126 results about "Packet arrival" patented technology

The invention relates to an office process automation data analysis method based on a symmetric encryption algorithm, and the technical scheme comprises the following steps: introducing an encryption strategy generator, and dynamically adjusting the parameters of the symmetric encryption algorithm including the key length and the encryption round number through the real-time analysis of the data communication content including the data sensitivity, the frequency and the data volume; constructing a self-adaptive optimization model, and adjusting an encryption strategy according to external conditions such as a network state, equipment computing power and user behaviors; fragmenting the data packet before transmission, and allocating different transmission paths according to current network conditions and security evaluation; constructing a dynamic data recombination module at a data receiving end, and verifying and recombining data when encrypted data packets of different paths arrive; a lightweight key negotiation protocol based on symmetric encryption is adopted, and a key is generated and negotiated immediately when two communication parties initiate data exchange; a secret key life cycle management mechanism is introduced, and the service life and the number of times of limitation are set for each secret key.

The invention provides a power system intrusion detection and defense method based on artificial intelligence, and belongs to the technical field of power system intelligent control, and the method comprises the steps: 1, collecting data based on a multi-dimensional data collection layer, and forming an original data flow containing a time-space synchronization mark; 2, dynamically segmenting the original data stream by adopting a self-adaptive sliding window mechanism, automatically adjusting the size of a window according to the arrival frequency of a data packet, and converting the continuous data stream into a final triple sequence; 3, extracting and analyzing the features of the final triple sequence, and determining an equipment behavior mode and sequential logic of power operation; 4, performing deviation analysis on the equipment behavior mode and the normal behavior mode, and generating a primary alarm signal when the deviation degree exceeds a dynamic threshold value; and 5, starting multi-stage interlocking verification based on the primary alarm signal to determine an intrusion type, and matching a preset response rule base according to the intrusion type. Intrusion behaviors in the power system are effectively detected and defended in real time.

Embodiments provide resource-efficient techniques to adapt to dynamically varying traffic using predictive scheduling. Various embodiments may project resource demands and request resources based on the projected resource demands. For example, embodiments may utilize scheduling requests (SRs) and / or buffer status reports (BSRs) to proactively request resources from a base station based on predicted traffic, such as predicted traffic at the time that uplink resource grants are expected. In some embodiments conditional multiple grants may be utilized. For example, multiple grants may be configured simultaneously, and the later grants may be used by the UE only if it cannot fully utilize the previous grants. In several embodiments, artificial intelligence and / or machine learning may be utilized to predict (or project) future data packet size and packet arrival times. In several such embodiments, these predictions may be used to request resources for data packets prior to their arrival in a buffer.

A server delay controller includes: a packet harvesting unit that refers to a packet held in a ring buffer when a packet arrives and executes harvesting to delete an entry of a corresponding queue from the ring buffer, a sleep management unit that puts the thread to sleep in a case in which a packet does not arrive for a predetermined period, and cancels the sleep of the thread through a hardware interrupt at the time of packet arrival, and an idle state recovery control unit that periodically wakes up the thread during sleep or wakes up the thread immediately before the packet arrival in accordance with a packet arrival timing.

The embodiment of the invention relates to the technical field of network and communication, in particular to a scheduling and routing technology in network communication, and provides a TSN network time-sensitive flow scheduling and forwarding method oriented to node collaboration, which specifically comprises the following steps: firstly, a network controller acquires network topology and time-sensitive flow information; then, all the time-sensitive streams are sorted and classified by adopting fuzzy reasoning and clustering analysis, and the priority of the time-sensitive streams and the forwarding path of the time-sensitive streams are determined; issuing the time-sensitive flow priority and the forwarding path to a corresponding node of a network for configuration; determining a time-sensitive flow scheduling forwarding table by adopting non-conflict analysis based on the arrival time of the first packet according to the node configuration information; and finally, the network node schedules and forwards the time-sensitive flow according to the node scheduling and forwarding table. The time-sensitive flow priority and the forwarding path are determined in a centralized manner, the node scheduling table is calculated and configured in a distributed manner to decouple the TSN network routing and scheduling decision process, the calculation complexity is reduced on the basis of ensuring the time-sensitive flow time delay certainty, and the scheduling efficiency and flexibility are improved.

