阅读说明：本技术 数据传输的拥塞控制方法、装置、计算机设备和存储介质 (Congestion control method and device for data transmission, computer equipment and storage medium ) 是由 阮勇辉 王东 于 2021-10-15 设计创作，主要内容包括：本申请涉及一种数据传输的拥塞控制方法、装置、计算机设备和存储介质。所述方法通过获取探测信息,并将探测信息输入至带宽测算网络进行测算,得到各连接通道对应的目标网络带宽,再根据各连接通道对应的目标网络带宽对各连接通道上待传输的数据进行拥塞控制。上述方法由于利用带宽测算网络进行网络探测,再基于探测结果进行拥塞控制,实现了探测与控制分离的效果,克服了传统的拥塞控制算法因同时进行网络探测和控制带来的拥塞控制算法复杂度高和控制效果不佳的问题。而且,上述方法中利用带宽测算网络基于多个维度的探测信息进行了网络带宽测算,达到了准确和快速测算网络当前带宽的效果,从而提高业务数据传输的效率和稳定性。(The application relates to a congestion control method and device for data transmission, computer equipment and a storage medium. The method comprises the steps of obtaining detection information, inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain target network bandwidths corresponding to all the connecting channels, and carrying out congestion control on data to be transmitted on all the connecting channels according to the target network bandwidths corresponding to all the connecting channels. According to the method, the bandwidth measuring and calculating network is used for network detection, and then congestion control is performed based on the detection result, so that the effect of separation of detection and control is realized, and the problems of high complexity and poor control effect of a congestion control algorithm caused by simultaneous network detection and control in the traditional congestion control algorithm are solved. In addition, the method utilizes the bandwidth measuring and calculating network to measure and calculate the network bandwidth based on the detection information of multiple dimensions, and achieves the effect of accurately and quickly measuring and calculating the current bandwidth of the network, thereby improving the efficiency and stability of service data transmission.)

1. A method of congestion control for data transmission, the method comprising:

acquiring detection information, wherein the detection information comprises path loss information and equipment state information;

inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain target network bandwidths corresponding to the connection channels;

and carrying out congestion control on the data to be transmitted on each connecting channel according to the target network bandwidth corresponding to each connecting channel.

2. The method according to claim 1, wherein the bandwidth estimation network is a network trained in advance according to the probe information samples, or the bandwidth estimation network is an initial network to be trained.

3. The method according to claim 2, wherein the bandwidth measurement network is a network trained in advance according to probe information samples, and after performing congestion control on data transmitted on each of the connection channels according to a target network bandwidth corresponding to each of the connection channels, the method further comprises:

measuring to obtain actual network bandwidth corresponding to each connection channel after congestion control;

and determining whether the actual network bandwidth corresponding to each connection channel meets a preset condition, if so, continuing to use the current bandwidth measuring and calculating network for measuring and calculating, and if not, optimizing the current bandwidth measuring and calculating network and measuring and calculating by using the optimized bandwidth measuring and calculating network.

4. The method of claim 2, wherein the bandwidth measurement network is an initial network to be trained, and after performing congestion control on data transmitted on each of the connection channels according to a target network bandwidth corresponding to each of the connection channels, the method further comprises:

measuring to obtain actual network bandwidth corresponding to each connection channel after congestion control;

determining the change condition of network parameters according to the actual network bandwidth;

and adjusting parameters on the bandwidth measuring and calculating network according to the change condition of the network parameters, and measuring and calculating by using the bandwidth measuring and calculating network after the parameters are adjusted.

5. The method according to any one of claims 1-4, wherein the probe information is probe information within a preset time period.

6. The method of claim 1, wherein obtaining path loss information comprises:

receiving a detection signal sent by a base station and acquiring current environment information; the current environment information comprises at least one of weather information, shelter information and terrain information;

and determining the path loss information according to the signal strength of the detection signal and the current environment information.

7. The method according to claim 1 or 6, wherein performing congestion control on the data to be transmitted on each of the connection channels according to the target network bandwidth corresponding to each of the connection channels comprises:

determining a congestion control algorithm adaptive to each connecting channel according to the target network bandwidth corresponding to each connecting channel;

and starting a congestion control algorithm adaptive to each connecting channel, and performing congestion control on the data to be transmitted on each connecting channel respectively.

8. A method of congestion control for data transmission, the method comprising:

the acquisition module is used for acquiring detection information; the detection information comprises path loss information and equipment state information;

the measuring and calculating module is used for inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain target network bandwidths corresponding to the connection channels;

and the control module is used for carrying out congestion control on the data to be transmitted on each connecting channel according to the target network bandwidth corresponding to each connecting channel.

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.

Technical Field

The present application relates to the field of communication technologies of medical devices, and in particular, to a congestion control method and apparatus for data transmission, a computer device, and a storage medium.

Background

The 5G cellular network is a latest wireless network technology, has the characteristics of high working frequency band, large coverage area, capability of bearing a large amount of services, millimeter wave frequency band and the like, is widely applied to service communication in various industries, and particularly, in a medical scene, file contents transmitted by various services include but are not limited to DICOM, JPEG, audio and video and the like.

