CN113839840B - Bandwidth self-adaptive estimation method and system for bottleneck link of satellite network - Google Patents

Bandwidth self-adaptive estimation method and system for bottleneck link of satellite network Download PDF

Info

Publication number
CN113839840B
CN113839840B CN202111399642.XA CN202111399642A CN113839840B CN 113839840 B CN113839840 B CN 113839840B CN 202111399642 A CN202111399642 A CN 202111399642A CN 113839840 B CN113839840 B CN 113839840B
Authority
CN
China
Prior art keywords
bandwidth
data packets
time
data
satellite network
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
Application number
CN202111399642.XA
Other languages
Chinese (zh)
Other versions
CN113839840A (en
Inventor
刘锋
杨程宇
石凌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beihang University
Original Assignee
Beihang University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beihang University filed Critical Beihang University
Priority to CN202111399642.XA priority Critical patent/CN113839840B/en
Publication of CN113839840A publication Critical patent/CN113839840A/en
Application granted granted Critical
Publication of CN113839840B publication Critical patent/CN113839840B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • 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
    • H04L41/142—Network analysis or design using statistical or mathematical methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/04—Large scale networks; Deep hierarchical networks
    • H04W84/06—Airborne or Satellite Networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Optimization (AREA)
  • Algebra (AREA)
  • Astronomy & Astrophysics (AREA)
  • Environmental & Geological Engineering (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Radio Relay Systems (AREA)

Abstract

The invention provides a bandwidth self-adaptive estimation method and a system of a bottleneck link of a satellite network, which are applied to a sending end of the satellite network; the method comprises the following steps: accumulating and receiving response time sequence and round-trip transmission time sequence of data packets communicated based on a satellite network; determining the maximum first k-1 data packets which belong to the same sending window in the data packets based on the response time sequence and the round-trip transmission time sequence; calculating the service time of the data flow of the bottleneck link bandwidth of the satellite network based on the response time sequence of the first k-1 data packets; and estimating the bandwidth of the bottleneck link of the satellite network based on the service time and the data volume accumulated in the service time to obtain the sampling bandwidth. The invention alleviates the technical problem of larger bandwidth value estimation error in the prior art.