The invention relates to the technical field of malicious software detection, in particular to a malicious code detection method based on behavior analysis, which comprises the following steps of: monitoring a system event stream and process resource occupation data, fixed time interval sampling is adopted to capture a network data packet arrival time interval, CPU occupancy rate fluctuation, a target file lock contention state and a mouse cursor pixel position. According to the method, multi-dimensional system event streams and process resource occupation data such as network data packet arrival time intervals, CPU occupancy rate fluctuation, target file lock contention states and mouse cursor pixel positions are monitored, mutual information entropy between different event streams is calculated, and hidden association which cannot be perceived by a traditional detection method can be revealed. The mode is no longer limited to analysis of isolated behaviors of a single process, but captures weak signals generated when malicious software performs communication or data leakage by using a covert channel by quantifying statistical dependency between seemingly unrelated events.

The invention relates to the technical field of cloud computing and information security services, and particularly discloses a network security and data hosting integrated cloud service system and method, and the method comprises the steps: obtaining a multi-dimensional behavior data flow of a user, and generating a user feature vector; inputting the user feature vector into an incremental clustering algorithm, calculating the distance between the feature vector and a clustering center, performing user classification according to a distance threshold, and generating a user type tag; calculating a user reputation score based on the historical behavior statistical data of the category to which the user belongs; a sliding window algorithm is adopted to collect a data packet arrival time interval sequence, a jitter value in a window is calculated, a jitter value at the next moment is predicted, the number of packet loss in the window is counted, and a packet loss rate estimation value is calculated; and inputting the user type label, the reputation score, the jitter prediction value and the packet loss rate estimation value into a QoS decision engine. According to the invention, the problem of poor high-value user experience caused by unreasonable resource allocation is solved.

The invention discloses a method and a system for identifying refined behaviors of tunnel users, and belongs to the field of network flow detection. The method comprises the following steps: extracting byte features of unlabeled tunnel traffic, learning a context relationship of the unlabeled tunnel traffic through a pre-training network model, and generating vector representation of the byte features; extracting byte features, a data packet length sequence and a data packet arrival time interval sequence of target tunnel user behavior traffic, and obtaining vector representation of the byte features through a pre-training network model; obtaining hidden state features of vector representation of the byte features, a data packet length sequence and a data packet arrival time interval sequence based on a convolutional neural network (CNN), and obtaining a comprehensive hidden state feature through fusion; and inputting the comprehensive hidden state features into a classifier to predict the user behavior of the target tunnel. According to the invention, the problem that tunnel user behaviors are difficult to identify in a real network environment in the prior art can be solved.

The invention provides a malicious encrypted traffic classification method and system based on a session spatio-temporal feature map. The method comprises the following steps: sliding on a cleaned encrypted traffic session by using a sliding window with a predefined duration, and extracting statistical characteristics of the encrypted traffic session, including a packet size characteristic, a packet arrival time characteristic and a packet load alpha-Renyi entropy; taking the packet size feature and the packet arrival time feature of the encrypted traffic session as a Y axis and an X axis respectively, mapping the packet load alpha-Renyi entropy into a gray value, and forming a session spatial-temporal feature map; and inputting the session spatio-temporal feature map into a ResNet-50 model of a CBAM attention mechanism to perform malicious encrypted traffic classification. The scheme provided by the invention can adapt to different malicious encrypted traffic application scenes, so that more efficient and more accurate encrypted traffic classification is realized.

The invention discloses a dynamic protocol identification method and system based on multi-modal data, and belongs to the technical field of data protocol identification, the identification method comprises the following steps: S1, calculating a data packet arrival interval time standard deviation, and judging whether a communication mode is a periodic or sudden communication mode; s2, dividing the data packet according to the length, calculating and counting the probability distribution of each interval, and calculating the Shannon entropy value of the data packet; s3, generating a protocol fingerprint according to the data packet arrival interval time standard deviation, the Shannon entropy value of the data packet and the probability distribution of each interval; and S4, classifying the data packets by adopting an edge AI classification engine. The protocol identification accuracy can be improved, and the network security protection capability is improved.

The invention relates to the technical field of network slicing, in particular to a communication bandwidth guarantee system based on service priority, which comprises a switching intention sensing module for receiving a measurement result of user equipment based on a source base station and judging a switching trend by comparing a preset threshold value of the signal strength of a service cell with a preset threshold value of the signal strength of an adjacent cell in the result. In the invention, the user switching service feature set is dynamically constructed by sensing the comparison of the signal intensity of the service cell and the adjacent cell before switching and combining the context information of the user and the historical service flow monitoring record, so that the predictive value of the user behavior in the network switching is further mined; in this way, the required bandwidth resources are quantized and calculated in advance when the slice user is about to switch. And resource block reservation positioning is performed in combination with the average data rate and the data packet arrival mode, so that the resource scheduling precision is optimized, and bandwidth occupation of a key service by burst traffic during switching is avoided.

