354 results about "Exchange network" patented technology

The invention relates to the technical field of digital information processing, and provides a photovoltaic power station data operation and maintenance management system, and a data exchange network service management system comprises a server, a cloud management module, an edge calculation module, a data exchange module, a performance evaluation module, an intelligent routing module and a self-adaptive data synchronization module. The performance evaluation module is used for monitoring key performance indexes of the network state of the whole system, evaluating the current running states of the cloud, the edge nodes and the network state through the key performance indexes to form an evaluation result, and feeding back the result to the cloud management module, the edge calculation module, the self-adaptive data synchronization module and the intelligent routing module; and the data exchange module is responsible for data synchronization and exchange between the cloud and the edge nodes, so that the data consistency of the edge nodes in the system is ensured.

The present application relates to the technical field of servers. Disclosed are a server system and a communication method therefor. The server system comprises: at least one first processor board and a host server, wherein the at least one first processor board is in communication connection with the host server by means of a switching network; the first processor board comprises a first field programmable gate array chip and a first processor chip; the first field programmable gate array chip and the first processor chip are packaged and interconnected; the host server is configured to transmit host data to the first field programmable gate array chip by means of the switching network; and the first field programmable gate array chip is configured to process the host data, receive request data which is sent by means of the first processor chip, generate a communication protocol message on the basis of the processed host data and the request data, and transmit the communication protocol message to a destination processor board by means of the switching network. By means of the present application, pooling acceleration of a server system is realized, thereby realizing efficient layout of computing power resources.

The invention relates to the technical field of micro-grid energy optimization, in particular to a distributed federal reinforcement learning-based hydrogen-containing micro-grid energy scheduling method, which comprises the steps of constructing a multi-region hydrogen-containing micro-grid system model, designing a state space, an action space and a reward function of an intelligent agent, constructing an Actor-Critic network and an experience pool, and completing environment initialization. The intelligent agent inputs the operation state of the equipment into the Actor network, updates the state of the equipment according to the output action, verifies the constraint and outputs a reward value; tuples are extracted from the experience pool to update local network parameters, and the exploration rate is updated regularly; when a federation interaction period is reached, exchanging Critic network parameters and updating federation parameters; and when the training round arrives, outputting an equipment operation plan, deploying the model to the local hydrogen-containing micro-grid in the island mode, and outputting an equipment output value. According to the scheme, strategy sharing and learning collaboration are realized through neighborhood collaboration and local communication among the regional intelligent agents, so that dependence on a central node is avoided.

The invention relates to the technical field of communication, and discloses a flow control method, electronic equipment and a storage medium, and the method comprises the steps: responding to data transmission of a target node, configuring a first-level cache of the target node, and configuring a data cache position corresponding to the target node as the first-level cache; under the condition that the data volume in the first-level cache reaches a preset back pressure threshold value, switching a data cache position corresponding to the target node to a second-level cache, and performing flow control on the target node; wherein the second-level cache is configured to be a shared cache of all nodes transmitting data to the local node. According to the invention, the problem of cache overflow caused by traffic burst of the switching network node can be solved.

The invention discloses a network-on-chip construction method and device, a medium and a product, and relates to the technical field of network-on-chip design, and the method comprises the steps: building a bottom layer cellular network based on a cellular topological structure, each node in the bottom layer network comprises a router and a processing unit, and carries out the data interaction with an adjacent node; the method comprises the following steps of: symmetrically dividing a network into a plurality of geometric sectors with the same coverage angle by taking a center node of a bottom-layer network as an original point, and selecting at least one node from each sector as a cross-layer node; and connecting the cross-layer nodes to corresponding nodes in the top-layer switched network through additional channels, wherein the top-layer network nodes only comprise routers and realize full interconnection through the additional channels. According to the invention, the long-distance communication is transferred to the top switching network through a hierarchical structure, the data transmission hop count and signal delay are effectively reduced, the hardware resource consumption is reduced, and the network expansibility and the communication efficiency are improved.