Description

Bandwidth self-adaptive estimation method and system for bottleneck link of satellite network
Technical Field
The invention relates to the technical field of satellite network bandwidth estimation, in particular to a bandwidth self-adaptive estimation method and system for a bottleneck link of a satellite network.
Background
The satellite network can realize global large-range coverage, can make up for serious defects of a ground network, enlarge a communication range and improve user experience. With the rapid development of satellite broadband communication technology and the unprecedented proliferation of the Internet, broadband satellite communication and network technology supporting Transmission Control/Internet Protocol (hereinafter referred to as TCP/IP Protocol) services are rapidly developed.
Because the satellite link has the characteristics of large time delay, high error rate, high time delay bandwidth product, asymmetric link bandwidth and the like which are different from the characteristics of a ground network, the throughput of the traditional TCP/IP protocol designed for a wired network with good transmission performance in the satellite broadband communication and network environment is greatly reduced. Therefore, it is a hot research problem to improve and enhance the error rate, long-delay TCP performance in satellite broadband communication and network.
At present, an end-to-end-based bottleneck link bandwidth estimation method in an improved method of TCP mainly comprises a TCPW-BE algorithm, a TCPW + algorithm and a TCPW-ASBE algorithm, and the methods have obvious effect on wireless lossy channels. It relies mainly on end-to-end bandwidth estimation to distinguish the cause of packet loss. The effective bandwidth is estimated by monitoring the rate of responses returned in the connection, thereby calculating the congestion window and slow start threshold after congestion occurs.
Due to the TCPW-BE algorithm and its improved TCPW + algorithm, the time for serving the data stream with the bottleneck link bandwidth is not always reflected by the two ACK intervals of the adjacent data packets and the round trip time RTT of a plurality of data packets, so that the estimated bandwidth values in the two sampling times have large errors under certain conditions, and the minimum interval Δ ACK of ACK in ASBE min The Round Trip Time (RTT) is relatively small, large and easily influenced by environment, so that a large error exists in the time judgment of the data stream service by the bandwidth, and the tracking bandwidth change precision of the first-order filter is limited.
Disclosure of Invention
In view of the above, the present invention provides a bandwidth adaptive estimation method and system for a bottleneck link of a satellite network, so as to alleviate the technical problem of large bandwidth estimation error in the prior art.
In a first aspect, an embodiment of the present invention provides a bandwidth adaptive estimation method for a bottleneck link of a satellite network, which is applied to a transmitting end of the satellite network; the method comprises the following steps: accumulating and receiving response time sequence and round-trip transmission time sequence of data packets communicated based on the satellite network; determining the maximum first k data packets which belong to the same sending window in the data packets based on the response time sequence and the round-trip transmission time sequence; k is a positive integer greater than 1; calculating the service time of the bottleneck link bandwidth of the satellite network as the data stream based on the response time sequence of the first k data packets; and estimating the bandwidth of the bottleneck link of the satellite network based on the service time and the data volume accumulated in the service time to obtain a sampling bandwidth.
Further, after obtaining the sampling bandwidth, the method further includes: and adopting a second-order nonlinear filter to carry out self-adaptive filtering on the sampling bandwidth to obtain the filtered sampling bandwidth.
Further, determining the maximum first k-1 data packets belonging to the same sending window from the data packets based on the response time sequence and the round trip transmission time sequence includes: calculating the time difference of the acknowledgement of two adjacent data packets to the transmitting end based on the acknowledgement time sequence; determining, based on the round trip transmission time sequence and the time difference, the first k-1 data packets among the data packets that simultaneously satisfy the following conditional relation:
Figure DEST_PATH_IMAGE001
；
Figure 101354DEST_PATH_IMAGE002
(ii) a Wherein RTTk-2、RTTk-1And RTTkThe round trip transmission time, RTT, of the kth-2 data packet, the kth-1 data packet and the kth data packet, respectivelyminFor the minimum round trip transmission time, Δ ACK, in the round trip transmission time sequence of the first k-1 data packetsk-2,k-1Delta ACK is the time difference between the acknowledgement arrival at the sender for the kth-2 and the acknowledgement arrival at the sender for the kth-1 data packetsk-1,kThe time difference between the acknowledgement arrival time of the kth data packet and the acknowledgement arrival time of the kth data packet at the transmitting end is represented by epsilon, which is a preset time small quantity.
Further, calculating the service time of the data flow of the bottleneck link bandwidth of the satellite network based on the response time sequence of the first k-1 data packets, comprising: calculating two adjacent data packets based on the response time sequence of the first k-1 data packetsTime difference of arrival of acknowledgement of each data packet at the transmitting end; calculating the service time based on the following equation:
Figure DEST_PATH_IMAGE003
(ii) a Wherein, tserviceFor said service time, Δ ACKi,i+1The time difference between the acknowledgement of the ith data packet and the acknowledgement of the (i + 1) th data packet arriving at the sender is obtained.
Further, estimating the bandwidth of the bottleneck link of the satellite network based on the service time and the data volume accumulated in the service time to obtain a sampling bandwidth, including: calculating the sampling bandwidth based on the following equation:
Figure 661648DEST_PATH_IMAGE004
；bkfor said sampling bandwidth, PiIs the data amount of the ith packet.
Further, adaptively filtering the sampling bandwidth by using a second-order nonlinear filter, including: calculating a bandwidth change rate and a filtering time constant of a bottleneck link of the satellite network; and performing adaptive filtering processing on the sampling bandwidth based on the historical sampling bandwidth of the bottleneck link of the satellite network, the bandwidth change rate, the filtering time constant and the service time to obtain the filtered sampling bandwidth.
In a second aspect, an embodiment of the present invention further provides a bandwidth adaptive estimation system for a bottleneck link of a satellite network, which is applied to a transmitting end of the satellite network; the method comprises the following steps: the device comprises a receiving module, a determining module, a calculating module and an estimating module; the receiving module is used for accumulatively receiving a response time sequence and a round-trip transmission time sequence of a data packet communicated based on the satellite network; the determining module is configured to determine, based on the response time sequence and the round-trip transmission time sequence, the maximum first k-1 data packets that belong to the same sending window in the data packets; k is a positive integer greater than 1; the computing module is used for computing the service time of the data flow of the bandwidth of the bottleneck link of the satellite network based on the response time sequence of the first k-1 data packets; and the estimation module is used for estimating the bandwidth of the bottleneck link of the satellite network based on the service time and the data volume accumulated in the service time to obtain the sampling bandwidth.
