CN115668882A - Apparatus and method for measuring transmission channel - Google Patents

Abstract

The invention provides a device and a method for measuring a transmission channel. The transmission channel is measured by transmitting a transmission signal including a plurality of data packets to a destination. The destination responds to the data packet by sending an acknowledgement message that serves as a measurement result. The measurements are then processed to remove possible silent periods from the measurements. Next, the processed measurement results are smoothed to remove irregularities, data bursts, and the like from the processed measurement results. Finally, the smoothed measurement result may be left unprocessed or used to calculate the bandwidth and delay of the transmission channel.

Description

Apparatus and method for measuring transmission channel

Technical Field

The present invention relates generally to the field of telecommunications. More particularly, the present invention relates to an apparatus and method for measuring a transmission channel.

Background

Modern telecommunication networks are complex. These networks may include a number of different small networks maintained by different owners. These different small networks may have different qualities and technologies. Users of different networks are typically connected to the internet and counterparts such as servers responding to client requests may be located in different countries or states. Thus, the client network is connected to the server network through an international connection. Thus, the quality of the connection depends on several factors. In addition, current network conditions, such as the number of users, may cause significant temporal changes in the transmission channel conditions. For example, when there are many users, their requests may exceed the capacity of the transmission channel, and thus the bandwidth of the users may be lower than expected and the delay may be higher than expected.

Measuring the status of a transmission channel, internet access or any other network access may be important for various reasons. For example, traffic equalization algorithms need to know the current information of the transport channel state. Equalization may be used to route more data through the highest available capacity connection. If the available transport channels cannot be measured accurately, the equalization algorithm may select a low capacity transport channel instead of a high capacity transport channel. It is simple to measure the data transmission rate of incoming data at the receiving end, and difficult to measure the data transmission rate of the transmission channel at the transmitting end. The sender typically sends packets at the maximum available data transmission rate, which is typically represented by the data transmission rate of the most recent connection.

The only way to estimate the data transmission rate at the transmitting end is to receive an acknowledgement message from the receiving end. High channel delays may result in bursts in the observed transmission data rate due to irregularities in the incoming acknowledgement packets. Furthermore, packet loss can cause gaps in a series of consecutive acknowledgements, causing more bursts, which can increase measurement difficulty.

One-way channel delay cannot be accurately estimated on a physically distributed system. Only Round Trip Time (RTT) can be accurately measured when data is transmitted using the acknowledged transport protocol. RTT values can be obtained directly from connection characteristics (e.g. TCP sessions), but the assumption that the channel delay is equal to RTT/2 cannot be true (true), especially in mobile wireless networks, especially in LTE networks where the network device buffer is large.

Therefore, there is a need for an improved method of measuring a transmission channel.

Disclosure of Invention

An apparatus and method for measuring a transmission channel are provided in the present invention. The transmission channel is measured by transmitting a plurality of data packets to a destination. The destination responds to the data packet by sending an acknowledgement message that serves as a measurement result. The measurements are then processed to remove possible silent periods from the measurements. Next, the processed measurement results are smoothed to remove irregularities, data bursts, and the like from the processed measurement results. Finally, the smoothed measurement result may be left unprocessed or used to calculate the bandwidth and delay of the transmission channel.

A first aspect discloses a method for measuring a transmission channel. The method comprises the following steps: transmitting a transmission signal including a plurality of data packets to a destination; receiving a plurality of acknowledgments as measurement results in response to transmitting the transmission signal; detecting a quiet period in the transmission signal; deleting the detected quiet period from the measurement results; smoothing the measurement after the detected quiet period is removed from the measurement.

The first aspect may measure the transport channel in an uplink direction. Such measurements provide a basis for determining transmission bandwidth and delay. This can be conveniently achieved by removing quiet periods from the transmission and further smoothing out irregularities, bursts and similar events that reduce the reliability of the measurements. Deleting the quiet period and smoothing the irregularity can measure the transmission bandwidth and the time delay under the current condition. This allows transmission channels to be allocated to increase the bandwidth and latency of the implementation.

In an implementation manner of the first aspect, the smoothing process includes: a piecewise rational function is used to approximate the exponential bandwidth function. It is advantageous to use a piecewise function so that different parts of the exponential bandwidth function can be approximated by taking into account local features of the function. Furthermore, this is useful when the environment using the smoothing algorithm cannot perform the operation of calculating the necessary function. The environment of use may not be able to compute floating point numbers. The segmentation process may be computed without floating point numbers.

