CN111682975B - Network state prediction method, device, electronic equipment and storage medium - Google Patents

Abstract

The invention provides a network state prediction method, device, electronic equipment and storage medium. The method includes: when receiving the current data packet sent by the sending end, determining the network time consumption of the current data packet; calculating the network time of the historical data packet received within the preset time period before receiving the current data packet Time-consuming average value and discrete value, and calculating the weighted value of the average value and the discrete value; comparing the network time consumption of the current data packet with the weighted value, and determining the current network state according to the comparison result . The present invention can determine the current network state more accurately.

Description

Network state prediction method, device, electronic equipment and storage medium

technical field

The present invention relates to the field of network technology, in particular to a network state prediction method, device, electronic equipment and storage medium.

Background technique

With the rapid development of network technology, various network services appear in large numbers, such as video conferencing, video surveillance, videophone, and so on. A large number of data packets, such as audio data packets and video data packets, are transmitted in network services.

During the transmission of data packets, the network status has a great influence on the transmission of data packets. For example, if the network is in a congested state, it will lead to increased network transmission delay, serious packet loss, and even network paralysis. Therefore, how to accurately predict the network state is particularly important to improve the overall network performance.

Contents of the invention

In view of the above problems, embodiments of the present invention are proposed to provide a network state prediction method, device, electronic device, and storage medium that overcome the above problems or at least partially solve the above problems.

In the first aspect, the embodiment of the present invention discloses a network state prediction method, the method comprising:

When receiving the current data packet sent by the sending end, determine the network time consumption of the current data packet;

Calculating the average value and discrete value of the network time consumption of the historical data packets received within the preset time period before receiving the current data packet, and calculating the weighted value of the average value and the discrete value;

The network time consumption of the current data packet is compared with the weighted value, and the current network state is determined according to the comparison result.

Optionally, the weighted value includes a first weighted value and a second weighted value, the first weighted value is smaller than the second weighted value; the network time consumption of the current data packet and the weighted value Comparing, determining the current network state according to the comparison result, including: when the network time consumption of the current data packet is less than the first weighted value, determining that the current network state is a smooth state; when the network of the current data packet When the time-consuming is greater than or equal to the first weighted value and less than or equal to the second weighted value, it is determined that the current network state is a normal state; when the network time-consuming of the current data packet is greater than the second weighted value, Determine that the current network status is congested.

Optionally, the network state includes a smooth state, a normal state and a congestion state; after determining the current network state according to the comparison result, it also includes: when the current network state is a smooth state, notify the sending end to increase the sending rate ; When the current network state is congested, notify the sending end to reduce the sending rate.

Optionally, the weighted value includes a first weighted value and a second weighted value, and the first weighted value is smaller than the second weighted value; the notifying the sending end to increase the sending rate includes: according to the first weighted value A first difference obtained after subtracting the network time consumption of the current data packet from a weighted value, calculating the first lower limit sending rate, and subtracting the network time consumption of the current data packet according to the second weighted value to obtain The second difference, calculate the first upper limit sending rate, notify the sending end to increase the sending rate according to the first lower limit sending rate and the first upper limit sending rate; or obtain the packet loss within the preset time length rate, and notify the sending end to increase the sending rate according to the packet loss rate.

Optionally, the weighted value includes a first weighted value and a second weighted value, and the first weighted value is smaller than the second weighted value; the notifying the sending end to reduce the sending rate includes: according to the current The third difference obtained after subtracting the first weighted value from the network time consumption of the data packet, calculating the second lower limit sending rate, and subtracting the second weighted value from the network time consumption of the current data packet to obtain Calculate the second upper limit sending rate, notify the sending end to reduce the sending rate according to the second lower limit sending rate and the second upper limit sending rate; or obtain the packet loss within the preset time length rate, and notify the sending end to reduce the sending rate according to the packet loss rate.

Optionally, the discrete values are standard deviation or variance.

In the second aspect, the embodiment of the present invention discloses a network state prediction device, the device comprising:

A determining module, configured to determine the network time consumption of the current data packet when receiving the current data packet sent by the sending end;

A calculation module, configured to calculate the average value and discrete value of the network time consumption of the historical data packets received within the preset time period before receiving the current data packet, and calculate the average value and the discrete value weighted value;

A comparing module, configured to compare the network time consumption of the current data packet with the weighted value, and determine the current network state according to the comparison result.