Further, the system comprises a filtering module for: and adopting a second-order nonlinear filter to carry out self-adaptive filtering on the sampling bandwidth to obtain the filtered sampling bandwidth.
In a third aspect, an embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect when executing the computer program.
In a fourth aspect, the present invention further provides a computer-readable medium having non-volatile program code executable by a processor, where the program code causes the processor to execute the method according to the first aspect.
The invention provides a bandwidth self-adaptive estimation method and a bandwidth self-adaptive estimation system for a bottleneck link of a satellite network, which are used for accurately distinguishing and judging data packets of the same sending serial port based on a data transmission process and a data characteristic relation, then accurately calculating the time and data quantity of the bottleneck link bandwidth serving for data streams based on series data packets of the same sending window, and carrying out sampling bandwidth estimation, thereby improving the stability and precision of estimated data and relieving the technical problem of larger bandwidth value estimation error in the prior art.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in 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 other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a bandwidth adaptive estimation method for a bottleneck link of a satellite network according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a satellite network data packet transmission process according to an embodiment of the present invention;
fig. 3 is a flowchart of another bandwidth adaptive estimation method for a bottleneck link of a satellite network according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a bandwidth adaptive estimation system for a bottleneck link of a satellite network according to an embodiment of the present invention;
fig. 5 is a schematic diagram of another bandwidth adaptive estimation system for a bottleneck link of a satellite network according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood 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 first embodiment is as follows:
fig. 1 is a flowchart for providing a bandwidth adaptive estimation method for a bottleneck link of a satellite network according to an embodiment of the present invention, and the method is applied to a transmitting end of the satellite network. As shown in fig. 1, the method specifically includes the following steps:
step S102, accumulating and receiving the response time sequence and the round trip transmission time sequence of the data packet communicated based on the satellite network. The response time sequence is a time sequence when the sending end receives the acknowledgement feedback of each data packet, and the round-trip transmission time sequence is a time interval sequence from the sending of each data packet to the receiving of the acknowledgement feedback of the data packet.
Fig. 2 is a schematic diagram of a satellite network data packet transmission process according to an embodiment of the present invention. As shown in FIG. 2, the sender sends k-1 data packets (1, 2,3, …, r, …, k-1) in Window 1, and the receiver acknowledges the feedback ACK when the sender receives the 1 st data packet1Then, start the transmission window 2, transmit the next set of packets (k, k +1, k +2, …) starting with the kth packet. As shown in FIG. 2, the acknowledgement time sequence { ACKkThe time (time, time point) when the sender receives the acknowledgement feedback of the kth data packet, and round trip transmission time sequence { RTTkThe time interval from sending the kth data packet to receiving the data packet acknowledgement feedback (i.e. the round-trip transmission time of the kth data packet) is.
Step S104, determining the maximum first k-1 data packets which belong to the same sending window and are sent out in the data packets based on the response time sequence and the round-trip transmission time sequence; k is a positive integer greater than 1.
And step S106, calculating the service time of the data flow as the bottleneck link bandwidth of the satellite network based on the response time sequence of the first k-1 data packets.
And S108, estimating the bandwidth of the bottleneck link of the satellite network based on the service time and the data volume accumulated in the service time to obtain the sampling bandwidth.
The invention provides a bandwidth self-adaptive estimation method of a bottleneck link of a satellite network, which is characterized in that data packets of the same sending serial port are accurately distinguished and judged based on a data transmission process and a data characteristic relation, then the time and the data quantity of the bottleneck link bandwidth serving for data flow are accurately calculated based on series data packets of the same sending window, and sampling bandwidth estimation is carried out, so that the stability and the precision of estimated data are improved, and the technical problem of large bandwidth value estimation error in the prior art can be solved.
Aiming at the technical problem that a first-order bandwidth filter in the prior art is difficult to respond to bandwidth change of a dynamic satellite network in time, after a sampling bandwidth is obtained, the method provided by the embodiment of the invention further comprises the following steps: and performing self-adaptive filtering on the sampling bandwidth by adopting a second-order nonlinear filter to obtain the filtered sampling bandwidth.
Specifically, firstly, calculating a bandwidth change rate and a filtering time constant of a bottleneck link of a satellite network; and then, based on the historical sampling bandwidth, the bandwidth change rate, the filtering time constant and the service time of the bottleneck link of the satellite network, carrying out self-adaptive filtering processing on the sampling bandwidth to obtain the filtered sampling bandwidth. In the embodiment of the invention, the second-order nonlinear adaptive filtering is adopted, so that the technical effects of smoothing the sampling bandwidth estimation result, improving the rapidity of sampling bandwidth estimation and increasing the tracking speed of bandwidth change can be achieved.
Specifically, step S104 further includes the following steps:
step S1041, calculating the time difference of the acknowledgement of two adjacent data packets to the sending end based on the acknowledgement time sequence;
step S1042, based on the round-trip transmission time sequence and the time difference, determining the first k-1 data packets in the data packets that simultaneously satisfy the following conditional relation:
Figure 433295DEST_PATH_IMAGE005
wherein RTTk-2、RTTk-1And RTTkThe round trip transmission time, RTT, of the kth-2 data packet, the kth-1 data packet and the kth data packet, respectivelyminFor the minimum round trip transmission time, Δ ACK, in the round trip transmission time sequence of the first k-1 data packetsk-2,k-1Delta ACK is the time difference between the acknowledgement arrival at the sender for the kth-2 and the acknowledgement arrival at the sender for the kth-1 data packetsk-1,kThe time difference between the acknowledgement arrival time of the kth data packet and the acknowledgement arrival time of the kth data packet at the transmitting end is represented by epsilon, which is a preset time small quantity.
In the embodiment of the invention, the round trip time RTT of any data packet kk(the duration from the time the sender sends a packet k until the sender receives acknowledgement feedback of the packet from the receiver) is:
Figure 328756DEST_PATH_IMAGE008
wherein, tpThe propagation delay of the end-to-end link is related to the distance; t is tq(k) Buffering the queued time, P, for the first packet at the bottleneck linkkData volume for the kth packet, b bandwidth for the bottleneck link, in general
Figure 743557DEST_PATH_IMAGE009
Relative tq(k) Smaller and generally negligible (the bandwidth of the non-bottleneck link is generally less than the bandwidth of the bottleneck link, and is also ignored, as the packet transmission service time). Thus, there are approximately: RTT (round trip time)k≈2×tp+tq(k)。
Minimum round trip time RTT for a packet flowk≥RTTmin≥2×tpTime of transmission of packet acknowledgement time Δ ACKk≥ACKmin≥tpGenerally, the approximation is:
