54results about How to "Reduce service latency" patented technology

A method of reducing network congestion and service latency associated with downloading Web pages containing third party advertisements. In one embodiment, pattern recognition algorithms are employed to determine whether a request for a URL may be satisfied by the content associated with a URL which is contained in the client's cache; if there is a pattern match, the cached contents associated with the URL are delivered to the browser to satisfy the request. In another embodiment, images associated with HTML snippet ads are requested and cached by client software before they are requested by the browser downloading the Web page where the images will be displayed. In a third embodiment, latency is reduced by “time shifting,” wherein a cached ad is displayed while client software requests and caches the ad originally requested ad, which will be shown the next time the URL is requested. In other embodiments, this time-shifting technique may also be combined with the pattern-recognition technique and the approach to accelerating delivery of HTML snippet ads.

The invention belongs to the technical field of networks, and relates to a position-based edge cloud resource scheduling method and a location-based edge cloud resource scheduling system. The method comprises the following steps of: establishing a resource list for the positions of edge nodes and services which can be provided by the edge nodes; and continuously and circularly carrying out the following steps: obtaining a cloud service requested by the terminal equipment and the position of the terminal equipment in real time; scheduling the edge nodes providing service for the terminal equipment nearby according to the resource list, the position of the terminal equipment and the requested cloud service in real time, wherein the edge node at least comprises edge terminal equipment with computing power. Related cloud services are dynamically deployed according to the position change of the user terminal equipment or the Internet of Things terminal, so that the marginalization of the cloud services is realized, the requirement of nearby providing of the cloud services of the mobile Internet of Things terminal or the user terminal is solved, the service delay is smaller, and the adaptability of a cloud platform is better embodied.

Many examples exist of a mobile node moving between the operational zones of multiple network access points or base stations. To minimize delay in re-authenticating with the network through a new base station, an additional form authenticated access mode called “credential authenticated” access is provided. The mobile unit is fully authenticated in the first base station (e.g., the user has logged in and paid for service). Thereafter, the first base unit transmits a “credential” to the mobile node that may be used by other base stations to establish trust with the mobile node prior to full re-authentication. Upon entering the operational zone of the second base station, the mobile node can transmit the credential to the second base station, which may accept the credential and allow access by the mobile node to the network through the second base station before full authentication has completed.

A method quickly resuming a downlink service in a hard handover in a cellular mobile communication system. To provide the fast downlink service to an MS during a hard handover from an OBS to an NBS, the NBS receives handover user information from the OBS, and generates an MS temporary ID using the handover user information to identify the MS. If user data is generated for the MS before a connection is established for traffic transmission between the MS and the NBS, the NBS transmits the user data to the MS on an HCCH using the MS temporary ID.

The invention discloses an Internet-of-Vehicles data-driven task unloading system and method based on mobile edge computing. The system comprises an application layer, a vehicle layer, an MEC layer and a cloud layer. The application layer comprises data perception management, ITS service management and road safety management; and the vehicle layer includes a sensing vehicle and a computing vehicle. The sensing vehicle collects various traffic data and unloads the traffic data to the computing server for computing, and the computing vehicle provides computing service for sub-tasks in the V2V communication range; the MEC layer comprises an MEC server and an RSU, and the MEC server serves as a computing server and a local scheduler to be deployed near the RSU; and the cloud layer comprises acloud server and a backbone network, and the vehicle can unload its subtasks to the cloud server through a cellular interface. The system and method have the advantages that the service delay and theservice cost of the data-driven task are reduced, the task unloading architecture is distributed, the decision time of task unloading scheduling can be effectively shortened, and the utilization rateof resources is increased.

The present disclosure relates to a pre-5th-Generation (5G) or 5G communication system to be provided for supporting higher data rates Beyond 4th-Generation (4G) communication system such as Long Term Evolution (LTE). Methods and apparatuses are provided for devices in a wireless communication system. Information requesting a channel estimation by at least one second device is transmitted from a first device to the at least one second device. Channel information is received at the first device as feedback from the at least one second device.