In a second implementation form of the first aspect, the smoothing process includes: and when the measurement result is rapidly reduced, smoothing the measurement result by using a maximum filter function. It is advantageous to use a maximum filter function for the measurement results, so that irregularities, data bursts and other temporary and local variations on the transmission channel can be eliminated from the measurement results. This provides a more reliable measurement result with respect to the overall measurement, since local irregularities distort the measurement result.

In a third implementation form of the first aspect, the method further includes: and calculating the bandwidth of the transmission channel according to the measurement result after the smoothing processing. Calculating the bandwidth of the transmission channel is advantageous because this information can be used directly in different applications that need information on the available bandwidth. Further, since the measurement result after the smoothing process is used as a basis for calculation, the calculated bandwidth corresponds to the currently available bandwidth, but does not include an irregular deviation.

In a fourth implementation form of the first aspect, the method further includes: the round trip time is determined by dividing the amount of data being transferred by the calculated bandwidth of the transmission channel. Calculating the round trip time of the data packet is beneficial because the round trip time can be used to calculate the one-way delay. The known on-going data is divided by the calculated bandwidth to obtain a reliable estimate of the round trip time.

In a fifth implementation form of the first aspect, the method further includes: a one-way delay value is estimated by multiplying the round trip time by a predetermined constant. Multiplying by a constant provides a simple and efficient way to approximate the delay.

In a sixth implementation form of the first aspect, the predetermined constant is 0.75. The constant 0.75 provides a reliable estimate in conventional devices due to the nature of the data path to the client.

A second aspect discloses a computer program comprising computer program code. The computer program code is for performing a method provided in accordance with the aspect or any discussed implementation. It is advantageous to implement the first aspect using a computer program that can be executed in a proxy server.

A third aspect discloses an apparatus for a transmission channel. The apparatus comprises processing circuitry to: transmitting a transmission signal including a plurality of data packets to a destination; receiving a plurality of acknowledgments as measurement results in response to the transmission; detecting a quiet period in the transmission signal; deleting the detected quiet period from the measurement results; smoothing the measurement after the detected quiet period is removed from the measurement.

The third aspect may measure a transport channel in an uplink direction. Such measurements provide a basis for determining transmission bandwidth and delay. This can be conveniently achieved by removing quiet periods from the transmission and further smoothing out irregularities, bursts and similar events that reduce the reliability of the measurements. Deleting the quiet period and smoothing the irregularity can measure the transmission bandwidth and the time delay under the current condition. This allows transmission channels to be allocated to increase the bandwidth and latency of the implementation.

In one implementation form of the third aspect, the processing circuit is configured to smooth the measurement result by approximating an exponential bandwidth function using a piecewise rational function. It is advantageous to use a piecewise function so that different parts of the exponential bandwidth function can be approximated by taking into account the local characteristics of the function. Furthermore, this is useful when the environment using the smoothing algorithm cannot perform the operation of calculating the necessary function. The environment of use may not be able to compute floating point numbers. The segmentation process may be computed without floating point numbers.

In a second implementation form of the third aspect, the processing circuit is configured to: and when the measurement result is rapidly reduced, smoothing the measurement result by using a maximum filter function. It is advantageous to use a maximum filter function for the measurement results, so that irregularities, data bursts and other temporary and local variations on the transmission channel can be eliminated from the measurement results. This provides a more reliable measurement result.

In a third implementation form of the third aspect, the processing circuit is further configured to calculate a bandwidth of the transmission channel according to the measurement result after the smoothing processing. Calculating the bandwidth of the transmission channel is advantageous because this information can be used directly in different applications that need information on the available bandwidth. In addition, since the measurement result after the smoothing process is used as a basis for calculation, the calculated bandwidth corresponds to the currently available bandwidth, but does not include irregular deviations.

In a fourth implementation form of the third aspect, the processing circuit is further configured to determine a round trip time by dividing an amount of data in transit by the calculated bandwidth of the transmission channel. Calculating the round trip time of the data packet is beneficial because the round trip time can be used to calculate the one-way delay. The known on-going data is divided by the calculated bandwidth to yield a reliable estimate of the round trip time.

In a fifth implementation form of the third aspect, the processing circuit is further configured to estimate a one-way delay value by multiplying the round trip time by a predetermined constant. Multiplying by a constant provides a simple and efficient way to approximate the delay.

