82 results about "Metrics" patented technology

In variants, the method can include determining training data, determining a router, and using the router. In variants, using the router can include receiving a runtime prompt, predicting performance scores for the runtime prompt for each of a set of candidate models, optionally predicting operational metrics for responding to the runtime prompt for each of the set of candidate models, selecting a candidate model based on the predicted performance scores and optionally the predicted operational metrics, and optionally determining a response based on the runtime prompt.

Discussed are systems, methods and computer readable media that use a segment routing system and compute a path for network traffic based on segment routing policies. Based on these computations, the system is able to determine a path, and if the path is unique. When the path is unique it is stored in a path database which includes the unique paths available to the segment routing system. Based on the path database and segment routing polices, the system will compute a best path from the available unique paths for the network traffic based on measured and predicted performance metrics of the unique paths.

Techniques for optimizing routing decisions based on security metrics within a network environment are described herein. In some cases, by using various security metrics, such as encryption indicators, attestation indicators, secureness metrics, and reliability metrics, an exemplary system can assess the security level and reliability of network paths. These metrics may provide valuable insights into the trustworthiness and integrity of participating nodes and links and enable informed decision-making regarding path selection.

A method for routing data traffic in a communication network includes decoding, by a source node, an Internet protocol (IP) data packet to determine a destination node. A routing table for the destination node is retrieved. The routing table identifies a plurality of next-hop nodes associated with a corresponding plurality of routing paths to the destination node. A plurality of saturation metrics corresponding to the plurality of routing paths are determined using the routing table. Each of the plurality of saturation metrics is indicative of data traffic saturation along a corresponding one of the plurality of routing paths. A routing path is selected from the plurality of routing paths based on the plurality of saturation metrics. The IP data packet is forwarded to a next-hop node in the selected routing path.

The invention relates to multi-path routing of a switch fabric. The switching fabric uses traffic congestion information to notify it of timely use of non-minimum routing. An ingress port of a network switch collects traffic congestion information from an egress port of the network switch. The traffic congestion information includes minimum and non-minimum routing congestion metrics for the egress port. A candidate egress port is identified for forwarding the data packet to the destination node. And selecting one of the candidate exit ports according to the traffic congestion information. The selection process is biased to select some candidate egress ports rather than other ports. In particular, a candidate egress port providing non-minimum routing to a destination node and having a high minimum routing congestion metric is not sponsored by a selection process.

The invention discloses a fast global wiring method based on multi-index driving. In a global wiring stage, pin accessibility is fully considered, wiring quality in the global wiring stage is improved, problems in a subsequent detailed wiring stage are effectively reduced, chip performance is improved, design violation is reduced, and detailed wiring speed is increased. In addition, the pin density and the RUDY drive global wiring device are considered for wiring, a global wiring initial solution can be better generated, multiple indexes (the pin accessibility, the pin density and the RUDY drive index) are mutually constrained, and a good global wiring solution is obtained. And finally, the global wiring resources are subjected to weight distribution modeling, so that the wiring resources can be utilized more efficiently.

The invention discloses a service network flow analysis system capable of giving an alarm in a second level, improving the abnormal response speed of a key link and reducing the risk of network attack, and the system comprises a flow collection module which collects flow data from a router / switch port of the key link through an SNMP protocol; the data processing module is used for cleaning, aggregating and analyzing the collected flow data to generate a flow index; the data storage module is used for storing historical data, baseline data, user information and alarm records; the baseline early warning module dynamically generates a workday / holiday flow threshold according to the historical data, compares the current flow with the flow threshold in real time, and triggers an alarm; the alarm module is used for giving an alarm and carrying out fault positioning when traffic abnormity or port state abnormity is detected; and the report query module provides a multi-dimensional report query interface and analyzes historical data. The invention further discloses a service network flow analysis method implemented by adopting the service network flow analysis system.

A switching fabric uses traffic congestion information to inform its opportunistic use of non-minimal routes. An ingress port of a network switch collects traffic congestion information from the egress ports of the network switch. The traffic congestion information includes minimal and non-minimal route congestion metrics for the egress ports. Candidate egress ports for forwarding a packet to a destination node are identified. One of the candidate egress ports is selected based on the traffic congestion information. The selection process is biased to prefer some candidate egress ports over others. Particularly, the candidate egress ports that provide non-minimal routes to the destination node and have high minimal route congestion metrics are disfavored by the selection process.

