+

CN119906533A - Time series data preprocessing system and method based on communication network - Google Patents

Time series data preprocessing system and method based on communication network Download PDF

Info

Publication number
CN119906533A
CN119906533A CN202510368692.3A CN202510368692A CN119906533A CN 119906533 A CN119906533 A CN 119906533A CN 202510368692 A CN202510368692 A CN 202510368692A CN 119906533 A CN119906533 A CN 119906533A
Authority
CN
China
Prior art keywords
sequence
subsequence
time series
node
subsequences
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202510368692.3A
Other languages
Chinese (zh)
Other versions
CN119906533B (en
Inventor
阎星娥
严荣明
杨昆
张�林
刘慰慰
赵万亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Huafei Data Technology Co ltd
Original Assignee
Nanjing Huafei Data Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Huafei Data Technology Co ltd filed Critical Nanjing Huafei Data Technology Co ltd
Priority to CN202510368692.3A priority Critical patent/CN119906533B/en
Publication of CN119906533A publication Critical patent/CN119906533A/en
Application granted granted Critical
Publication of CN119906533B publication Critical patent/CN119906533B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/0001Arrangements for dividing the transmission path
    • H04L5/0003Two-dimensional division
    • H04L5/0005Time-frequency
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00Arrangements for detecting or preventing errors in the information received
    • H04L1/0001Systems modifying transmission characteristics according to link quality, e.g. power backoff
    • H04L1/0006Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission format
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00Arrangements for detecting or preventing errors in the information received
    • H04L1/12Arrangements for detecting or preventing errors in the information received by using return channel
    • H04L1/16Arrangements for detecting or preventing errors in the information received by using return channel in which the return channel carries supervisory signals, e.g. repetition request signals
    • H04L1/1607Details of the supervisory signal
    • H04L1/1657Implicit acknowledgement of correct or incorrect reception, e.g. with a moving window
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00Arrangements for detecting or preventing errors in the information received
    • H04L1/12Arrangements for detecting or preventing errors in the information received by using return channel
    • H04L1/16Arrangements for detecting or preventing errors in the information received by using return channel in which the return channel carries supervisory signals, e.g. repetition request signals
    • H04L1/1607Details of the supervisory signal
    • H04L1/1671Details of the supervisory signal the supervisory signal being transmitted together with control information
    • H04L1/1678Details of the supervisory signal the supervisory signal being transmitted together with control information where the control information is for timing, e.g. time stamps
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/003Arrangements for allocating sub-channels of the transmission path
    • H04L5/0044Allocation of payload; Allocation of data channels, e.g. PDSCH or PUSCH
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/003Arrangements for allocating sub-channels of the transmission path
    • H04L5/0048Allocation of pilot signals, i.e. of signals known to the receiver
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/003Arrangements for allocating sub-channels of the transmission path
    • H04L5/0078Timing of allocation

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Quality & Reliability (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The invention relates to the field of signal processing, in particular to a time sequence data preprocessing system and method based on a communication network, wherein the system comprises a signal monitoring module, a wave frequency analysis module, a standard fitting module, a sequence processing module and a node scheduling module, wherein the signal monitoring module is used for expanding and storing a time sequence, the wave frequency analysis module is used for determining a time frequency window, cutting the sequence and calculating the composition of a subsequence, the standard fitting module is used for outputting a standardized sequence and an error interval, the sequence processing module is used for filtering a subsequent sequence, and the node scheduling module is used for scheduling an information processing task of a node.