However, in the actual transmission process, the 5G cellular network has poor penetration and the air signal is sensitive to the obstruction, so performance indexes such as network bandwidth and time delay often fluctuate, and network packet loss may occur. Various service data are sent through a 5G cellular network, a transmission layer adopts a TCP protocol, when the 5G cellular network is unstable, conditions such as temporary bandwidth reduction, time delay increase or network packet loss can occur, and therefore a congestion control mechanism of the TCP protocol can be triggered to start, network throughput is greatly reduced, time delay is greatly increased, service data transmission efficiency is reduced finally, and transmission time is greatly increased. Therefore, how to improve the service data transmission efficiency becomes a technical problem to be solved urgently in the application of the 5G cellular network.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a congestion control method and apparatus for data transmission, a computer device, and a storage medium, which can improve the efficiency of service data transmission.

In a first aspect, a method for congestion control of data transmission, the method comprising:

acquiring detection information, wherein the detection information comprises path loss information and equipment state information;

inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain target network bandwidths corresponding to the connection channels;

and carrying out congestion control on the data to be transmitted on each connecting channel according to the target network bandwidth corresponding to each connecting channel.

In one embodiment, the bandwidth estimation network is a network trained in advance according to the probe information samples, or the bandwidth estimation network is an initial network to be trained.

In one embodiment, the bandwidth measurement and calculation network is a network obtained by training in advance according to a probe information sample, and after congestion control is performed on data transmitted on each connection channel according to a target network bandwidth corresponding to each connection channel, the method further includes:

measuring to obtain actual network bandwidth corresponding to each connection channel after congestion control;

and determining whether the actual network bandwidth corresponding to each connection channel meets a preset condition, if so, continuing to use the current bandwidth measuring and calculating network for measuring and calculating, and if not, optimizing the current bandwidth measuring and calculating network and measuring and calculating by using the optimized bandwidth measuring and calculating network.

In one embodiment, the bandwidth measurement and calculation network is an initial network to be trained, and after congestion control is performed on data transmitted on each connection channel according to a target network bandwidth corresponding to each connection channel, the method further includes:

measuring to obtain actual network bandwidth corresponding to each connection channel after congestion control;

determining the change condition of network parameters according to the actual network bandwidth;

and adjusting parameters on the bandwidth measuring and calculating network according to the change condition of the network parameters, and measuring and calculating by using the bandwidth measuring and calculating network after the parameters are adjusted.

In one embodiment, the probe information is probe information within a preset time period.

In one embodiment, the probe information further includes load characteristic information and/or interference information.

In one embodiment, obtaining path loss information comprises:

receiving a detection signal sent by a base station and acquiring current environment information; the current environment information comprises at least one of weather information, shelter information and terrain information;

and determining the path loss information according to the signal strength of the detection signal and the current environment information.

In one embodiment, the performing congestion control on the data to be transmitted on each connection channel according to the target network bandwidth corresponding to each connection channel includes:

determining a congestion control algorithm adaptive to each connecting channel according to the target network bandwidth corresponding to each connecting channel;

and starting a congestion control algorithm adaptive to each connecting channel, and performing congestion control on the data to be transmitted on each connecting channel respectively.

In a second aspect, an apparatus for congestion control of data transmission, the apparatus comprising:

the acquisition module is used for acquiring detection information; the detection information comprises path loss information and equipment state information;

the measuring and calculating module is used for inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain target network bandwidths corresponding to the connection channels;

and the control module is used for carrying out congestion control on the data to be transmitted on each connecting channel according to the target network bandwidth corresponding to each connecting channel.

In a third aspect, a computer device comprises a memory storing a computer program and a processor implementing the method of the first aspect when the processor executes the computer program.

In a fourth aspect, a computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the method of the first aspect described above.

According to the congestion control method and device for data transmission, the computer equipment and the storage medium, the detection information is obtained and input to the bandwidth measuring and calculating network for measurement and calculation, the target network bandwidth corresponding to each connection channel is obtained, and congestion control is performed on the data to be transmitted on each connection channel according to the target network bandwidth corresponding to each connection channel. According to the method, the bandwidth measuring and calculating network is used for network detection, and then congestion control is performed based on the detection result, so that the effect of separation of detection and control is realized, and the problems of high complexity and poor control effect of a congestion control algorithm caused by simultaneous network detection and control in the traditional congestion control algorithm are solved. In addition, the method utilizes the bandwidth measurement and calculation network to measure and calculate the network bandwidth based on the detection information of multiple dimensions, achieves the effect of accurately and quickly measuring and calculating the current bandwidth of the network, can avoid the phenomenon of over-control or under-control during the later-stage congestion control caused by inaccurate current network detection, and further can greatly improve the accuracy and the efficiency of the later-stage congestion control, thereby improving the efficiency and the stability of service data transmission. In addition, the traditional congestion control algorithm is based on a TCP/IP protocol to carry out network detection, the detection method has the problems of long detection time and prolonged time, and the congestion control method provided by the application can shorten the detection time and reduce the time delay because an independent bandwidth measuring and calculating network is used for carrying out network detection.

