accuracy of measuring the transmission delay time are not high.
Disclosure of Invention
The invention provides a transmission delay time measuring method, a device, an electronic device and a storage medium, which are used for solving the defect of low applicability and accuracy of transmission delay time measurement caused by the need of synchronizing a sending end and a client when the transmission delay is measured in the prior art, and the applicability and the accuracy of transmission delay measurement can be realized in an actual application environment without the need of time synchronization of the sending end and the client.
The invention provides a transmission delay time measuring method, which comprises the following steps:
acquiring historical time intervals corresponding to historical data packets transmitted frame by a server;
inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame; the preset delay prediction model is a model obtained by training an LSTM model based on sample historical time intervals;
and outputting transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end.
According to a transmission delay time measuring method provided by the present invention, outputting a transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet, and the data packet transmission time interval of the transmitting end, includes:
comparing the size of the predicted time interval with the actual time interval corresponding to the current data packet;
and when the actual time interval is determined to be larger than the predicted time interval, outputting transmission delay time based on the actual time interval and the data packet sending time interval of the sending end.
According to the method for measuring the transmission delay time provided by the invention, the obtaining of the historical time interval corresponding to the historical data packets transmitted by the server frame by frame comprises the following steps:
receiving historical data packets transmitted frame by a server;
filtering the historical data packets based on a preset data packet receiving protocol;
storing the filtered residual historical data packets as data packet files according to a preset file format;
and analyzing the timestamp information in the data packet file and performing time format conversion to obtain the historical time interval corresponding to the remaining historical data packets.
According to a transmission delay time measuring method provided by the present invention, the filtering the historical data packet based on a preset data packet receiving protocol includes:
sequentially writing the historical data packets into a receiving buffer area;
screening out a first historical data packet from the historical data packets in the receiving buffer area based on a preset data packet communication protocol;
and filtering the data packets which are not matched with the data packet identification information in the first historical data packets based on preset data packet identification information.
According to a transmission delay time measuring method provided by the present invention, after filtering the data packets in the first history data packet that do not match with the data packet identification information, the method further includes:
writing the filtered second historical data packets into a play buffer area in sequence;
and instructing the playing buffer area to play the second historical data packet after the second historical data packet is played in sequence.
According to a transmission delay time measuring method provided by the present invention, after the history data packets are sequentially written into a receiving buffer, the method further comprises:
obtaining the buffer capacity of the historical data packet written into the receiving buffer;
if the capacity of the buffer area is determined to be larger than the maximum preset capacity, indicating a sending end to reduce the sending rate of the data packet;
and if the capacity of the buffer area is determined to be smaller than the minimum value of the preset capacity, indicating the sending end to increase the sending rate of the data packet.
According to a transmission delay time measuring method provided by the present invention, before the step of obtaining the historical time interval corresponding to the historical data packets transmitted frame by the server, the method further includes:
establishing a data communication link with a sending end;
sending a data transmission request to the sending end, wherein the data transmission request carries a data packaging requirement and a data sending mode;
and receiving a data packet sent by the sending end aiming at the data transmission request.
According to the method for measuring the transmission delay time provided by the invention, the training process of the preset delay prediction model comprises the following steps:
determining a training set and a testing set based on the sample historical time interval;
training the LSTM model based on the training set to obtain a trained LSTM model;
testing the trained LSTM model based on the test set to obtain a test result;
and determining the trained LSTM model as a preset delay prediction model based on the error between the test result and the test set.
According to a transmission delay time measuring method provided by the present invention, the method further comprises:
and updating the training set and the test set respectively based on a new historical time interval received in a preset time length.
The present invention also provides a transmission delay time measuring apparatus, comprising:
the acquisition module is used for acquiring historical time intervals corresponding to historical data packets transmitted by the server frame by frame;
the prediction module is used for inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame; the preset delay prediction model is a model obtained by training an LSTM model based on sample historical time intervals;
and the output module is used for outputting the transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end.
The present invention also provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the transmission delay time measurement method as described in any of the above.
The present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the transmission delay time measurement method as described in any of the above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements a method of measuring a propagation delay time as defined in any one of the above.
The transmission delay time measuring method predicts a prediction time interval corresponding to a current data packet transmitted frame by inputting a historical time interval corresponding to a historical data packet transmitted frame by a server into a preset delay prediction model, and outputs transmission delay time based on the prediction time interval, an actual time interval corresponding to the current data packet and a data packet transmission time interval of a transmitting end. The data transmission delay is reduced by combining a frame-by-frame transmission mode, the purpose of taking account of the real-time performance and the bandwidth utilization rate of the whole transmission system is realized, the transmission delay measurement can be realized in the practical application environment without time synchronization of a transmitting end and a client, and the applicability of the transmission delay measurement is improved; furthermore, the preset delay prediction model is obtained by training the LSTM model based on the sample historical time interval, so that the aim of improving the accuracy of the prediction time interval can be fulfilled by combining a mode of training a recurrent neural network, and the accuracy and the reliability of transmission delay measurement can be effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a transmission delay time measurement method provided by the present invention;
fig. 2 is a schematic structural diagram of a transmission delay measurement system provided by the present invention;
FIG. 3 is a general flow chart of the transmission delay time measurement method provided by the present invention;
FIG. 4 is a schematic structural diagram of a transmission delay measuring device provided in the present invention;
fig. 5 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The transmission delay is an important technical index in a video monitoring system, and generally indicates that encoding delay, transmission delay and decoding display delay exist in an end-to-end transmission process, which affects not only user experience but also communication quality; for example, a large-scale monitoring system is based on a camera, a server and a client, a large amount of video calling and control do not exist all the time, the server and the camera are required to react and transmit video streams to the client in the video calling process, a data transmission request is sent from the client to the server and the camera to respond, and then the video streams reach the specified client, a large number of switches and routers are required to pass through, so that transmission delay is inevitably caused. In addition, there is a case where the clocks of the camera and the client are not synchronized during the video streaming, which also causes inconvenience and difficulty in measuring the delay time.