In a sixth implementation form of the third aspect, the predetermined constant is 0.75. The constant 0.75 provides a reliable estimate in conventional devices due to the nature of the data path to the client.

The above aspects and implementations provide a more reliable method of measuring upstream bandwidth and delay. These aspects and implementations are beneficial because they can be implemented without significant changes to the underlying architecture. The principles discussed are applicable to different types of devices that need to measure the current state of the uplink channel.

Drawings

Other exemplary embodiments will be described in conjunction with the following drawings, in which:

fig. 1 shows one example of a block diagram of an apparatus for measuring a transmission channel;

FIG. 2 illustrates one example of a transmission;

FIG. 3 illustrates one example of data transfer rate estimation for file downloading using small chunks;

FIG. 4 illustrates one example of data transmission rate calculation with elimination of quiet periods;

FIG. 5 shows one example of a method for measuring a transmission channel;

FIG. 6 illustrates an example of a piecewise rational function;

FIG. 7 illustrates an example of an approximation function;

fig. 8 shows an example of applying a maximum filter function to the measured bandwidth values to remove irregularities.

In the following figures, the same reference numerals are used to denote the same or at least functionally equivalent features.

Detailed Description

The following description, taken in conjunction with the accompanying drawings, form a part hereof and show by way of illustration specific aspects of apparatus and methods in which the invention may be practiced. It is to be understood that other aspects may be utilized and structural or logical changes may be made without departing from the scope of the claims. The following detailed description is, therefore, not to be taken in a limiting sense.

For example, it is to be understood that the disclosure relating to the described method is equally applicable to the corresponding device or system for performing the method, and vice versa. For example, if a specific method step is described, the corresponding apparatus may comprise means for performing the described method step, even if such means are not explicitly described or illustrated in the figures. Further, it is to be understood that features of the various exemplary aspects described herein may be combined with each other, unless explicitly stated otherwise.

Detailed and very specific examples are given in the following description. These examples should be understood as a description of one possible way to implement transport channel measurements.

Fig. 1 shows one example of an apparatus for multi-channel data transmission presence for cell phones 100, tablets and similar devices. Cell phones 100, tablets and similar devices have a mobile connection 120 and a wireless lan connection 110. In this example, the proxy server 140 aggregates multiple streams from the handset 100 and sends the aggregated data to the web server 150. Accordingly, the proxy server 140 distributes data from the web server 150 over all available connections.

In the example of fig. 1, the handset 100 is a generic handset that includes circuitry for performing tasks common to mobile devices. Common tasks include making phone calls and using packet data connections, such as viewing or transmitting real-time video or browsing the world wide web. The handset 100 in this example is connected to the internet 130 using a mobile connection 120 and a wireless local area network connection 110, where the mobile connection 120 may be an LTE connection. The proxy server 140 includes circuitry for performing the usual tasks of a proxy server. The proxy server 140 acts as an intermediary for requests issued by the handset 100 and seeks resources from the web server 150. In the example of fig. 1, web server 150 provides real-time video to handset 100. The web server 150 includes circuitry for providing real-time video upon request from the mobile device 100. In the example of fig. 1, only one mobile device 100, one proxy server 140, and one web server 150 are shown, but this is for simplicity only. Proxy server 140 typically serves many more mobile devices and other devices. The common proxy server 140 and the web server 150 typically include multiple servers, and thus the mobile device's requests are distributed among the servers, such that the end user views the servers as one large server.

In the example of fig. 1, video stream data is requested from web server 150 using an HTTP GET request with a specified range of data to be transmitted. This method is very useful for dynamic changes in video quality. However, if the channel delay between the client (i.e., handset 100) and the web server 150 is significant, the data download will occur in bursts. This is further illustrated in fig. 2, a detailed description of which is provided below.

Fig. 2 shows an example of transmission when measuring a transmission channel. As can be seen in fig. 2, the client 200 transmits a request, such as an HTTP GET request. HTTP GET requests are used to retrieve and request data from a specified source in a server using hypertext transfer protocol. The client 200 transmits a first request 250 having a range of 0kB to 256 kB. The first request 250 is transmitted through the proxy server 210 to the server 220, and the server 220 may be a web server, similar to the web server 150 in fig. 1. Server 220 provides a response to client 200 through proxy server 210 in response to first request 250. The client 200 responds by sending an acknowledgement. Upon receiving the response of server 220, client 200 transmits a second request 260 similar to first request 250 but having a range of 256kB to 512 kB. The client 200 later receives a response to the second request 260 and the client 200 transmits a third request 270 to the server 220. Both transmission directions, i.e. the transmission direction from the client 200 to the server 220 and the transmission direction from the server 220 to the client 200, have silent periods, both providing requests and responses as bursts.