Optionally, the weighted value includes a first weighted value and a second weighted value, and the first weighted value is smaller than the second weighted value; the comparison module includes: a first determining unit, configured to when the current When the network time consumption of the data packet is less than the first weighted value, it is determined that the current network state is a smooth state; the second determining unit is configured to when the network time consumption of the current data packet is greater than or equal to the first weighted value, And when it is less than or equal to the second weighted value, determine that the current network state is a normal state; a third determination unit is configured to determine the current network state when the network time consumption of the current data packet is greater than the second weighted value The state is congested.

Optionally, the network state includes a smooth state, a normal state, and a congestion state; the device further includes: a first notification module, configured to notify the sending end to increase the sending rate when the current network state is a smooth state; The second notification module is configured to notify the sending end to reduce the sending rate when the current network state is a congested state.

Optionally, the weighted value includes a first weighted value and a second weighted value, the first weighted value is smaller than the second weighted value; the first notification module is specifically configured to The first difference obtained after subtracting the network time consumption of the current data packet, calculating the first lower limit sending rate, and the second difference obtained after subtracting the network time consumption of the current data packet according to the second weighted value difference, calculate the first upper limit sending rate, notify the sending end to increase the sending rate according to the first lower limit sending rate and the first upper limit sending rate; or obtain the packet loss rate within the preset time length, and notify The sending end increases the sending rate according to the packet loss rate.

Optionally, the weighted value includes a first weighted value and a second weighted value, the first weighted value is smaller than the second weighted value; the second notification module is specifically configured to The third difference obtained after subtracting the first weighted value from the network time consumption, calculating the second lower limit sending rate, and the fourth difference obtained after subtracting the second weighted value from the network time consumption of the current data packet difference, calculate the second upper limit sending rate, notify the sending end to reduce the sending rate according to the second lower limit sending rate and the second upper limit sending rate; or obtain the packet loss rate within the preset time length, and notify The sending end reduces the sending rate according to the packet loss rate.

Optionally, the discrete values are standard deviation or variance.

In a third aspect, the embodiment of the present invention discloses an electronic device, including: one or more processors; and one or more machine-readable media with instructions stored thereon; when the instructions are executed by the one or more When a processor is executed, the processor is made to execute the network state prediction method described in any one of the above.

In a fourth aspect, the embodiment of the present invention discloses a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the network state prediction method described in any one of the preceding items is implemented.

In the embodiment of the present invention, when the receiving end receives the current data packet sent by the sending end, it determines the network time consumption of the current data packet; The average value and discrete value of the network time consumption of the historical data packet, and calculate the weighted value of the average value and the discrete value; compare the network time consumption of the current data packet with the weighted value, according to the comparison result Determine the current network status. It can be seen that, in the embodiment of the present invention, the average value represents the average network time consumption of the historical data packets, and the average value takes into account the interference factors in the respective transmission processes of the historical data packets. The discrete value represents the discrete degree of the network time consumption of the historical data packets, and the discrete value takes into account the change of the network state. Therefore, the current network state can be more accurately determined by using the weighted value of the average value and the discrete value as a judgment basis. However, if only discrete values are used as the basis for judgment, on the one hand, it is necessary to preset a threshold for comparison with the discrete value, which is an empirical value, so the accuracy of the judgment depends heavily on the empirical value; on the other hand, the discrete value It can only indicate the discrete degree of network time consumption, and does not take into account the interference factors in the transmission process, so the accuracy of judgment is poor.

Description of drawings

FIG. 1 is a flow chart of steps of a network state prediction method according to Embodiment 1 of the present invention.

FIG. 2 is a flowchart of steps of a network state prediction method according to Embodiment 2 of the present invention.

FIG. 3 is a schematic diagram of calculating average values and discrete values in Embodiment 2 of the present invention.

Fig. 4 is a structural block diagram of a network state prediction device according to Embodiment 3 of the present invention.

FIG. 5 is a structural block diagram of a network state prediction device according to Embodiment 4 of the present invention.

Detailed ways

In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

The network state prediction method in the embodiment of the present invention involves the process of transmitting data packets between the sending end and the receiving end. In the process of data packet transmission, any party in the communication can be the sender or the receiver. Wherein, the sending end and the receiving end may be devices with network communication functions such as smart phones, tablet computers, notebook computers, and Internet-of-Vision terminals (such as set-top boxes). The data packets transmitted between the sending end and the receiving end may be audio data packets, video data packets, and the like. Next, the network state prediction method will be described in detail through the following embodiments.