Therefore, in order to improve the reliability and the security of the video monitoring system, a backup line is usually deployed in a network design, and when a main line is unexpectedly interrupted or fails, the backup line is automatically used to switch data streams, and a process of switching the data streams, that is, a process of switching a communication link, in the switching process, if a client is connected via different communication links before and after switching, a problem of interruption of data communication between a server and the client inevitably occurs, and the switching of the communication link may cause communication interruption within a certain time. For a system with low requirement on communication quality, short-time communication interruption is acceptable, and if the requirement on the reliability and real-time performance of communication of a video monitoring system is high and the interruption time of system communication is strictly limited, real-time information cannot be transmitted in real time due to sudden interruption of communication, so that a fault or an emergency is further difficult to find and solve, and even a safety accident may be caused in a severe case. Therefore, the measurement and calculation of the transmission delay time of the video monitoring system have important significance and value.
The existing method for measuring the transmission delay time in the laboratory environment is to measure the delay time of a monitoring system in a direct connection mode, namely, a sending end and a client are directly connected, the transmission delay time is calculated by calculating the time difference of the same video frame image, the test scene is simple, the video stream delay is not considered to be influenced by route distribution, network congestion, communication interference and the like in the actual application process, and the delay time measured in the ideal environment of the laboratory environment is often obviously lower than that in the actual application scene. Meanwhile, in the measurement process, a sending end (such as a camera) and a client are required to have a common time reference, but in practice, many video monitoring systems do not have a common time reference signal and cannot synchronize the sending end and the client. Therefore, more convenient and accurate delay time measurement is important.
Based on this, the present invention provides a transmission delay time measuring method, an apparatus, an electronic device and a storage medium, wherein the transmission delay time measuring method can be applied to a scenario of a transmission delay time measuring system formed by a plurality of transmitting ends, a server and a plurality of clients, an execution subject of the transmission delay time measuring method is any one of the clients in the transmission delay time measuring system, the client can be a Personal Computer (PC), a portable device, a notebook Computer, a smart phone, a tablet Computer, a portable wearable device and other electronic devices, and the client at least has a packet receiving and playing function, a packet capturing function, a storage function, an analysis function and a statistical analysis function. The invention is not limited to the specific form of the client.
It should be noted that the execution subject of the method embodiments described below may be part or all of any one client in the transmission delay time measurement system. The following method embodiments take an execution subject as an example of a client.
Fig. 1 is a transmission delay time measuring method provided by the present invention, as shown in fig. 1, the transmission delay time measuring method includes the following steps:
and step 110, acquiring historical time intervals corresponding to historical data packets transmitted by the server frame by frame.
The historical data packets may be data packets received by the client within a preset time length T, T = Ft, F is an integer greater than 1, T is a data packet sending time interval, and the data packet sending time interval T may be set based on a maximum throughput that can be supported by the ethernet, so as to determine whether packet loss occurs and a packet loss rate when packet loss occurs within the preset time length T.
Specifically, in the transmission delay time measurement system shown in fig. 2, the server may be a high-concurrency streaming media server and has a relay function, and its main task is to transmit, schedule, distribute, buffer, and the like the received data packets, when the transmission delay time measurement system is applied to a video monitoring system, the transmitting end may be one or more cameras and may be in wired connection with the server, and when there are multiple transmitting ends, the transmitting ends may be a transmitting end 1, a transmitting end 2, and a transmitting end 3 shown in fig. 2; the clients are usually multiple and each client is connected with the server through the internet, such as client 1, client 2 and client 3 in fig. 2; when the transmission delay time measurement system is applied to a communication system, the sending end may be a terminal device identical to the client and may be wirelessly connected to the server. And is not particularly limited herein.
Based on this, the client can receive the data packet transmitted by the transmitting end through the server, and when the server transmits the data packet to the client frame by frame, the client can also receive the data packet frame by frame. Therefore, each time the client receives one data packet, the arrival time of the data packet is correspondingly analyzed, and the time interval corresponding to each two adjacent data packets is determined based on the difference between the arrival times of each two adjacent data packets at the client, so that the historical time interval corresponding to the historical data packets transmitted by the server frame by frame is determined.
And 120, inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame.
The preset delay prediction model is obtained by training an LSTM model based on sample historical time intervals, and the current data packet is a data packet in transmission.
Specifically, the client inputs the determined historical time interval to a preset delay prediction model, and predicts a prediction time interval corresponding to a current data packet transmitted frame by the server, for example, n-1 historical time intervals corresponding to n historical data packets may be input to the preset delay prediction model, and an nth time interval corresponding to an nth historical data packet and an nth +1 current data packet being transmitted is predicted, that is, the nth prediction time interval; the difference between the time when the (n + 1) th current data packet reaches the client and the time when the (n) th historical data packet reaches the client is the n-th actual time interval corresponding to the (n + 1) th current data packet, and n is an integer greater than 1.
It should be noted that, considering that a Long-Short Term Memory model (LSTM) is a recurrent neural network and has Long-Short Term Memory energy, it is suitable for prediction of a Long time sequence and can solve the problem of gradient disappearance. Therefore, the accuracy and precision of the prediction time interval can be improved by adopting the preset delay prediction model obtained by training the LSTM model by adopting the sample historical time interval.
