94 results about "Burstiness" patented technology

The invention relates to an equipment fault prediction method based on industrial Internet of Things and related equipment, and the method comprises the following steps: carrying out the physical signal collection of target equipment through a preset industrial Internet of Things, and obtaining an original sequence signal; identifying whether an abnormal signal exists in the original sequence signal to obtain an identification result; if the identification result is that the abnormal signal exists, performing fault type analysis on the target equipment based on the abnormal signal to obtain a fault position and a fault type corresponding to the fault position; performing failover prediction on the target equipment based on the abnormal signal, the fault position and the fault type corresponding to the fault position to obtain a predicted failover path; according to the method, the early warning instruction is generated on the basis of the predicted fault transfer path, and fault alarm is performed on the basis of the early warning instruction, so that the technical problems that a regular inspection or post-fault maintenance mode is mostly adopted in a traditional equipment maintenance mode, the cost is high, and sudden faults cannot be effectively prevented are solved.

The invention discloses a novel electric power system source network load storage coordinated optimization planning method, and relates to the technical field of electric power system optimization, and the method comprises the steps: S1, building a load prediction model based on various user side load dynamic adjustment data, and improving the prediction precision, S2, determining parameters and constraint conditions of each link of source network load storage of an electric power system, s3, carrying out source network load storage collaborative optimization scheduling by utilizing an optimization algorithm; S4, evaluating and verifying an optimization result; according to the novel power system source-network-load-storage coordinated optimization planning method, the precision of load prediction is greatly improved, so that the problem that supply and demand matching is difficult is effectively solved, rapid fluctuation or sudden change of user loads can be rapidly responded, the adaptability and flexibility of a scheduling strategy are remarkably improved, and the scheduling efficiency is improved. The problems of supply and demand matching and scheduling flexibility caused by low load prediction precision under the condition of dynamic adjustment of various user side loads in the prior art are solved.

Techniques for managing cloud computing resources hosting burstable performance instances are described. A host computer system of a provider network executes burstable performance compute instances. Compute capacity usage data is obtained from the host computer system, the compute capacity usage data including a first indication of a first compute capacity used by a first burstable performance compute instance. A first weight for the first burstable performance compute instance is calculated, the first weight being inversely related to the first compute capacity. A scheduler of the host computer system is updated with process prioritization weights, the process prioritization weights including a first process prioritization weight that is based at least in part on the first weight. The scheduler allocates compute capacity based on the process prioritization weights.

The invention belongs to the technical field of network test equipment, and discloses network response test equipment and a test method thereof, and is characterized in that the network response test equipment comprises the following modules: a distributed multi-mode dynamic sensing probe used for capturing service flow characteristics and microsecond-level performance indexes of a network link in real time; the extensible data middle table is in data connection with the probe and is used for establishing a unified spatio-temporal index for cross-level performance data from a physical layer to an application layer; and the causal atlas analysis engine based on artificial intelligence is used for positioning a network fault root cause according to the cross-level performance data. According to the invention, an evaluation standard is automatically calibrated according to historical business load characteristics through an extensible data-in-station dynamic baseline threshold mechanism, so that a test environment completely fits complex scenes such as video burst frame transmission, database synchronization ACK, high-frequency transaction chain and the like, the simulation distortion of a traditional tool to business traffic burst and multi-protocol mixed characteristics is eliminated, and the test efficiency is improved. And the test result is ensured to accurately map the long-term stability requirement.

The invention discloses a cloud task fault prediction method based on a sparrow search and gating cycle unit network. The method comprises the following steps: S1, obtaining a cloud task fault prediction standardized data set; s2, constructing cloud task fault prediction features; s3, obtaining an initial multi-scale gating circulation unit network model; s4, obtaining a sparrow search algorithm initial population matrix; s5, outputting a cloud task fault prediction optimal hyper-parameter vector; s6, obtaining cloud task fault prediction training completion model parameters; s7, deploying parameters of the cloud task fault prediction training completion model to a cloud computing platform reasoning environment, generating a cloud task fault probability sequence, comparing the cloud task fault probability sequence with a cloud task fault risk threshold value, and outputting a cloud task fault early warning signal when any cloud task fault probability exceeds the cloud task fault risk threshold value; and S8, sending the cloud task fault early warning signal to a cloud computing platform scheduling module. According to the invention, resource waste and service interruption risks caused by sudden task faults are effectively reduced.