In such cases, it is difficult to determine the exact data transfer rate for the data transfer between the proxy server 210 and the client 200, since the acknowledgement packet from the client 200 appears in bursts and is not transmitted at all for a longer period of time. The direct calculation of the data transmission rate by means of the amount of data acknowledged in the time interval results in a variable value, and after a period of silence the estimated data transmission rate value decreases. This is illustrated in fig. 3, a detailed description of which is provided below.

Fig. 3 shows an example of data transfer rate estimation for file downloading using small chunks. The actual maximum bandwidth available to the user in the measurement is different, possibly depending on the current network conditions. In fig. 3, the y-axis corresponds to the data transmission rate of the transmission, in bits per second (referred to as "bps" in fig. 3). The x-axis corresponds to system time in seconds. The values shown are examples only and may be different when measurements are made during normal use of the data transmission device. In the example of fig. 3, it is assumed that the buffers in the network are empty. Thus, at the beginning of the measured transmission, a period of time to fill the buffer in the network may occur. This can be seen as an increase in the data transmission rate of the transmission at 300 in fig. 3. In the measurements, several quiet periods can be seen, such as an example of the identified quiet period 305. As can be seen from the measurements, after the quiet period 305, a data transmission rate drop occurs at 310. Furthermore, it can be seen from the measurements that a similar drop occurs after each similar quiet period. During the quiet period, the measured transmission channel is not used to transmit data. This temporary quiet period reduces the transmission data transmission rate, which is recovered during transmission, as shown at 320 in fig. 3. This reduction in data transmission rate results in a non-ideal data balance between channels. This reduces the aggregate data transmission rate.

When using measured transmissions to equalize data between several transmission channels, it is beneficial to accurately calculate the current bandwidth of one or more used transmission channels in order to move more data transmissions from a slow channel to a fast channel. If the measurement results shown in fig. 3 are not processed, the bandwidth of the transmission channel in fig. 3 may be reduced. Therefore, to reduce the degradation caused by quiet periods, a measurement device, such as proxy server 140 in fig. 1, detects quiet periods through TCP socket features and removes these quiet periods from the bandwidth calculation to obtain the actual current bandwidth of the transmission channel. This is illustrated in fig. 4, a detailed description of which is provided below.

Fig. 4 shows an example of data transmission rate calculation with elimination of silent periods. In the measurements, the actual maximum bandwidth available to the user is different, possibly depending on the current network conditions. In fig. 4, the y-axis corresponds to the data transmission rate of the transmission, in bits per second (referred to as "bps" in fig. 4). The x-axis corresponds to system time in seconds. The measurement results in fig. 4 are implemented using a transmission channel similar to the transmission channel in fig. 3. As with the example in fig. 3, at the beginning of the measured transmission, a period of time occurs to fill the buffer in the network. This can be seen as an increase in the data transmission rate of the transmission at 400 in fig. 4.

Fig. 4 shows the result of data transmission rate calculation for the transmission channel. After each quiet period at the beginning of the data transmission, the calculated data transmission rate rises, as shown at 405, to reach the actual value of the bandwidth available on the measured transmission channel. Thus, more fast channels can be used during equalization, thereby reducing the quiet periods. This improves the overall data transmission rate. When compared to fig. 3, it can be seen that there are few quiet periods 410 during which data is not transmitted over the channel. Thus, more data is sent over the channel. The data transmission rate is increased based on improved measurements, which helps to allocate resources more efficiently. One example of a method of improving the measurement is provided below in conjunction with fig. 5.

Fig. 5 discloses an example of a method of measuring a transmission channel. In the example of fig. 5, if the method is completed, the bandwidth and the delay to the transmission channel are measured. However, depending on the measurement, the method may also be stopped in step 508 or in any step after step 508. For example, if only the bandwidth of the transmission channel is needed, the method need not be continued after the bandwidth of the transmission channel is calculated.