And step 130, outputting the transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end.
Specifically, based on a predicted time interval for a current data packet to arrive at the client and an actual time interval for the current data packet to arrive at the client, the client may first determine whether a transmission delay occurs, and if it is determined that no transmission delay occurs based on the predicted time interval and the actual time interval, output the transmission delay time as 0; if the occurrence of the transmission delay is determined based on the predicted time interval and the actual time interval, the transmission delay time may be further output in combination with the data packet transmission time interval of the transmitting end. Based on the above, the invention can be applied to the measurement of the transmission delay time in the wired and wireless video monitoring systems, and can also be applied to the measurement of the link interruption and the network disconnection recovery time in the communication system and the judgment of the transmission abnormity.
The transmission delay time measuring method predicts the prediction time interval corresponding to the current data packet transmitted frame by inputting the historical time interval corresponding to the historical data packet transmitted frame by the server into a preset delay prediction model, and outputs the transmission delay time based on the prediction time interval, the actual time interval corresponding to the current data packet and the data packet transmission time interval of the transmitting end. The data transmission delay is reduced by combining a frame-by-frame transmission mode, the purpose of taking account of the real-time performance and the bandwidth utilization rate of the whole transmission system is realized, the transmission delay measurement can be realized in the practical application environment without time synchronization of a transmitting end and a client, and the applicability of the transmission delay measurement is improved; furthermore, the preset delay prediction model is obtained by training the LSTM model based on the sample historical time interval, so that the aim of improving the accuracy of the prediction time interval can be fulfilled by combining a mode of training a recurrent neural network, and the accuracy and the reliability of transmission delay measurement can be effectively improved.
Optionally, before step 110, the method may further include:
firstly, establishing a data communication link with a sending end; then, sending a data transmission request to the sending end, wherein the data transmission request carries a data packaging requirement and a data sending mode; and further receiving a data packet sent by the sending end aiming at the data transmission request.
Specifically, in the transmission delay time measurement system shown in fig. 2, each sending end and the server may be connected by a wire, the bandwidth of the wired ethernet is high and the signal is stable, and when measuring the transmission delay time, the sending end sets a suitable data packet sending time interval and a data packet size according to the maximum throughput that can be supported by the ethernet; if the sending rate of the data packet exceeds the maximum throughput, network delay is caused, the transmission delay is also closely related to the length of the data packet, the length of the data packet cannot exceed the maximum transmission unit of the network, and the problem of data transmission queuing or packet loss is easily caused when the length of the data packet is too small, so that the delay problem is more prominent. Therefore, when a communication connection is established between the client and the sending end and a data transmission request is sent to the sending end, the sending end can adopt a no-response mode and package a data packet and send the data packet to the client according to a package requirement and a data sending mode of data carried by the data transmission request. That is, the sending end uses the FFmpeg frame to perform processing such as collecting, decoding, encoding, and compressing on data required by the sending end, for example, the collected data is compressed and encoded into a data packet format with better network transmission characteristics by using an h.264 encoding algorithm, the compressed and encoded data is encapsulated into individual data packets by the FLV221 encapsulation specification, and finally, the encapsulated data packets are sent to the server frame by using a User Datagram Protocol (UDP), so that the collection frequency and the image frame number of the data are determined in combination with the high portability, the realization flexibility, and the data processing efficiency of the FFmpeg frame, and the purpose of controlling the data delay at the source media quality and the code rate can be realized by using a Real-time Transport Control Protocol (RTCP).
In fig. 2, a data packet sent by a sending end is first transmitted to a server frame by frame, and then buffered by the server and then forwarded frame by frame to a client; the client and the server can communicate one to one or many to one, so that the risk of transmission delay is reduced by combining a server buffering mode.
According to the transmission delay time measuring method provided by the invention, the client side is ensured to receive the data packet which meets the maximum throughput of the network and does not exceed the bandwidth of the maximum transmission unit of the network by sending the data transmission request carrying the data encapsulation request and the data sending mode to the sending end which has established the communication connection, and the purpose of giving consideration to both the real-time property and the fluency of data packet transmission is realized.
Optionally, the implementation process of step 110 may include:
firstly, receiving historical data packets transmitted frame by a server; then, based on a preset data packet receiving protocol, filtering the historical data packet; further storing the filtered residual historical data packets as data packet files according to a preset file format; and finally, analyzing the timestamp information in the data packet file and performing time format conversion to obtain the historical time interval corresponding to the residual historical data packets.
Specifically, the history data packet is a received data packet, such as a data packet received by a server. Therefore, when the server receives a data packet sent by the sending end, the data packet can be sent to the client frame by frame, the client can also receive the data packet frame by frame, and for the data packet received frame by frame, the client filters the data packet which is not matched with the data packet receiving protocol in the received data packet based on the preset data packet receiving protocol, so as to obtain the filtered residual historical data packet, and the preset data packet receiving protocol can be used for representing the receiving indication of the data packet required by the client.
Then, the client stores the filtered data packets in a pacp file format to generate a data packet file, when the historical time interval needs to be calculated, the stored data packet file is analyzed, the timestamp information in the data packet file is converted into the local time of the client and is accurate to a microsecond, for example, the converted time format is year/month/day/hour/minute/second/microsecond, the time of each historical data packet arriving at the client is accurately recorded, and the historical time interval corresponding to the residual filtered historical data packets is determined based on the difference of the time of two adjacent data packets arriving at the client in the arrived data packets.
