19 results about "Congestion control algorithm" patented technology

The embodiment of the present application relates to the technical field of photovoltaic communication test, and discloses a kind of distributed photovoltaic multi-protocol communication test method and related equipment, the method comprises: communication signal interference is simulated based on network signal attenuation simulator, whether communication protocol is switched according to communication quality parameter and parameter threshold value, communication data is cached based on multi-level data caching mechanism, communication interruption is detected, and interrupted data is continued to be transmitted based on congestion control algorithm, data loss is identified by missing data algorithm, data is completed by completion algorithm, and test report is generated according to data recovery rate, time efficiency index, resource consumption index, protocol adaptability index, protocol switching parameter, caching parameter, continuation parameter and data completion parameter.The embodiment of the present application can simulate the test of communication protocol switching, data caching, interruption identification, data continuation, data loss identification and completion under a variety of weak network environments, and has high test precision and good test effect.

The invention provides a communication method and device, and the method comprises the steps: a terminal device can determine the maximum uplink rate and the maximum downlink rate of a current air interface, and notifies a server of the maximum downlink rate, so that after the terminal device and the server establish a communication connection, the maximum uplink rate and the maximum downlink rate of the current air interface can be obtained. The terminal device can send uplink service data to the server according to the maximum uplink rate, and the server can also send downlink service data to the terminal device according to the maximum downlink rate of the terminal device. According to the method, the process that the sending window and the transmission rate are gradually increased through multiple rounds of detection and iteration in the initial stage by a congestion control algorithm used by the terminal equipment and the server can be avoided, so that the transmission delay of uplink service data and downlink service data is reduced, and the communication efficiency between the terminal equipment and the server is improved; and the time for completing the uploading and downloading tasks by the terminal equipment is obviously shortened.

The invention provides a congestion control system and a control method for jointly adjusting a sending rate based on queues and time delays under a wireless local area network, relates to the technical field of congestion control of the wireless local area network, and aims to solve the problems that a traditional congestion control algorithm depends on single signal sensing, is lagged in response, cannot adapt to bottleneck dynamic switching of the wireless local area network, and is low in cost. And the transmission delay and the link throughput are difficult to balance. According to the method, after each round of data transmission, a network card driving queue residual length RQ is obtained, a data packet round trip time RTT is monitored, a congestion scene is cooperatively judged, a congestion window cwnd is dynamically adjusted to optimize the transmission rate, and corresponding formulas or strategies are adopted for adjustment according to scenes. According to the method, the problems of one-sided sensing and response lag of a traditional congestion control algorithm can be solved, a scene is judged through RQ and RTT dual-sensing cooperation, cwnd is dynamically adjusted, time delay is reduced when the network is good, throughput is guaranteed when the network is poor, and the performance is superior to Cubic and BBR.

Example methods and network interface devices for congestion control are described. In one example, a network interface device may include a first processing layer and a second processing layer. The first processing layer may receive an event notification from the second processing layer. In response to determination that congestion control is required based on the event notification, the first processing layer may determine an adjustment to a packet forwarding parameter by applying a congestion control algorithm. The congestion control algorithm may be one of multiple congestion control algorithms that the first processing layer is programmable to apply. The first processing layer may generate and send an instruction to the second processing layer to perform the adjustment. Based on the instruction, the second processing layer may configure a component to control packet forwarding towards a physical network based on the second value of the packet forwarding parameter.

A method of improving the utilization of a data communications link is provided. The method includes sending a request, to a round trip time, RTT, meter (304), requesting a measurement of the base round trip time of a data communications flow. The method includes setting an increase parameter of a congestion control algorithm based on the base round trip time measurement received from the round trip time meter in response to the request.

The application discloses a data transmission method in a network, which is applied to a sending device and comprises the following steps: determining a current network state of a network between the sending device and a receiving device; if the current network state indicates that the network is currently normal, calling a first congestion control algorithm in a transmission protocol which supports the normal network to perform network data transmission; and if the current network state indicates that the network is currently a weak network, calling a second congestion control algorithm in the transmission protocol which supports the weak network to perform network data transmission. It can be seen that the application supports the congestion control under the normal network and the weak network simultaneously, and selects a proper congestion control algorithm according to the current network state to perform network data transmission, thereby improving the data transmission performance. The application further discloses a data transmission system and device in a network and a computer readable storage medium, which have the same beneficial effects as the data transmission method.

An improved method of performing congestion control on a network device is disclosed. The network device establishes a plurality of connections with two nodes. After receiving a data packet from a first node, the network device transmits data to a second node through the plurality of connections according to an outbound traffic policy. When network congestion reaches a certain threshold, the network device may establish multiple new connections with the second node, assigning different congestion control algorithms to them, and replacing multiple connections previously established between the network device and the second node.