The invention belongs to the technical field of fog computing and information security, and discloses a block-level data de-duplication method for supporting dynamic ownership management in fog storage. The method provides an improved block-level client de-duplication technology, and solves the problem of data sensitive information revealing of the current block-level client during de-duplicationwhile saving network bandwidth. The method also provides a secondary ownership list and a key update mechanism, can realize the access control of fine grain at a lower cost while effectively saving storage space, and fills up the blank of no compatibility between ownership management technologies and the block-level client de-duplication technologies. In addition, the method also introduces a datablock dynamic storage mechanism, data blocks in a system can be transferred in the system according to service needs, and therefore, service costs and file access delay can be reduced, system security and user service experience can be enhanced, and the problem of low system resource utilization rates in a current fog storage de-duplication scheme can be solved.

The invention discloses a calculation task dynamic unloading method based on energy consumption and delay trade-off in vehicle fog calculation, and belongs to the technical field of fog calculation application. In order to make full use of computing resources of nearby vehicles, tasks of the cloud nodes are issued to the vehicle nodes from the cloud nodes, overload of the cloud nodes is reduced,service delay in peak hours is reduced and electric energy is saved for the cloud nodes powered by batteries. The method includes: defining a VFC environment corresponding to the unloading method; constructing an energy consumption cost for a single task of a single vehicle node, the energy consumption cost being a weighted sum of total energy consumption and total delay: constructing a joint objective function for models of energy consumption and delay of all tasks of all nodes in a VFC environment, giving constraint conditions and defining an optimization problem; and aiming at the optimization problem in the step 3, solving a vehicle node to which each task should be unloaded when the joint target function reaches a minimum value, thereby obtaining an optimal task unloading scheme. According to the invention, energy consumption is reduced, and overall processing delay is reduced.

The invention provides a complex task allocation method based on a server-free fog computing system architecture, which comprises the following steps that 1, terminal equipment sends a task request toa fog node, and the fog node receives the task request and transmits the task request to an application layer to start service; 2, an access control module of the application layer performs access control on the task request; 3, the access control module transmits the task requests allowed to be accessed to a request forwarding module of the application layer to perform priority ranking of the task requests; and 4, the request forwarding module transmits the sorted task requests to a service manager of the application layer, and the service manager performs difficulty judgment and allocationon the task requests. According to the complex task allocation method based on the server-free fog computing system architecture provided by the invention, task request allocation can be carried out according to the performance of the fog node, a cask effect is avoided, the service delay of a large task is reduced, and the task request of a high-mobility and high-dynamic scene is effectively solved.

The invention discloses a task scheduling method based on deep reinforcement learning in a hierarchical edge computing environment. The method comprises the following steps: establishing a neural network model based on Sequence-to-Sequence (Seq2Seq), and applying the model to solve mapping from an optimal task to an edge service node to serve as a neural network structure in an intelligent agent; training the model by adopting a deep reinforcement learning method based on Monte Carlo strategy gradient, so that the model has a self-learning capability and a capability of optimizing a task scheduling decision; and deploying a task scheduling algorithm fusing neural network solution and a heuristic algorithm in the system, so that the quality of a scheduling decision can be remarkably improved, and the efficiency and the quality can be balanced.

A method and apparatus of detecting a radio link failure in a wireless communication system is provided. A mobile station initializes a radio link failure (RLF) counter for detecting the radio link failure and determines whether decoding of a message on a downlink channel is successful. The mobile station decrements a value of the RLF counter if the decoding fails, and increments the value of the RLF counter if the decoding is successful, and declaring the radio link failure if the value of the RLF counter is less than or equal to a specific value. A decrement size of the value of the RLF counter varies according to a received signal strength of the downlink channel.

A method quickly resuming a downlink service in a hard handover in a cellular mobile communication system. To provide the fast downlink service to an MS during a hard handover from an OBS to an NBS, the NBS receives handover user information from the OBS, and generates an MS temporary ID using the handover user information to identify the MS. If user data is generated for the MS before a connection is established for traffic transmission between the MS and the NBS, the NBS transmits the user data to the MS on an HCCH using the MS temporary ID.