A network interface module for coupling a host device to a switched network as a network node is described. The network interface module comprises a single half-duplex port for communicatively coupling to a shared bus of the switched network, at least one frame queue sized to store one multicast read frame received via the shared bus, and logic circuitry. The logic circuitry is configured to decode a read command for the interface module included in a payload of the multicast read frame that includes multiple read commands for other network nodes of the switched network, and transmit a response frame including read data on the shared bus when detecting the shared bus is available for transmitting.

The invention belongs to the field of PCIe (Peripheral Component Interconnect Express) chips, and relates to a CXL switching chip of a multi-core-grain architecture and a cross-core-grain routing switching method thereof, and a plurality of CXL switching core grains with uniform specifications are packaged and interconnected to form the CXL switching chip; each CXL switching core particle comprises a plurality of ports, each port can be configured to be in a CXL mode and a D2D mode, and the port of each CXL switching core particle at least comprises a physical layer, a CXL link layer, a CXL transaction layer, a D2D routing layer, a bypass and a multipath selection module; the CXL switching chip further comprises a multi-VC on-chip CXL switching network, and the multi-VC on-chip CXL switching network comprises at least one order-preserving switching VC and one out-of-order switching VC. According to the method, CXL switching chips of various specifications can be flexibly constructed, the design complexity and verification difficulty of the large-scale or multi-port CXL switching chips are effectively reduced, and the production yield of the chips is improved.

An apparatus comprises a memory communicatively coupled to a processor. The memory is configured to store network interchange parameters and user profiles. The processor is configured to receive a data exchange request triggered by a user device. Further, the processor is configured to request, to a decentralized network, a token indicating that a user profile associated with the user device is entitled to access an entitlement, determine whether a data exchange network is available to exchange data in accordance with the network interchange parameters, identify a second data exchange network that is available in accordance with second network interchange parameters in response to determine that the data exchange network is unavailable, and request a data exchange output from the second data exchange network via the token. The processor is configured to receive the data exchange output from the second data exchange network.

The present disclosure relates to methods and apparatuses for processing a control packet in a collective communication system, where the collective communication system includes a switch network and multiple computing nodes, and the switch network includes a first switch. In one example method, the first switch forwards a query packet transmitted by a source node to a destination node, where the query packet is generated by the source node based on a context of the collective communication system. Then, the first switch forwards a notification packet transmitted by the destination node to the source node, where the notification packet carries an in-network computing capability of the switch network.

The invention discloses a mixed flow safe scheduling method of an electric power voice exchange network, and belongs to the technical field of electric power communication. Comprising the steps of obtaining a to-be-scheduled data stream, and determining a scheduling priority and a security level of the to-be-scheduled data stream according to a service category of the to-be-scheduled data stream; generating a scheduling queue according to the scheduling priority; forwarding a to-be-scheduled data stream to a corresponding scheduling queue, performing encryption processing based on the security level, and completing scheduling under time slot constraint, network control stream traffic constraint and audio stream traffic constraint; and if the service category of the to-be-scheduled data stream is an audio stream, determining the priority of the audio stream and adjusting the sequence of injecting the audio stream into the switch by taking the bandwidth occupancy rate constraint and the delay constraint as a target. The scheduling success rate of the high-bandwidth voice service in the electric power voice switching network is improved, the delay is reduced, and the schedulability of the network is improved; the problem that safety and reliability of existing transmission messages are difficult to achieve at the same time is solved.

The invention discloses a switch, system and method for data transmission based on a shared pool and a fan-out structure.The switch comprises a plurality of ports, the shared pool and a fan-out cache unit, and the ports comprise the first port and the second port; the first port receives data outside the switch, transmits the data to the shared pool and transmits a first data transmission request to the second port, and the first data transmission request comprises a data length; the second port receives the first data transmission request, and the target port generates a second data transmission request according to the first data transmission request, the data length and the remaining storage space of the target port so as to transmit the second data transmission request to the fan-out cache unit; and the fan-out cache unit schedules the data at the corresponding position in the shared pool according to the second data transmission request and outputs the data to the target port when the residual storage space of the target port is greater than the storage space required by the data length. The bandwidth utilization rate and the response speed of the data exchange network can be effectively improved, and congestion and delay are reduced.