Systems and methods are provided for implementing enhanced Low Latency, Low Loss, and Scalable throughput (L4S) mechanisms at a bottleneck network node to detect and more accurately / selectively address congestion. Low and high watermark limits can be established for access category (AC) queues at the bottleneck network node, such as an access point (AP). Incoming packets can be analyzed to determine their priority, and then assigned to an AC queue. Depending on the state of a queue (whose thresholds can differ) packets can be marked or not marked with a “congestion experienced” (CE) indication. Additionally, if a congestion indication is received by an AP from a receiver application, but the congestion no longer exists, the AP can forgo forwarding this feedback upstream.

The invention relates to the technical field of communication, and provides a user-defined RDMA (Remote Direct Memory Access) congestion control simulation method, which comprises the following steps that: a host side request end initializes related congestion control parameters; the host side request end sends a data packet according to the current congestion control algorithm; the switch side forwards the data packet, and executes ECN marking or INT information insertion according to a congestion control algorithm; after receiving the data packet, the host side response end generates feedback information according to the network state; and the host side finishing end analyzes the feedback information, calls a corresponding congestion control algorithm to process logic, and executes rate adjustment. According to the method, a user can flexibly realize and deploy a self-defined congestion control mechanism, and function verification and performance evaluation are carried out on an algorithm in a simulation environment.

The application provides a user state-based RDMA network QoS coordination method, which comprises the following steps: a sending end configures different QoS initial parameters for different service flows, and sends data packets with the same sending window size; a receiving end carries a network congestion control signal in an ACK packet returned after receiving the packet; the sending end acquires the network congestion control signal; the sending end adjusts the sending window by using a user state congestion control algorithm; the sending end periodically reports QoS parameters and service quality of the service flow to a correction node; and the correction node adjusts the QoS parameters by using a parameter adjustment algorithm according to the QoS parameters and service quality of the service flow reported by the sending end, and delivers the QoS parameters to the sending end. The application performs fine-grained control on a single service flow, so that more priority levels are realized, and the correction module can recover the pre-set QoS as soon as possible, so that good fairness, convergence and stability are achieved.

The invention discloses an Internet of Vehicles distributed network congestion control method and system using a double-layer deep reinforcement learning architecture, and relates to the field of wireless distributed multi-node communication. The method solves the problem of insufficient adaptability of a distributed congestion control algorithm in an existing cellular Internet of Vehicles network in a dynamic environment, and comprises the following steps: analyzing a target communication system, and determining an optimal transmission parameter by controlling a data packet transmission interval and sending power so as to maximize the average data packet transmissibility of vehicle user equipment; the method comprises the following steps: constructing a problem model, setting constraint conditions, carrying out multi-parameter joint regulation and control, dividing an action domain into a plurality of sub-action domains based on a deep Q network, and selecting corresponding sub-action domains for output in different environments to realize dynamic adjustment of communication parameters; and constructing a double-layer deep reinforcement learning architecture model, and performing parameter optimization by using the double-layer deep reinforcement learning architecture model. The method is also suitable for the application fields of distributed congestion control and the like in a cellular Internet of Vehicles network.

The application discloses a data transmission method and related device, determines a congestion control algorithm and a congestion control parameter, obtains a next packet sending opportunity from a congestion control module, the next packet sending opportunity is determined by the congestion control module according to current network packet status by using the congestion control algorithm and the congestion control parameter, and the receiving end sends a packet when the write operation base class waits to meet the next packet sending opportunity, and the write operation base class receives an ACK packet returned by the receiving end, and the existing congestion state information of the congestion control module is updated based on the ACK packet. The application perceives the network state in real time through the congestion control module, and determines the next packet sending opportunity of the write operation base class according to the current network packet status, effectively avoids that the write operation base class sends a packet when the network is congested, improves the data transmission efficiency, and guarantees the reliability of data transmission through the receiving end sending the ACK packet.

The invention discloses an improved optimization method of an end-network cooperative congestion control algorithm based on in-band network telemetering, which relates to the technical field of computer networks, and comprises the following steps: S1, initializing a sending end; s2, switch processing, S3, receiving end feedback and S4, end-network cooperative closed-loop control: the sending end updates a transmission strategy according to a credit quota fed back by the receiving end, the switch adjusts an INT sampling and data packet processing mode according to a network load, and the receiving end continuously optimizes credit distribution based on INT information to form an end-network cooperative congestion control closed loop; through closed-loop linkage of the sending end, the switch and the receiving end, on the basis of network path state information collected in real time through in-band network telemetering, a bottleneck link can be accurately recognized, credit quota and a transmission strategy can be dynamically adjusted, efficient congestion control can still be kept in a high-bandwidth delay product scene, and the congestion control efficiency is improved. And the requirements of a data center network on high throughput and low delay communication can be met.