Drawings

Fig. 1 is a diagram of an application environment of a congestion control method for data transmission according to an embodiment;

fig. 2 is a flow chart illustrating a congestion control method for data transmission according to an embodiment;

fig. 3 is a flow chart illustrating a congestion control method for data transmission according to an embodiment;

fig. 4 is a flow chart illustrating a congestion control method for data transmission according to an embodiment;

FIG. 5 is a flowchart illustrating an implementation manner of S101 in the embodiment of FIG. 2;

FIG. 6 is a flowchart illustrating an implementation manner of S103 in the embodiment of FIG. 2;

fig. 7 is a flowchart illustrating a congestion control method for data transmission according to an embodiment;

fig. 8 is a flow chart illustrating a congestion control method for data transmission according to an embodiment;

fig. 9 is a schematic diagram of a congestion control system for data transmission in one embodiment;

fig. 10 is a block diagram showing the structure of a congestion control apparatus for data transmission according to an embodiment;

fig. 11 is a block diagram showing the structure of a congestion control apparatus for data transmission in one embodiment;

fig. 12 is a block diagram showing the structure of a congestion control apparatus for data transmission in one embodiment;

fig. 13 is a block diagram showing the structure of a congestion control apparatus for data transmission in one embodiment;

fig. 14 is a block diagram showing the structure of a congestion control apparatus for data transmission in one embodiment;

FIG. 15 is a diagram showing an internal structure of a computer device according to an embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The congestion control method for data transmission provided by the application can be applied to the application environment shown in fig. 1. The medical device 106 and the base station 104 communicate with each other through a network, and the application environment may be a network scenario of a 5G architecture, a network scenario of a 4G architecture, or a network scenario applied to both the 4G architecture and the 5G architecture. The medical device 106 interacts with the base station 104 to realize uplink and downlink transmission of service data, and when a data transmission link between the medical device 106 and the base station 104 is congested, a congestion control algorithm is configured in advance on the medical device 106, and when the congestion of the data transmission link is detected, congestion processing is performed on data to be transmitted by adopting a corresponding congestion control algorithm, so that the congestion problem of the data transmission link is solved, and the throughput of data transmission between the medical device 106 and the base station 104 is further improved. The congestion control algorithm may be various types of congestion control algorithms, and is not limited herein; the medical device 102 may be one or a combination of a plurality of diagnostic devices including an X-ray diagnostic device, an ultrasonic diagnostic device, a functional examination device, an endoscopic device, a nuclear medicine device, an experimental diagnostic device, and a pathological diagnosis device, or may be a treatment device including a surgical device, a radiotherapy device, and the like. Optionally, the control end of the medical device 106 may further include one or more of a PACS system, a HIS system, and a LIS system connected to the hospital via a medical dedicated cable, wherein the PACS system is an own patient film transmission system in the hospital; the HIS system is a patient basic data system; the LIS system is a test data system of a clinical laboratory; the doctor can directly retrieve and view the patient information already present in the hospital system in the operating room through the hub. The control end of the medical device 106 is not limited to various personal computers, laptops, smartphones, tablets and portable wearable devices, and the base station 104 may be any type of base station, such as a micro base station, a pico base station, etc.

Those skilled in the art will appreciate that the architecture shown in fig. 1 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the application environments in which the disclosed aspects may be used, and that a particular application environment may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

The file contents transmitted by various services in the existing medical scene include, but are not limited to, DICOM, JPEG, audio and video, and the like. The characteristics of the 5G cellular network include high speed, low time delay, high security, etc., which are theoretically ideal choices for file transmission, but in the actual transmission process, the 5G cellular network is sensitive to obstruction by air signals due to poor penetration and coverage, so performance indexes such as network bandwidth and time delay often fluctuate, and network packet loss may occur. Various files are sent through a 5G cellular network, a transmission layer adopts a TCP protocol, when the 5G cellular network is unstable, conditions such as temporary bandwidth reduction, time delay increase or network packet loss can occur, and the conditions can trigger a congestion control mechanism of the TCP protocol to start, so that the network throughput is greatly reduced, the time delay is greatly increased, the sending process of the files is reflected, namely the file transmission efficiency is reduced, and the transmission time is greatly increased. Therefore, the unstable characteristic of the 5G network part is relatively unique, but the traditional TCP protocol congestion control algorithm, such as Tahoe, Reno, CUBIC, BBR, etc., does not fully consider the unstable characteristic of the aerial part of the 5G cellular network, and cannot fully exert the performance of the 5G cellular network, thereby causing the problem of low transmission efficiency of service data in the 5G network.

In one embodiment, as shown in fig. 2, a congestion control method for data transmission is provided, which is described by taking the method as an example applied to the medical device in fig. 1, and includes the following steps:

s101, acquiring detection information.

Wherein the probe information includes path loss information and device state information. Optionally, the detection information further includes load characteristic information and/or interference information. The path loss information represents the loss of signal transmission between the base station and the medical device, and can be determined by the strength of the signal transmitted between the base station and the medical device or the stability of the signal transmitted between the base station and the medical device. The device status information indicates the transceiving status of the base station and the medical device for the signal, and specifically, the device status information may be the transmitting status of the medical device and the receiving status of the base station, or the transmitting status of the base station and the receiving status of the medical device, for example, whether the status of the receiving antenna of the medical device is abnormal or not. The load characteristic information refers to analysis of all network loads in a network link where data to be transmitted are located, and includes load characteristics, priority, a network Service Level Agreement (SLA), and the like; the interference information indicates the degree of interference or interference status of the medical device by signals or interference signals emitted by surrounding interfering devices.