The invention discloses a base station load prediction method and device combining deep learning and a statistics method, and electronic equipment, and belongs to the field of mobile communication. The method comprises the following steps: defining a load as the number of users entering a coverage range of a base station, and decomposing historical load data Y (t) of the base station into two parts: a part Y1 (t) which follows a long-term trend and changes along with time according to a specific rule, and a load change Y2 (t) caused by short-term random fluctuation; accurate prediction is carried out according to the inherent rule of Y1 (t) changing along with time, and an LSTM network is trained to complete prediction; according to the fact that Y2 (t) has high burstiness and real-time performance, a statistical method is used for prediction; and finally, predicting the load at a plurality of moments in the future, and performing base station dormancy control according to the load. According to the method, the problem of how to minimize the error of load prediction in a high mobility scene is solved, the loads at multiple moments in the future are predicted through the loads of the base station in a past period of time and at the current moment, and a base station dormancy control strategy is formulated.

The invention provides a historical load analysis-based power supply path dynamic generation and evaluation method, which comprises the following steps of: acquiring historical load data of a commercial district and topological structure data of a power distribution network, extracting load space distribution characteristics, and determining a dynamic change trend of load space distribution by adopting a clustering algorithm; performing time sequence analysis on the offset distance of the load center and the change rate of the power utilization density, and identifying the change period of the load in the commercial district and the sudden characteristics of sudden increase or sudden decrease of the load; key section distribution is identified according to the section identification standard, the load matching degree of the topological structure of the power distribution network is evaluated according to the key section distribution, and the load distribution balance and the line bearing capacity between topological nodes are calculated; and identifying weak nodes and areas with unbalanced load distribution according to the load distribution balance among the topological nodes and the line bearing capacity, and adjusting the line layout according to the identified weak nodes.

The invention discloses a Teensy scripting attack detection and interception method supporting multiple systems, and relates to the technical field of scripting attack detection and interception, according to the Teensy scripting attack detection and interception method, through application layer protocol analysis and dynamic entropy calculation, the protection requirements of old industrial terminals such as Windows XP and the like are adapted without depending on operating system driving or hardware upgrading; a multi-OS instruction jump graph is constructed, an abnormal path in a mixed environment is identified, and the risk of missing detection caused by fragmentation of a system version is reduced; in combination with protocol entropy fluctuation ratio and time sequence form matching, rapid response of sudden attacks and depth identification of low-frequency penetration behaviors are considered; through a challenge-response protocol and physical port control, the fundamental defect that a pure software scheme is easily bypassed by a malicious process is overcome; industrial protocol instruction sets such as Modbus / OPC UA are integrated in the white list keyword library, and normal operation and malicious injection are accurately distinguished.

The invention specifically discloses a low-overhead burst data stream detection algorithm, which filters and identifies an input data stream by using a constructed small stream filter and a burst stream detection table so as to output a real burst stream, and continuously filters a low-frequency stream by setting a time period so as to identify a potential burst stream. The detection precision of the subsequent burst flow is improved; meanwhile, a burst flow detection table is used for tracking potential burst flows, and whether the potential burst flows are real burst flows or not is recognized based on the frequency and the sudden increasing period of each potential burst flow in two adjacent time periods; moreover, a replacement strategy of the burst period and the data stream frequency probability is adopted to eliminate the data stream with lower burst, so that potential burst streams with higher possibility can be stored, and the memory consumption is further reduced. Therefore, the burst data stream detection algorithm provided by the invention has the characteristics of high accuracy, low overhead and high throughput.

The invention relates to the technical field of switches, and particularly discloses a switch congestion control method and device, a medium and a computer program product. The current average queue length is calculated according to the historical average queue length of a target queue of a switch port and the instantaneous queue length at the current moment; and calculating a queue length change parameter to determine a packet loss probability threshold value of the target queue instead of adopting a pre-configured fixed parameter. Meanwhile, a packet loss probability distribution function corresponding to the target queue is expressed in a nonlinear function mode, at least one of the current average queue length, the historical average queue length and the instantaneous queue length is substituted into the packet loss probability distribution function, and the packet loss probability is output; and carrying out packet loss processing on the newly arrived data packet of the target queue according to the packet loss probability. Compared with the traditional linear packet loss probability function, the method is more suitable for the burstiness and randomness of the current data center network data flow.