A first network device of a first data center may encode a source tenant system interface (TSI) group identifier into a tag protocol identifier and a group-based policy identifier, and may encode the tag protocol identifier and the group-based policy identifier into a virtual extensible local area network (VXLAN) packet with the source TSI group identifier, where the source TSI group identifier is not included in a header of the VXLAN packet. The first network device may provide the VXLAN packet, with the source TSI group identifier, to a second network device of a second data center, via an Ethernet virtual private network (EVPN) multiprotocol label switching (MPLS) network.

The invention relates to the technical field of data exchange networks, and discloses a hardware-level link health monitoring system and a self-healing method, the hardware-level link health monitoring system comprises a flow analysis and data acquisition module; a multi-dimensional link quality state module; and a hardware-level self-healing and collaborative execution module. The hardware-level link self-healing method comprises the following steps: collecting a performance index of a link by hardware and generating a traffic portrait vector; after real-time reporting, dynamically adjusting the weight in an evaluation model according to the traffic portrait vector, and calculating a link health score in combination with the performance index so as to judge the health state; and finally, executing hierarchical self-healing actions on a hardware level according to the health state. According to the method and the system, hardware-level monitoring and self-healing closed loop without CPU intervention are realized, the evaluation model can be adaptively adjusted according to the service type, the monitoring accuracy and the fault self-healing speed are remarkably improved, and the service continuity is guaranteed.

The invention relates to the technical field of data exchange networks, in particular to an intelligent commanding and dispatching method for a unified communication network, which comprises the following steps of: 1, dynamically sensing the state of a heterogeneous network; 2, emergency task grading quantification: analyzing command instruction text keywords, and matching a task emergency grading label library to output a task type code and a time delay tolerance threshold; based on the task type code and the current network load rate, generating a resource demand vector through historical task data interpolation; step 3, reinforcement learning dynamic decision making; step 4, carrying out survivability resource scheduling; step 5, optimizing a closed-loop strategy: acquiring actual task completion time delay, path switching times and node resource utilization rate standard deviation as evaluation indexes; and when the average reward value of the continuous tasks is lower than a historical average threshold value, finely adjusting actor network parameters. Through multi-dimensional state perception and reinforcement learning decision, in combination with historical data analysis and network load correction, efficient scheduling and dynamic optimization of different tasks are realized.

The invention discloses a path determination method, device and system, and belongs to the technical field of communication. The method comprises the following steps: after a first controller determines a port group set, determining paths corresponding to each port group in the port group set in parallel, and determining paths corresponding to the port groups of which the corresponding paths are not determined in a part outside the determined paths in a switching network. The port group comprises a first port and a second port of data to be exchanged, and the first port and the second port in different port groups are different; the port group set comprises at least two port groups of which the first ports and the second ports belong to different switching structures; the path corresponding to any port group is the path between the first port and the second port in the port group; moreover, the paths corresponding to different port groups are mutually independent. The problem that the path determination mode of the controller is relatively single can be solved, and the path determination method and device are used for path determination.

The invention discloses an Ethernet-based distributed cache coherence protocol, an implementation method, an implementation device and an implementation system. A plurality of computing nodes are connected through a packet switching network. Each computing node comprises a CPU / GPU (Central Processing Unit / Graphics Processing Unit) and a local cache thereof, and is provided with a cache agent. The far-end memory is organized in home nodes, and each home node manages a part of physical address space and is equipped with a directory controller. When the CPU of the computing node accesses a far-end memory address and does not hit in the local cache, the CA of the computing node replaces the far-end memory address and communicates with the DC managing the address through the network so as to maintain the cache consistency of the data among all the nodes. Based on a cache consistency protocol of a directory, the CXL.cache consistency of a plurality of independent computing nodes can be maintained in a low-overhead and high-reliability mode on a high-delay and lossy packet switching network, and broadcast storm caused by a monitoring protocol is avoided.