The present disclosure relates to systems, non-transitory computer-readable media, and methods that improve efficiency and flexibility of implementing computer devices by providing efficient user interfaces to provider devices that include optimal digital routes selected based on dynamic route efficiency metrics. In particular, the disclosed systems can identify and surface an optimal alternative route from a pickup location to a drop-off location associated with a transportation match based on a variety of dynamic non-temporal factors. The disclosed systems can utilize a variety of computer implemented models to determine non-temporal factors, such as distance efficiency metrics, route-segment access efficiency metrics, congestion efficiency metrics, risk efficiency metrics, and match-based efficiency metrics. The disclosed systems can then combine these non-temporal factors utilizing a common efficiency framework to determine and surface an optimal alternative route.

Systems and methods are disclosed for optimizing network routing and data processing through dynamic route optimization. The invention features a dynamic route optimization engine that uses real-time performance metrics such as latency, bandwidth availability, memory utilization, CPU load, and throughput capacity. It allows for rule-based configurations, enabling custom parameters for transaction processing, data retrieval, and user authorization. Integration with network monitoring tools provides continuous visibility into network performance. The system supports multi-cloud and hybrid cloud environments, dynamically selecting optimal paths based on real-time conditions and regulatory compliance. Predictive analytics anticipate network congestion, allowing proactive routing adjustments. Adaptive algorithms learn from past conditions to optimize performance continuously. Scalability is achieved through automated updates to routing tables and security groups. The invention reduces latency and ensuring efficient data transfer, providing a cost-effective and reliable solution for modern network management, addressing a long-standing need for adaptability and efficiency in network routing.

In variants, the method can include determining training data, determining a router, and using the router. In variants, using the router can include receiving a runtime prompt, predicting performance scores for the runtime prompt for each of a set of candidate models, optionally predicting operational metrics for responding to the runtime prompt for each of the set of candidate models, selecting a candidate model based on the predicted performance scores and optionally the predicted operational metrics, and optionally determining a response based on the runtime prompt.

The invention discloses an energy-saving QoS (Quality of Service) routing protocol implementation method based on ant colony optimization, which aims at solving the problems of low routing efficiency and high path energy consumption in a UANET (User Ad Hoc Network) based on RF / FSO (Radio Frequency / Free Space Optimization) communication, and realizes an energy-saving QoS routing protocol based on ant colony optimization. An energy-saving QoS routing algorithm based on ant colony optimization is provided, and node neighborhood energy density is considered in a path transition probability model, so that the search efficiency of the ant colony algorithm is improved, and energy balance in the network is ensured; energy and distance factors are added into a pheromone updating rule, and the difference between the optimal path and other paths is increased; a self-adaptive pheromone volatilization mechanism is added, and the volatilization rate of pheromones is dynamically adjusted according to the real-time state of the network; and a cross-layer data exchange interface is added, so that real-time updating of link interaction data is ensured, and stable communication in a dynamic network environment is supported.

In variants, the method can include determining training data, determining a router, and using the router. In variants, using the router can include receiving a runtime prompt, predicting performance scores for the runtime prompt for each of a set of candidate models, optionally predicting operational metrics for responding to the runtime prompt for each of the set of candidate models, selecting a candidate model based on the predicted performance scores and optionally the predicted operational metrics, and optionally determining a response based on the runtime prompt.

Systems and methods for generating routing tables and providing these tables to routers in a network for use in routing data to various destination routers. One embodiment comprises an apparatus that includes a centralized controller for a network. The centralized controller is adapted to receive link metrics for a plurality of links between routers in a WAN. For each pair of routers, the centralized controller determines the paths between the router pair, determines suitability metrics for each path, wherein each metric is specific to a corresponding data type, and selects, for each data type, a corresponding subset of the paths between the router pair based at least in part on the suitability metrics for the data type. The centralized controller then transmits, to each of the routers in the WAN, the selected subsets of the paths for the corresponding router.

A system is provided for optimizing dynamic routing in a capsule network. The system includes an autoencoder configured to encode input data into a latent space representation; a plurality of capsule networks comprising capsule layers; and a generative adversarial network (GAN) including (a) a generator that receives the latent space representation and a noise vector and outputs routing coefficients, and (b) a discriminator that evaluates the routing coefficients by assessing performance metrics from one or more of the capsule networks. The routing coefficients determine how outputs from a capsule layer in one capsule network are routed to a capsule layer in another. Based on performance feedback, the discriminator adjusts the generator for subsequent iterations to improve routing effectiveness. This architecture enables adaptive, performance-optimized routing across modular capsule networks using adversarial learning.