Embodiment one

Referring to FIG. 1 , it shows a flow chart of steps of a network state prediction method according to Embodiment 1 of the present invention. The network state prediction method in the embodiment of the present invention can be applied to the receiving end.

The network state prediction method in the embodiment of the present invention may include the following steps:

Step 101, when the receiving end receives the current data packet sent by the sending end, determine the network time consumption of the current data packet.

After the sending end encapsulates the data to be sent to the receiving end into a data packet, it sends the data packet to the receiving end. Each time the receiving end receives a data packet, it can mark the receiving time of the data packet, determine the network time consumption of the data packet, and store the receiving time and network time consumption of the data packet.

Step 102, the receiving end calculates the average value and discrete value of the network time consumption of the historical data packets received within the preset time period before receiving the current data packet, and calculates the average value and the discrete value weighted value.

After receiving the current data packet sent by the sending end, the receiving end determines the historical data packets received within the preset time period before receiving the current data packet according to the stored receiving time of each data packet, and according to the stored The network time consumption of each historical data packet received within the duration, and the average value and discrete value of the network time consumption of each historical data packet are calculated. The receiving end calculates the weighted value of the average value and the discrete value, and the weighted value serves as a basis for subsequent determination of the network state. Wherein, the discrete value can be standard deviation or variance.

Step 103, the receiving end compares the network time consumption of the current data packet with the weighted value, and determines the current network state according to the comparison result.

The receiving end compares the network time consumption of the current data packet with the weighted value calculated above, and determines the current network state according to the comparison result. The specific comparison process will be described in detail in the following examples.

In the embodiment of the present invention, the average value represents the average network time consumption of the historical data packets, and the average value takes into account the interference factors in the respective transmission processes of the historical data packets. The discrete value represents the discrete degree of the network time consumption of the historical data packets, and the discrete value takes into account the change of the network state. Therefore, the current network state can be more accurately determined by using the weighted value of the average value and the discrete value as a judgment basis. However, if only discrete values are used as the basis for judgment, on the one hand, it is necessary to preset a threshold for comparison with the discrete value, which is an empirical value, so the accuracy of the judgment depends heavily on the empirical value; on the other hand, the discrete value It can only indicate the discrete degree of network time consumption, and does not take into account the interference factors in the transmission process, so the accuracy of judgment is poor.

Embodiment two

Referring to FIG. 2 , it shows a flowchart of steps of a network state prediction method according to Embodiment 2 of the present invention. The network state prediction method in the embodiment of the present invention can be applied to the receiving end.

The network state prediction method in the embodiment of the present invention may include the following steps:

In step 201, a receiving end receives a data packet.

In the embodiment of the present invention, the sending end has a timing function. When the sending end sends a data packet, the sending end can use the timing function to obtain the sending time of the sent data packet according to the system clock of the sending end, and record the time in the sent data packet. Carry the sending time and send it to the receiving end.

Step 202, the receiving end parses the data packet.

Each time the receiving end receives a data packet, it parses the received data packet to obtain the sending time of the received data packet. In the embodiment of the present invention, the receiving end has a timing function, and each time the receiving end receives a data packet, it can use the timing function to obtain the receiving time of the received data packet according to the system clock of the receiving end.

Step 203, the receiving end calculates the network time consumption of the data packet.

Each time the receiving end receives a data packet, it calculates the network time consumption of the received data packet. For example, the receiving end can calculate the receiving time of the received data packet, subtract the time difference obtained after subtracting the sending time of the received data packet, and use the time difference as the network time consumption of the received data packet .

Step 204, the receiver stores the time.

For each received data packet, the receiving end stores the receiving time and network time consumption of the received data packet.

Step 205, the receiving end judges the network status. When the network state is a smooth state, execute step 206; when the network state is a congested state, execute step 207. When the network status is normal, there is no need to adjust the sending speed of the sender.

After receiving the current data packet sent by the sending end, the receiving end calculates the network time consumption of the current data packet through the above step 203 .

The receiving end determines the historical data packets received within the preset time period before receiving the current data packet according to the receiving time of each received data packet stored in step 204 above. And according to the network time consumption of each received data packet stored in step 204 above, the network time consumption of each historical data packet received within the preset time period before receiving the current data packet is obtained. And calculate the average value and discrete value of the network time consumption of each historical data packet received within the preset time period.