The invention provides a LoRa networking method and system of a virtual tree topology structure, and relates to the technical field of networking, and the method comprises the steps: receiving a network access request data packet of a LoRa terminal node, and constructing a virtual connection relation for nodes based on signal strength parameters in a layering manner, thereby forming the virtual tree topology structure; setting a spherical search space based on node position coordinates, calculating a space density contribution value, and dividing an autonomous domain by adopting a density clustering algorithm; and selecting proper domain management nodes and boundary nodes to exchange network state information. According to the invention, the data transmission efficiency of the LoRa network is optimized, and the reliability and stability of the network are improved.

The invention discloses a carrier rocket avionics system based on a TSN (Time Sensitive Network) and a carrier rocket avionics data transmission method, and belongs to the technical field of carrier rocket control. A network is physically or logically divided into a periodic time-sensitive data stream, a high-speed time-sensitive data stream and a best effort data stream, the three data streams are subjected to isolation management, and transparent interconnection between a 1553B bus network and a TSN switching network is realized on a protocol layer through an intelligent protocol conversion gateway. Meanwhile, in a network management layer, through an instruction response type configuration protocol, common Ethernet equipment is seamlessly incorporated into the global scheduling and control category of the TSN network. According to the invention, by constructing the avionics network system with three-layer partition and dual-network fusion, multi-network seamless fusion on the rocket can be realized, the real-time performance of the network is improved, and the key requirements of rocket recovery are met.

The invention belongs to the field of switch chips, and relates to a hardware and software combined PCIE address translation and networking design device and method, the hardware and software combined PCIE address translation and networking design device comprises an address translation unit, a built-in CPU and firmware and a TLP transceiving unit, the address translation unit comprises a control register and an address or BDF translation module for implementing TLP address or BDF translation; the firmware is used for completing the simulation of the iEP, and the simulation method is that software is used for completing the response to a received configuration request TLP, so that a DSP and an EP are simulated; and the TLP receiving and transmitting unit connects the built-in CPU to a switching network, so that the built-in CPU receives and transmits a TLP data packet. According to the PCIe switching chip, a tree topology structure of a traditional PCIe switching chip can be broken through, and any needed network topology structure can be flexibly connected through software configuration; a plurality of hosts and devices can be connected at any port as required; the required iEP is realized by using internal firmware, the function of the iEP can be realized by more flexible programming, and the design cost is reduced compared with the method for realizing the iEP by using hardware.

The invention relates to the technical field of unmanned aerial vehicles, and discloses an auxiliary positioning unmanned aerial vehicle nest system which comprises an autonomous control system used for controlling an automatic system of the whole nest system, and is responsible for monitoring and adjusting the position and attitude of an unmanned aerial vehicle and managing landing, charging and take-off processes at the same time. The task scheduling module is used for determining the priority of tasks in the communication process, the communication and data transmission module is used for realizing information exchange between the airport nest system and the unmanned aerial vehicle, and the network compensation module is used for solving the problems of data transmission, communication delay and time sequence synchronization among different networking. And the off-network communication module is used for taking a response when the communication connection with the base station is lost. Through the arrangement of a task priority allocation algorithm and a dynamic scheduling strategy unit in the task scheduling module, emergency processing of the task can be performed according to the emergency degree of the task, the emergency task can be processed in time, and then economic loss can be avoided or other larger loss can be avoided.

A switched network, an online computing method for a switched network, an electronic device, and a non-transitory computer-readable storage medium. The switching network includes a plurality of switching nodes connected to each other to provide a communication network, where the plurality of switching nodes each include an in-network computing proxy node configured to receive and perform in-network computing tasks. The switching network can reduce communication delay and improve efficiency.