It should be noted that the client may further include a data packet capture unit, where the data packet capture unit is configured to capture a historical data packet forwarded by the server to the client and store the historical data packet in a pacp file format according to a data packet transmission protocol with the sending end, a port address of the data packet output by the server, and a source address of the sending end.
According to the transmission delay time measuring method provided by the invention, a client acquires historical time intervals corresponding to historical data packets by means of filtering, storing in a file format, analyzing and converting in a time format aiming at the data packets sent by a server frame by frame. The method combines the modes of frame-by-frame sending and frame-by-frame receiving, avoids the limitation that a sending end and a client end need to be synchronous, and further combines the modes of filtering, storing and format conversion, ensures the accuracy and the easy identification of the time when the client end records the data packet to reach the client end, thereby laying a foundation for the subsequent accurate measurement of the transmission delay time.
Optionally, when the number of the sending ends is multiple, the filtering the historical data packet based on a preset data packet receiving protocol includes:
firstly, sequentially writing the historical data packets into a receiving buffer area; then, based on a preset data packet communication protocol, screening out a first historical data packet from the historical data packets in the receiving buffer; and finally, filtering the data packets which are not matched with the data packet identification information in the first historical data packet based on preset data packet identification information.
Specifically, a buffer area may be preset in the client, and the buffer area is specifically divided into a receiving buffer area and a playing buffer area, and the receiving buffer area may adopt a first-in first-out queue structure. And when a plurality of sending ends exist, the server can receive the data packets sent by each sending end frame by frame and respectively transmit the data packets sent by the corresponding sending end to the client, when the client receives each historical data packet frame by frame, each historical data packet can be firstly sequentially inserted into the FIFO queue structure until the tail of the FIFO queue, but the client may not need to receive the data packet of each sending end, so that the data packet to be received and the data packet not needed to be filtered can be limited by setting a data packet communication protocol, and the data packet communication protocol can be used for representing the sending end which sends the data packet requested by the client, so as to realize the purpose of filtering the data packet which is not matched with the data packet communication protocol in the historical data packets in the receiving buffer area, and further screen out the first historical data packet. For example, there are three sending terminals, namely, a sending terminal 1, a sending terminal 2, and a sending terminal 3, if the packet communication protocol indicates that the client requests to receive the packet of the sending terminal 2, the packet sent by the sending terminal 1 and the sending terminal 3 and the packet sent by the sending terminal 2 are filtered from the historical packets, and the packet sent by the sending terminal 2 that is kept at this time is the first historical packet.
Further, for the first historical data packet in the fifo queue structure, header verification may be performed sequentially from the tail of the queue to the head of the queue based on preset data packet identification information, and the data packet identification information is used to represent a header identification of a corresponding data packet. For example, when the sending end sends a data packet to the server by using the UDP, and the server also uses the UDP to forward the data packet frame by frame to the client, the header of each data packet received by the client may at least represent whether the corresponding data packet satisfies the UDP, that is, determine whether the header of each first historical data packet is the UDP header, retain the first historical data packet corresponding to the UDP header as an effective data packet, discard the first historical data packet other than the UDP header as an invalid data packet, and thus screen out the effective historical data packet from the plurality of first historical data packets in the receiving buffer.
It should be noted that, when an effective historical data packet is screened from the first historical data packet in the receiving buffer, corresponding verification may be performed according to different data packet identification information, for example, the sending end may set, in advance, identification information indicating whether the corresponding data packet is effective in the header of each data packet to be sent, so that the client may quickly and accurately screen the effective data packet when receiving each data packet frame by frame. And is not particularly limited herein. In addition, when the number of the sending ends is one, when the client receives the historical data packets sent frame by the sending end through the server, each received historical data packet can be sequentially inserted into the first-in first-out queue structure to the tail of the queue, and then header verification is sequentially performed from the tail of the queue to the head of the queue of the first-in first-out queue structure based on the preset data packet identification information, the header verification process is similar to the previous process, and details are not repeated here.
According to the transmission delay time measuring method provided by the invention, the client writes the received data packet into the receiving buffer area, and filters the data packet in the receiving buffer area based on the data packet communication protocol and the data packet identification information in sequence, so that the client buffering mode and the client internal memory dividing mode are combined, the loss probability of the data packet is reduced, the stability and the reliability of the transmission data packet are improved, and the occurrence probability of transmission delay can be reduced.
Optionally, after filtering the data packets in the first history data packet that do not match the data packet identification information, the method further includes:
firstly, writing the second history data packets obtained after filtering into a play buffer area in sequence; and further instructing the playing buffer area to play the second historical data packet after the second historical data packet is played in sequence.
Specifically, for the second history data packets obtained after filtering the receiving buffer, the client sequentially writes the second history data packets into the playing buffer, and then instructs each second history data packet written into the playing buffer to perform an order-sorting operation, because the order of the history data packets received by the client is already disturbed after being filtered, in order to ensure the playing effect, the client may instruct the second history data packets to perform the order-sorting operation and then instruct the playing operation, so that the second history data packets after the order-sorting operation are decoded and rendered for playing.
According to the transmission delay time measuring method provided by the invention, the client sequentially writes the second historical data packets obtained by filtering into the play buffer area, and further instructs to play the second actual data packets after ordering, so that the client buffering mode and the ordering mode are combined, and the fluency and the reliability of the client for playing the video are improved.
