13 results about "Scalable distributed" patented technology

This application provides a distributed wireless resource scheduling method and electronic device, relating to the field of wireless communication network technology. In this method, the coordinator and computing nodes only need one round of information exchange, avoiding the huge signaling overhead and accumulated latency caused by multiple rounds of iterative negotiation. Time-consuming optimization calculations are offloaded to multiple computing units for parallel execution, achieving a linear reduction in overall computation time. Furthermore, it leverages the approximate achievable rate to provide theoretical feasibility for distributed solutions, while global coordination by edge devices ensures the performance of critical users, allowing the performance of the distributed solution to approach that of centralized algorithms, which serve as the performance ceiling. Because the coordination overhead is constant and minimal, and the computational load is effectively distributed, the system performance is far less affected by network size growth than centralized solutions. This makes it highly suitable for deployment in future network scenarios such as ultra-dense networking and large-scale carrier aggregation, enabling high-performance, low-overhead, and scalable distributed resource allocation under an O-RAN architecture.

A first hypervisor running on a first processor cluster is provided. During operation, the first hypervisor can determine a first set of processing nodes and a first memory unit of the first processor cluster in response to the booting up of a first Basic Input / Output System (BIOS) of the first processor cluster. The first hypervisor can discover a second hypervisor running on a second processor cluster comprising a second set of processing nodes and a second memory unit. The first hypervisor can operate, with the second hypervisor, a distributed system comprising the first and second sets of processing nodes and the first and second memory units. The first hypervisor can then operate, with the second hypervisor, a global virtual machine on the distributed system. The virtual memory space of the global virtual machine can be mapped to respective memory spaces of the first and second processor clusters.

An integrated circuit (IC) design may be received by a first process. First reset domain crossing (RDC) analysis may be performed by the first process on the IC design to generate first RDC analysis results. A set of processes may be spawned by the first process, where a second process in the set of processes may read the first RDC analysis results, obtain information for an RDC scenario from the first process, perform second RDC analysis on the IC design based on the information for the RDC scenario to obtain second RDC analysis results, and send the second RDC analysis results to the first process. The second RDC analysis results received from the set of processes may be merged by the first process to obtain merged RDC analysis results.

A system and method for self-executing graphs wherein execution semantics are encoded within graph elements themselves rather than imposed by external schedulers. The system comprises a dynamic property graph with vertices and edges that encode execution semantics specifying computational operations and graph-internal triggering conditions. An execution engine evaluates these triggering conditions by monitoring graph state, detects satisfaction through graph-internal evaluation, and initiates bound computational operations. Triggering conditions are expressed in terms of vertex or edge traversal, property changes, geometric properties such as curvature, or topological connectivity patterns. The graph autonomously determines when and which operations execute based on graph-resident execution semantics. In distributed embodiments, multiple local coordinators evaluate triggers within assigned graph regions and coordinate through peer-to-peer messaging without centralized scheduling. Applications include autonomous cognitive systems, adaptive control systems, and scalable distributed computation requiring self-regulating execution without centralized bottlenecks.

This invention discloses a scalable distributed multi-chamber open-path photosynthetic measurement system and method, relating to the field of plant physiological and ecological measurement technology. The system includes a main unit and at least two distributed chambers. The main unit centrally manages gas supply, concentration mixing, flow control, and high-precision concentration differential analysis. Each chamber is an independent unit, equipped with an adjustable LED light source, thermoelectric temperature control module, multiple types of sensors, independent power supply, and wireless communication module. An open path is formed through the gas supply pipeline and the return pipeline. The core of the method lies in the main unit polling and sampling the return gas from each chamber according to a preset program through a multi-channel automatic switching valve group. Combined with a "flushing stabilization" strategy, a single gas analysis unit is used to achieve high-precision, high-throughput parallel measurement of multiple chambers. This invention solves the problems of low throughput and high cost of traditional open-path instruments, achieving a balance between high precision and high throughput, and supports in-situ deployment in the field and remote monitoring.

The invention discloses a safe extensible distributed system implementation method supporting corruption self-repairing, which comprises the following steps: a registration node generates a key pair and pays guarantee deposit, and a node passing verification enters a candidate pool; each fragment runs a Byzantine fault-tolerant consensus algorithm to process the transaction, and a state snapshot is broadcasted when the time is ended; when activity loss is detected, the node broadcasts a stagnation report and reports in a cross-piece manner after a threshold value is reached, and other nodes verify the authenticity of the report; when security loss is detected, the nodes broadcast conflict state proof, and the nodes in the fragments broadcast committed snapshots and receipts; if no security loss exists, selecting the highest committed height state, otherwise, selecting the bifurcation state with the highest total transaction amount; comparing the signature with the receipt to identify malicious nodes; new nodes are selected from the candidate pool to replace the old nodes, and all the nodes committ new states and member configurations. The method and the device are used for solving the problems that a fragment configuration scheme of an existing fragment block chain is poor in expandability and low in security, and too high extra overhead is introduced for transaction processing.