A method for continuously providing an edge computing service to user equipment (UE) by an edge enabler server (EES) of a mobile edge computing (MEC) system is provided, which includes receiving, from a source edge application server (EAS), update information including UE information and source EAS information, wherein the source EAS provides the edge computing service to the UE; retrieving, from an edge configuration server (ECS), target EES information based on the update information; transmitting, to a target EES, the UE information and the EAS information based on the target EES information; receiving, from the target EES, target EAS information; and transferring, to the source EAS, the target EAS information.

The invention belongs to the technical field of cloud computing and information security. The invention discloses an attribute encryption method supporting efficient data deduplication and attribute revocation in cloud storage. According to the method, attribute authority is introduced between a cloud server and a data owner; the attribute authority finds out a specific prime number correspondingto the outsourcing data label through mapping, and the cloud server can judge whether corresponding outsourcing data exists in the cloud or not only by performing simple division operation on the prime number, so that the problem of low repeated data searching efficiency in the current duplicate removal scheme is solved; according to the method, private cloud is required to complete ciphertext updating according to an updating key issued by attribute authority, so that the problem that an unauthorized user cannot be revoked in a current duplicate removal scheme is solved; in addition, the method supports a ciphertext outsourcing decryption function, and the calculation burden of a user is reduced.

The invention provides an application service operation processing system based on multi-machine hot backup. On the basis that the multi-machine hot backup is adopted, according to the communication control and the switching on-line operation strategy between a plurality of application program operation units and a plurality of service database units, the application program operation units subjected to on-line operation do not need to directly participate in hot backup data processing, the processing performance of the application service, which is outwards provided by the application program operation units, is guaranteed; only when each service database unit in the system obtains that the operation state of the application program operation units subjected to on-line operation is abnormal, the active / standby switching of the application program operation units is triggered; the possibility of the operation of switching by mistake is greatly lowered; the application program operation units and the service database units can be independently subjected to active / standby switching; the transition of the active / standby switching is smoother and quicker; and the application service operation switching smoothness and stability of the multi-machine hot backup system can be greatly improved.

The invention relates to a data processing method and device and electronic equipment. The method comprises the steps of: carrying out the first heterogeneous acceleration of a data block if the datablock written by a server host is detected to be stored in a data cache region, wherein the server host is used for receiving to-be-processed data sent by a client at a time, dividing the to-be-processed data into at least two data blocks, and writing each data block into the data cache region; counting the number of the data blocks subjected to the first heterogeneous acceleration processing in the data cache region; and if the number of the data blocks subjected to the first heterogeneous acceleration processing in the data cache region reaches the number of the data blocks divided by the to-be-processed data, performing second heterogeneous acceleration processing on a processing result corresponding to each data block to obtain the target processing result of the to-be-processed data.By adopting the method, the problem of relatively low data processing efficiency of the server in related technologies can be solved, so that the data processing efficiency of the server is improved.

The present invention discloses a method for transmitting Near Video on Demand (NVoD) using Catch and Rest (CAR) and sub-channels which includes: dividing an L-sized content into N segments using the CAR broadcasting scheme, allocating the segments to K channels including a replicate channel, and broadcasting the segments; dividing a first segment S1R (SiR represents an i-th segment of a regular channel) into Nsb sub-segments again at given bandwidth using the harmonic broadcasting scheme, and dividing an i-th sub-segment Sisb into i segments again; broadcasting the sub-segments {Si.1sb, . . . , Si.isb} in n sub-channels; and adding the segments {S2R, . . . , SNR} to a sub-layer and broadcasting the segments, the first segment broadcast in the first channel being divided and allocated to a few sub-channels, the succeeding segments broadcast in the other channels being just shifted and broadcast.

The invention provides a service chain deployment method and device for a cloud edge collaborative Internet of Things. The method comprises the following steps: obtaining a first construction scheme of a service chain SFC according to a preset arrangement sequence and a preset dependency relationship of VNFs in the SFC, and determining the VNFs with parallel function requirements in the SFC according to the service types of the VNFs, parallel processing is carried out on a part of VNFs in the SFC to form a second construction scheme; merging partial virtual nodes in the second construction schemes of the plurality of different SFCs to obtain a comprehensive construction scheme; and establishing a service chain deployment optimization model of the comprehensive construction scheme, obtaining a deployment scheme of each virtual node and each virtual link in the comprehensive construction scheme according to an optimal solution of the service chain deployment optimization model, and deploying each virtual node and each virtual link on the cloud edge collaborative network according to the deployment scheme. According to the invention, the service chain time delay is reduced, and the quality, reliability and stability of the network are improved.

