37 results about "Bottleneck bandwidth" patented technology

The invention discloses a wide area network-oriented decomposition support method for an animation rendering task and an implementation method, which belong to the field of computer networks. According to the intensive computation characteristic of the animation rendering task and the characteristic that the transmission rate in a wide area network environment is limited to a network bottleneck bandwidth, the method comprises a visible range-based scene file and picture set splitting method, a node performance assessment method, an operation distribution strategy and integration and process control of the methods. During composition of the rendering task of a user, the scene file and picture set splitting method related to the invention is used and a scene is optimized according to the analysis of objects and pictures which are visible and invisible for the current scene camera, so that the aim of reducing a final rendering file is fulfilled. In a simplified model scene, a transmission data volume in a network can be effectively decreased, equivalent splitting of a scene file and a calculated amount is realized, and the distribution and execution of the fineness of rendering operation are facilitated. By using the method, the computing efficiency of each rendering client is brought into full play, and very high expandability is achieved.

A novel packet filtering and processing mechanism solves bandwidth estimation problems related to cross-traffic, host limitations, and fabric-specific issues in order to accurately estimate bottleneck bandwidth in fluctuating environments such as home networks. In particular, the process controls the number of packet train experiments, the size of trains and packets within trains, and other factors to eliminate errors due to cross-traffic, network capture, receiver CPU overload, interrupt moderation, and other networking factors. In an embodiment of the invention, a history window is applied to estimates derived from individual trains to ensure that data used to make a bottleneck bandwidth estimate was taken at a time when the network is relatively stable.

This invention relates to measure method and system for bottle wide and remain wide band in the label barrel speed limit network path, wherein, the method comprises the following steps: establishing send end and receive end for data interacting; firstly detecting and judging whether the linkage is label speed limit network path; if yes, then computing linkage each label parameters, bottle and remain wide band; if not adopting traditional method to measure and compute the bottle wide band and remain wide band. The invention is free of label speed limited.

The invention discloses multi-service and multi-path routing optimization method in a named data network. The multi-service and multi-path routing optimization method comprises the following steps: dividing services in an NDN network into time delay sensitive services and bandwidth sensitive services; marking a corresponding differentiated service code point value in a service type field of an interest packet by use of an edge node; carrying out routing selection and forwarding on the interest packet; and after a content issuer receives the interest packet, generating a corresponding data packet, and updating the pheromone concentration of a core node according a timer field, a bottleneck bandwidth recorder field and the service type field in the data packet. The multi-service and multi-path routing optimization method disclosed by the invention can be used for classifying multiple services in a network and optimizing and selecting routing of different service types according to the measurement requirements thereof by means of ant colony optimization, so as to better support QoS of the NDN network and achieve differentiated services.

The invention pertains to the field of photoelectric imaging and tracking technology, and relates to an in-situ programmable logic array detector for calculating in real-time the center-of-mass of a light spot. The detector comprises an image input unit (21), an image output unit (22), a center-of-mass data output unit (25), an in-situ programmable logic array (31), and a in-situ programmable logic array auxiliary device unit (32). The detector can resolute the center-of-mass data of a light spot of an image in several tens ns, makes the bottleneck bandwidth limit of APT system transfers from an image processing device to a photoelectric imaging device, namely, CCD camera or CMOS camera, hence the overall bandwidth of APT system is greatly improved. The calculation speed is improved from 500-2000 images per second with prior DSP built-in image processing system to 3000-10000000 images per second; the size of the equipment is reduced from former 200mm is multiplied by 300mm is multiplied by 30mm swung dash 300mm is multiplied by 500mm is multiplied by 800mm to 150mm is multiplied by 150mm is multiplied by 30mm; and the power consumption is reduced from former 0.8W swung dash 2.0W to 0.5 W; and the quantity of devices is reduced from former 20-30 to 15.

The invention provides a network bottleneck bandwidth measurement assessment method based on active measurement and a packet gap model. According to the method, on the basis of the packet pair measurement technology principle, a three-time handshaking interaction consultation method regulated by a TCP is utilized for improving and optimizing an AllBest algorithm. A data packet pair model is adopted in the method for transmitting data packet pairs in two combination forms alternatively to the opposite terminal in a network, and the transmitting terminal tests and estimates a bottleneck bandwidth of a transmission link according to two-way transmission time and the packet length of a TCP response message returned by the opposite terminal from transmitting to receiving. The method overcomes the defects that an ICMP response message is too long, and transmission delay for returning to the transmitting terminal of a feedback message responded by the opposite terminal can not be omitted, and can achieve single-terminal deployment and fast measure the bottleneck bandwidth of the transmission link, so that practicality and accuracy of network measurement are effectively improved.

The invention discloses an integrated routing setting method and an integrated routing setting device. The method comprises the following steps of: converting a physical topology crossing different wavelength division multiplexing networks into a multi-fiber auxiliary chart; dividing a bandwidth of a request service into an integral bandwidth and a decimal bandwidth; determining a cost function of each chain between a source node and a destination node of the request service; seeking k shortest integral bandwidth alternative channels for the integral bandwidth part, and selecting one channel with the maximum bottleneck bandwidth from the k shortest integral bandwidth alternative channels as a label switching path of the integral bandwidth part; and seeking k shortest decimal bandwidth alternative channels for the decimal bandwidth part, and selecting one channel with the minimum path influence function value from the k shortest decimal bandwidth alternative channels as a label switching path of the decimal bandwidth part. By the method and the device, the bandwidth of the service is divided into an integral bandwidth part and a decimal bandwidth part; and the label switching paths are determined for the two bandwidth parts according to the cost function and a path influence function respectively.