Optionally, after the history data packets are sequentially written into the receiving buffer, the method further includes:
obtaining the buffer capacity of the historical data packet written into the receiving buffer; if the capacity of the buffer area is determined to be larger than the maximum preset capacity, indicating a sending end to reduce the sending rate of the data packet; and if the capacity of the buffer area is determined to be smaller than the minimum value of the preset capacity, indicating the sending end to increase the sending rate of the data packet.
Specifically, the client instructs the sending end to adjust the rate of sending the data packet according to the space occupied by the historical data packet, that is, two capacity critical values of the receiving buffer are preset in the client, including a preset capacity maximum value and a preset capacity minimum value, and then the size relationship between the capacity of the buffer occupied by the historical data packet written in the receiving buffer and the two capacity critical values is judged, if the capacity of the buffer is greater than the preset capacity maximum value, the sending end is instructed to reduce the sending rate of the data packet, so as to avoid the overflow risk; if the buffer area capacity is smaller than the preset capacity minimum value, indicating the sending end to increase the sending rate of the data packet so as to avoid underflow risk; and if the capacity of the buffer area is greater than or equal to the minimum preset capacity and less than or equal to the maximum preset capacity, indicating the sending end to maintain the original rate to send the data packet.
It should be noted that, the server may use the timestamp of the FLV file as a control standard for controlling the data packet sending rate of the sending end, and preset two critical values MAX and MIN in its buffer area, when the server puts the received historical data packet into the buffer area, the server may monitor the size relationship between the capacity of the buffer area and the MAX and MIN, and when the capacity of the buffer area is greater than MAX, to avoid the overflow risk, the server may instruct the sending end to reduce the data packet sending rate; when the capacity of the buffer area is smaller than MIN, in order to avoid underflow risk, the sending end can be instructed to increase the sending rate of the data packet; when the capacity of the buffer area is greater than or equal to MIN and less than or equal to MAX, the sending end can be instructed to send the data packet according to the original rate, so that the problem of data packet loss under the condition that the network condition is extremely undesirable is solved.
According to the transmission delay time measuring method provided by the invention, the client instructs the sending end to reduce or increase the sending rate of the data packet through the size relation between the capacity of the buffer area occupied by the historical data packet written in the receiving buffer area and the preset maximum capacity value or the minimum capacity value, so that the flexible interactivity of the sending end and the client is improved, the data loss rate is effectively reduced, and the reliability and the stability of data transmission are determined.
Optionally, the implementation process of step 130 may include:
comparing the size of the predicted time interval with the actual time interval corresponding to the current data packet; and when the actual time interval is determined to be larger than the predicted time interval, outputting transmission delay time based on the actual time interval and the data packet sending time interval of the sending end.
Specifically, for a predicted time interval corresponding to a current data packet transmitted by a server frame by frame, a client may first compare the predicted time interval with an actual time interval corresponding to the current data packet, and when the actual time interval is greater than the predicted time interval, it may be determined that a large transmission delay or other abnormalities such as link interruption and packet loss occur in a communication process, and at this time, a difference between the actual time interval and a data packet transmission time interval of a transmitting end may be determined as a transmission delay time and output; otherwise, when the actual time interval is less than or equal to the predicted time interval, it indicates that there is no transmission delay and abnormality currently, and at this time, it may predict the next data packet being transmitted and determine whether a transmission delay occurs. For example, when the nth actual time interval is greater than the nth predicted time interval, the difference between the nth actual time interval and the data packet transmission time interval t may be used as the transmission delay time; on the contrary, when the nth actual time interval is less than or equal to the nth predicted time interval, the previous n historical time intervals may be input into the preset delay prediction model, the (n + 1) th predicted time interval is predicted, and then it is determined whether the transmission delay occurs in the relationship between the (n + 1) th predicted time interval and the (n + 1) th actual time interval, and the process is cycled in this way until the flow of measuring the transmission delay ends.
According to the transmission delay time measuring method provided by the invention, when the client judges that the actual time interval of the current data packet transmitted frame by the server is greater than the predicted time interval, the difference value between the actual time interval and the data packet sending time interval is determined as the transmission delay time, so that the visual effectiveness and the reliable stability of the transmission delay time measurement are improved.
Optionally, the training process of the preset delay prediction model includes:
firstly, determining a training set and a testing set based on a sample historical time interval; further training the LSTM model based on the training set to obtain a trained LSTM model; then, testing the trained LSTM model based on the test set to obtain a test result; and finally, determining the trained LSTM model as a preset delay prediction model based on the error between the test result and the test set.
Specifically, a client receives and records arrival time corresponding to N arrived data packets to obtain N arrival times, time intervals of every two arrival times are used as sample historical time intervals to obtain N-1 sample historical time intervals, normalization processing is further carried out on the N-1 sample historical time intervals to generate a sample data set, the sample data set is divided into a training set and a testing set according to a preset proportion of p: q, N is an integer larger than 1, p and q are positive integers larger than 0, and p > q.
Then setting an initial training frequency M, and training the LSTM model by using a training set until the training frequency reaches M to obtain the LSTM model after the current round of training; and further testing the LSTM model after the training of the current round by using the test set to obtain a test result of the current round, and calculating the root mean square error delta t between the test result of the current round and the historical time interval of the sample in the test set1Then, using a RMSProp first-order optimization algorithm to perform model parameter optimization on the LSTM model after training for M times in a gradient descending mode, such as updating the learning rate and the next iteration times, using the updated iteration times to train the LSTM model after the training for the current time again until the training times reaches M, obtaining the LSTM model after the next training, using a test set to test the LSTM model after the next training to obtain a next test result, and calculating the time interval between the next test result and the historical time interval of the sample in the test setRoot mean square error Δ t between2. And continuously training and testing in the mode, stopping training and testing until the obtained root mean square error does not decrease any more, and determining the corresponding trained LSTM model when the root mean square error is minimum as the preset delay prediction model.