Embodiments provide resource-efficient techniques to adapt to dynamically varying traffic using projected resource demands. Various embodiments utilize a dynamic grant-less (DGL) transmission scheme that synchronizes UEs and BSs including synchronization of allocated resources with incoming packets using complimentary AI and / or ML models at the UEs and BSs. For example, an ML model at the BS may predict the size and time of upcoming packet arrival using reports from the UE to align with incoming packets at the UE, and then the BS allocates resources using the prediction. Further, a complimentary ML model at the UE may predict the size and time of upcoming packet arrival using historical packet arrival pattern and calculate the allocated resources simultaneously.

The invention discloses an encrypted malicious traffic detection method and system and a computer readable storage medium, and belongs to the technical field of traffic detection. The encrypted malicious traffic detection method comprises the following steps: acquiring original network traffic data, and constructing a packet length sequence and a packet arrival time interval sequence to form an original time sequence matrix; and extracting a time-frequency energy distribution diagram and a frequency band energy sequence from the packet length sequence through continuous wavelet transform. A time domain time sequence convolution network based on an expansion causal convolution structure is adopted, and a time domain feature vector is extracted from an original time sequence matrix. And extracting frequency domain feature vectors from the time-frequency energy distribution diagram and the frequency band energy sequence by adopting a time-frequency attention and frequency band re-scaling attention module. And performing malicious traffic dichotomy and malicious traffic behavior type multi-classification processing on the time-frequency aggregation feature vector through a hierarchical classifier, and outputting a classification result. According to the scheme, the malicious traffic characterization capability of deep fusion of time-frequency features is realized, and the detection precision of the encrypted malicious traffic is improved.

The invention discloses a priority scheduling delay compensation method and system for star flash multi-link transmission, particularly relates to the field of network transmission optimization, and is used for solving the problems of reliability and resource efficiency of ultrahigh priority data transmission in a star flash multi-link system. According to the method, high-efficiency links are accurately identified and preferentially utilized by quantifying real-time states and historical performance of links through a dynamic link evaluation and screening mechanism, and ineffective occupation of bandwidth resources by low-efficiency links is avoided; the nonlinear replica quantity decision is combined with the delay distribution characteristic and the bandwidth margin to optimize the distribution strategy of the redundant replica, so that the high efficiency of resource utilization is ensured; according to the time window embedding technology, a first packet arriving at a prediction time window label is embedded into a data packet, so that a receiving end can quickly identify effective data in a prediction range, time sequence interference of redundant copy analysis is reduced, the transmission efficiency of a star flash multi-link system is remarkably enhanced in a dynamic interference environment, and systematic optimization of reliability and resource efficiency is realized.

Methods, systems, and devices for wireless communication are described for user equipment (UE) indication of uplink scheduling information to a base station. The uplink scheduling information may provide information on a periodic traffic pattern, such as for periodic extended reality (XR) data flows. The uplink scheduling information may provide uplink assistance information (UAI) to a base station to assist the base station with providing uplink resources that efficiently serve an XR session. The UAI may indicate one or more of a periodicity of uplink traffic, an offset between uplink traffic and a packet arrival, a data size for uplink traffic for each time period associated with the XR session, a request to enable uplink transmission skipping, or any combinations thereof. A base station may provide one or more dynamic grants, configured grants, or proactive grants to a UE based on the uplink scheduling information.

This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for rendering delay aware packet pacing for real time multimedia applications. A processor of a first device transmits, to a second device, an indication of a processing delay associated with a set of packets associated with media content. The processor receives, from the second device, the set of packets in a packet arrival pattern that is based on the processing delay.

A server delay control device (100) includes: a packet harvesting unit (120) that refers to a packet held in a ring buffer (72) when a packet arrives and executes harvesting to delete an entry of a corresponding queue from the ring buffer, a sleep management unit (130) that puts the thread to sleep in a case in which a packet does not arrive for a predetermined period, and cancels the sleep of the thread through a hardware interrupt at the time of packet arrival, and an idle state recovery control unit (150) that periodically wakes up the thread during sleep or wakes up the thread immediately before the packet arrival in accordance with a packet arrival timing.