RTTmin≈2tp；
ACKmin≈tp；
the k-1 data packets (1, 2,3, …, r, …, k-1) sent out by the same sending window have the following relationship due to the different arrival time of the system list at the receiving end and the different time of the acknowledgement feedback when the sending time system list arrives at the receiving end:
RTTmin≤RTT1<RTT2<…<RTTr-1<RTTr<RTTr+1<…<RTTk-1
therefore, for k-1 data packets (1, 2,3, …, r, …, k-1) of the same sending window and the head data packet k of the series of data packets (k, k +1, k +2, …) sent out by the next window, it is important to consider them in the bottleneck link (BottleneckLink) buffer (B)bl) Based on the ACK sequence { ACKkAnd RTT sequence (RTT)kAnd analyzing and discussing the distinguishing and judging conditions of the data packets of different sending windows.
(1) For k-1 packets (1, 2,3, …, r, …, k-1) of the same send window, they are in turn at B of the bottleneck linkblQueued up and served, their acknowledgement sequence ACKrTime difference, RTT sequence (RTT)rThe relationship of the time difference is as follows:
Figure 686105DEST_PATH_IMAGE010
，
wherein,
Figure 699540DEST_PATH_IMAGE011
。
therefore { RTTrIs a monotonically increasing series.
(2) If the kth data packet sent by the next sending window is the 1 st data packet to confirm the feedback ACK1Triggering transmission, at this time, based on fig. 2, since the kth data packet and the k-1 data packet of the same previous transmission window are not transmitted from the same window, and the kth data packet is acknowledged by the 1 st data packet and fed back with ACK1Triggering transmission, so there are:
Figure 120157DEST_PATH_IMAGE012
namely:
Figure 592727DEST_PATH_IMAGE013
for the data packets k-2 and k-1 of the same transmission window, there are:
Figure 768493DEST_PATH_IMAGE014
and RTT1≥RTTmin≈2tpIs relatively large, and therefore RTTr-1+△ACKr-1,r-RTTrOr approximately 0, or approximately RTT1And the difference is large, and judgment is convenient.
Thus approximating RTTk-1+△ACKk-1,k-RTTk=RTT1≥RTTmin≈2tpJudging and distinguishing whether the kth data packet and the previous data packet k-1 are data packets sent out by the same sending window or not by taking the kth data packet and the previous k-1 data packet as conditions, if the equal sign is approximately true, the kth data packet and the previous k-1 data packet are not data packets sent out by the same sending window; otherwise if RTTk-1+△ACKk-1,k-RTTkAnd the k-th data packet and the previous k-1 data packets are data packets sent out by the same sending window.
In summary, for the different transmission window packets, it is not assumed that the first k-1 packets (1, 2,3, …, r, …, k-1) are the same transmission window, the kth packet belongs to the next transmission window, and the kth packet is ACK1And (5) triggering. At this time, the kth data packet sent by the following window and the k-1 data packet sent by the same preceding window are judged whether belong to the data packet of the same sending window through the following two equations, if the following two equations are true, the kth data packet and the k-1 data packet do not belong to the data packet of the same sending window:
RTTk-1+△ACKk-1,k-RTTk=RTT1≥RTTmin≈2tp
RTTk-2+△ACKk-2,k-1-RTTk-1≈0
it should be noted that, in the embodiment of the present invention, in order to determine whether the above equation is approximately satisfied, a preset time small amount epsilon is introduced to determine the RTTk-2+△ACKk-2,k-1-RTTk-1<If epsilon is true, the equation RTT is explainedk-2+△ACKk-2,k-1-RTTk-1Approximately 0 holds true.
Specifically, the service time in step S106 is calculated by the following steps:
calculating the time difference of the acknowledgement of two adjacent data packets to the transmitting end based on the response time sequence of the first k-1 data packets;
the service time is calculated based on the following equation:
Figure 693724DEST_PATH_IMAGE015
wherein, tserviceFor service time, Δ ACKi,i+1The time difference between the acknowledgement of the ith data packet and the acknowledgement of the (i + 1) th data packet arriving at the sender is obtained.
Specifically, the sampling bandwidth in step S108 is obtained by the following calculation:
Figure 980349DEST_PATH_IMAGE016
bkfor sampling bandwidth, PiIs the data amount of the ith packet.
Specifically, the calculation formula of the nonlinear second-order low-pass filtering estimation value of the sampling bandwidth is as follows:
Figure 41846DEST_PATH_IMAGE017
wherein the time constant τ and the bandwidth change rate ρbeRespectively as follows:
Figure 326196DEST_PATH_IMAGE018
θ、kτis a constant (in the embodiment of the invention, all take the value of 1.01),
Figure 801040DEST_PATH_IMAGE019
as an estimate of historical bandwidth, bk-1The bandwidth is sampled for history.
Therefore, the embodiment of the invention provides a bandwidth self-adaptive estimation method for a bottleneck link of a satellite network, which can be based on a transmission process of TCP and an ACK sequence { ACKk}, RTT sequence { RTTkAccurately distinguishing whether the data characteristic relationship is a sequence data packet of the same sending window; then based on ACK sequence { ACKkAccurately calculating the service time t of sending a sequence data packet for the same sending window by the bottleneck link bandwidthservice(i.e., the cumulative time a series of packets sent out by the same send window across the bottleneck link); and finally, a second-order nonlinear filter is adopted to perform adaptive filtering processing on the bandwidth sampling value, so that the response speed and the estimation precision are improved.
Furthermore, the method provided by the embodiment of the invention adopts the data packet responseThe time sequence for answering ACK estimates the service time of the bottleneck link bandwidth for the data flow, is less easily influenced by the noise of the network environment compared with the RTT time, is simple and efficient, can improve the stability and the precision of the estimated data, and reduces the influence of the RTT and the delta ACK on the ASBE based method in the prior artminAnd distinguishing and judging whether the data packets in the same sending window are inaccurate due to overlarge numerical value difference.
Example two:
fig. 3 is a flowchart of another bandwidth adaptive estimation method for a bottleneck link of a satellite network according to an embodiment of the present invention. As shown in fig. 3, the method specifically includes the following steps:
step 1: ACK sequence { ACK when sending end receives data packetkAnd round trip time RTT sequence (RTT)kWhere k is denoted as the index of the kth packet, initialize k =0, Pk=0, calculating and updating ACKmin、RTTmin、△ACKmin。
(1) Initializing the system, wherein the sampling value of the bandwidth of the initial bottleneck link is b0=0。
(2) And initializing and starting TCP connection, wherein a sending end sends data and a receiving end receives the data.
(3) Parameter initialization k =0, Pk=0。
(4) Initializing, recording and updating bandwidth data.
(5) Receiving a returned ACK sequence ACKkGet the data packet size { P }kSending time of data packet k { t _ send }kTime for sending acknowledgement feedback of data packet k { t _ ack }kGet RTT, ACK sequence { RTT of calculating updating data packetk}、{△RTTk-1,k}、{ACKk}、{△ACKk}、{△ACKk-1,k}, and ACKmin、RTTmin、△ACKmin、△RTTmin. Wherein Δ ACKkThe transmission time, RTT, from the receiver to the sender of the acknowledgement indicating the kth packetkIndicates the round trip transmission time, Δ ACK, of the kth packetk-1,kIndicates the k-1 data packet and theTime difference between k data packets and the time when the acknowledgement arrives at the sender, Δ RTTk-1,kIndicating the difference between the round trip transmission time of the (k-1) th packet and the (k) th packet. Namely:
Figure 829039DEST_PATH_IMAGE020
step 2: acknowledgement of ACK sequence according to accumulatively received data packet based on { RTTkAnd { ACK }kJudging and distinguishing whether the received serial data packets are sent out by the same sending window, and cumulatively calculating the time t of the bottleneck link bandwidth serving the data streamserviceAnd its data amount, estimate the sampling bandwidth bk。