In fig. 5, the method is initiated by transmitting a plurality of data packets in step 500. The transmission may be a specific measurement transmission or the data packet may be part of a normal transmission. In the example of fig. 5, the bandwidth and latency of such transmissions are measured. This is achieved by measuring the acknowledgement in step 502 in relation to the transmission in step 500. The received acknowledgement is the basis for the measurement result. The received acknowledgement corresponds to the transmission. Thus, if there is a quiet period in the transmission, it can be seen in the measurement results. In step 504, the measurements are processed by detecting a quiet period in the measurements. For example, the quiet period may be detected by analyzing the socket buffer and the number of packets being transmitted by the sender. A quiet period is found if the buffer is empty and no earlier transmitted packets wait for an acknowledgement. This will only start a new statistical calculation when the sender receives a new acknowledgement. At this time, the time collected in the statistical information is updated by the round trip time. The measurements may include one or more quiet periods. Then, in step 506, the detected quiet-period is deleted from the measurement results. For example, deleting the detected quiet-period may be accomplished simply by eliminating from the measurements the time period during which the detected quiet-period occurred. Thus, the data transmission rate indicated by the measurement results better corresponds to the current bandwidth of the transmission channel.

Finally, in step 508, the processed measurement results without the quiet period are smoothed. The purpose of the smoothing process is to remove portions where the measurement results fall off quickly. The smoothing may be applied to various irregularities and the purpose of the smoothing is to remove these irregularities, e.g. bursts, from the measurement results so that the measurement results better represent the overall situation. For example, the smoothing process may be performed by using an averaging window with a reduced weight and storing a small amount of additional data in the TCP socket data structure. Furthermore, this approximation (approximation) applies to any statistical value.

Even in the case where silent periods are not detected and deleted, smoothing is beneficial because the transmission may include bursts and the data distribution may not be ideal if there are measurements of bursts for data distribution between transmission channels. The smoothed measurements may be left unprocessed, e.g. for diagnostic purposes, or further processed, as shown in steps 510 to 514 below.

The bandwidth calculation in step 510 may be performed as follows. For arrival time of t _n Is carrying x _n A series of acknowledgements of individual bits, the following rules can be used to update the current estimate of bandwidth:

to approximate the exponential bandwidth function, a piecewise rational function may be used. Fig. 6 shows an example, and a detailed description is provided below.

After the bandwidth calculation in step 510, a round-trip time (RTT) is measured in step 512. The RTT value can be accurately measured. In modern networks, where the on-net buffer may be very large, it is wrong to estimate the one-way delay as RTT/2. A period of time to fill a buffer in the network may occur if the buffer is empty or only partially full at the beginning of the measured transmission. In the case where traffic arriving at the mobile device is much larger than traffic from the mobile device, the one-way delay depends to a large extent on the direction of the main traffic flow. When the main traffic flows to the mobile device, the one-way delay may be estimated in step 514 according to the following formula:

this equation represents the average between RTT/2 and RTT. The measured RTT value has a certain "inertia", and instead of displaying the current value, a certain state of the channel in the past is displayed. This is particularly evident when the channel is long and a smoothing algorithm is applied to the channel. The RTT value can be accurately calculated from the amount of data being transmitted (data that has been transmitted but has not been acknowledged) using the following formula:

where B is the currently calculated channel bandwidth, D _inflight Is the amount of data that has been sent but not yet acknowledged.

Figure 6 shows an example of a transmission based segmentation rational function. The piecewise function shown in FIG. 6 shows the result based on the exponential approximation used in the Linux kernel. The piecewise function shown in FIG. 6 is used to approximate the exponential bandwidth function because in the Linux kernel, it is not possible to use floating point numbers, and floating point numbers are typically required to compute the function that is approximated using the piecewise function. Therefore, this method is very useful when an environment using a smoothing algorithm cannot perform an operation of calculating a necessary function.

Considering a series of time points X ₀ <X ₁ <…<X _n And a series of rational functions, rational function R ₀ (x),R ₁ (x) \8230R _ n (x) is the ratio of two polynomials and the approximation can be written as follows:

for the experimental results, which are described in detail below, we implemented an exponential approximation method in the Linux kernel using the next parameter:

n＝2，X ₀ ＝0，

X ₂ =2, and

R ₀ (x)＝1-x，

R ₂ (x)＝0。

in this method, n represents the number of stages of the function in fig. 6. X ₀ 、X ₁ And X ₂ Representing the value of X indicating a point. The piecewise function in fig. 6 is defined by a number of sub-functions between these points. From X ₀ To X ₁ The piecewise function is formed by R ₀ (x) 1-X limit from X ₁ To X ₂ Piecewise function of

Is limited from X ₂ The piecewise function is formed by R ₂ (x) =0 limit.