The invention discloses an intelligent electronic information exchange processing method and system, and relates to the technical field of information processing, an anti-attack capability coefficient is calculated by obtaining a key length of a used encryption algorithm, and a network signal value of encrypted electronic information in an exchange processing process is obtained to calculate an exchange network environment fluctuation coefficient; acquiring data exchange quantities at different moments to calculate a data volume exchange stagnation coefficient, calculating an encryption leakage risk coefficient according to the anti-attack capability coefficient, the network environment fluctuation coefficient and the data volume exchange stagnation coefficient, and judging whether an encryption leakage risk exists in an electronic information exchange processing process or not and whether exchange processing needs to be continued or not; whether the encrypted data may be leaked in the information exchange process or not can be detected and prevented in time, it is ensured that the encrypted data cannot be cracked or leaked in the exchange process, and the possibility of safety accidents is reduced.

The invention discloses a 4K multi-frame-rate YUV422 low-delay collaborative coding and decoding method, which relates to the technical field of video coding and decoding, and comprises the following steps of: configuring coding and decoding device parameters, establishing network connection, and setting a multi-frame-rate range and a buffer area; acquiring a 4K YUV422 original frame sequence from a video source and temporarily storing the 4K YUV422 original frame sequence; analyzing the difference and texture change between the current frame and the previous frame, and calculating the comprehensive content complexity; dynamically selecting an optimal target frame rate according to the complexity value and the network delay; the codec exchanges a frame rate switching command through a control channel and realizes synchronization, adjusts a compression parameter according to a selected frame rate, and generates a bit stream; and periodically exchanging network state information while transmitting the coded data. According to the invention, by introducing a dynamic frame rate collaborative adjustment mechanism based on content complexity, adaptive matching of coding parameters, scene contents and network states can be realized, and the problem that the stability of video image quality cannot be ensured while low delay is maintained in the prior art is solved.

The invention belongs to the field of switching chips, and relates to a PCIe switching chip system supporting on-network computing, which is provided with a distributed switching unit, and the distributed switching unit comprises a front-end processing module, a task scheduling module, a storage module, a computing module and a switching network; the front-end processing module comprises a PCIe protocol processing module, a DMA function module and an online computing analysis module. According to the invention, a distributed on-network computing architecture of the distributed switching units is adopted, and compared with centralized on-network computing, the architecture has the characteristics of high resource utilization rate and simple back-end implementation, can achieve efficient transmission performance, can flexibly support various network topology structures, and realizes on-network computing acceleration and data exchange with high bandwidth and low delay; the method has the advantages that hardware implementation is simple and flexible, rear-end implementation is friendly, parallel multi-group online computing is supported, and the method is suitable for design implementation of other network switching chips.

The invention relates to the technical field of data transmission, and provides a device for realizing fgOTN transmission and intersection, which comprises a first branch unit, a switch unit and at least one second branch unit, and is characterized in that the first branch unit is connected with the switch unit, and the switch unit is respectively connected with each second branch unit; the first branch unit is used for receiving customer service data and packaging the customer service data in an fgOTN frame format to obtain an Ethernet packet corresponding to the customer service data; the switch unit is used for receiving the Ethernet packet transmitted by the first branch unit, and determining a target transmission port required for transmitting the Ethernet packet to each second branch unit based on a static MAC table and a media access control MAC address of each second branch unit; and forwarding the Ethernet packet to each second branch unit in a cross manner through the target transmission port. According to the invention, fgOTN cross transmission is directly realized by using the existing switch, the characteristics of the existing switching network are compatible, and the cost of fgOTN cross equipment is reduced.

The invention belongs to the field of data communication distribution, and relates to a DDS data distribution method based on a TSN, a computing device and a storage medium, and the method comprises the steps: dividing distribution data into key data and non-key data; the key data is packaged into an IEEE 1722 Ethernet data frame through a publisher TSN node device, and the IEEE 1722 Ethernet data frame is sent to a first TSN switch; packaging the non-critical data into a conventional Ethernet data frame through a first transceiver, and sending the conventional Ethernet data frame to a first TSN switch; the first TSN switch shapes and schedules the Ethernet data frame, and sends the Ethernet data frame to the second TST switch based on the priority; the second transceiver is used for receiving a conventional Ethernet data frame; the subscriber TSN node equipment is used for acquiring an IEEE 1722 Ethernet data frame; according to the invention, the characteristic that the switching network preferentially forwards key DDS data and preempts other low-priority Ethernet packets is realized, and the data transmission efficiency is improved.