For the average value of the network time consumption of each historical data packet received within the preset time length, the sum of the network time consumption of each historical data packet received within the preset time length can be calculated, and the preset The total number of historical data packets received within the time period, and then calculate the ratio obtained by dividing the sum by the total number, and use the ratio as the average network time consumption of the historical data packets received within the preset time period. For example, the total number of historical data packets received within the preset duration is N, and the network time consumption of each historical data packet received within the preset duration is M ₁ , M ₂ , M ₃ ,  … , M _n , the average network time consumption of each historical data packet received within the preset time length is a, then a=(M ₁ +M ₂ +M ₃ +...+M _n )/N.

Discrete values can be standard deviation or variance.

In probability theory and statistics, the variance of a random variable describes its degree of dispersion, that is, the distance of the variable from its expected value. The variance is the average of the sum of squares of the deviations of each data from its arithmetic mean. The variance of the network time consumption of each historical data packet received within the preset time length may be the average of the square value of the difference between the network time consumption of each historical data packet received within the preset time length and the above average value number. For example, the total number of historical data packets received within the preset duration is N, and the network time consumption of each historical data packet received within the preset duration is M ₁ , M ₂ , M ₃ ,  … , M _n , the average value of the network time consumption of each historical data packet received within the preset time length is a, and the variance of the network time consumption of each historical data packet received within the preset time length is B, then B=[(M ₁ -a) ² +(M ₂ -a) ² +(M ₃ -a) ² +...+(M _n -a) ² ]/N.

In probability theory and statistics, standard deviation is used as a measure of the extent of a statistical distribution. In the physical sciences, for example, when making repeated measurements, the standard deviation of a set of measured values represents the precision of those measurements. The standard deviation of the measured value plays a decisive role when deciding whether the measured value corresponds to the predicted value: If the measured mean is too far from the predicted value (compared with the standard deviation value at the same time), the measured value and the predicted value are considered to be contradictory. The standard deviation is defined as the square root of the arithmetic mean of the square of the deviation between the standard value of each unit of the population and its mean, that is, the standard deviation is defined as the square root of the variance. Compared with the variance, the standard deviation can more accurately indicate the degree of dispersion. The standard deviation of the network time consumption of each historical data packet received within the preset time period may be the square root of the variance of the network time consumption of each historical data packet received within the preset time period. For example, if according to the above example of variance, the standard deviation of the network time consumption of each historical data packet received within the preset duration is b, then

The receiving end continues to calculate the weighted value of the above average and discrete values. In an optional implementation manner, the weighted value includes a first weighted value and a second weighted value, and the first weighted value is smaller than the second weighted value. Optionally, the weight of the average value in the first weighted value is the same as the weight of the average value in the second weighted value, and the weight of the discrete value in the first weighted value is smaller than the weight of the discrete value in the second weighted value. For example, the weight of the average value in the first weighted value and the weight of the average value in the second weighted value may both be 1. The weight of the discrete value in the first weighted value may be 1, and the weight of the discrete value in the second weighted value may be 2; or the weight of the discrete value in the first weighted value may be 1, and the weight of the discrete value in the second weighted value The weights in can be 3, and so on. For example, if the above-mentioned average value is a, and the discrete value is standard deviation b, then the first weighted value can be a+b, and the second weighted value can be a+2b; or the first weighted value can be a+b, and the second weighted value can be Values can be a+3b, etc. Specifically, related settings may be performed according to actual conditions, which is not limited in this embodiment of the present invention.

The receiving end compares the network time consumption of the current data packet with the weighted value, and determines the current network state according to the comparison result. In an optional implementation manner, when the network time consumption of the current data packet is less than the first weighted value, it is determined that the current network state is a smooth state; when the network time consumption of the current data packet is greater than or equal to the When the first weighted value is less than or equal to the second weighted value, it is determined that the current network state is a normal state; when the network time consumption of the current data packet is greater than the second weighted value, the current network state is determined is in a congested state. For example, the network time consumption of the current data packet is c, the first weighted value is a+b, and the second weighted value is a+2b, then when c<a+b, it is determined that the current network state is a smooth state; when a When +b≤c≤a+2b, it is determined that the current network state is a normal state; when c>a+b, it is determined that the current network state is a congested state.