The invention discloses a method for identifying weak signals of an emerging technology. The method comprises the following steps of: extracting and normalizing keywords; preliminarily filtering weak signals of the emerging technology; evaluating a weak signal of the emerging technology; and comprehensively studying and judging the emerging technology weak signals. According to the method, academic papers and technical patent scientific and technical literature data are adopted, policy and strategy data are introduced to evaluate the importance of emerging technology weak signals, and the strength of national strategy layout is reflected; a pre-training model is adopted to represent keywords and related data, the occurrence conditions of the keywords in various types of data are reflected from the semantic level, and evaluation of emerging technology weak signals is accurately carried out; the method comprises the following steps of: performing multi-round filtering on emerging technology weak signals through preliminary filtering of keywords with overhigh word frequency and calculation and analysis of three indexes, namely burstiness, concentration ratio and importance, and eliminating noise; according to the method, a complete and systematic analysis process is constructed, and systematic evaluation and identification of emerging technology weak signals can be 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 is suitable for the technical field of wireless communication system communication, and provides a touch teleoperation service-oriented bandwidth estimation method, which comprises the following steps of: modeling a touch service arrival process; performing correlation analysis on the arrival process of the two parts; a yoke expression method of the tactile sudden arrival process; predicting a service arrival process; and estimating the bandwidth of the service flow. The tactile service arrival process is modeled, the correlation of the tactile service arrival process from master control to slave control and from slave control to master control is analyzed, the time domain, frequency domain and high-order characteristics of service arrival are considered, a new method for constructing an arrival yoke process is provided, service arrival is predicted, accurate measurement of tactile service burstiness is achieved, and the accuracy of the tactile service burstiness is improved. A new bandwidth estimation method is provided, and dynamic estimation of the haptic service bandwidth demand is realized. According to the method and the system, the abruptness of the tactile service can be efficiently processed, and a foundation is laid for guaranteeing the service quality of tactile communication, optimizing bandwidth resource configuration and improving network performance.

The invention discloses a wireless network dynamic flow optimization method based on CSI (Channel State Information) feedback and a storage medium, and relates to the technical field of wireless network communication, and the method can accurately judge the change trend of channel quality by collecting CSI channel state information in real time and combining the running track of a train or a fleet to carry out channel prediction. When the channel gain is quickly deteriorated, such as entering a tunnel or a high-rise sheltered area, the code rate and the redundant coding can be optimized in advance, and meanwhile, an HARQ retransmission mechanism is started, so that the data packet loss is reduced, and the transmission stability is improved. Under the condition that a channel deteriorates gradually, data flow parameters can be adjusted stably, sudden transmission interruption is avoided, the robustness and the anti-interference capability of a wireless network are improved, the intelligent intervention strategy can effectively reduce data packet loss and improve the transmission reliability of the wireless network, and the method is particularly suitable for high-throughput business in a high-speed mobile environment and has a wide application prospect. And the overall communication quality is improved.

The invention discloses an industrial data transmission optimization management system based on service link quality, and relates to the technical field of data transmission. Weak delay oscillation and a periodic packet loss rule are reserved through multi-scale processing, so that the system can discover precursor anomalies which are difficult to capture by a traditional monitoring mechanism; minute-level even second-level early warning of link disturbance is realized, and data congestion caused by sudden quality reduction is avoided; a dynamic discrimination mechanism driven by a precursor score is utilized, so that a scheduling decision is converted from passive response to active adjustment, and the probability of cascade failure caused by mass mutation is greatly reduced; an interference spectrum adaptive strategy enables the system to adaptively match the optimal coding mode and the redundant structure when facing narrow-band noise, periodic interference or transient impact, so that the anti-interference capability and the bandwidth utilization efficiency are improved; priority adjustment is carried out in combination with a link risk trend and a state evolution rule, and the protection timeliness and resource allocation efficiency of the key link are remarkably improved.