The present disclosure relates to a pre-5th-Generation (5G) or 5G communication system to be provided for supporting higher data rates Beyond 4th-Generation (4G) communication system such as Long Term Evolution (LTE). Methods and apparatuses are provided for devices in a wireless communication system. Information requesting a channel estimation by at least one second device is transmitted from a first device to the at least one second device. Channel information is received at the first device as feedback from the at least one second device.

The present invention relates to an inter region handover method in a communication system. An inter region handover method in a communication system according to the present invention comprises a region monitoring step, a region rescanning step, a region redecision step and a CoMP connection reconfiguration step in cases where a terminal moves between regions in a communication environment in which a communication area, in which at least one base station provides a service, is divided into at least two of at least one center region, at least one boundary region and at least one common region.

The invention discloses a smart travel method based on edge computing and a cloud platform system, the system comprises a computer cloud platform and a user mobile terminal, and the computer cloud platform is wirelessly connected with the user mobile terminal; the computer cloud platform is used for receiving a tourism service request of the user mobile terminal, planning a tourism route, generating a user tourism route scheme, configuring an edge calculation support packet according to the tourism recommended route, and sending the edge calculation support packet to the user mobile terminal;and the user mobile terminal is used for collecting and transmitting a tourism service request of a user, receiving the edge calculation support packet, and analyzing and calculating the edge calculation support packet according to the requirements of the user. The system does not need continuous interaction between a cloud platform and a mobile terminal, improves the automation of tourism services, reduces the service delay, and improves the user experience.

The invention discloses a reliable edge-cloud computing service delay optimization method for a cyber-physical system. The method is a service delay optimization method combining a static stage and a dynamic stage. In the static stage, Monte Carlo simulation and integer linear programming are adopted to search for optimal computing unloading mapping and task backup quantity. In the dynamic stage, an adaptive backup dynamic mechanism is proposed to avoid redundant data transmission and execution, thereby achieving additional energy saving and enhancement of service delay. According to the method, the problem of edge cloud computing service delay minimization of a coupled CPS under the constraints of energy budget and reliability requirements is solved, service delay optimization is carried out by combining the static stage and the dynamic stage, and the system service delay is effectively reduced.

The invention provides a distributed cloud service implementation method and device, equipment and a storage medium, and the method comprises the steps that a plurality of service platforms comprise a main platform and a plurality of sub-platforms, the service management system corresponding to the main platform regularly obtains idle information of multiple application services corresponding to the main platform and idle information of multiple application services corresponding to each sub-platform; the service management system corresponding to the main platform updates an idle table according to the idle information, and issues the updated idle table to the service management systems corresponding to the plurality of sub-platforms; the service requester submits an access request to the service management system of the initial service platform; the service management system of the initial service platform searches an idle table according to the access request; according to the idle table, a target application service capable of responding to the access request is determined, and the target application service is returned to the service requester; and the service requester accesses the target application service. The occurrence of network congestion and the like can be reduced, and the service efficiency is improved.

The invention belongs to the field of mobile communication, and provides a task unloading and parameter optimization method and system of an MAR client in edge computing. The method comprises the following steps: determining a fitness function according to real-time information of all tasks to be executed, business characteristics of all MAR client users, energy loss of all MAR clients, service period delays of all MAR clients and a target detection function; generating an unloading decision according to the state of the edge server and the state of the MAR client; carrying out related parameter calculation by using a server selection and parameter optimization algorithm, returning calculation parameters to the MAR client for adjustment, and then sending a single image frame to an associated edge server by the MAR client for target detection; and repeating the processes of parameter calculation and target detection until the fitness function converges, and obtaining a final parameter value and an unloading decision.