For example, the network time consumption of the data packets received within the preset duration is 73, 72, 71, 69, 68, and 67 milliseconds respectively, and the calculated standard deviation of this group of network time consumption is 2.16, and the average value is 70 . FIG. 3 is a schematic diagram of calculating average values and discrete values in Embodiment 2 of the present invention. As shown in Figure 3, input the network time consumption of the data packets received in the preset duration, each network time consumption is separated by a comma, and the total number of groups, the average number, and the overall standard deviation (also That is, the above-mentioned standard deviation), the variance of the population standard deviation (that is, the above-mentioned variance). If the network time consumption of the current data packet is 65, then 65<70+2.16, indicating that the current network is in a smooth state; if the network time consumption of the current data packet is 75, then 75>70+2×2.16, indicating that the current network is congested Status; if the network time consumption of the current data packet is 73, then 70+2.16<73<70+2×2.16, indicating that the current network is in a normal state.

Step 206, the receiving end notifies the sending end to increase the sending rate.

When the receiving end determines that the current network status is unblocked, it may also notify the sending end to increase the sending rate.

In an optional implementation manner, the receiving end may calculate a first lower limit sending rate and a first upper limit sending rate according to the network time consumption of the current data packet, the first weighted value, and the second weighted value, And notify the sending end to increase the sending rate according to the first lower limit sending rate and the first upper limit sending rate. After receiving the notification, the sending end knows the first lower limit sending rate and the first upper limit sending rate, and can increase the current sending rate to the first lower limit sending rate and the first upper limit sending rate according to the actual situation. Any rate between rates (including the first lower limit sending rate and the first upper limit sending rate).

In an implementation, the sending end calculates a first difference obtained by subtracting the network time consumption of the current data packet from the first weighted value, and calculates a first lower limit sending rate according to the first difference. For example, the fifth difference obtained by subtracting the first difference from the network time consumption of the current data packet may be calculated, and then calculated by dividing the data amount of the current data packet by the fifth difference The first ratio is used as the first lower limit sending rate. For example, the number of current data packets is m, the network time consumption of the current data packets is c, the first weighted value is a+b, and the first lower limit sending rate is v1, then v1=m/[c-(a+b-c) ].

The sending end calculates a second difference obtained by subtracting the network time consumption of the current data packet from the second weighted value, and calculates a first upper limit sending rate according to the second difference. For example, it is possible to calculate the sixth difference obtained by subtracting the second difference from the network time consumption of the current data packet, and then calculate the data amount of the current data packet divided by the sixth difference The second ratio, using the second ratio as the first upper limit sending rate. For example, the number of current data packets is m, the network time consumption of the current data packets is c, the second weighted value is a+2b, and the first upper limit sending rate is v2, then v2=m/[c-(a+2b- c)].

In an optional implementation manner, the receiving end may obtain the packet loss rate within the preset time period, and notify the sending end to increase the sending rate according to the packet loss rate. After receiving the notification, the sending end knows the packet loss rate, and can increase the current sending rate by any percentage within (including the packet loss rate) according to the actual situation.

In implementation, the sending end can calculate the packet loss within the preset time length according to the number of data packets sent by the sending end within the preset time length and the number of data packets received by the receiving end within the preset time length Rate. For example, calculate the number of data packets sent by the sending end within the preset time period, subtract the number difference obtained after subtracting the number of data packets received by the receiving end within the preset time length, and then calculate the number difference divided by The ratio obtained after the number of data packets sent by the sending end within the preset time period is used as the packet loss rate.

Step 207, the receiving end notifies the sending end to reduce the sending rate.

When the receiving end determines that the current network state is congested, it can also notify the sending end to reduce the sending rate.

In an optional implementation manner, the receiving end may calculate a second lower limit sending rate and a second upper limit sending rate according to the network time consumption of the current data packet, the first weighted value, and the second weighted value, And notify the sending end to reduce the sending rate according to the second lower limit sending rate and the second upper limit sending rate. After receiving the notification, the sending end knows the second lower limit sending rate and the second upper limit sending rate, and may reduce the current sending rate to the second lower limit sending rate and the second upper limit sending rate according to the actual situation. Any rate between rates (including the second lower limit sending rate and the second upper limit sending rate).