The invention discloses a flow behavior perception-based photoelectric double-plane cross-layer interconnection scheduling method, which comprises the following steps of: acquiring communication service data flow in a distributed training task, and generating flow behavior time sequence characteristics; performing flow behavior time sequence feature modeling based on the flow behavior time sequence features; identifying flow behavior time sequence characteristics of different types of communication service data streams, and dividing the communication service data streams into lightweight control streams, periodic synchronization streams and sudden transport streams; the method comprises the following steps: acquiring a network state of a link in a data transmission plane, establishing a transmission path reachability constraint, allocating capacity for the link, detecting a link capacity occupation value and a link capacity upper limit, and generating a scheduling strategy; the scheduling strategy is converted into a mapping instruction, and the data transmission plane executes distribution of a transmission path of the communication service data flow according to the scheduling strategy; according to the invention, data stream differential transmission and cross-layer cooperative control based on photoelectric biplanes are realized, the training iteration time is remarkably shortened, and the utilization rate of network resources is improved.

The present application relates to the technical field of semantic processing, and more particularly to a word element aggregation and distribution method and system based on multi-level cache and semantic preheating, which obtains historical word element request interaction logs, analyzes the access characteristics of different business scenarios and context fragments; in combination with semantic dependency relationships, identifies regular repetition and sudden hotspot characteristics of word element access, determines a preloading target set; real-time acquisition of context semantic data of the current inference request, analysis of word element prediction demand parameters to be generated for output; fusion of word element prediction demand parameters and preloading target set, dynamic generation of word element aggregation parameters and distribution scheduling strategy. The present application realizes forward-looking preheating and accurate scheduling of word element resources by deeply mining historical rules and real-time semantic intent, effectively solves the problems of weak semantic perception, low hit rate and response lag of traditional cache strategies, significantly reduces the inference delay of large models, and improves the throughput and stability of the system in high-concurrency scenarios.

The application relates to a time division multiple access time slot allocation method based on a manta ray algorithm and belongs to the technical field of communication networking. The application divides a time frame into an information collection period and a time slot allocation period, and further divides the time slot allocation period into a dedicated time slot period and a dynamic time slot period. In the information collection period, a central node collects time slot application requests of other nodes, judges whether the nodes can continue to apply according to relevant criteria, and gives the nodes priorities according to the traffic volume and the service importance of the nodes. In the dedicated time slot allocation period, high-priority nodes are allocated by using a binary tree block internal equal division method. In the dynamic time slot allocation period, the manta ray algorithm is used to allocate time slots to other nodes. The application is relatively simple to implement, guarantees absolute transmission of the nodes, considers the priorities of the nodes, meets burstiness and long message transmission of the nodes, improves the convergence speed of the algorithm, and improves the overall performance of the network.

The invention relates to the field of electric power business scheduling, and particularly discloses an electric power system business collaborative scheduling method based on a 5G technology, which constructs a high-low layer collaborative double-layer intelligent scheduling architecture. In a high level, situation prediction is carried out by fusing power grid operation data and historical traffic, and the macroscopic resource ratio of network slices is adjusted prospectively to cope with the sudden demand of power business, so that the problem of insufficient resources of static resource allocation in sudden scenes such as faults is solved. And at the lower layer, service semantic analysis is carried out deeply in the data packet, so that the real-time emergency level of key services such as differential protection and the like is accurately identified, and resources are further refined into a micro resource pool special for the services in combination with slice configuration issued by the higher layer, so that real-time scheduling and preemption based on semantics are realized. Through the combination of macroscopic predictive reservation and microscopic semantic scheduling, it is ensured that high-priority power services can obtain communication guarantee under any network load.

The invention discloses a short message sending method and device, equipment, a storage medium and a program product, and the method comprises the steps: segmenting short message service flow according to preset time slice configuration, and obtaining short message data under a plurality of time slices; performing rate segmentation on the plurality of channel resources according to a preset rate arrangement strategy and a thread concurrency number to obtain rate configuration of a plurality of threads of each channel resource; wherein the rate arrangement strategy is used for indicating rate configuration of each channel resource; binding the short message data with a plurality of threads so as to enable the threads to execute sending on the bound short message data in each time slice according to own rate configuration; according to time arrangement and careful division of the channel rate, the sending efficiency of a multi-short-message service large-batch sending scene can be improved, sudden surge short message data can be effectively dealt with, multi-short-message service channel blockage caused by short message backlog is avoided, and the success rate of short message service sending loss is improved.