It should be noted that the root mean square error mentioned in the embodiments of the present invention may be calculated by using a conventional root mean square error calculation method, and is not limited herein.
According to the transmission delay time measuring method provided by the invention, the preset delay prediction model is obtained by using the way that the training set is used for training the LSTM model, and then the testing set is used for testing the trained LSTM model, so that the purpose of accurately predicting the next time interval is realized by combining the method of learning the recurrent neural network model, and the accuracy of measuring the transmission delay time is further improved.
Optionally, for the training of the LSTM model, in addition to updating the number of iterations and model parameters of each round, the training set and the test set of each round participating in the training and testing may also be updated. Based on this, the method may further include:
and updating the training set and the test set respectively based on a new historical time interval received in a preset time length.
Specifically, since the data packet transmission time interval at the transmitting end is T, in order to improve the model accuracy, the training set and the test set of each round may also be updated, that is, the client records a new historical time interval that arrives within a preset time length T, and after normalization processing is performed on the new historical time interval, the new historical time interval is divided into the current training set and the current test set according to the preset ratio of p: q, so as to update the training set and the test set. Wherein T = Ft, F being an integer greater than 1.
According to the transmission delay time measuring method, the training set and the test set are updated through a new historical time interval reaching the client within the preset time length, the purpose that the training set and the test set can be updated while the iteration times and the model parameters of each round are updated is achieved, and compared with the existing mode that the process of training the LSTM model is separated from the prediction process, the training process and the test process of the method both depend on the newly acquired new historical time interval, so that the accuracy and the stability of the preset delay prediction model are further improved.
Based on the foregoing embodiments, fig. 3 is a general flowchart of a transmission delay time measurement method provided by the present invention, and as shown in fig. 3, the transmission delay time measurement method includes:
and 310, the sending end sends the data packets to the server frame by adopting the data packet sending time interval t.
And step 360, the client analyzes the stored pacp file and determines the historical time interval corresponding to the filtered historical data packet.
The transmission delay time measuring method predicts the prediction time interval corresponding to the current data packet transmitted frame by inputting the historical time interval corresponding to the historical data packet transmitted frame by a server into a preset delay prediction model, and outputs the transmission delay time based on the prediction time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of a sending end. The data transmission delay is reduced by combining a frame-by-frame transmission mode, the purpose of giving consideration to the real-time performance and the bandwidth utilization rate of the whole transmission system is realized, the time synchronization of a sending end and a client is not needed, and the applicability of transmission delay measurement is improved; furthermore, the preset delay prediction model is obtained by training the LSTM model based on the sample historical time interval, so that the aim of improving the accuracy of the prediction time interval can be fulfilled by combining a mode of training a recurrent neural network, and the accuracy and the reliability of transmission delay measurement can be effectively improved.
The following describes the propagation delay time measuring device provided by the present invention, and the propagation delay time measuring device described below and the propagation delay time measuring method described above can be referred to correspondingly.
Referring to fig. 4, a propagation delay time measuring apparatus according to an embodiment of the present invention is shown in fig. 4, in which the propagation delay time measuring apparatus 400 includes:
the obtaining module 410 is configured to obtain a historical time interval corresponding to a historical data packet transmitted by the server frame by frame.
A prediction module 420, configured to input the historical time interval to a preset delay prediction model, so as to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame; the preset delay prediction model is obtained by training an LSTM model based on sample historical time intervals.
An output module 430, configured to output the transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet, and the data packet sending time interval of the sending end.
Optionally, the obtaining module 410 may be specifically configured to receive a history data packet transmitted frame by the server; filtering the historical data packets based on a preset data packet receiving protocol; storing the filtered residual historical data packets as data packet files according to a preset file format; and analyzing the timestamp information in the data packet file and performing time format conversion to obtain the historical time interval corresponding to the remaining historical data packets.
Optionally, the obtaining module 410 may be further specifically configured to establish a data communication link with a sending end; sending a data transmission request to the sending end, wherein the data transmission request carries a data packaging requirement and a data sending mode; and receiving a data packet sent by the sending end aiming at the data transmission request.
Optionally, the obtaining module 410 may be further configured to write the historical data packets into a receiving buffer in sequence; screening out a first historical data packet from the historical data packets in the receiving buffer area based on a preset data packet communication protocol; and filtering the data packets which are not matched with the data packet identification information in the first historical data packets based on preset data packet identification information.
Optionally, the output module 430 may be specifically configured to compare the size of the predicted time interval with the size of the actual time interval corresponding to the current data packet; and when the actual time interval is determined to be larger than the predicted time interval, outputting transmission delay time based on the actual time interval and the data packet sending time interval of the sending end.
Optionally, the apparatus may further include a playing module, configured to sequentially write the filtered second history data packets into a playing buffer; and instructing the playing buffer area to play the second historical data packet after the second historical data packet is played in sequence.
Optionally, the apparatus may further include an adjusting module, configured to obtain a buffer capacity of the history data packet written in the receiving buffer; if the capacity of the buffer area is determined to be larger than the maximum preset capacity, indicating a sending end to reduce the sending rate of the data packet; and if the capacity of the buffer area is determined to be smaller than the minimum value of the preset capacity, indicating the sending end to increase the sending rate of the data packet.