Provided in the present application is a fault recovery method, which is applied to a controller, the controller being used for performing fault recovery when a bus switching network in a computing cluster has had a fault, the bus switching network comprising at least one switching node, and the bus switching network being used for achieving memory access between computing nodes in the computing cluster. The method comprises: the controller acquiring fault information reported by at least one switching node, the fault information indicating a fault mode and a fault position, then determining, according to the fault information, from the at least one switching node an execution node used for fault recovery, determining, according to the fault information, a memory address communication path impacted by the fault, and then instructing the execution node to update the memory address communication path impacted by the fault. By means of updating the memory address communication path impacted by the fault, the method achieves fault recovery without shutdown, and does not require shielding of single or multiple computing nodes, thus avoiding waste of computing power.

The invention relates to a dynamic reconstruction method and system for a digital twin optical switching network, and relates to the technical field of optical communication network intellectualization, in particular to a dynamic reconstruction system applied to an optical switching network, comprising the following steps: in a digital twin, establishing a topological graph capable of being dynamically updated in real time by adopting multi-dimensional real-time topology perception, and combining key parameter data to obtain a topological graph; and high-precision twinning synchronization is established for the digital twinning body and the physical network state. And service intention analysis is performed on service requests or fault triggering reconstruction through an intention driving control layer, different services are constrained and mapped, and a constraint set is quantified. And combining the constraint set with source and destination nodes, and analyzing on a topological graph to generate a candidate strategy. And performing simulation verification by the digital twin through a simulation engine and pre-verification, selecting an optimal strategy, and outputting an instruction. In a physical network layer, physical processing such as port switching and light emitting of an optical module is executed according to an instruction, and performance deviation is corrected through closed-loop feedback. According to the invention, high-reliability and high-efficiency dynamic optical path reconstruction is realized.

The invention provides a redundancy real-time control system based on a TSN. The redundancy real-time control system comprises a CTC, a controller, IO equipment and a time sensitive network TSN switch. Each main controller is provided with one or more standby controllers in a working state, each main IO device is provided with one or more standby IO devices in a working state, and each main TSN switch is provided with one or more standby TSN switches in a working state; the controller and the IO equipment in the system form a switched network through the TSN switch; at least two TSN switches are respectively provided with clock sources, the clock sources comprise a main clock source and at least one standby clock source, and the clock sources transmit clock signals outwards hop by hop through adjacent links; the CTC is connected to each clock source, the CTC comprises a main CTC and a standby CTC, and the CTC is used for managing a clock domain of the system and sensing clock synchronization states of all nodes in the system. The technical problem of low transmission efficiency of a bus-based redundancy control system in related technologies is solved.

The invention relates to a heat exchange network transformation method and device. The method comprises the steps that a heat exchange network topological structure is constructed; continuously updating model parameters of the basic model of each heat exchange device based on the time sequence data to obtain updated model parameters of each time period in the plurality of time periods; calculating evaluation indexes of the heat exchange devices according to the updated model parameters, and comprehensively sorting all the heat exchange devices based on the evaluation indexes to obtain a sorting result; target time periods in typical working conditions are determined from the multiple time periods, and heat exchange equipment to be transformed is screened out from all the heat exchange equipment on the basis of the sorting result of the target time periods; solving the constructed optimization problem to obtain a transformation scheme of the heat exchange equipment to be transformed; the optimization problem takes the increase amplitude of the heat exchange area of the heat exchange equipment to be transformed as an optimization variable, and takes the minimum total annual cost as an optimization target, so that the dependence on artificial experience can be reduced, and the transformation scheme generation efficiency is improved.