Techniques are disclosed for computing a cost of an advertised route to a next-hop network device along a path to a destination based at least in part on a preference for the path. In one example, a computing system computes a cost of a route to a next-hop network device along a path to a destination. The computed cost is based at least in part on (1) a metric for the route and (2) a preconfigured preference for the path. In some examples, the preference for the path is based at least in part on (a) a type of the path as compared to other types of other paths to the destination or (b) a latency of the path as compared to other latencies of the other paths. The computing system sends a route advertisement for the route that includes data indicative of the cost of the route.

An off-path or in-path connection-ordering update (COU) function enables the relative priorities of network and compute metrics to be fine-tuned when generating global utility values used to generate a re-ordered list from an initial list of Internet Protocol (IP) addresses corresponding to a domain name identified by an application client. The initial list may contain IP addresses of edge servers corresponding to the domain name. The re-ordered list may contain either (i) the (re-ordered) edge-server IP addresses or (ii) IP address pairs identifying the (re-ordered) edge-server IP addresses and IP addresses of corresponding egress edge routers of an intervening routing network also having an ingress edge router connected to the application client.

Systems, methods, and machine-readable media facilitate adaptive multi-system operations. Electronic communications from resource-controlling systems and / or monitoring devices may be monitored to identify signals corresponding to processes performed by the resource-controlling systems, resource capacities of resources controlled by the resource-controlling systems, and states of the resource-controlling systems. System interactions that correspond to a defined event may be detected. A protocol that includes parameter constraints mapped to the defined event identified. Operating conditions of the resource-controlling systems and / or metrics of processes performed may be determined based on the monitoring. A subset of the resource-controlling systems may be identified as a function of the operating conditions and / or the metrics. A resource-controlling system may be caused to allocate corresponding resources and perform the processes in accordance with the protocol.

Described are aspects of a sharded monitoring system that collects metrics data from a plurality of targets within a monitored system. The monitoring system includes multiple monitoring-server instances each collecting metrics data from a respective subset of the targets, as well as a federation server that collects aggregated metrics data from the other monitoring-server instances. Mappings between monitoring targets and monitoring-server instances collecting their metrics data may be stored in a temporal routing map, e.g., on the federation server, which may build the map based on time-series routing metrics received from the other monitoring-server instances. The routing map may be used to direct queries for metrics data from a client to the appropriate monitoring-server instance.

In variants, the method can include determining training data, determining a router, and using the router. In variants, using the router can include receiving a runtime prompt, predicting performance scores for the runtime prompt for each of a set of candidate models, optionally predicting operational metrics for responding to the runtime prompt for each of the set of candidate models, selecting a candidate model based on the predicted performance scores and optionally the predicted operational metrics, and optionally determining a response based on the runtime prompt.

Systems and methods for generating routing tables and providing these tables to routers in a network for use in routing data to various destination routers. One embodiment comprises an apparatus that includes a centralized controller for a network. The centralized controller is adapted to receive link metrics for a plurality of links between routers in a WAN. For each pair of routers, the centralized controller determines the paths between the router pair, determines suitability metrics for each path, wherein each metric is specific to a corresponding data type, and selects, for each data type, a corresponding subset of the paths between the router pair based at least in part on the suitability metrics for the data type. The centralized controller then transmits, to each of the routers in the WAN, the selected subsets of the paths for the corresponding router.

This application discloses a routing method, including: A first user site egress device receives identification information of a target object, a first path index, and a first path performance metrics that are advertised by a first gateway, where the first path index identifies a first path for the first gateway to access the target object, and the first path performance metrics indicates performance of the first path. After receiving the identification information of the target object, the first path index, and the first path performance metrics, the first user site egress device selects, based on the first path performance metrics, a target path for accessing the target object. It can be learned that, according to the solutions, the selected target path can provide good quality of service.