The application provides a mobile edge computing dynamic service deployment method based on deep reinforcement learning. In the learning process, a migration conflict resolution mechanism is introduced to maintain the service performance of the user. Specifically, not only the network state is predicted, but also the user connected to each edge node is calculated according to the user trajectory, and it is determined which node is the crowded node according to the user request and the service on the edge node, the resource reservation is carried out for the crowded node, and whether the conflict will be produced is detected. In order to achieve this goal, first, the network architecture of edge computing is determined, then the system model and the quality of service (QoS) model are established, and the problem to be solved is formulated. The application studies the joint optimization problem of delay and cost under the constraints of physical resources and operation cost, taking the minimum total cost of users as the target, and considering guaranteeing that multiple service requests can be responded in time under the sudden aggregation.

The invention discloses a non-cellular intelligent beam management-oriented generative learning-assisted twinning enhancement pre-training method, which comprises the following steps of: firstly, constructing a long short-term memory network fusion diffusion model generative model as a channel prediction digital twinborn body, and predicting a future channel state in a probability mode; secondly, constructing an autoregressive comprehensive moving average model and a variational auto-encoder mixed model to carry out generative flow prediction, and accurately capturing the periodicity and the burstiness of the flow; and finally, jointly applying channel and flow prediction results to a monotonic Q value function decomposition beam selection algorithm after state enhancement. According to the invention, through prior knowledge provided by generative learning, the problems of difficult data sample acquisition, high training cost, slow convergence and poor dynamic traffic adaptability faced by training a beam selection algorithm in a real environment are solved. Compared with a traditional method, the training efficiency, the convergence speed and the final performance in a complex dynamic scene of a beam selection algorithm can be remarkably improved.

The application discloses a time slot allocation method and device, equipment and medium, and relates to the field of time slot allocation. The method comprises the following steps: an unmanned system generates a backbone network based on network topology information of a plurality of communication nodes in a previous time frame through a center node, so as to dynamically determine backbone nodes of a current time frame by using the backbone network; the center node dynamically predicts time slot segments allocated to the center node and the backbone nodes in the current time frame based on traffic demands of the plurality of communication nodes in the previous time frame; and each node in the center node and the backbone nodes dynamically predicts time slots allocated to each node and management sub-nodes of each node in a time slot segment corresponding to each node based on traffic demands of each node and the management sub-nodes of each node in the previous time frame, so as to meet the networking communication demand of the unmanned system with high reliability and low delay, better adapt to the non-stationary environment with strong business burstiness and frequent topology changes of the unmanned system, and realize efficient and reliable time slot allocation for large-scale unmanned system networking.

The application discloses a kind of dynamic protocol identification method and system based on multi-modal data, belong to the technical field of data protocol identification, identification method includes: S1: calculate data packet arrival interval time standard deviation, judge communication mode is periodic or burst communication mode;S2: data packet is divided according to length, calculate and count the probability distribution of each interval, and calculate the Shannon entropy value of data packet;S3: according to data packet arrival interval time standard deviation, the Shannon entropy value of data packet and the probability distribution of each interval, generate protocol fingerprint;S4: using edge AI classification engine classifies data packet.The application can improve the accuracy of protocol identification, improve network security protection capability.

The invention discloses an Internet of Things time sequence system automatic test script generation method based on a large model, and relates to the technical field of Internet of Things system testing. The method comprises the steps that 1, key characteristics of device data streams are extracted through a time sequence analysis tool, the key characteristics comprise time sequence dependence and data stream mode characteristics, the time sequence dependence is used for analyzing the triggering relation between devices, and the data stream mode characteristics are used for identifying periodicity, tendency and sudden characteristics; the large model is finely adjusted according to an internet of things time sequence system scene, the external knowledge base is enhanced and connected through RAG retrieval, related information is dynamically retrieved and combined with the large model, test scripts are generated according to key characteristics of equipment data flow, and the test scripts comprise a real-time test script, a time sequence dependence test script and an abnormal test script; the real-time test script is used for verifying the response time, delay and throughput of the system, the time sequence dependence test script is used for simulating a complex causal relationship chain, and the exception test script is used for inserting an exception data stream and verifying the fault-tolerant capability of the system.