Example methods and network interface devices for user-defined congestion control are described. In one example, a network interface device may include a first processing layer and a second processing layer. The first processing layer may receive an event notification from the second processing layer. In response to determining that congestion control is required based on the event notification, the first processing layer may determine adjustments to packet forwarding parameters by applying a congestion control algorithm. The congestion control algorithm may be one of a plurality of congestion control algorithms that the first processing layer is programmable to apply. The first processing layer may generate and send instructions to perform the adjustment to the second processing layer. Based on the instruction, the second processing layer may configure a component to control packet forwarding to a physical network based on the second value of the packet forwarding parameter.

The application provides a round-trip delay correction method and system based on reverse path timestamp, comprising: collecting data packet sending timestamp, acknowledgement packet sending timestamp and acknowledgement packet receiving timestamp; storing reverse path delay samples dynamically through a sliding window, and calculating a reference delay by selecting a minimum value method or a least square regression method according to the sample quantity; removing reverse path congestion interference in the round-trip delay according to the difference between the current reverse path delay and the reference delay, and obtaining a corrected round-trip delay; and sharing the reference delay of the same source-destination pair under a symmetric topology. The application can accurately separate forward and reverse path congestion, avoid misjudgment of the traditional RTT caused by reverse path congestion, and improve the bandwidth utilization and short flow performance of the congestion control algorithm; through hardware timestamp and dynamic baseline estimation, low-cost deployment without hardware modification is realized, and the application is suitable for high-precision delay optimization of a data center network.

The invention provides a transmission control method and device, sending equipment and a readable storage medium. The method comprises the following steps: acquiring a first recording parameter in a first time window, wherein the first recording parameter comprises at least one of the following items: a maximum bandwidth delay product (BDP), a maximum bandwidth and a data volume in maximum transmission; when the first record parameter comprises the maximum BDP and / or the maximum bandwidth, determining a first congestion window according to the maximum BDP and / or the maximum bandwidth, and determining whether to send a message according to the relationship between the data volume in actual transmission and the first congestion window; when the first record parameter comprises the data volume in the maximum transmission, determining whether to send the message according to the data volume in the actual transmission, the data volume in the maximum transmission and the second congestion window; the second congestion window is determined based on the maximum bandwidth acquired in the second time window; the length of the first time window is greater than that of the second time window. According to the invention, the problem of poor fairness of a current congestion control algorithm can be solved.

The application provides a hot upgrade method, device and medium for congestion control, and relates to the field of hot upgrade; the method comprises the following steps: loading a hot patch file corresponding to a congestion control algorithm obtained by a network card basic firmware into a preset storage area of a memory; after the loading is completed, determining a target network congestion event based on the hot patch file, and generating a patch function table comprising a pointer pointing to a new version of a congestion control function; modifying the value of a global function table pointer in the network card basic firmware to the memory address of the patch function table; the value of the global function table pointer is initially the memory address of an initial function table comprising a pointer pointing to an old version of a congestion control function; when the target network congestion event occurs, the network card basic firmware calls a new version of a congestion control function related to the target network congestion event through the global function table pointer and the pointer in the patch function table; the response capability and effective throughput of the system during the hot upgrade are ensured, and the efficiency of the hot upgrade is improved.

This invention provides a hybrid online and offline learning method for bandwidth estimators in real-time communication, and a bandwidth estimation method. The method includes: employing an offline policy learning mechanism based on behavior cloning to train a preset neural network model offline using an expert decision dataset, thereby training the neural network model to output an offline bandwidth prediction result based on input network layer quality data. The expert decision dataset includes multiple network layer quality data points and corresponding bandwidths collected in real-time communication based on a heuristic congestion control algorithm; and employing an online policy optimization mechanism based on reinforcement learning to optimize the initial bandwidth estimator online using real-time network layer quality data, thereby training the initial bandwidth estimator to output a target bandwidth prediction result based on the corresponding real-time network layer quality data. This invention improves the bandwidth prediction capability for complex dynamic networks.

The invention belongs to the technical field of real-time communication video congestion control, and particularly relates to a new volume video transmission scene control method based on a network state and a sending queue state. The invention provides a congestion control algorithm for combining sending queue and network state information and reducing video frame delay, aiming at the problems that the end-to-end delay of video frames is too large due to sending queue accumulation in a transmission volume video scene, a standard real-time communication congestion control algorithm is insensitive to bandwidth increase, the bandwidth utilization rate is low and the like. The algorithm can regularly detect the length of the sending queue and respond to the accumulation of the sending queue in advance; experimental results show that the method can effectively reduce sending queue accumulation in a real-time transmission volume video scene, reduce frame-to-frame delay and improve the bandwidth utilization rate.