In this embodiment, the medical device may detect the signal sent by the base station through a signal transceiver or a signal detection device mounted thereon, and further determine path loss information between the base station and the medical device according to a detection result; then, whether the detection signal transmitting and receiving device is abnormal or not is determined, equipment state information of the medical equipment is obtained, and then detection information is determined according to the path loss information and the equipment state information so as to be used later. When the detection information further comprises load characteristic information, the medical equipment can analyze the network load of the air network link to obtain the load characteristic information; when the detection information further includes interference information, the medical device may obtain the interference information by detecting an interference signal of another device.

S102, inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain the target network bandwidth corresponding to each connection channel.

The bandwidth measurement and calculation network is a network obtained by training in advance according to the detection information sample, or the bandwidth measurement and calculation network is an initial network to be trained. In practical applications, the bandwidth estimation network may be a neural network or a machine learning network, which is not limited herein. The target network bandwidth corresponding to each connection channel refers to the network bandwidth allocated to each connection channel, and the target network bandwidths of different connection channels may be the same or different.

In this embodiment, when the medical device acquires the probe information, the probe information may be further input to a bandwidth measurement and calculation network trained in advance to perform measurement and calculation, so as to measure and calculate network bandwidths corresponding to a plurality of connection channels at the same time, and obtain target network bandwidths corresponding to the connection channels; optionally, the medical device may also input the acquired detection information as a detection information sample to an initial network to be trained, train to obtain a bandwidth measurement and calculation network, and then directly input the acquired detection information to the trained bandwidth measurement and calculation network for measurement and calculation, so as to measure and calculate network bandwidths corresponding to the multiple connection channels at the same time, and obtain target network bandwidths corresponding to the connection channels.

S103, carrying out congestion control on the data to be transmitted on each connecting channel according to the target network bandwidth corresponding to each connecting channel.

The data to be transmitted may be any type of service data, for example, the data may include, but is not limited to, DICOM, JPEG, audio and video, and the like.

In this embodiment, when the medical device obtains the target network bandwidth corresponding to each measured connection channel, accurate detection of the current network performance is achieved, and then the medical device may determine a data transmission method, such as a data transmission rate, a data transmission amount, and the like, on each connection channel according to the target network bandwidth corresponding to each connection channel. And then, data transmission on each connecting channel is carried out according to the data transmission method on each connecting channel so as to realize congestion control on each connecting channel. It should be noted that the data transmission methods on different connection channels may be the same or different.

The congestion control method for data transmission obtains the detection information, inputs the detection information into the bandwidth measuring and calculating network for measuring and calculating to obtain the target network bandwidth corresponding to each connection channel, and then performs congestion control on the data to be transmitted on each connection channel according to the target network bandwidth corresponding to each connection channel. According to the method, the bandwidth measuring and calculating network is used for network detection, and then congestion control is performed based on the detection result, so that the effect of separation of detection and control is realized, and the problems of high complexity and poor control effect of a congestion control algorithm caused by simultaneous network detection and control in the traditional congestion control algorithm are solved. In addition, the method utilizes the bandwidth measurement and calculation network to measure and calculate the network bandwidth based on the detection information of multiple dimensions, achieves the effect of accurately and quickly measuring and calculating the current bandwidth of the network, can avoid the phenomenon of over-control or under-control during the later-stage congestion control caused by inaccurate current network detection, and further can greatly improve the accuracy and the efficiency of the later-stage congestion control, thereby improving the efficiency and the stability of service data transmission. In addition, the traditional congestion control algorithm is based on a TCP/IP protocol to carry out network detection, the detection method has the problems of long detection time and prolonged time, and the congestion control method provided by the application can shorten the detection time and reduce the time delay because an independent bandwidth measuring and calculating network is used for carrying out network detection.

In one application, when the used bandwidth calculating network is a network trained in advance according to probe information samples, after performing the step S103 "congestion control is performed on data transmitted on each connection channel according to a target network bandwidth corresponding to each connection channel", as shown in fig. 3, the method in the embodiment of fig. 2 further includes:

and S104, measuring to obtain the actual network bandwidth corresponding to each connection channel after congestion control.

After the medical device performs congestion control on the data to be transmitted of each connection channel based on the step S103, in order to evaluate the congestion control effect, the actual network bandwidth corresponding to each connection channel may be further measured, so as to determine the congestion control effect according to the actual network bandwidth.

And S105, determining whether the actual network bandwidth corresponding to each connection channel meets a preset condition, if so, executing the step S106, and if not, executing the step S107.

And S106, continuing to use the current bandwidth measuring and calculating network for measuring and calculating.

S107, optimizing the current bandwidth measuring and calculating network, and measuring and calculating by using the optimized bandwidth measuring and calculating network.

The preset conditions are used for measuring whether the congestion control effect reaches the standard or not, and if the actual network bandwidth corresponding to each connection channel meets the preset conditions, the control effect after congestion control reaches the standard before, that is, the data transmission efficiency on each connection channel is extremely high at present; if the actual network bandwidth corresponding to each connection channel does not meet the preset condition, it indicates that the control effect after congestion control is not good enough before, that is, the data transmission efficiency on each connection channel is low at present.