Calculating an ideal expression of the bandwidth sampling value, wherein the bottleneck link bandwidth is the accumulated data volume passing through the service time of the serial data packets of the same data flow, namely:
Figure 574403DEST_PATH_IMAGE021
。
where the denominator tserviceCumulative time, numerator, for a series of packets traversing a bottleneck link
Figure 764076DEST_PATH_IMAGE022
Is the total data volume passing through the series of data packets in the accumulation time. Since Δ ACK cannot be calculated only for the 1 st packetk-1,kThe kth packet may be sent out by the next transmission window, so that the calculation is performed for convenience and uniformity, with the time interval from the 1 st packet to the k-1 st packet (i.e., k-2 Δ ACK packets)i,i+1I =1,2, …, k-2) and the amount of data (i.e. k-2 data packets P)i+1I =1,2, …, k-2) to discriminate and distinguish between different transmission windows and packets, i.e.:
Figure 663899DEST_PATH_IMAGE023
，
Figure 292326DEST_PATH_IMAGE024
。
this is based on the TCP transmission process and the ACK sequence ACKk}, RTT sequence { RTTkThe data characteristic relation of the system can accurately distinguish and judge whether the received data packets are sequence data packets of the same sending window or not, and is based on an ACK sequence { ACK sequencekAccurately calculating the service time t of sending a sequence data packet for the same sending window by the bottleneck link bandwidthservice(i.e. the accumulated time of a series of data packets sent out by the same sending window passing through the bottleneck link) without adopting an approximate calculation method of ASBE, the calculation precision can be improved. Here, it is specifically expressed as:
Figure 16886DEST_PATH_IMAGE025
specifically, the method for distinguishing and judging different sending windows and data packets and the estimation process for serving the data stream by the bottleneck link bandwidth are as follows:
(1) calculating sigma i △ACK i,i+1、Σ i P i 。
(2) Determining RTTk-1+△ACKk-1,k-RTTk0, if yes, indicating that the kth data packet and the kth-1 data packet are data packets sent out by the same sending window, k + +, returning to (1) to continue collecting the data packets; if not, the next step is carried out, and the judgment is continued.
(3) Determining RTTk-1+△ACKk-1,k-RTTk≥RTTmin≈2tpIf yes, the kth data packet and the kth-1 data packet are not data packets sent by the same sending window, and the first k-1 data packets are sent by the same sending window, the next step is carried out; if not, the situation that whether the kth data packet and the kth-1 data packet are data packets sent by the same sending window and are abnormal cannot be judged, and then the operation is carried out (8).
(4) Computing
Figure 404005DEST_PATH_IMAGE026
，
Figure 836123DEST_PATH_IMAGE027
。
(5) Calculating bandwidth sample values
Figure 726719DEST_PATH_IMAGE028
And updating the sampling bandwidth.
(6) Parameter initialization parameter k =0, Pk=0。
(7) The kth packet is set as the 1 st packet of the next transmission window, k =1, and the process returns to Step1 (4).
(8) Not calculating bkContinuing the data updating process, and initializing the parameter k =0, Pk=0, return to Step1 (4).
Step 3: and second-order nonlinear adaptive filtering of the bottleneck link sampling bandwidth.
Meanwhile, second-order nonlinear adaptive filtering processing is adopted, so that the sampling bandwidth value can be further smoothed according to the change of the sampling bandwidth in real time, and the tracking speed and the response speed of bandwidth change are improved. Specifically, the second-order nonlinear adaptive filtering process is as follows:
(1) calculating the bandwidth rate of change ρbe：
Figure 87555DEST_PATH_IMAGE029
(2) Setting constants theta, kτIs a constant (in the present embodiment, θ, k)τ= 1.01), the filter time constant τ is calculated:
Figure 696391DEST_PATH_IMAGE030
(3) based on historical bandwidth estimates
Figure 932200DEST_PATH_IMAGE031
Historical sample bandwidth value (b)k-1) And the data service time t of the current bottleneck linkserviceCalculating the current bandwidth estimation value
Figure 942882DEST_PATH_IMAGE032
：
Figure 910838DEST_PATH_IMAGE033
(4) Ending the estimation and updating the estimated bandwidth
Figure 69287DEST_PATH_IMAGE032
。
(5) Updating and recording the bandwidth.
Example three:
fig. 4 is a schematic diagram of a bandwidth adaptive estimation system for a bottleneck link of a satellite network, which is applied to a transmitting end of the satellite network according to an embodiment of the present invention. As shown in fig. 4, the system includes: a receiving module 10, a determining module 20, a calculating module 30 and an estimating module 40.
Specifically, the receiving module 10 is configured to accumulate a response time sequence and a round trip transmission time sequence of a data packet received from a satellite network.
A determining module 20, configured to determine, based on the response time sequence and the round-trip transmission time sequence, the maximum first k-1 data packets that belong to the same sending window in the data packets; k is a positive integer greater than 1.
And the calculating module 30 is configured to calculate a service time of the data stream based on the response time sequence of the first k-1 data packets, where the service time is the bandwidth of the bottleneck link of the satellite network.
And the estimation module 40 is configured to estimate a bandwidth of a bottleneck link of the satellite network based on the service time and the data amount accumulated in the service time, so as to obtain a sampling bandwidth.
The invention provides a bandwidth self-adaptive estimation system of a bottleneck link of a satellite network, which accurately distinguishes and judges data packets of the same sending serial port based on a data transmission process and a data characteristic relation, then accurately calculates the time and data quantity of the bottleneck link bandwidth serving for data flow based on series data packets of the same sending window, and carries out sampling bandwidth estimation, thereby improving the stability and precision of estimated data and relieving the technical problem of larger bandwidth value estimation error in the prior art.
Fig. 5 is a schematic diagram of another bandwidth adaptive estimation system for a bottleneck link of a satellite network according to an embodiment of the present invention. As shown in fig. 5, the system further comprises a filtering module 50 for: and performing self-adaptive filtering on the sampling bandwidth by adopting a second-order nonlinear filter to obtain the filtered sampling bandwidth.
Optionally, the determining module 20 is further configured to:
calculating the time difference of the acknowledgement of two adjacent data packets to the transmitting end based on the acknowledgement time sequence;
based on the round trip transmission time sequence and the time difference, determining the first k-1 data packets which simultaneously satisfy the following conditional relation:
Figure 780891DEST_PATH_IMAGE034
wherein RTTk-2、RTTk-1And RTTkThe round trip transmission time, RTT, of the kth-2 data packet, the kth-1 data packet and the kth data packet, respectivelyminFor the minimum round trip transmission time, Δ ACK, in the round trip transmission time sequence of the first k-1 data packetsk-2,k-1Delta ACK is the time difference between the acknowledgement arrival at the sender for the kth-2 and the acknowledgement arrival at the sender for the kth-1 data packetsk-1,kThe time difference between the acknowledgement arrival time of the kth data packet and the acknowledgement arrival time of the kth data packet at the transmitting end is represented by epsilon, which is a preset time small quantity.
The embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the computer program, the steps of the method in the first embodiment are implemented.
The embodiment of the invention also provides a computer readable medium with a non-volatile program code executable by a processor, wherein the program code causes the processor to execute the method in the first embodiment.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims (7)

