31 results about "Adaptive routing algorithm" patented technology

The invention discloses a distributed node self-adaptive routing algorithm for LEO satellite network. Its technical characteristics are: constructing a grid-like LEO satellite communication system similar to the Iridium constellation; , using the mesh topology of the satellite constellation, each satellite node is independently responsible for forwarding the data packets in the queue; by adding and transmitting additional network status information in the datagram, the satellite nodes can realize the awareness of the network status in different routing directions And predict, and then guide the selection of data reported to the link. The present invention is reasonable in design, and its determined self-adaptive multi-path routing mechanism balances flow through load balancing means to avoid congestion, and is applied to low-orbit Iridium constellation satellite network systems, and the network performance index is superior to other traditional routing algorithms; especially in Under the premise of a small increase in the number of routing hops, the network load balance can be significantly improved, and the performance of the algorithm is better than that of the traditional algorithm.

The present application relates to a wireless ad hoc network communication method and device. The method sends data to a node through a wireless ad hoc network, and receives data sent by the node through the wireless ad hoc network; wherein, the wireless ad hoc network uses carrier sense multiple access CSMA / collision avoidance CA and time division The frame structure of the multiple-access TDMA hybrid frame, in the signal processing of the LTE transmission link, combines coding processing, diversity control and anti-interference control, and in the signal processing of the LTE receive link, the decoding processing, diversity control and anti-interference control are combined. Control the combination and increase the centerless multi-hop broadband wireless mesh network realized by the adaptive routing algorithm across the protocol layers. The wireless ad hoc network is a peer-to-peer network, in which all nodes have equal status, and nodes can join and leave the network at any time. The failure of any node will not affect the operation of the entire network, which improves the invulnerability of the network.

The invention discloses a fault-tolerant self-adaptive routing method based on ant colony algorithm, which includes: marking the position of each node in a two-dimensional network and setting the routing table; detecting a faulty node, if there is a faulty node, calculating the number of nodes adjacent to the faulty node The fault value of the node and the effective buffer length; if there is no faulty node, use the adaptive routing algorithm to find and obtain one or more routing paths to be selected; select an optimal routing path from the routing paths to be selected according to the evaluation scale, Update the pheromone routing table according to the ant colony routing algorithm; check whether the destination node is reached, and if so, end the routing; otherwise, judge whether there is a deadlock in the routing path, and end if there is a deadlock; otherwise, re-detect the faulty node. Based on the ant colony algorithm, the path selection mechanism in the fault-tolerant adaptive routing algorithm is optimized and the pheromone routing table is updated. In the case of faulty nodes, the data transmission delay of the entire network on chip is reduced, and the network load is balanced.

The invention discloses a router power model on the basis of a network-on-chip, which simplifies router operations into four power dissipation links namely write-cache, read-cache, a bestride switch and a bestride link according to the power dissipation specific weight and attributes dynamic power dissipation to bit flipping activities which are triggered when a present data film arrives, and numbers the power dissipation by the bit flipping activities to obtain the router power model. Considering that the implementation complexity which is required by the network-on-chip requirements to the power model is as low as possible, the invention can adopt the statistical average in stead of the instantaneous sampled value to obtain a power dissipation simplified model. Hardware implementation methods of two power dissipation models are given out aiming at a five-channel rooter structure, the simplified model is introduced to a self-adaptive routing algorithm, which realizes the power dissipation distribution optimization of the network-on-chip. The router power model which is proposed by the invention has low algorithm complexity and simple realization, is suitable for network-on-chip, and can be used in research and application in the aspects of power dissipation performance statistics, the power dissipation distribution optimization, thermal protection and the like.

The invention discloses a routing method for greedy geographical routing protocol tangent switching hole processing, and mainly solves the problems that a greedy geographical routing protocol adopts an edge recovery algorithm when meeting a routing hole and routing has blindness. The realization scheme is that if the greedy geographical routing protocol meets the routing hole when searching a target node, the left hand and right hand rules are simultaneously used when entering an edge recovery mode, three conditions of tangent judgment are added from the second hole node, a greedy forwarding mode is recovered if the conditions are met, and routing hops under the left and right hand rules are compared and the optimal path for data forwarding is selected. The routing hops are reduced in comparison with the greedy geographical routing protocol, and control overhead is reduced in comparison with a self-adaptive hole processing algorithm based on road sign distributed iterative extraction and elimination so that the routing method can be used for a mobile wireless sensor network.