The TCP congestion algorithm may have a very aggressive behavior when it comes to satisfying data loss. For example, the commonly used CUBIC algorithm greatly shortens the transmit window when data is lost. Other congestion control algorithms may be used instead of the CUBIC algorithm. This results in a reduction in the data sent, and therefore the calculated data transmission rate suddenly drops and returns to the previous value after a period of time. For equalization purposes, it is desirable to eliminate variations in the measured values that do not correspond to actual transmission channel variations.

To eliminate such value drops, a maximum filter function may be used, such that the rapidly dropping measurement values are smoothed and used as statistical values within c seconds. After c seconds, the statistical value begins to approximate the current measurement by calculating the next maximum value by a function h (x) that approximates the speed at which the current value is approximated from the minimum maximum measurement value. These values may be bandwidth or round trip time values. An example of such a function is h (x) =1-x, however, other approximating functions (approaches) may also be used, which may be determined in different ways in certain time intervals.

Fig. 7 shows an example of an approximation function. When t is _diff ＝t _now -t _max When-c (only at t) _now -t _max >c), a new maximum value can be calculated by means of an auxiliary function h (x) set at the time interval m, n selected for the measurement]Above, the rapid drop in value is included according to the following formula, as shown in FIG. 7:

in fig. 7, some points on the h (x) approximation function are shown. The start and end values of the interval m, n are shown. Further, the figure shows a point h (p), which can be determined as follows:

in fig. 7, a rapid decrease is observed in the time interval [ m, p ], and then a smoothing process is performed in the time interval [ p, n ]. The time interval p, n is set according to the determined value c. After c seconds, the statistical value starts to approximate the current measurement value by calculating the next maximum value by the function h (x), as described above. The value of c may be selected by the operator of the smoothing entity. One example of a value suitable for c is 0.5s. This is used in fig. 8 to further illustrate the maximum filter function.

Fig. 8 shows an example of smoothing processing using a maximum filter function. In fig. 8, the y-axis corresponds to the data transmission rate of the transmission in bits per second (referred to as "bps" in fig. 8). The x-axis corresponds to system time in seconds. The values shown are examples only and may differ when measurements are made during normal use of the data transmission device. Two measurements are described: one for the measured bandwidth values 810 and the other for the bandwidth values using the maximum filter function 800. Let h (x) =1-x, c =0.5s. As can be seen from fig. 8, the use of the maximum filter function allows to remove irregularities, and the resulting measurement results better describe the real state of the transmission channel. In fig. 8, the bandwidth measurement without using the maximum filter function includes several drops 820 in the data transmission rate. The large drop 830 is shown on the right side of fig. 8, so it can be seen that even though the measurement without the maximum filter function shows a drop in the measured data transmission rate, the measurement 800 does not change any significant during the drop when the maximum filter function is used.

The following table shows various measurements of the apparatus provided by examples of the present invention. Measurements are made in various combinations of Wi-Fi and LTE connections of different quality. As is apparent from the measurement results in the table below, the improvement obtained when using small chunks of download data is greatest in cases where one channel is fast and has little delay (hereinafter referred to as "strong") and the other channel is slow and has great delay (hereinafter referred to as "weak" or "very weak"). In such cases, the default bandwidth measurement algorithm reduces the data transmission rate of the fast channel, and in the dual channel mode, most of the data is transmitted over the slow, long channel. A method according to the above principles may be used to more accurately estimate the channel bandwidth. This results in moving the transmission of most data from a fast and short channel to a slow and long channel. In the table, "strong" means a bandwidth of at least 20Mbit/s and a delay of less than 50ms, "weak" means a bandwidth of at least 8Mbit/s and a delay of less than 800ms, "very weak" means a bandwidth of 2Mbit/s and a delay of at least 800ms.

TABLE 1

TABLE 2

TABLE 3

TABLE 4

TABLE 5

In each table, the file size for the transfer is 128 megabytes. These tables show measurements for different thread counts and different block sizes. The results include the current available bandwidth and aggregation ratio. The aggregation ratio is the ratio of the cumulative data transmission rate on two channels to the maximum possible data transmission rate on those channels, provided that each channel is used individually. It can be seen that the above method provides improved bandwidth when the situation is one connection good and the other connection significantly poor, but the strong Wi-Fi and weak LTE cases do not achieve improvement.