In practical application, after congestion control, whether the measured actual network bandwidth corresponding to each connection channel meets a preset condition is further determined, if yes, the currently used bandwidth measuring and calculating network plays a role in accurately measuring and calculating the network bandwidth, so that the current bandwidth measuring and calculating network can be continuously used for measuring and calculating, or the currently used congestion control method is more effective, and the current congestion control method can be used for continuously carrying out congestion control; if the current bandwidth measurement and calculation network is not met, the currently used bandwidth measurement and calculation network is possibly inaccurate in measurement and calculation, so that the current bandwidth measurement and calculation network needs to be further optimized, and congestion control is performed again after the optimized bandwidth measurement and calculation network is used for measurement and calculation; or the effect of the currently used congestion control method is poor, a new congestion control method needs to be determined after measurement and calculation are carried out according to the optimized bandwidth measurement and calculation network again, and congestion control is carried out according to the new congestion control method until the actual network bandwidth corresponding to each connection channel meets the preset condition.

In the method of the embodiment, after congestion control is performed on data transmitted on each connection channel, the actual network bandwidth after congestion control can be further measured to determine the congestion control effect, and then whether measurement and calculation of the bandwidth measurement and calculation network are accurate is evaluated according to the congestion control effect, so that the bandwidth measurement and calculation network is optimized in time, and the bandwidth measurement and calculation network in use can always maintain accurate measurement and calculation capability.

In another application, when the used bandwidth calculating network is an initial network to be trained, after performing the step S103 "congestion control is performed on data transmitted on each connection channel according to a target network bandwidth corresponding to each connection channel", as shown in fig. 4, the method in the embodiment of fig. 2 further includes:

and S108, measuring to obtain the actual network bandwidth corresponding to each connection channel after congestion control.

After the medical device performs congestion control on the data to be transmitted of each connection channel based on the step S103, in order to evaluate whether the target network bandwidth calculated by the currently used bandwidth prediction network is accurate, the actual network bandwidth corresponding to each connection channel may be further measured, so as to determine the measurement and calculation effect of the bandwidth prediction network according to the actual network bandwidth.

And S109, determining the change condition of the network parameters according to the actual network bandwidth.

Wherein the network parameter includes at least one parameter of network throughput, network delay, network data transmission rate, etc. When the medical device measures and obtains the actual network bandwidth after congestion control, the current network parameter can be further obtained through calculation according to the actual network bandwidth, and the current network parameter is compared with the network parameter before congestion control to determine the change condition of the network parameter, so that whether a congestion control algorithm determined based on the measurement and calculation result of the bandwidth measurement and calculation network in the network achieves the best congestion control effect or not is evaluated according to the change condition of the network parameter, the congestion control effect is related to the measurement and calculation accuracy of the bandwidth measurement and calculation network, the more accurate the bandwidth measurement and calculation network is, the better the congestion control effect is, the more inaccurate the bandwidth measurement and calculation network is, the worse the congestion control effect is, and therefore, the congestion control effect is evaluated, namely, whether the bandwidth measurement and calculation network is accurate is evaluated.

S110, adjusting the parameters on the bandwidth measuring and calculating network according to the change condition of the network parameters, and measuring and calculating by using the bandwidth measuring and calculating network after the parameters are adjusted.

If the change condition of the network parameter indicates that the network parameter after congestion control meets the network stability requirement, determining that the congestion control effect after congestion control is better, for example, if the network delay after congestion control is reduced, the previous congestion control achieves the optimal congestion control effect; if the change condition of the network parameters indicates that the network parameters after congestion control do not meet the network stability requirement, it is determined that the congestion control effect after congestion control is poor and does not achieve the expected congestion control effect, which indicates that the measurement and calculation results of the bandwidth measurement and calculation network may be inaccurate before, thereby causing the congestion control effect of the congestion control algorithm determined based on the measurement and calculation results to be unsatisfactory in the later period.

Optionally, in an application environment where the bandwidth calculating network is an initial network to be trained, when a change condition of a network parameter is determined according to an actual network bandwidth, it may be further determined whether the change condition of the network parameter meets a preset network requirement, if so, the parameter on the bandwidth calculating network is adjusted, and the step of acquiring the detection information is executed based on the bandwidth calculating network after the parameter adjustment until the change condition of the network parameter meets the preset network requirement, and the finally obtained bandwidth calculating network after the parameter adjustment is used for calculating.

If the change condition of the network parameters does not meet the preset network requirement, the initial network to be trained is not trained, namely the currently used bandwidth prediction network is not a network capable of accurately predicting the network bandwidth and needs to be trained continuously; if the change condition of the network parameters meets the preset network requirement, the initial network to be trained is trained, namely the currently used bandwidth prediction network is a network capable of accurately predicting the network bandwidth, and under the condition, the currently trained initial network can be used as a bandwidth measurement and calculation network for measuring and calculating the network bandwidth, so that the effect of accurately measuring and calculating the network bandwidth is achieved.