1. A bandwidth self-adaptive estimation method of a bottleneck link of a satellite network is applied to a sending end of the satellite network; it is characterized by comprising:
accumulating and receiving response time sequence and round-trip transmission time sequence of data packets communicated based on the satellite network;
determining the maximum first k-1 data packets which belong to the same sending window and are sent out in the data packets based on the response time sequence and the round-trip transmission time sequence; k is a positive integer greater than 1;
calculating the service time of the data flow of the bottleneck link bandwidth of the satellite network based on the response time sequence of the first k-1 data packets;
estimating the bandwidth of the bottleneck link of the satellite network based on the service time and the data volume accumulated in the service time to obtain a sampling bandwidth;
determining the maximum first k-1 data packets which belong to the same sending window and are sent out from the data packets based on the response time sequence and the round-trip transmission time sequence, wherein the determining comprises the following steps:
calculating the time difference of the acknowledgement of two adjacent data packets to the transmitting end based on the acknowledgement time sequence;
determining, based on the round trip transmission time sequence and the time difference, the first k-1 data packets among the data packets that simultaneously satisfy the following conditional relation:
Figure P_220111105432556_556297001
wherein RTTk-2、RTTk-1And RTTkThe round trip transmission time, RTT, of the kth-2 data packet, the kth-1 data packet and the kth data packet, respectivelyminFor the minimum round trip transmission time, Δ ACK, in the round trip transmission time sequence of the first k-1 data packetsk-2,k-1Delta ACK is the time difference between the acknowledgement arrival at the sender for the kth-2 and the acknowledgement arrival at the sender for the kth-1 data packetsk-1,kThe time difference between the acknowledgement of the kth data packet and the acknowledgement of the kth data packet arriving at the sending end is shown, and epsilon is a preset time small quantity;
calculating the service time of the bottleneck link bandwidth of the satellite network as the data stream based on the response time sequence of the first k-1 data packets, wherein the service time comprises the following steps:
calculating the time difference of the acknowledgement of two adjacent data packets to the transmitting end based on the response time sequence of the first k-1 data packets;
calculating the service time based on the following equation:
Figure P_220111105432634_634406001
wherein, tserviceFor said service time, Δ ACKi,i+1The time difference of the acknowledgement of the ith data packet and the (i + 1) th data packet reaching the sending end is obtained;
estimating the bandwidth of the bottleneck link of the satellite network based on the service time and the data volume accumulated in the service time to obtain a sampling bandwidth, wherein the method comprises the following steps:
calculating the sampling bandwidth based on the following equation:
Figure P_220111105432681_681265001
bkfor said sampling bandwidth, PiIs the data amount of the ith packet.
2. The method of claim 1, wherein after obtaining the sampling bandwidth, the method further comprises: and adopting a second-order nonlinear filter to carry out self-adaptive filtering on the sampling bandwidth to obtain the filtered sampling bandwidth.
3. The method of claim 2, wherein adaptively filtering the sampling bandwidth with a second order nonlinear filter comprises:
calculating a bandwidth change rate and a filtering time constant of a bottleneck link of the satellite network;
and performing adaptive filtering processing on the sampling bandwidth based on the historical sampling bandwidth of the bottleneck link of the satellite network, the bandwidth change rate, the filtering time constant and the service time to obtain the filtered sampling bandwidth.
4. A bandwidth self-adaptive estimation system of a bottleneck link of a satellite network is applied to a sending end of the satellite network; it is characterized by comprising: the device comprises a receiving module, a determining module, a calculating module and an estimating module; wherein,
the receiving module is used for accumulatively receiving a response time sequence and a round-trip transmission time sequence of a data packet communicated based on the satellite network;
the determining module is configured to determine, based on the response time sequence and the round-trip transmission time sequence, the maximum first k-1 data packets that belong to the same sending window in the data packets; k is a positive integer greater than 1;
the computing module is used for computing the service time of the data flow of the bandwidth of the bottleneck link of the satellite network based on the response time sequence of the first k-1 data packets;
the estimation module is used for estimating the bandwidth of the bottleneck link of the satellite network based on the service time and the data volume accumulated in the service time to obtain a sampling bandwidth;
the determining module is further configured to:
calculating the time difference of the acknowledgement of two adjacent data packets to the transmitting end based on the acknowledgement time sequence;
determining, based on the round trip transmission time sequence and the time difference, the first k-1 data packets among the data packets that simultaneously satisfy the following conditional relation:
Figure P_220111105432775_775028001
wherein RTTk-2、RTTk-1And RTTkThe round trip transmission time, RTT, of the kth-2 data packet, the kth-1 data packet and the kth data packet, respectivelyminFor the minimum round trip transmission time, Δ ACK, in the round trip transmission time sequence of the first k-1 data packetsk-2,k-1Delta ACK is the time difference between the acknowledgement arrival at the sender for the kth-2 and the acknowledgement arrival at the sender for the kth-1 data packetsk-1,kThe time difference between the acknowledgement of the kth data packet and the acknowledgement of the kth data packet arriving at the sending end is shown, and epsilon is a preset time small quantity;
the computing module is further configured to:
calculating the time difference of the acknowledgement of two adjacent data packets to the transmitting end based on the response time sequence of the first k-1 data packets;
calculating the service time based on the following equation:
Figure P_220111105432884_884406001
wherein, tserviceFor said service time, Δ ACKi,i+1The time difference of the acknowledgement of the ith data packet and the (i + 1) th data packet reaching the sending end is obtained;
the estimation module is further configured to:
calculating the sampling bandwidth based on the following equation:
Figure P_220111105432931_931295001
bkfor said sampling bandwidth, PiIs the data amount of the ith packet.
5. The system of claim 4, further comprising a filtering module to: and adopting a second-order nonlinear filter to carry out self-adaptive filtering on the sampling bandwidth to obtain the filtered sampling bandwidth.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any of the preceding claims 1 to 3 are implemented when the computer program is executed by the processor.
7. A computer-readable medium having non-volatile program code executable by a processor, wherein the program code causes the processor to perform the method of any of claims 1-3.
CN202111399642.XA 2021-11-24 2021-11-24 Bandwidth self-adaptive estimation method and system for bottleneck link of satellite network Active CN113839840B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111399642.XA CN113839840B (en) 2021-11-24 2021-11-24 Bandwidth self-adaptive estimation method and system for bottleneck link of satellite network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111399642.XA CN113839840B (en) 2021-11-24 2021-11-24 Bandwidth self-adaptive estimation method and system for bottleneck link of satellite network