Tables 2 to 5 differ from table 1 in the number of threads. Further, the block size used is larger than that in table 1. As is apparent from tables 2, 3 and 4, the block sizes are 256 kilobytes, 512 kilobytes and 2 megabytes, respectively, all pairs achieving improvements except for the strong Wi-Fi and strong LTE cases. With a block size of 2 megabytes, the improvement is not as significant as with small block sizes of 256 kilobytes and 512 kilobytes. In table 5, a block size of 4 megabytes is used. With a block size of 4 megabytes, the improvement is not as significant and is limited to only one pair of strong and very weak connections.

The measurement results shown in tables 1 to 5 show that when the above principle is used, in most configurations, especially when the connection quality differs significantly, improved bandwidth and aggregation ratio can be achieved.

As mentioned above, the above-mentioned means for measuring a transmission channel may be implemented in hardware, such as a mobile phone, a tablet, a computer, a telecommunication network base station or any other network connection device, or as a method. The method may be implemented as a computer program. The computer program is then executed in the computing device.

The apparatus, for example for measuring a transmission channel, is adapted to perform one of the above-mentioned methods. The apparatus includes the necessary hardware components. These hardware components may include at least one processor, at least one memory, at least one network connection, a bus, and the like. For example, instead of dedicated hardware components, memory or processors may be shared with other components, or accessed from a cloud service, centralized computing unit, or other resource that may be used via a network connection.

An apparatus and corresponding method for measuring a transmission channel are described herein in connection with various embodiments. However, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. A computer program may be stored or distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the internet or other wired or wireless telecommunication systems.

Claims (15)

1. A method for measuring a transmission channel, the method comprising:

transmitting (500) a transmission signal comprising a plurality of data packets to a destination;

receiving (502) a plurality of acknowledgements as measurement results in response to transmitting the transmission signal;

detecting (504) a quiet period in the transmission signal;

deleting (506) the detected quiet-period from the measurements;

smoothing (508) the measurements after the detected quiet-period is removed from the measurements.

2. The method according to claim 1, wherein the smoothing process (508) comprises: a piecewise rational function is used to approximate the exponential bandwidth function.

3. The method according to claim 1 or 2, wherein the smoothing process (508) comprises: and when the measurement result is rapidly reduced, smoothing the measurement result by using a maximum filter function.

4. The method according to any one of claims 1 to 3, further comprising: -calculating (510) the bandwidth of the transmission channel based on the smoothed measurements.

5. The method of claim 4, further comprising: determining (512) a round trip time by dividing an amount of data being transferred by the calculated bandwidth of the transmission channel.

6. The method of claim 5, further comprising: a one-way delay value is estimated (514) by multiplying the round trip time by a predetermined constant.

7. The method of claim 6, wherein the predetermined constant is 0.75.

8. A computer program comprising computer program code for performing the method according to any of claims 1 to 7 when the computer program code is executed in a computing device.

9. An apparatus for measuring a transmission channel, the apparatus comprising processing circuitry to:

transmitting a transmission signal including a plurality of data packets to a destination;

receiving a plurality of acknowledgments as measurement results in response to transmitting the transmission signal;

detecting a quiet period in the transmission signal;

deleting the detected quiet period from the measurement results;

smoothing the measurement after the detected quiet period is removed from the measurement.

10. The apparatus of claim 9, wherein the processing circuit is configured to smooth the measurement by approximating an exponential bandwidth function using a piecewise rational function.

11. The apparatus of claim 9 or 10, wherein the processing circuitry is to: and when the measurement result is rapidly reduced, smoothing the measurement result by using a maximum filter function.

12. The apparatus according to any of claims 9 to 11, wherein the processing circuit is further configured to calculate a bandwidth of the transmission channel according to the smoothed measurement result.

13. The apparatus of claim 12, wherein the processing circuit is further configured to determine a round trip time by dividing an amount of data being transferred by the calculated bandwidth of the transmission channel.

14. The apparatus of claim 13, wherein the processing circuit is further configured to estimate a one-way delay value by multiplying the round trip time by a predetermined constant.

15. The apparatus of claim 14, wherein the predetermined constant is 0.75.

Images