A switching fabric uses traffic congestion information to inform its opportunistic use of non-minimal routes. An ingress port of a network switch collects traffic congestion information from the egress ports of the network switch. The traffic congestion information includes minimal and non-minimal route congestion metrics for the egress ports. Candidate egress ports for forwarding a packet to a destination node are identified. One of the candidate egress ports is selected based on the traffic congestion information. The selection process is biased to prefer some candidate egress ports over others. Particularly, the candidate egress ports that provide non-minimal routes to the destination node and have high minimal route congestion metrics are disfavored by the selection process.

The present disclosure relates to multi-path routing of a switch fabric. The switch fabric uses traffic congestion information to inform its timely use of non-minimal routes. An ingress port of a network switch collects traffic congestion information from egress ports of the network switch. The traffic congestion information includes minimal and non-minimal route congestion metrics for the egress ports. Candidate egress ports are identified for forwarding a packet to a destination node. One of the candidate egress ports is selected in accordance with the traffic congestion information. The selection process favors selecting some candidate egress ports over others. In particular, non-minimal routes to the destination node and candidate egress ports having high minimal route congestion metrics are disfavored by the selection process.

Techniques for optimizing routing decisions based on security metrics within a network environment are described herein. In some cases, by using various security metrics, such as encryption indicators, attestation indicators, secureness metrics, and reliability metrics, an exemplary system can assess the security level and reliability of network paths. These metrics may provide valuable insights into the trustworthiness and integrity of participating nodes and links and enable informed decision-making regarding path selection.

Aspects of the subject disclosure may include, for example, responsive to a request for an end-to-end service, obtaining power-related data for each of a plurality of network elements, identifying a set of candidate service routes that is each associated with a respective subset of the plurality of network elements, for each of the candidate service routes, calculating at least one power metric based on the power-related data of each network element in the respective subset associated with that candidate service route, resulting in a plurality of power metrics, and presenting or utilizing the plurality of power metrics to facilitate selection of a desirable service route from the set of candidate service routes for the end to end service. Other embodiments are disclosed.

Embodiments herein comprise obtaining states of network links of paths from an initiator (e.g., host) to a target (e.g., storage subsystem) to determine weight factors for the paths in a multipath scenario between the initiator and the target. Given the weight factors, they may be used with an NVMe initiator implementation of a multipath weight / load-balancing methodology or system to distribute workloads (e.g., IO tasks / requests) across the paths of the set of paths in the multipath. In one or more embodiments, each state may have a metric associated with it, which may act as a cost or be used to determine / assign a cost to the corresponding link. In one or more embodiments, one or more additional rules may be set for converting metrics to costs, costs and / or metrics to weights, and / or for distributing the workloads.

Systems and methods for generating routing tables and providing these tables to routers in a network for use in routing data to various destination routers. One embodiment comprises an apparatus that includes a centralized controller for a network. The centralized controller is adapted to receive link metrics for a plurality of links between routers in a WAN. For each pair of routers, the centralized controller determines the paths between the router pair, determines suitability metrics for each path, wherein each metric is specific to a corresponding data type, and selects, for each data type, a corresponding subset of the paths between the router pair based at least in part on the suitability metrics for the data type. The centralized controller then transmits, to each of the routers in the WAN, the selected subsets of the paths for the corresponding router.

A network device includes a processor and a non-transitory computer-readable storage medium storing logic executable by the processor to perform operations. The operations include receiving, from a second network device, an advertisement for a subnet and a first value of an inbound path preference attribute of a routing protocol; determining a link speed of a link between the network device and a third network device; determining a second value of the inbound path preference attribute based on the received first value and the determined link speed; advertising the subnet to the third network device in association with the second value of the inbound path preference attribute; and routing a data packet from the third network device to the second network device in accordance with a routing table comprising a routing entry based on the first value of the inbound path preference attribute.

Systems and methods for optimizing break-out / break-in paths of voice calls between a source operator's (SO) IP Multimedia Core Network Subsystems (IMS) and a target operator's IMS (TO IMS), the method includes: obtaining a voice call originating from a user equipment (UE) in the SO IMS and terminating at an UE in the TO IMS; determining a routing policy for the voice call; determining an optimal TO Interconnect Session Border Controller (ISBC) by applying at least one path metric according to the routing policy to a machine learning (ML) model for determining an optimal route between the SO IMS and the TO IMS; and route the voice call to the optimal TO ISBC, wherein, the ML model, for determining the optimal TO ISBC using, for each of the path metrics, one or more routing parameter rankings of a plurality of possible paths between the SO IMS and the TO IMS.