A deadlock-free minimal routing algorithm called clue is first disclosed for VCT tori. Only two virtual channels are required. One channel is applied in the deadlock-free routing algorithm for the mesh sub-network based on a known base routing scheme, such as, negative-first or dimension-order routing. The other channel is similar to an adaptive channel. This combination completes a very novel fully-adaptive routing scheme because the first channel does not supply routing paths for every source-destination pair. Based on clue, we proposed two other algorithms named flow controlled clue and wormhole clue. Flow controlled clue is also proposed for VCT-switched tori. It is fully adaptive deadlock-free. Each input port requires at least two buffers, each of which is able to keep a packet. A simple but well-designed flow control function is used in the proposed flow controlled clue routing algorithm to avoid deadlocks. Wormhole clue is proposed for wormhole-switched tori. It is partially adaptive because we add some constraints to the adaptive channel for deadlock avoidance.

This invention discloses a dynamic steering routing algorithm based on ''package-circuit'' switching technology. The dynamic steering routing algorithm is characterized in being applied to the link establishment stage of the ''package-circuit'' switching technology, can select a proper route to transmit data according to information, such as traffic distribution, congestion situation and the like, in a network-on-chip, and is a self-adaptive algorithm. According to the port usage of a current routing node and a downstream routing node, the algorithm selects a congestion-free routing node to realize dynamic steering route; thus, the probability of network congestion can be reduced; the data stream can be distributed in the network evenly; and then, the network resource can be utilized adequately, and the performance of the system can be improved. At the same time, the success rate for establishing the link can be improved, so that the link is prevented to be established and cancelled for many times during the link establishing process; and thus, the power consumption of the network and the system can be reduced.

The present invention relates to the field of on-chip network technology, and discloses a low-power adaptive routing method in an on-chip network, including the following steps: S1. Calculate the distance between the source node and the destination node of the message in the two directions of x-dimension and y-dimension, if If the sum of the distances is zero, the routing is completed, otherwise step S2 is executed; S2, the network is divided into two virtual subnets x+y* and x-y*; S3, the message enters the virtual subnet x+y* or x-y* for routing . The present invention divides the physical network into two virtual subnets x+y* and x-y*, and the virtual subnets x+y* and x-y* all adopt the complete adaptive routing algorithm of the shortest path and the new EVC flow control technology, According to the offset value of the destination node of the data packet relative to the source node, it is injected into the corresponding virtual network, and adaptively routed to the destination in the virtual network. The EVC channel is used first when the data packet is routed, and the NVC channel is used only when there is no free EVC channel available. It proceeds according to the normal pipeline stage, which effectively improves performance and reduces power consumption.

The invention discloses a content distribution method, system, device and medium of a dynamic cloud content distribution network, and constructs a cloud content distribution network based on an existing cloud proxy server; regards all cloud proxy servers in the cloud content distribution network as nodes, and determines Source node, relay node, destination node and the connection relationship between nodes; construct Q table for each node; based on Q-learning adaptive routing selection algorithm, select a route to its termination node for each destination node path; establish a path from the terminal node to the destination node through reverse routing information, and construct an adaptive distribution tree; based on the adaptive distribution tree, the distribution of content is realized. The algorithm propagates local and non-local congestion information through network learning packets. Choose a path with low congestion cost and be able to adapt to the dynamic cloud distribution environment.

The invention belongs to the technical field of distributed routing, and specifically relates to a data packet routing algorithm based on multi-agent deep reinforcement learning. In order to alleviate the congestion in the computer network, the present invention uses multi-agent deep reinforcement learning technology to design an end-to-end adaptive routing algorithm, and each router completes data packet scheduling according to local information, reducing the transmission delay of data packets . The invention first constructs a mathematical model of distributed routing, defines the specific meaning of each element in reinforcement learning, then trains a neural network, and finally performs algorithm performance testing in a simulation environment. The simulation experiment results show that the introduction of the deep neural network can mine the characteristic information in the input network state and realize the trade-off between the smooth path and the shortest path. Compared with other commonly used routing algorithms, the present invention achieves a shorter data packet transmission time delay.

The invention discloses a self-adaptive WSN (wireless sensor network) routing algorithm based on biological inspiring, and belongs to the technical field of WSN. The self-adaptive WSN routing algorithm based on the biological inspiring solves the problems of local optimizing and routing void easily caused by the greedy method which is relied by the existing GPSR (greedy perimeter stateless routing) algorithm. The method comprises the two basic steps of (1) sending data in the quadrant of Sink nodes in a flooding way to find a backbone network; (2) utilizing the found backbone network to send data. In the establishing process of the backbone network, the forming strategy of the physarum polycephalum feeding path is simulated, namely utilizing the geological location information and embodying the path weights to establish the route main network. In the process of sending data by nodes, the non-related nodes enter the sleeping state, the energy difference of all adjacent nodes should not be greater than Threshold, then the balance of energy consumption is realized, and the robustness of the network system is further improved. After the data is sent, the path information of the backbone network is remained. When the node sends the data next time, the backbone network can be continuously used, the time of researching the path is saved, the data transmission efficiency is improved, and the energy consumption is reduced.