The invention discloses a network resource allocation method, device and equipment and a computer storage medium, and relates to the technical field of communication. The method comprises the following steps: firstly, acquiring network resource data of a node, wherein the network resource data comprises resource use data and resource allocation data; inputting the resource allocation data into a resource allocation model under the condition that at least one of the network resource data meets a first preset condition and the detection time reaches the preset time, randomly generating a plurality of resource allocation sub-data based on the input resource allocation data, and selecting resource allocation sub-data of which the resource use data and the resource allocation sub-data meet a second preset condition as target resource allocation sub-data, calculating a decision value of the target resource allocation sub-data according to a preset weight in the resource allocation model, and determining the resource allocation sub-data with the highest decision value as the target resource allocation data. According to the embodiment of the invention, the method can timely adapt to the sudden network flow change, thereby improving the flexibility and adaptability of network distribution.

The invention provides a PCIe (Peripheral Component Interconnect Express) dynamic bandwidth allocation and low-delay communication method and system based on an FPGA (Field Programmable Gate Array), and the method comprises the steps: carrying out the real-time statistics of the data transmission quantity of a plurality of virtual channels, and obtaining the flow data of the plurality of virtual channels; dynamically allocating bandwidth weights of the plurality of virtual channels according to the traffic data of the plurality of virtual channels to obtain credit values of the plurality of virtual channels; according to the credit values of the plurality of virtual channels, controlling the data transmission burst amount of the plurality of virtual channels, and performing hardware unloading processing on a transaction layer data packet received by the PCIe interface through a transaction layer packet analysis operation to obtain target address information and a data load; according to the target address information, the data load is directly written into an internal storage area of the FPGA through memory mapping operation, and transmission completion data is obtained. The method and the device can adapt to sudden data transmission requirements, and the bandwidth utilization rate is improved.

The invention is suitable for the technical field of data identification, and provides a power consumption optimization method and device for network equipment, and the method comprises the steps: obtaining communication data volumes corresponding to a plurality of time periods corresponding to a plurality of dates; extracting first communication data volumes corresponding to the to-be-predicted time period in a plurality of dates; according to a plurality of first communication data volumes corresponding to the plurality of to-be-predicted time periods, matching traffic feature tags corresponding to the to-be-predicted time periods; calculating a predicted communication data volume of the to-be-predicted time period according to the traffic feature tag; and matching a power consumption optimization strategy of the network equipment according to the predicted communication data volume, and executing the power consumption optimization strategy. According to the scheme, the periodic change and sudden fluctuation of the network traffic can be better captured, so that the accuracy and timeliness of traffic prediction are improved.

The present application relates to a kind of value burst flow detection method based on P4 and Sketch.Break through the detection scheme of traditional based on successive burst, propose value burst flow definition, observe the burst of traffic on the flow level, process the input data packet under the limited memory overhead by the data structure design based on Sketch, detect burst data packet according to the time interval between data packet, and then detect value burst flow. When data packet arrives, each data packet is mapped to a bucket set, but at most to one bucket is operated, under appropriate conditions, can vote according to the voting mechanism based on burst; when each measurement period ends, traverse all buckets, obtain the value burst flow detected by query operation and feedback to control plane. The present application reduces bandwidth overhead and user burden in burst detection process, while only limited memory occupation and low time complexity are generated.

The invention discloses a network switch control method and system, particularly relates to the technical field of network flow management, and is used for solving the problem that low-frequency flow is suddenly lost or rearranged when high-frequency flow is dynamically compressed in the prior art. The method comprises the following steps: monitoring all traffic entering a network switch to obtain frequency characteristics of the traffic, and classifying the traffic into high-frequency traffic and low-frequency traffic according to the frequency characteristics; compressing the high-frequency traffic by applying a dynamic traffic compression algorithm; for the low-frequency flow, analyzing a topological link by adopting a sparse representation iteration reweighted least square method, and identifying the interference intensity of the link; evaluating the logical coherence of the low-frequency flow data packet through a variational auto-encoder; determining a priority scheduling strategy of the low-frequency traffic based on the link interference intensity and the logic coherence; and finally, carrying out resource allocation and scheduling on the compressed high-frequency flow and the preferentially processed low-frequency flow.