Optionally, the apparatus may further include a training module configured to determine a training set and a testing set based on the sample historical time interval; training the LSTM model based on the training set to obtain a trained LSTM model; testing the trained LSTM model based on the test set to obtain a test result; and determining the trained LSTM model as a preset delay prediction model based on the error between the test result and the test set.
Optionally, the apparatus may further include an updating module, configured to update the training set and the test set respectively based on a new historical time interval received within a preset time period.
Fig. 5 illustrates a physical structure diagram of an electronic device, and as shown in fig. 5, the electronic device 500 may include: a processor (processor) 510, a communication interface (communication interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a propagation delay time measurement method comprising:
acquiring historical time intervals corresponding to historical data packets transmitted frame by a server;
inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame; the preset delay prediction model is obtained by training an LSTM model based on sample historical time intervals;
and outputting transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, a computer is capable of executing the transmission delay time measurement method provided by the above methods, the method comprising:
acquiring historical time intervals corresponding to historical data packets transmitted frame by a server;
inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame; the preset delay prediction model is a model obtained by training an LSTM model based on sample historical time intervals;
and outputting transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements a method for measuring a transmission delay time provided by the above methods, the method including:
acquiring historical time intervals corresponding to historical data packets transmitted frame by a server;
inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame; the preset delay prediction model is a model obtained by training an LSTM model based on sample historical time intervals;
and outputting transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (13)
1. A transmission delay time measuring method, comprising:
acquiring historical time intervals corresponding to historical data packets transmitted frame by a server;
inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame; the preset delay prediction model is a model obtained by training an LSTM model based on sample historical time intervals;
and outputting transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end.
2. The method according to claim 1, wherein outputting the transmission delay time based on the predicted time interval, the actual time interval corresponding to the current packet, and the packet transmission time interval at the transmitting end comprises:
comparing the size of the predicted time interval with the actual time interval corresponding to the current data packet;
and when the actual time interval is determined to be larger than the predicted time interval, outputting transmission delay time based on the actual time interval and the data packet sending time interval of the sending end.
3. The method according to claim 1, wherein the obtaining the historical time interval corresponding to the historical data packets transmitted by the server frame by frame comprises:
receiving historical data packets transmitted frame by a server;
filtering the historical data packets based on a preset data packet receiving protocol;
storing the filtered residual historical data packets as data packet files according to a preset file format;
and analyzing the timestamp information in the data packet file and performing time format conversion to obtain the historical time interval corresponding to the remaining historical data packets.
4. The method according to claim 3, wherein the filtering the history data packet based on a predetermined packet receiving protocol comprises:
sequentially writing the historical data packets into a receiving buffer area;
screening out a first historical data packet from the historical data packets in the receiving buffer area based on a preset data packet communication protocol;
and filtering the data packets which are not matched with the data packet identification information in the first historical data packets based on preset data packet identification information.
5. The transmission delay time measuring method according to claim 4, wherein after filtering the packets in the first history packets that do not match the packet identification information, the method further comprises:
writing the filtered second historical data packets into a play buffer area in sequence;
and instructing the playing buffer area to play the second historical data packet after the second historical data packet is played in sequence.
6. The transmission delay time measuring method according to claim 4, wherein after said sequentially writing the history data packets into a reception buffer, the method further comprises:
obtaining the buffer capacity of the historical data packet written into the receiving buffer;
if the capacity of the buffer area is determined to be larger than the maximum preset capacity, indicating a sending end to reduce the sending rate of the data packet;
and if the capacity of the buffer area is determined to be smaller than the minimum value of the preset capacity, indicating the sending end to increase the sending rate of the data packet.
7. The transmission delay time measuring method according to claim 1, wherein before the step of obtaining the historical time interval corresponding to the historical data packets transmitted by the server frame by frame, the method further comprises:
establishing a data communication link with a transmitting end;
sending a data transmission request to the sending end, wherein the data transmission request carries a data packaging requirement and a data sending mode;
and receiving a data packet sent by the sending end aiming at the data transmission request.
8. The transmission delay time measuring method according to any one of claims 1 to 7, wherein the training process of the preset delay prediction model includes:
determining a training set and a testing set based on the sample historical time interval;
training the LSTM model based on the training set to obtain a trained LSTM model;
testing the trained LSTM model based on the test set to obtain a test result;
and determining the trained LSTM model as a preset delay prediction model based on the error between the test result and the test set.
9. The transmission delay time measuring method according to claim 8, further comprising:
and updating the training set and the test set respectively based on a new historical time interval received in a preset time length.
10. A transmission delay time measuring apparatus, comprising:
the acquisition module is used for acquiring historical time intervals corresponding to historical data packets transmitted by the server frame by frame;
the prediction module is used for inputting the historical time interval into a preset delay prediction model to obtain a prediction time interval corresponding to the current data packet transmitted frame by frame; the preset delay prediction model is obtained by training an LSTM model based on sample historical time intervals;
and the output module is used for outputting the transmission delay time based on the predicted time interval, the actual time interval corresponding to the current data packet and the data packet sending time interval of the sending end.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the propagation delay time measurement method according to any one of claims 1 to 9 when executing the program.
12. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the transmission delay time measurement method according to any one of claims 1 to 9.
13. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the transmission delay time measurement method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210716495.2A CN115277497B (en) | 2022-06-22 | 2022-06-22 | Transmission delay time measurement method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210716495.2A CN115277497B (en) | 2022-06-22 | 2022-06-22 | Transmission delay time measurement method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115277497A true CN115277497A (en) | 2022-11-01 |
| CN115277497B CN115277497B (en) | 2023-09-01 |
Family
ID=83762101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210716495.2A Active CN115277497B (en) | 2022-06-22 | 2022-06-22 | Transmission delay time measurement method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115277497B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116668475A (en) * | 2023-05-18 | 2023-08-29 | 泰州市元根体育器材有限公司 | Online education operation system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101022369A (en) * | 2007-03-23 | 2007-08-22 | 中山大学 | End-to-end quening time delay measuring method |
| JP2012182747A (en) * | 2011-03-02 | 2012-09-20 | Ntt Communications Kk | Network quality measurement method, delay fluctuation estimation apparatus, network monitoring system, and program |
| CN107454017A (en) * | 2017-06-05 | 2017-12-08 | 上海交通大学 | Mixed data flow coordinated dispatching method in a kind of cloud data center network |
| CN111539780A (en) * | 2019-09-04 | 2020-08-14 | 拉扎斯网络科技（上海）有限公司 | Task processing method and device, storage medium and electronic equipment |
| CN113992599A (en) * | 2021-11-18 | 2022-01-28 | 北京达佳互联信息技术有限公司 | Training method and device of time delay prediction model and congestion control method and device |
| US20220092530A1 (en) * | 2020-09-22 | 2022-03-24 | Convey Inc. | Systems and methods for ai-based detection of delays in a shipping network |
| US20220107496A1 (en) * | 2020-10-07 | 2022-04-07 | Industrial Technology Research Institute | Orientation predicting method, virtual reality headset and non-transitory computer-readable medium |
-
2022
- 2022-06-22 CN CN202210716495.2A patent/CN115277497B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101022369A (en) * | 2007-03-23 | 2007-08-22 | 中山大学 | End-to-end quening time delay measuring method |
| JP2012182747A (en) * | 2011-03-02 | 2012-09-20 | Ntt Communications Kk | Network quality measurement method, delay fluctuation estimation apparatus, network monitoring system, and program |
| CN107454017A (en) * | 2017-06-05 | 2017-12-08 | 上海交通大学 | Mixed data flow coordinated dispatching method in a kind of cloud data center network |
| CN111539780A (en) * | 2019-09-04 | 2020-08-14 | 拉扎斯网络科技（上海）有限公司 | Task processing method and device, storage medium and electronic equipment |
| US20220092530A1 (en) * | 2020-09-22 | 2022-03-24 | Convey Inc. | Systems and methods for ai-based detection of delays in a shipping network |
| US20220107496A1 (en) * | 2020-10-07 | 2022-04-07 | Industrial Technology Research Institute | Orientation predicting method, virtual reality headset and non-transitory computer-readable medium |
| CN113992599A (en) * | 2021-11-18 | 2022-01-28 | 北京达佳互联信息技术有限公司 | Training method and device of time delay prediction model and congestion control method and device |
Non-Patent Citations (3)
| Title |
|---|
| 冯忠华;王新龙;王彬;: "一种数据链传输延迟建模及其补偿方法", 北京航空航天大学学报, no. 08 * |
| 周瑞;魏正英;张育斌;张千;: "基于LSTM递归神经网络的番茄目标产量时间序列预测", 节水灌溉, no. 08 * |
| 陈瑞;焦良葆;: "基于延迟预测的自适应媒体播放算法", 计算机工程, no. 24 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116668475A (en) * | 2023-05-18 | 2023-08-29 | 泰州市元根体育器材有限公司 | Online education operation system |
| CN116668475B (en) * | 2023-05-18 | 2023-12-26 | 尚学仕教育科技(北京)有限公司 | Online education operation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115277497B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5406362B2 (en) | Monitoring system, apparatus and method | |
| US9237108B2 (en) | Jitter buffer emulation for RTP streams in passive network monitoring systems | |
| Cizmeci et al. | A multiplexing scheme for multimodal teleoperation | |
| US10659380B2 (en) | Media buffering | |
| EP3329641B1 (en) | Monitoring network conditions | |
| CN104115448A (en) | Method and apparatus for monitoring transmission characteristics in a network | |
| US20120039391A1 (en) | System and method for transmission of data signals over a wireless network | |
| EP3125497B1 (en) | Estimating processor load | |
| US20130091528A1 (en) | Video reproduction system, receive terminal, home gateway device, and quality control system | |
| US9210058B2 (en) | Systems and methods for assessing jitter buffers | |
| AU2018257929B2 (en) | Method and apparatus for synchronizing applications' consumption of remote data | |
| CN107306192B (en) | Service data transmission method, device and system | |
| CN110198311B (en) | Data stream processing method, device, equipment and medium | |
| CN115277497B (en) | Transmission delay time measurement method, device, electronic equipment and storage medium | |
| AU2021200428C1 (en) | System and method for automatic encoder adjustment based on transport data | |
| Gokhale et al. | Congestion control for network-aware telehaptic communication | |
| WO2016008131A1 (en) | Techniques for separately playing audio and video data in local networks | |
| CN114640886A (en) | Bandwidth-adaptive audio and video transmission method and device, computer equipment and medium | |
| US9697328B2 (en) | Transmission apparatus, transmission method, reception apparatus, reception method, and computer program | |
| GB2459814A (en) | Measuring method, measuring device, and computer program | |
| US20130250120A1 (en) | Wireless communication system and method, and data receiving apparatus, method and program | |
| US8649283B2 (en) | Packet analysis apparatus and method thereof | |
| CN115734043A (en) | Video quality problem determination method, device, storage medium and program product | |
| WO2015044104A1 (en) | Video traffic management | |
| JP2004080102A (en) | Packet processing apparatus |
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 |