In an implementation, the sending end calculates a third difference obtained by subtracting the first weighted value from the network time consumption of the current data packet, and calculates the second lower limit sending rate according to the third difference. For example, it is possible to calculate the first sum obtained by adding the network time consumption of the current data packet to the third difference, and then calculate the data volume of the current data packet divided by the first sum. A third ratio, using the third ratio as the second lower limit sending rate. For example, the number of current data packets is m, the network time consumption of the current data packets is c, the first weighted value is a+b, and the second lower limit sending rate is v3, then v3=m/[c+c-(a+ b)].

The sending end calculates a fourth difference obtained by subtracting the second weighted value from the network time consumption of the current data packet, and calculates a second upper limit sending rate according to the fourth difference. For example, it is possible to calculate the second sum obtained by adding the network time consumption of the current data packet to the fourth difference, and then calculate the data volume of the current data packet divided by the second sum. A fourth ratio, using the fourth ratio as the second upper limit sending rate. For example, the number of current data packets is m, the network time consumption of the current data packets is c, the second weighted value is a+2b, and the second upper limit sending rate is v4, then v4=m/[c+c-(a+ 2b)].

In an optional implementation manner, the receiving end may obtain the packet loss rate within the preset time period, and notify the sending end to reduce the sending rate according to the packet loss rate. After receiving the notification, the sending end knows the packet loss rate, and can reduce the current sending rate by any percentage within (including the packet loss rate) according to the actual situation.

In the embodiment of the present invention, the weighted value of the average value and the discrete value is used as the basis for judging the network state, the network state can be accurately predicted, the calculation process is more convenient, and the receiving end can also notify the sending end to adjust the sending rate accordingly according to the network state.

Embodiment three

Referring to FIG. 4 , it shows a structural block diagram of a device for network state prediction according to Embodiment 3 of the present invention.

The network state prediction device of the embodiment of the present invention may include the following modules:

The determination module 401 is configured to determine the network time consumption of the current data packet when receiving the current data packet sent by the sender.

Calculation module 402, configured to calculate the average value and discrete value of the network time consumption of historical data packets received within the preset time period before receiving the current data packet, and calculate the average value and the discrete value weighted value of .

The comparison module 403 is configured to compare the network time consumption of the current data packet with the weighted value, and determine the current network state according to the comparison result.

In the embodiment of the present invention, the average value represents the average network time consumption of the historical data packets, and the average value takes into account the interference factors in the respective transmission processes of the historical data packets. The discrete value represents the discrete degree of the network time consumption of the historical data packets, and the discrete value takes into account the change of the network state. Therefore, the current network state can be more accurately determined by using the weighted value of the average value and the discrete value as a judgment basis.

Embodiment Four

Referring to FIG. 5 , it shows a structural block diagram of an apparatus for network state prediction according to Embodiment 4 of the present invention.

The network state prediction device of the embodiment of the present invention may include the following modules:

The determination module 501 is configured to determine the network time consumption of the current data packet when receiving the current data packet sent by the sender.

Calculation module 502, configured to calculate the average value and discrete value of the network time consumption of historical data packets received within the preset time period before receiving the current data packet, and calculate the average value and the discrete value weighted value of .

The comparison module 503 is configured to compare the network time consumption of the current data packet with the weighted value, and determine the current network state according to the comparison result.

Optionally, the weighted value includes a first weighted value and a second weighted value, and the first weighted value is smaller than the second weighted value; the comparison module 503 includes: a first determining unit configured to When the network time consumption of the current data packet is less than the first weighted value, it is determined that the current network state is a smooth state; the second determination unit is used to determine when the network time consumption of the current data packet is greater than or equal to the first weighted value , and is less than or equal to the second weighted value, determine that the current network state is a normal state; the third determination unit is used to determine the current network state when the network time consumption of the current data packet is greater than the second weighted value The network status is congested.

Optionally, the network state includes a smooth state, a normal state, and a congestion state; the device further includes: a first notification module 504, configured to notify the sending end to increase the sending rate when the current network state is a smooth state ; The second notification module 505 is configured to notify the sending end to reduce the sending rate when the current network state is congested.