The invention provides a reliable multi-link transmission method for resisting cascade degradation of a scheduling system, which comprises the following steps: a sender updates link state information based on a data packet arrival event, and implements a degradation strategy on available links based on the updated link state information, so as to determine a degraded link in the available links; the data packet to be sent is sent through the remaining undegraded links in the available links; and the receiver receives the to-be-sent data packet and evaluates whether the current scheduling mode satisfies a preset condition based on the to-be-sent data packet, if not, a notification data packet is sent to the sender, and the sender selects a proper link to be promoted to a scheduling state based on the notification data packet and a promotion strategy. According to the method and the device, the transmission performance caused by link deterioration can be greatly reduced, the problem of transmission state division error caused by environment burst interference can be avoided, and the accuracy of link state evaluation can be improved.

The present invention proposes an information age minimization access method for large-scale Internet of Things scenarios, which relates to the technical field of wireless communications. First, the discretized time is divided into a number of small slots with a certain time length, and the number of user nodes in the network and the data packet arrival rate of the user nodes are obtained by a central base station to obtain a state equation of the probability of successful network transmission, and then the access channel probability in the state equation is optimized. By analyzing the expected optimal access channel probability and the solution of the monostable boundary optimal access channel probability within (0, 1), the optimal access channel probability is obtained. Finally, the central base station notifies each user node of the optimal access channel probability, and performs channel access and data packet transmission according to the optimal access channel probability, thereby minimizing the average peak information age of the network, and ensuring the stability of the network transmission performance while achieving the optimal information timeliness of the network.

The embodiment of the application provides a kind of mining behavior detection method, wherein the method comprises: the first computer equipment obtains data packet arrival time sequence, the data packet arrival time sequence includes the time that at least one data packet from target equipment arrives second computer equipment;The first computer equipment obtains block arrival time sequence, and the block arrival time sequence includes the time that at least one mining task arrives mining equipment;The first computer equipment judges the approximate degree of data packet arrival time sequence and block arrival time sequence in time;If the approximate degree is greater than or equal to the first threshold value of preset, determine that the target equipment is suspected mining equipment.The technical scheme of the application can be free from manual operation and maintenance, cover multiple mining scenarios, and can protect user privacy, with strong versatility.

This application provides a software switch caching acceleration method and related apparatus based on FPGA, belonging to the field of network packet processing technology. The method includes: compiling a caching rule set into a decision tree forest using a decision tree construction algorithm, the decision tree forest comprising multiple decision trees of equal depth; mapping the decision tree forest to multiple parallel tree pipelines, the tree pipelines running on the FPGA, each tree pipeline corresponding to a decision tree, and each pipeline stage corresponding to a node layer of the decision tree; broadcasting a preset data packet to all tree pipelines for parallel processing; for each tree pipeline, guiding the preset data packet to traverse each pipeline stage until the preset data packet reaches the target leaf node of the decision tree; performing parallel rule matching on the preset data packet at the target leaf node of each decision tree to obtain the target caching rule matching the preset data packet, thereby accelerating flow table caching classification.

A method, system and apparatus are disclosed for more fully utilizing a periodic or semi-static scheduled resource, including the repetition resource. In accordance with various embodiments, a network node is configured to allocate a periodic or semi-static scheduled resource to a wireless device (WD) for use in communication for at least two services having different reliability or transmission characteristics. The periodic or semi-static scheduled resource may be allocated by estimating a packet arrival from each of the WD services or in proportion to a services' priority. A periodicity of the resource may be set to a periodicity of an ultra-reliable and low latency communication (URLLC) packet arrival periodicity of a URLLC stream. A repetitious configured grant (CG) can be utilized for additional services or throughput gain. The spared periodic or semi-static scheduled resource may also be allocated for a retransmission of failed packets from a service.

The invention discloses a distributed machine learning training system based on network flow rate control. The distributed machine learning training system comprises a flow information collector module and a job scheduler module, a traffic information collector module collects the number of bytes in a job stream communication mode on a switch, records the timestamp of arrival of a data packet, and calculates the remaining iteration completion time of the job stream; and the job scheduler module determines the priority of the job according to the residual iteration completion time of the job flow, so that the switch preferentially sends the job flow with the shortest residual iteration completion time. According to the distributed machine learning training system and method based on network flow rate control, the utilization rate of a network link can be remarkably improved; by optimizing the communication stage of the job flow, training tasks, such as DNN training tasks, can share network resources more efficiently, thereby reducing network congestion and idle time.