In practical application, after preliminary congestion control, further determining whether the change condition of network parameters meets preset network requirements, if not, indicating that the current initial network to be trained is not trained, training is required to be continued, specifically, adjusting the parameters of the bandwidth measurement and calculation network is required, acquiring detection information again, inputting new detection information into the bandwidth measurement and calculation network after parameter adjustment to measure and calculate the current network bandwidth again, realizing congestion control on the current data to be transmitted according to the target network bandwidth calculated again, then measuring the actual network bandwidth corresponding to each connection channel again, determining the change condition of the network parameters based on the actual network bandwidth measured again, determining whether the training of the initial network to be trained is finished based on the change condition of the network parameters, and repeating the steps in the same way, and (4) until the change condition of the network parameters meets the preset network requirement, namely, until the training of the initial network to be trained is finished. If the change condition of the network parameters meets the preset network requirement, the current initial network to be trained is trained, and then the trained bandwidth measuring and calculating network (bandwidth measuring and calculating network) can be used for measuring and calculating the current network bandwidth, so that congestion control is performed on data to be transmitted according to the target network bandwidth measured and calculated by the bandwidth measuring and calculating network. The embodiment realizes the method for directly using the trained bandwidth measuring and calculating network to measure and calculate the bandwidth after the bandwidth measuring and calculating network is trained in the actual application process, and can realize the timely optimization of the bandwidth measuring and calculating network by combining the actual network state, thereby improving the accuracy of the bandwidth measuring and calculating network measurement and calculation. In addition, an offline training bandwidth measuring and calculating network is not needed, the detection information collected in practical application is effectively utilized, and the purpose of efficiently training the bandwidth measuring and calculating network can be achieved, so that the congestion control efficiency of data to be transmitted in the later period is improved, and the transmission efficiency of the data to be transmitted is improved.

Optionally, the present application further provides a method for obtaining path loss information, as shown in fig. 5, the method includes:

s201, receiving a detection signal sent by a base station, and acquiring current environment information.

The current environment information includes at least one of weather information, shelter information, and terrain information, where the weather information may be, for example, cloudy, sunny, rainy and snowy, a maximum temperature, a minimum temperature, a wind direction, a wind force, and the like in a space region between the base station and the medical device within a preset time period. As another example, typical current environmental information includes: rain fade, shadow fade, leaf fade, atmospheric absorption, terrain/humidity, fresnel blockage, etc.

In this embodiment, the medical device may be provided with a wireless signal transceiver, the wireless transceiver is enabled to receive the detection signal sent by the base station, and the current environment information of the environment between the base station and the medical device is obtained at the same time, specifically, the current environment information may be obtained from the cloud server, the current environment information may also be obtained from the base station side, or the current environment information updated in real time is stored locally.

And S202, determining path loss information according to the signal strength of the detection signal and the current environment information.

In this embodiment, a wireless signal propagation loss analyzer may be disposed on the medical device in advance, and when the medical device receives the detection signal, the wireless signal propagation loss analyzer analyzes the detection signal to obtain the signal intensity of the real-time detection signal, for example, the wireless signal propagation loss analyzer is disposed on the 5G base station and the medical device respectively, during the file transmission process, the medical device serves as a 5G signal transmitting end, the 5G base station serves as a 5G signal receiving end, and the wireless signal propagation loss analyzer is disposed at both ends respectively to simulate the 5G signal transmitting intensity to obtain the real-time 5G signal intensity. The late-stage medical device may determine path loss information based on the signal strength of the probe signal in combination with current environmental information. The method for determining the path loss information fully considers the current environment information of signal transmission, and can improve the accuracy of obtaining the path loss information.

Optionally, when the medical device executes the step S103 of performing congestion control on the data to be transmitted on each connection channel according to the target network bandwidth corresponding to each connection channel, as shown in fig. 6, the steps may be specifically executed:

s301, determining a congestion control algorithm adaptive to each connection channel according to the target network bandwidth corresponding to each connection channel.

The congestion control algorithm is used to implement congestion control of the current network, for example, the congestion control algorithm may be Tahoe, Reno, CUBIC, BBR, or the like.

In this embodiment, when the medical device determines the target network bandwidth corresponding to each connection channel, the congestion control algorithm used in each connection channel may be further determined according to the target network bandwidth corresponding to each connection channel, and the congestion control algorithms used in each connection channel may be the same or different. It should be noted that, since the target network bandwidths corresponding to the connection channels may be the same or different, the determined congestion control algorithms used on the connection channels may be the same or different. If the congestion control algorithms are the same, the congestion control is carried out on the data to be transmitted on each connecting channel by adopting the same congestion control algorithm, and if the congestion control algorithms are different, the congestion control is carried out on the data to be transmitted on each connecting channel by adopting different congestion control algorithms sequentially or simultaneously. In addition, the medical device may pre-store a corresponding relationship between the network bandwidth and the congestion control algorithm, and when the medical device determines the congestion control algorithm adapted to each connection channel according to the target network bandwidth corresponding to each connection channel, the medical device may determine the corresponding congestion control algorithm according to the target network bandwidth according to the corresponding relationship, for example, a list recording a corresponding relationship between the network bandwidth and the congestion control algorithm is pre-stored on the medical device, and when the congestion control algorithm adapted according to the target network bandwidth is determined, the congestion control algorithm corresponding to each target network bandwidth may be screened by querying the list, for example, the target network bandwidth a corresponds to the congestion control algorithm a, and the target network bandwidth B corresponds to the congestion control algorithm B. It can be understood that different target network bandwidths may correspond to different congestion control algorithms, different target network bandwidths may correspond to the same congestion control algorithm, and the correspondence between the network bandwidths and the congestion control algorithms is determined according to actual control requirements.