Optionally, the weighted value includes a first weighted value and a second weighted value, the first weighted value is smaller than the second weighted value; the first notification module 504 is specifically configured to The first difference obtained after subtracting the network time consumption of the current data packet from the value, calculates the first lower limit sending rate, and the first difference obtained after subtracting the network time consumption of the current data packet according to the second weighted value Two difference values, calculate the first upper limit sending rate, notify the sending end to increase the sending rate according to the first lower limit sending rate and the first upper limit sending rate; or obtain the packet loss rate within the preset time length, Informing the sending end to increase the sending rate according to the packet loss rate.

Optionally, the weighted value includes a first weighted value and a second weighted value, the first weighted value is smaller than the second weighted value; the second notification module 505 is specifically configured to The third difference obtained after subtracting the first weighted value from the network time consumption of the current data packet, the second lower limit sending rate is calculated, and the first difference obtained after subtracting the second weighted value from the network time consumption of the current data packet Four difference values, calculating the second upper limit sending rate, notifying the sending end to reduce the sending rate according to the second lower limit sending rate and the second upper limit sending rate; or, obtaining the packet loss rate within the preset time length, Informing the sending end to reduce the sending rate according to the packet loss rate.

Optionally, the discrete values are standard deviation or variance.

In the embodiment of the present invention, the network state can be accurately predicted, the calculation process is simpler, and the receiving end can also notify the sending end to adjust the sending rate accordingly according to the network state.

As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

In an embodiment of the present invention, an electronic device is also provided. The electronic device may include one or more processors and one or more machine-readable media having instructions, such as application programs, stored thereon. When the instructions are executed by the one or more processors, the processors are made to execute the above network state prediction method.

In an embodiment of the present invention, there is also provided a non-transitory computer-readable storage medium, on which a computer program is stored, and the program can be executed by a processor of an electronic device to complete the above-mentioned network state prediction method. For example, the non-transitory computer readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.

Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, devices, or computer program products. Accordingly, embodiments of the invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowcharts and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor or processor of other programmable data processing terminal equipment to produce a machine such that instructions executed by the computer or processor of other programmable data processing terminal equipment Produce means for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the The instruction means implements the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded into a computer or other programmable data processing terminal equipment, so that a series of operational steps are performed on the computer or other programmable terminal equipment to produce computer-implemented processing, thereby The instructions executed above provide steps for implementing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

Having described preferred embodiments of embodiments of the present invention, additional changes and modifications to these embodiments can be made by those skilled in the art once the basic inventive concept is appreciated. Therefore, the appended claims are intended to be interpreted to cover the preferred embodiment and all changes and modifications which fall within the scope of the embodiments of the present invention.

Finally, it should also be noted that in this text, relational terms such as first and second etc. are only used to distinguish one entity or operation from another, and do not necessarily require or imply that these entities or operations, any such actual relationship or order exists. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or terminal equipment comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements identified, or also include elements inherent in such a process, method, article, or end-equipment. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising said element.

A network state prediction method, device, electronic equipment, and storage medium provided by the present invention have been introduced above in detail. In this paper, specific examples are used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only It is used to help understand the method of the present invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation and scope of application. In summary, this The content of the description should not be construed as limiting the present invention.

Claims (10)

1. A method of predicting network status, the method comprising:

when a current data packet sent by a sending end is received, determining network time consumption of the current data packet, wherein the network time consumption of the data packet is a time difference value obtained by subtracting the sending time of the received data packet from the receiving time of the received data packet;

calculating an average value and a discrete value of network time consumption of a received historical data packet within a preset time period before the current data packet is received, and calculating a weighted value of the average value and the discrete value;

comparing the network time consumption of the current data packet with the weighted value, and determining the current network state according to the comparison result;

when the current network state is in an unblocked state, notifying the transmitting end to improve the transmitting rate;

the weighted values include a first weighted value and a second weighted value, the first weighted value being less than the second weighted value; the notifying the sending end to increase the sending rate includes:

calculating a fifth difference value obtained by subtracting the first difference value from the network time consumption of the current data packet, dividing the data volume of the current data packet by a first ratio obtained by dividing the fifth difference value, and taking the first ratio as a first lower limit sending rate, wherein the first difference value is obtained by subtracting the network time consumption of the current data packet according to the first weighting value;

calculating a sixth difference value obtained by subtracting a second difference value from the network time consumption of the current data packet, dividing the data volume of the current data packet by a second ratio obtained by dividing the sixth difference value, and taking the second ratio as a first upper limit sending rate, wherein the second difference value is obtained by subtracting the network time consumption of the current data packet according to the second weighting value;

and notifying the transmitting end to increase the transmitting rate according to the first lower limit transmitting rate and the first upper limit transmitting rate.