Publications (2)

Publication Number Publication Date
CN113839840A CN113839840A (en) 2021-12-24
CN113839840B true CN113839840B (en) 2022-02-18

Family

ID=78971583

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111399642.XA Active CN113839840B (en) 2021-11-24 2021-11-24 Bandwidth self-adaptive estimation method and system for bottleneck link of satellite network

Country Status (1)

Country Link
CN (1) CN113839840B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114745042B (en) * 2022-03-28 2023-12-19 广东天镝科技有限公司 Method and device for transmitting data of broadband and narrowband integrated satellite network

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101369980A (en) * 2008-09-26 2009-02-18 北京航空航天大学 Band width estimation method based on self-adapting sampling
CN101557607A (en) * 2009-05-15 2009-10-14 东南大学 Method for controlling transmission of sink nodes in wireless sensor network
CN101854738A (en) * 2010-05-21 2010-10-06 南京邮电大学 Transmission control protocol method for satellite network
CN101917342A (en) * 2010-08-25 2010-12-15 天津理工大学 Pervasive service-oriented adaptive network congestion control method
CN102420676A (en) * 2011-11-30 2012-04-18 中国人民解放军西安通信学院 High efficient interactive transmission method applicable to deep space interplanetary satellite network
CN102664867A (en) * 2012-03-15 2012-09-12 南京邮电大学 Method for enhancing transmission protocols in satellite communication system
CN104283605A (en) * 2014-09-26 2015-01-14 东软集团股份有限公司 Satellite network data transmission method and device based on UDP