S302, starting a congestion control algorithm adaptive to each connection channel, and performing congestion control on the data to be transmitted on each connection channel respectively.

In this embodiment, when the medical device determines the congestion control algorithm adapted to each connection channel based on the foregoing steps, the congestion control algorithm adapted to each connection channel may be used to perform congestion control on the data to be transmitted on each connection channel, so as to maintain stable and efficient transmission of the data to be transmitted in the entire network. It should be noted that the congestion control algorithm in this embodiment does not need to perform network detection any more, but focuses on performing congestion control on a network, and is different from a conventional congestion control algorithm (e.g., Tahoe) that a network bandwidth needs to be detected through a TCP/IP protocol.

In summary of the foregoing embodiments, the present application further provides a congestion control method for data transmission, as shown in fig. 7, the method includes:

s401, receiving a detection signal sent by a base station, and acquiring current environment information.

And S402, determining path loss information according to the signal strength of the detection signal and the current environment information.

And S403, determining detection information according to the path loss information and the acquired equipment state information.

S404, inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain the target network bandwidth corresponding to each connection channel.

S405, determining a congestion control algorithm adaptive to each connection channel according to the target network bandwidth corresponding to each connection channel.

S406, a congestion control algorithm adaptive to each connection channel is started, and congestion control is performed on the data to be transmitted on each connection channel respectively.

S407, measuring to obtain actual network bandwidth corresponding to each connection channel after congestion control

And S408, determining whether the actual network bandwidth corresponding to each connection channel meets a preset condition, if so, executing the step S409, and if not, executing the step S410.

And S409, continuing to use the current bandwidth measuring and calculating network for measuring and calculating.

S410, optimizing the current bandwidth measuring and calculating network, and measuring and calculating by using the optimized bandwidth measuring and calculating network.

The above steps are all explained, and please refer to the above contents for details, which are not described herein.

In summary of the foregoing embodiments, the present application further provides another congestion control method for data transmission, as shown in fig. 8, the method includes:

s501, receiving a detection signal sent by a base station, and acquiring current environment information.

And S502, determining path loss information according to the signal strength of the detection signal and the current environment information.

And S503, determining detection information according to the path loss information and the acquired equipment state information.

S504, the detection information is input to a bandwidth measuring and calculating network for measuring and calculating to obtain the target network bandwidth corresponding to each connection channel.

And S505, determining a congestion control algorithm adaptive to each connection channel according to the target network bandwidth corresponding to each connection channel.

S506, starting a congestion control algorithm adaptive to each connection channel, and performing congestion control on the data to be transmitted on each connection channel respectively.

And S507, measuring to obtain the actual network bandwidth corresponding to each connection channel after congestion control.

And S508, determining the change condition of the network parameters according to the actual network bandwidth.

S509, adjusting parameters on the bandwidth measuring and calculating network according to the change condition of the network parameters, and measuring and calculating by using the bandwidth measuring and calculating network after the parameters are adjusted.

The above steps are all explained, and please refer to the above contents for details, which are not described herein.

Based on the methods described in all the above embodiments, the present application further provides a congestion control system for data transmission, as shown in fig. 9, the system includes: the device comprises a detection module and a control module, wherein the detection module comprises a path loss detection unit, an equipment state detection unit, a load characteristic detection unit, other information detection units and a machine learning unit. The control module comprises control units corresponding to all the connection channels (for example, a control unit corresponding to a TCP connection channel 1 and a control unit corresponding to a TCP connection channel 2 which are arranged in parallel in FIG. 9)

The path loss detection unit is used for acquiring path loss information, the equipment state detection unit is used for acquiring equipment state information, the load characteristic detection unit is used for acquiring load characteristic information, and the other information detection units are used as expansion interfaces and used for acquiring other types of detection information; the machine learning module is used for learning according to detection information acquired by the path loss detection unit, the equipment state detection unit, the load characteristic detection unit and the other information detection units, so that network bandwidth of each connection channel is detected or distributed, and target network bandwidth of each connection channel is obtained.

The control unit corresponding to the TCP connection channel 1 is used for realizing congestion control on the service data on the TCP connection channel 1 according to the target network bandwidth on the connection channel output by the detection module; and the control unit corresponding to the TCP connection channel 2 is used for realizing congestion control on the service data on the TCP connection channel 2 according to the target network bandwidth on the connection channel output by the detection module. Specifically, the method for implementing congestion control by applying the congestion control system for data transmission may refer to the method described in the foregoing embodiment, which is not described herein again.