Disclosed are techniques for wireless communication. In an aspect, a radio frequency identification (RFID) station may receive a first packet from an RFID tag at a first arrival time. The RFID station may receive a second packet from the RFID tag at a second arrival time after the first arrival time. The RFID station may estimate a distance between the RFID station and the RFID tag based on an inter-packet arrival time between the first packet and the second packet, the inter-packet arrival time being based on a time difference between the first arrival time and the second arrival time.

This invention discloses a dynamic optimization method for network switch port WRR scheduling resources based on convex optimization modeling. Applied to the field of switching equipment scheduling and control, it addresses the problem that existing scheduling weight configurations cannot adapt to environmental changes, resulting in unstable forwarding performance of switching equipment. This invention establishes constraint functions based on port bandwidth, token resources, and queue number, collects the arrival probability distribution of data packets in each queue within the switch port to establish a distribution model, and combines the constraint functions and the collected model to construct a convex optimization problem for switch port queue resource allocation. The objective of the optimization problem is defined as minimizing the sum of queuing probabilities of the switch queues. The problem is solved using an existing convex optimization solver, and the results are configured as the weights of each port queue based on the Weighted Round Robin (WRR) scheduling algorithm. This invention solves the problem of adaptive resource allocation during dynamic network traffic exchange, enabling network switching equipment to provide stable network performance under different service loads.

Methods, devices, and systems are provided for synchronizing a source device with a sink device. In some examples, the source device plays first audio using, e.g., an electro-acoustic transducer. The source device transmits a stream of packets to the sink device to be used by the sink device for playing second audio, where the playing of the second audio is to be synchronized within a predefined tolerance with the playing of the first audio. In response to determining there is a delay in average packet arrival times of the stream of packets at the sink device, the source device adjusts the playing of the first audio to maintain synchronization with the playing of the second audio within the predefined tolerance.

A 5G energy consumption optimization method for mobile applications, including: (1) converting RRC states; (2) defining symbols; (3) extracting features; (4) identifying EOC; (5) predicting the arrival time of the next data packet. The present invention aims at the energy consumption optimization problem of mobile applications on 5G smartphones and proposes a 5G radio energy saving method 5GSaver with two-stage learning: 1) In the first stage, 5GSaver uses random forest (RF) to identify EOC events (IEOC); 2) In the second stage, if an EOC event is identified, 5GSaver further uses deep forest (DF) to predict the next packet arrival time (PPAT) by utilizing the program execution mode and the statistical information of each application. The present invention utilizes the newly introduced inactive state in 5G NR to optimize UE energy consumption. Compared with the existing tail optimization method, the present invention has better effects in energy saving and communication delay.

A method for managing transmission over a network by adjusting a flow control window based on one or more parameters obtained from one or more connections, applications or network conditions. In one embodiment a controller modifies the receiver TCP advertised window of one or several connections to match the end-to-end bandwidth-delay product (BDP) for bandwidth fair sharing and improving the quality of experience (QoE). The controller can be placed in any given entity managing packets, such as a sender entity, a transmitting entity or any other entity handling connection packets. A mechanism for estimating available path bandwidth and / or link capacity and location by analyzing the distribution of inter-packet arrival times. Packet pair dispersion analysis can be utilized based on passive evaluation of the acknowledgements of a TCP flow or based on active probing. Machine learning using a neural network can be used to analyze the distribution of inter-packet arrival times.

The invention relates to a data transmission method, device and equipment of a time-sensitive network, a medium and a program. The method comprises the following steps: constructing a network simulation topology model of an energy management system according to communication topology information and data information of the energy management system; performing time synchronization on the network simulation topology model to obtain a time synchronization model; performing flow scheduling on the energy management system according to the time synchronization model to obtain a flow scheduling result; generating a gating list and flow release time of the energy management system according to the flow scheduling result; and performing data stream transmission control on the energy management system by using the gating list and the flow release time. The sending time point of the data flow can be controlled, the time for the data packet to arrive at the next node is predicted, and the reliability and the real-time performance of data transmission are improved.

To provide an OLT and the like that achieve low delay guarantee.SOLUTION: An OLT used in a PON using an optical splitter has a collection unit and a processing unit. The collection unit collects time information of arrival of packets from an ONU and data volume information of the packets. The processing unit determines transmission timing of the ONU on the basis of transmission timing information assigned to the ONU, the time information, and the data volume information.SELECTED DRAWING: Figure 2