2. The method of claim 1, wherein the weight values comprise a first weight value and a second weight value, the first weight value being less than the second weight value; comparing the network time consumption of the current data packet with the weighted value, and determining the current network state according to the comparison result, wherein the method comprises the following steps:

when the network time consumption of the current data packet is smaller than the first weighting value, determining that the current network state is an unblocked state;

when the network time consumption of the current data packet is greater than or equal to the first weighted value and less than or equal to the second weighted value, determining that the current network state is a normal state;

and when the network time consumption of the current data packet is larger than the second weighted value, determining that the current network state is a congestion state.

3. The method of claim 1, wherein the network states include a clear state, a normal state, and a congested state; after determining the current network state according to the comparison result, the method further comprises:

and when the current network state is a congestion state, notifying the sending end to reduce the sending rate.

4. The method of claim 3, wherein the step of,

and acquiring the packet loss rate in the preset time length, and informing the sending end to improve the sending rate according to the packet loss rate.

5. A method according to claim 3, wherein the weighting values comprise a first weighting value and a second weighting value, the first weighting value being smaller than the second weighting value; the notifying the transmitting end to reduce the transmitting rate includes:

calculating a second lower limit sending rate according to a third difference value obtained by subtracting the first weighting value from the network time consumption of the current data packet, and calculating a second upper limit sending rate according to a fourth difference value obtained by subtracting the second weighting value from the network time consumption of the current data packet, and notifying the sending terminal to reduce the sending rate according to the second lower limit sending rate and the second upper limit sending rate;

or,

and acquiring the packet loss rate in the preset time length, and informing the sending end to reduce the sending rate according to the packet loss rate.

6. The method of claim 1, wherein the discrete value is a standard deviation or a variance.

7. A network state prediction apparatus, the apparatus comprising:

the determining module is used for determining network time consumption of the current data packet when the current data packet sent by the sending end is received, wherein the network time consumption of the data packet is a time difference value obtained by subtracting the sending time of the received data packet from the receiving time of the received data packet;

the calculation module is used for calculating the average value and the discrete value of the network time consumption of the received historical data packet within the preset time before the current data packet is received, and calculating the weighted value of the average value and the discrete value;

the comparison module is used for comparing the network time consumption of the current data packet with the weighted value and determining the current network state according to a comparison result;

the first notification module is used for notifying the transmitting end to increase the transmitting rate when the current network state is in an unblocked state;

the weighted values include a first weighted value and a second weighted value, the first weighted value being less than the second weighted value; the first notification module is specifically configured to calculate a fifth difference value obtained by subtracting a first difference value from the network time consumption of the current data packet, divide the data volume of the current data packet by a first ratio obtained by dividing the fifth difference value, and use the first ratio as a first lower limit sending rate, where the first difference value is obtained by subtracting the network time consumption of the current data packet according to the first weighting value; calculating a sixth difference value obtained by subtracting a second difference value from the network time consumption of the current data packet, dividing the data volume of the current data packet by a second ratio obtained by dividing the sixth difference value, and taking the second ratio as a first upper limit sending rate, wherein the second difference value is obtained by subtracting the network time consumption of the current data packet according to the second weighting value; and notifying the transmitting end to increase the transmitting rate according to the first lower limit transmitting rate and the first upper limit transmitting rate.

8. The apparatus of claim 7, wherein the weight values comprise a first weight value and a second weight value, the first weight value being less than the second weight value; the comparison module comprises:

a first determining unit, configured to determine that a current network state is an unblocked state when network time consumption of the current data packet is less than the first weighting value;

the second determining unit is used for determining that the current network state is a normal state when the network time consumption of the current data packet is greater than or equal to the first weighted value and less than or equal to the second weighted value;

and the third determining unit is used for determining that the current network state is a congestion state when the network time consumption of the current data packet is greater than the second weighting value.

9. An electronic device, comprising:

one or more processors; and

one or more machine-readable media having instructions stored thereon;

the instructions, when executed by the one or more processors, cause the processor to perform the network state prediction method of any one of claims 1 to 6.

10. A computer readable storage medium, having stored thereon a computer program which when executed by a processor implements the network state prediction method according to any one of claims 1 to 6.

Images