In one application, when the detection module obtains the detection information including the path loss information, the device state information, the load characteristic information, and the like, the detection module may specifically obtain the detection information within a preset time period, that is, obtain the detection information within a network stable time period, and then send a detection result determined by the detection information to the control module for congestion control, so that a problem that the control module performs invalid congestion control based on the detection result due to inaccurate detection information obtained by the detection module at a jitter time point due to network jitter can be avoided. For example, in a 5G network, when the 5G millimeter waves are transmitted, network jitter is easily caused by factors such as environment, weather and shielding, and the detection information acquired by the detection module is inaccurate, the detection result is also inaccurate, so that if congestion control is performed based on the inaccurate detection result, there is no doubt, a good congestion control effect cannot be achieved, and fluctuation of the whole network is also caused. The preset time period may be determined in advance according to an actual detection requirement, and is not limited herein.

The congestion control system for data transmission builds a control framework for separating detection and control, the detection and separation are designed independently and do not interfere with each other, so that a congestion control algorithm used by the control module does not need to detect the network bandwidth any more, and is concentrated on controlling the network, the complexity of the congestion control algorithm can be reduced, and the congestion control efficiency is improved. Moreover, the method is free from the control constraint during detection, can calculate the network bandwidth through technologies other than TCP/IP, considers more influencing factors, improves the detection speed and accuracy, and better copes with the burst state. In addition, the control system also predicts the network bandwidth through a machine learning unit, allows a control module to take measures before network congestion to avoid congestion, and realizes intelligent congestion control. And in a medical scene, in consideration of the aspects of path loss, load characteristics, equipment state and the like in the file transmission process, bandwidth calculation is carried out by analyzing the multi-dimensionally collected detection information, and the accuracy of bandwidth detection is improved. The congestion control system provided by the application can use any congestion control algorithm without recreating the congestion control algorithm only by slightly changing the existing congestion control algorithm, so that the congestion control system can be compatible with all existing congestion control algorithms, and has extremely high applicability.

It should be understood that although the various steps in the flow charts of fig. 2-8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-8 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.

In one embodiment, as shown in fig. 10, there is provided a congestion control device for data transmission, including:

an obtaining module 10, configured to obtain detection information; the detection information comprises path loss information and equipment state information;

the measuring and calculating module 11 is configured to input the detection information to a bandwidth measuring and calculating network for measuring and calculating to obtain a target network bandwidth corresponding to each connection channel;

and the control module 12 is configured to perform congestion control on the data to be transmitted on each connection channel according to the target network bandwidth corresponding to each connection channel.

In one embodiment, the bandwidth estimation network is a network trained in advance according to the probe information samples, or the bandwidth estimation network is an initial network to be trained.

In an embodiment, the bandwidth measurement network is a network trained in advance according to probe information samples, and the congestion control apparatus for data transmission, as shown in fig. 11, further includes:

a first measurement module 13, configured to measure and obtain an actual network bandwidth corresponding to each of the connection channels after congestion control;

the second determining module 14 is configured to determine whether an actual network bandwidth corresponding to each connection channel meets a preset condition, if so, continue to use the current bandwidth measurement and calculation network for measurement and calculation, and if not, optimize the current bandwidth measurement and calculation network and measure and calculate using the optimized bandwidth measurement and calculation network.

In an embodiment, the bandwidth calculating network is an initial network to be trained, and the congestion control apparatus for data transmission, as shown in fig. 12, further includes:

a second measurement module 15, configured to measure an actual network bandwidth corresponding to each of the connection channels after congestion control is performed;

a third determining module 16, configured to determine a change condition of a network parameter according to the actual network bandwidth;

and the adjusting module 17 is configured to adjust parameters on the bandwidth measurement and calculation network according to the change condition of the network parameters, and measure and calculate using the bandwidth measurement and calculation network after the parameters are adjusted.

In one embodiment, the detection information is detection information within a preset time period.

In an embodiment, the obtaining module 10, as shown in fig. 13, includes:

a receiving unit 101, configured to receive a probe signal sent by a base station, and acquire current environment information; the current environment information comprises at least one of weather information, shelter information and terrain information;

a first determining unit 102, configured to determine the path loss information according to the signal strength of the probe signal and the current environment information.

In one embodiment, the control module 12, as shown in fig. 14, includes:

a second determining unit 121, configured to determine a congestion control algorithm adapted to each of the connection channels;

the starting unit 122 is configured to start a congestion control algorithm adapted to each connection channel, and perform congestion control on the data to be transmitted on each connection channel based on the target network bandwidth corresponding to each connection channel.

For the specific definition of the congestion control device for data transmission, reference may be made to the above definition of the congestion control method for data transmission, which is not described herein again. The modules in the congestion control device for data transmission may be implemented in whole or in part by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 15. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing business data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of congestion control for data transmission.

Those skilled in the art will appreciate that the architecture shown in fig. 15 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:

acquiring detection information; the detection information comprises path loss information and equipment state information;

inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain target network bandwidths corresponding to the connection channels;

and carrying out congestion control on the data to be transmitted on each connecting channel according to the target network bandwidth corresponding to each connecting channel.

The implementation principle and technical effect of the computer device provided by the above embodiment are similar to those of the above method embodiment, and are not described herein again.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:

acquiring detection information; the detection information comprises path loss information and equipment state information;

inputting the detection information into a bandwidth measuring and calculating network for measuring and calculating to obtain target network bandwidths corresponding to the connection channels;

and carrying out congestion control on the data to be transmitted on each connecting channel according to the target network bandwidth corresponding to each connecting channel.

The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.

The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.