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003043288A1 (en) * 2001-11-13 2003-05-22 Ems Technologies, Inc. Enhancements for tcp perfomance enhancing proxies
US8116225B2 (en) * 2008-10-31 2012-02-14 Venturi Wireless Method and apparatus for estimating channel bandwidth
CN101645765B (en) * 2009-08-03 2012-10-03 四川大学 Reliable transmission acceleration method facing networks with high error rate and long delay characteristics
US8582518B2 (en) * 2010-11-09 2013-11-12 Telefonaktiebolaget L M Ericsson (Publ) Power control for ACK/NACK formats with carrier aggregation
US8832515B2 (en) * 2012-02-29 2014-09-09 Qualcomm Incorporated Block acknowledgement mechanism including sequence number acknowledgement and retry bit
US8923123B2 (en) * 2012-11-02 2014-12-30 Lockheed Martin Corporation ECN-enabled multicast protocol for wireless communication systems under blockage
US9509802B1 (en) * 2013-03-15 2016-11-29 PME IP Pty Ltd Method and system FPOR transferring data to improve responsiveness when sending large data sets
US9538439B2 (en) * 2013-05-10 2017-01-03 Qualcomm Incorporated Method and apparatus for estimating an achievable link throughput based on assistance information
CN104155669B (en) * 2014-08-04 2016-08-24 成都天奥信息科技有限公司 The deep combination implementing method of receiver based on Beidou II satellite navigation system
CN105634978A (en) * 2014-11-26 2016-06-01 安徽中杰信息科技有限公司 Data exchange protocol UDT-Sat
US10149284B2 (en) * 2015-02-05 2018-12-04 Qualcomm Incorporated Systems and methods for group block acknowledgment transmissions
US10244270B2 (en) * 2015-03-25 2019-03-26 Amazon Technologies, Inc. Determining initial bit rate for adaptive bit rate video playback
CN105406915B (en) * 2015-10-16 2018-10-26 中国人民解放军国防科学技术大学 A kind of document transmission method towards satellite-ground link
CN106160953B (en) * 2016-07-06 2019-04-16 四川大学 A kind of transmission method based on learning-oriented energy efficiency model
US10440698B2 (en) * 2017-02-06 2019-10-08 Qualcomm Incorporated Transmitting uplink control information
CN107395325B (en) * 2017-07-10 2020-04-17 中国电子科技集团公司第二十八研究所 Adaptive estimation transmission method serving tactical communication network
CN108260022B (en) * 2017-12-04 2021-06-01 南京超聚通信科技有限公司 Broadband hybrid network based on broadcast and television unidirectional HFC access network and operation method thereof

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101369980A (en) * 2008-09-26 2009-02-18 北京航空航天大学 Band width estimation method based on self-adapting sampling
CN101557607A (en) * 2009-05-15 2009-10-14 东南大学 Method for controlling transmission of sink nodes in wireless sensor network
CN101854738A (en) * 2010-05-21 2010-10-06 南京邮电大学 Transmission control protocol method for satellite network
CN101917342A (en) * 2010-08-25 2010-12-15 天津理工大学 Pervasive service-oriented adaptive network congestion control method
CN102420676A (en) * 2011-11-30 2012-04-18 中国人民解放军西安通信学院 High efficient interactive transmission method applicable to deep space interplanetary satellite network
CN102664867A (en) * 2012-03-15 2012-09-12 南京邮电大学 Method for enhancing transmission protocols in satellite communication system
CN104283605A (en) * 2014-09-26 2015-01-14 东软集团股份有限公司 Satellite network data transmission method and device based on UDP

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
《A TCP Enhanced Scheme based on Bottleneck Bandwidth Estimation for Satellite Links》;zhizhong yin等;《IEEE》;20091231;全文 *
《卫星网络中的TCP跨层技术研究》;张连连;《现代电子技术》;20210101;全文 *
《基于同步骨干卫星的天地一体化IP网络互联模式设计及真星试验》;刘华峰;《中国电子科学研究院学报》;20181031;第13卷(第5期);全文 *

Also Published As

Publication number Publication date
CN113839840A (en) 2021-12-24

Similar Documents

Publication Publication Date Title
CN112217686B (en) System, method and device for evaluating round trip delay
US7675856B2 (en) Bandwidth estimation in broadband access networks
US8665745B2 (en) Method and device for determining a jitter buffer level
CN107624232B (en) Apparatus and method for controlling downlink throughput in communication system
CN105141542A (en) TCP communication protocol-based congestion window control algorithm and system
CN106713166B (en) Method and device for determining size of congestion window
WO2011006372A1 (en) Method and system for end to end available bandwidth measurement
CN101369980B (en) Band width estimation method based on self-adapting sampling
US20110292800A1 (en) Systems and Methods For Controlling Data Transmission Rates
KR20060100512A (en) Method and system for estimating average bandwidth in a communication network based on transmission control protocol
US8565249B2 (en) Queue management system and methods
CN110730469B (en) Method for predicting bandwidth based on extended Kalman wireless network and congestion control thereof
Wang et al. Using adaptive rate estimation to provide enhanced and robust transport over heterogeneous networks
CN113839840B (en) Bandwidth self-adaptive estimation method and system for bottleneck link of satellite network
US9948565B2 (en) Method and implementation of zero overhead rate controlled (ZORC) information transmission via digital communication link
CN105432054B (en) The method and apparatus for determining transmission buffer amount
KR100912178B1 (en) Congestion control method over wireless link
Liang et al. Smoothly estimate the RTT of fast TCP by ARMA function model
Casagrande et al. Tcpmoon: Monitoring the diffusion of tcp congestion control variants in the internet
Kampichler et al. Plain end-to-end measurement for local area network voice transmission feasibility
Qu An enhanced TCP Vegas algorithm based on route surveillance and bandwidth estimation over geo satellite networks
Lee et al. A two-phase TCP congestion control for reducing bias over heterogeneous networks
Satoh Optimum, stable, and fair flow control for packet networks
WO2017061075A1 (en) Control system, available bandwidth estimating system, device, method, and program
Yamasaki et al. Estimating TCP packet loss ratio from sampled ACK packets

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