The application discloses a kind of turbo-shaft turboprop engine mechanical hydraulic product test intelligent knowledge fusion platform.The platform includes distributed mass test data storage, data warehouse-text knowledge fusion and system plug-in function enhancement mechanism;Based on distributed mass data storage, flexible and scalable distributed storage scheme is provided for the mass data generated by test;On this basis, mass data is organized through data warehouse, based on data warehouse-text knowledge fusion, unstructured text data and structured mass data stored in data warehouse are linked through the form of URL, the fusion of unstructured and structured is realized;Through system plug-in function enhancement mechanism, the function of adding and updating decision algorithm at any time is realized.The application solves the technical problems of storage, management and query of product mass test data, provides data support for decision algorithm, realizes the extension and dynamic updating of system function.

This invention discloses a highly scalable serverless computing distributed scheduling system, comprising a gateway, a central layer, and a local layer. The central layer further includes an auto-scaling engine and a global scheduler. The local layer includes a local scheduler on each node. The auto-scaling engine processes user function call requests from the gateway and determines whether to generate a scaling task. The local scheduler interacts with received scaling tasks through a local check phase, a local probing phase, and a global scheduling phase. The global scheduler schedules scaling tasks issued during the global scheduling phase by finding the optimal node among all nodes in the cluster. This invention combines "local-central" scheduling with highly scalable distributed instance scheduling technology based on local probing, significantly improving the instance scheduling throughput and elastic scaling capabilities of serverless platforms.

This invention relates to the field of hard disk technology, and solves the technical problems of low global storage utilization in existing technologies, unnecessary redundancy waste when node reliability is high, and inability to provide sufficient fault tolerance when node reliability is insufficient. In particular, it relates to a data storage system, method, and storage medium based on edge computing. The method involves the following steps: collecting the raw data stream of the target data device, and obtaining preprocessed data blocks through data preprocessing based on the raw data stream. This invention uses consistent hashing to map nodes and data blocks to a ring space, providing a structured and scalable distributed basis for replica placement. It calculates the data reliability benefits under different replica numbers through an exponential decay availability model, and solves the Nash equilibrium point through a particle swarm optimization algorithm, minimizing global storage costs while ensuring availability, effectively solving the problem of excessive data redundancy between edge nodes.

A scalable, distributed load control system for home automation based on a network of microphones may include control devices (e.g., load control devices) that may include microphones for monitoring the system and communicating audio data to a cloud server for processing. The control devices of the load control system may receive a single voice command and may be configured to choose one of the load control devices to transmit the voice command to the cloud server. The load control devices may be configured to receive a voice command, control a connected load according to the voice command if the voice command is a validated command, and transmit the voice command to a voice service in the cloud if the voice command is not a validated command. The voice service to which the load control devices transmit audio data to may be selectable.

The invention discloses an SCADA method and system based on MQTT edge-to-service, and belongs to the technical field of industrial Internet of Things. The system adopts a five-layer architecture of an equipment layer, an edge layer, a centralized management and control layer, a development layer and a security isolation layer. The method is characterized in that edge nodes collect multi-protocol industrial equipment data at high frequency; the method comprises the following steps: integrating MQTTBroker and sFTP services by an edge controller deployed in a DMZ area to realize data aggregation, edge calculation and offline caching, and uploading data to a central server through independent dual channels; and the central server carries out centralized monitoring, analysis and instruction issuing. And the development layer realizes configuration multiplexing through a unified information model. The safety level is combined with DMZ isolation, double firewalls and transmission encryption to construct deep protection. The system solves the problems that a traditional SCADA system is difficult to expand, poor in heterogeneous compatibility, low in remote operation and maintenance efficiency and the like, and distributed monitoring which is low in cost, high in safety and easy to expand is achieved.

One embodiment provides for a non-transitory machine readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising providing an interface to define a neural network using machine-learning domain specific terminology, wherein the interface enables selection of a neural network topology and abstracts low-level communication details of distributed training of the neural network.

The invention discloses an extensible distributed financial system and method based on post-quantum security and auditing and a storage medium. A market transaction method of the system comprises the steps that a network node receives a transaction request from a client; performing simulation execution on the transaction request by a peer-to-peer node in the network node, and signing an endorsement response by adopting a password agility module; the sorting service of the system adopts a consensus mechanism which separates transaction data propagation from a Byzantine fault-tolerant consensus of transaction metadata certification, globally sorts endorsed transactions, and generates blocks containing ordered transactions; verifying the validity of each transaction in the block through a zero-knowledge proof protocol; and providing an auditing key for an auditing mechanism to realize supervision and auditing. According to the invention, the strong guarantee requirement of the future digital financial market on the long-term safety of the system, the extremely high performance requirement on transaction processing, the strong protection requirement on transaction privacy and the strong penetration requirement on national financial supervision can be met at the same time.