A software-defined network (SDN) controller and a multipath routing method thereof are provided. In the method, a maximum bottleneck bandwidth (MBB) and a minimum hop count (MHC) of each of the nodes in the SDN are initiated. Next, a source node is visited, and neighboring nodes thereof are discovered to relax paths between the source node and each neighboring node. Then, a forwarding node having a maximum MBB among other nodes is visited, and its neighboring nodes which are connected therewith and unvisited are discovered to relax the paths between the forwarding node and each neighboring node. Afterwards, the rest of the nodes are consecutively visited until all nodes are visited. Finally, a disjoint path lookup table is established according to relation between the paths recorded for each node, and accordingly k disjoint paths having the maximum bottleneck bandwidth are found for transmitting k sub-flows divided from a data flow.

The invention discloses a multi-path congestion control method for a space-ground integrated intelligent network, which comprises the following steps of: establishing a congestion state judgment method, and judging a network congestion state by adopting round-trip time (RTT) and bottleneck bandwidth estimation; and establishing an improved congestion control method. Aiming at the high bit error rate and the high delay characteristic of the space-ground integrated intelligent network, a scheme based on RTT and bandwidth estimation is improved by referring to a BBR congestion control mechanism, and a calculation method based on bottleneck bandwidth and propagation delay is refined, so that the judgment on the network congestion state is more accurate. On the basis of mechanism research on MPTCP multi-path congestion control, an improved LIA algorithm is provided, aiming at different QoS requirements, under the condition that network utility is maximized, the congestion window reduction proportion is adjusted in a self-adaptive mode, and the throughput and the bandwidth utilization rate are improved. The space-ground integrated intelligent network congestion control mechanism provided by the invention has a good application prospect.

The invention discloses a multi-path TCP congestion control method. The method comprises the steps that firstly, substream weight factors for describing network environment features of different substreams in a multi-path TCP are introduced into a google BBR congestion control algorithm; secondly, convergence features of the different substreams of different multi-path TCP sessions at a shared bottleneck link when the different substreams deploy the congestion control algorithm are analyzed, and a weight-bandwidth model is built; thirdly, bottleneck bandwidth parameters and background stream parameters for recovering the shared bottleneck link weight-bandwidth model are calculated; and finally, traffic migration is achieved by taking the network fairness as a principle and utilizing a distributed substream weight factor updating iteration algorithm according to bottleneck bandwidth parameters and background stream parameters which are reproduced by the various substreams at different shared bottleneck links, and finally the network fairness guarantee is achieved.

A data center network multi-path dynamic load balancing method based on an SDN comprises the following steps: monitoring a network state, and obtaining real-time state information of equipment; dividing large and small streams; for the small flow, carrying out routing in an ECMP mode, and carrying out hash operation based on the 10-tuple value of the flow to select a forwarding path; for the large flow, adopting a large flow routing algorithm; calculating the average link utilization rate and the link load variance, and re-routing the flow occupying the maximum bandwidth on the link with the maximum link utilization rate to the path with the maximum bottleneck bandwidth. According to the method, an initial routing algorithm and a rerouting algorithm are combined, and the load balancing effect is enhanced; the low time delay requirement of the small flow is met, and the high throughput requirement of the large flow is met; a dynamic routing algorithm based on a probability selection algorithm is adopted for the large flow, and the problem that the large flow is distributed to the same path due to the fact that path information is not updated in time is avoided; the upper limit of the number of times of rerouting in a single period is set, unnecessary rerouting caused by network fluctuation is avoided, and the overhead of a controller is reduced.

A method and device for estimating the bottleneck bandwidth over a communication network is provided. The method includes the steps of: transmission by the sever through a bottleneck link a plurality of bursts comprised of packets to the client; calculating a set of bandwidth samples for each burst received by the client end; determining a new bottleneck bandwidth from the calculated bandwidth samples for the following transmission of data packets between the server and the client. The device capable of estimating a bottleneck bandwidth includes: a means for transmitting a plurality of bursts comprised of packets; a means for receiving each burst packets via a bottleneck link; a means for generating a set of bandwidth samples based on a difference between an inter-packet spacing between the first and the last packet within each burst; and, a means for determining the current bottleneck bandwidth from the generated bandwidth samples.

The invention discloses a fully distributed repair method based on erasure codes, aiming at improving the repair efficiency of failure data. The technical proposal is to construct a distributed storage system composed of a control node and a storage node, and the control node is provided with a data writing management program and a data repairing management program. A data writing program and a data repairing program are installed on the storage node; The data writing management program divides the data object into blocks and calculates the encoding, and writes the original data block and theredundant data block into different storage nodes. The data repair management program selects a new storage node LN for the failed data block D'i. The data repair management program and the data repair program cooperate with each other, and after decoding calculation, the data sub-blocks which have been repaired successfully are obtained and stored in the LN. The data repair program of LN combinesthe data sub-blocks to get the D'i recovered Di. The invention can fully utilize the uplink bandwidth of each storage node, effectively avoid the bottleneck bandwidth in the network, and improve therepair efficiency of invalid data.

The invention relates to a universal TCP performance diagnosis method and device. The method comprises the steps of capturing a TCP message and copying to a kernel buffer area; recombining the messagestored in the kernel buffer into a user state from a kernel state so as to obtain each TCP stream through reduction; calculating the propagation delay according to the time sequence information of the TCP stream; performing granularity division on the TCP stream to obtain a granularity division result and a corresponding filter window length; calculating a bottleneck bandwidth according to the particle size division result and the corresponding filter window length; and combining the propagation delay and the bottleneck bandwidth to output a performance diagnosis result. Compared with the prior art, the method is suitable for various congestion control algorithms, has high practicability, is easy to deploy, and can diagnose a plurality of TCP connections in real time.