Description

Time sequence data preprocessing system and method based on communication network
Technical Field
The invention relates to the field of signal processing, in particular to a time sequence data preprocessing system and method based on a communication network.
Background
A communication network is a system of communication links of a plurality of communication nodes and connecting nodes in order to enable the transmission and exchange of data information between the different nodes. In a communication network, signals are transmitted in a binary time sequence, wherein the time sequence is a series of data points arranged according to a time sequence, the change condition of information along with time is reflected, and the processing of the time sequence is beneficial to improving the data quality and optimizing the resource allocation among nodes.
Because the signal is easy to mix with noise in the transmission process, error codes exist in the restored time sequence signal during digital sampling, and the signal transmission precision is affected. Since the status codes, instruction sentences and the like in the communication network have the same expression form, the error codes can be filtered through signal analysis, but are limited by high instability of time sequences, and the error information is difficult to accurately distinguish by the prior processing technology.
In addition, each node in the communication network is composed of computers with different specifications, and has different hardware parameters, so that the processing capability and the adaptation capability of time series signals are different, and if the time series signals are not preprocessed, the node blockage phenomenon is easy to occur, and the operation efficiency of the communication network is affected.
Disclosure of Invention
The present invention is directed to a system and a method for preprocessing time-series data based on a communication network, so as to solve the problems set forth in the background art.
In order to solve the technical problems, the invention provides the technical scheme that the time sequence data preprocessing system based on the communication network comprises a signal monitoring module, a wave frequency analysis module, a standard fitting module, a sequence processing module and a node scheduling module;
The signal monitoring module is used for loading a monitoring control in a node server of a communication network, acquiring input data and output data of each communication network node, expanding the communication data in a time sequence, setting an information processing device or a signal transmission path at an input/output port of the node so as to store the expanded time sequence, and carrying out operation analysis on the time sequence;
the wave frequency analysis module is used for processing the expanded time sequence by adopting windowing transformation of the variable window, determining a time-frequency window of the time sequence according to the window interval when the correlation coefficient is highest, cutting the sequence according to the time-frequency window to obtain subsequences, carrying out dimensionless broken line transformation on each subsequence and the preamble subsequence, and calculating the composition difference, the composition ratio and the T-shaped correlation coefficient of each subsequence according to the information distribution among the subsequences;
The standard fitting module is used for calculating the association degree of each subsequence with other subsequences according to the T-shaped association coefficient among the subsequences, reserving all sequence sets with the association degree smaller than a threshold value to obtain a first reference set, discarding the sets with the sequence number smaller than the threshold value in the first reference set to obtain second reference sets, performing differential fitting on all the subsequences in each second reference set, and outputting a standardized sequence and an observation error interval corresponding to each second reference set;
the sequence processing module is used for acquiring a subsequent input or output sequence, separating a subsequent subsequence according to a time-frequency window cutting sequence, calculating the association degree of the subsequent subsequence and each standardized sequence, carrying out standardized processing on the subsequent sequence when the association degree is positioned in an error interval, enabling the subsequent sequence to be consistent with the standardized fitting sequence and then outputting, otherwise repeating time window cutting, and fusing a cutting result into a first reference set;
the node scheduling module is used for acquiring the number of the input and output subsequences of each node in the communication network, determining the operation speed of the node according to the ratio of the number of the input and output subsequences, and carrying out tasking node management on the communication network according to the operation speed of the node so as to keep the number of the input and output subsequences of each node in a uniform ratio to stabilize the data processing efficiency of the communication network.
Further, the signal monitoring module comprises a port control unit and a central processing unit;
the port control unit is arranged in an input/output port of the node server and is used for monitoring the time sequence of the input/output signals;
The central processing unit is used for providing calculation force support for time sequence analysis through a terminal data operation chip or a feedback path.
Further, the wave frequency analysis module comprises a windowing conversion unit, a time-frequency cutting unit and a composition analysis unit;
The windowing transformation unit is used for selecting a window function according to the data information entropy and performing discrete wavelet transformation on the time sequence based on the window function;
The time-frequency cutting unit is used for calculating the time delay of a window function when the discrete wavelet transformation function takes the maximum value, and cutting the sequence by using a time-frequency window to obtain a subsequence;
The composition analysis unit is used for calculating composition differences, composition ratios and T-type correlation coefficient functions of the subsequences according to information distribution among the subsequences.
Further, the standard fitting module comprises a correlation grouping unit and a differential fitting unit;
The association grouping unit is used for calculating the association degree of the T-shaped association coefficient among the subsequences and grouping the subsequences according to the calculation result;
the difference fitting unit is used for screening grouping results, removing invalid groupings and non-significant groupings, and obtaining a second reference set.
Further, the sequence processing module comprises a signal filtering unit and a sequence fusion unit;
The signal filtering unit is used for cutting the subsequent subsequence and filtering the subsequent subsequence according to the corresponding standard sequence information;
The sequence fusion unit is used for fusing the filtered subsequent subsequences, reducing the subsequent subsequences into a time sequence and sending the time sequence to the communication node for processing.
Further, the node scheduling module comprises a node testing unit, a task management unit and an efficiency stabilizing unit;
The node test unit is used for calculating the information processing speed of the communication node according to the proportion of the information quantity of the input subsequence and the output subsequence in the communication node;
the task management unit is used for planning an optimal task allocation mode according to the data volume of the signal to be transmitted and the information processing speed of each node;
The efficiency stabilizing unit is used for calculating the overall efficiency of the communication network in real time and uploading the information quantity of the input and output time sequence of the communication network in real time.
The time sequence data preprocessing method based on the communication network comprises the following steps:
S1, monitoring input and output signals at a port of a node server, expanding the signals in a time sequence form, calculating information entropy of the time sequence, selecting a window function according to the information entropy, and performing discrete wavelet transform on the time sequence by taking the window function as a fundamental frequency to obtain a discrete wavelet transform function;
s2, calculating the time delay of a window function when the discrete wavelet transformation function takes the maximum value, recording the time delay as a time-frequency window, taking the time-frequency window as a cutting time sequence, obtaining subsequences with fixed code element length, carrying out dimensionless broken line transformation on each subsequence, and calculating the composition difference, the composition ratio and the T-shaped association coefficient of each subsequence;
S3, calculating T-type association coefficients between each subsequence and other subsequences, classifying all subsequences with the degree of association smaller than a threshold value into one type to obtain a first reference set, and discarding the set with the number of elements smaller than the threshold value to obtain a second reference set;
s4, superposing and sampling sub-sequences in each reference set to obtain a standardized sequence and an error interval, cutting a subsequent time sequence according to a time-frequency window, calculating T-shaped association coefficients of the sub-sequences of the subsequent time sequence and each standardized sequence, and carrying out standardized processing on each subsequent sub-sequence when the association degree is in the error interval;
s5, representing the information processing speed of the communication node according to the information quantity ratio of the input subsequence and the output subsequence in the communication node, and performing task allocation according to the data quantity of the signal to be transmitted and the information processing speed of each node so as to maximize the overall efficiency of the communication network.
Further, step S1 includes:
S11, loading a monitoring control in a node server of a communication network, monitoring input and output signals, and transmitting the input and output signals into a processing chip through a terminal data operation chip or a feedback path;
S12, expanding the monitored input and output signals into a time sequence in a processing chip, wherein the time sequence is a finite length sequence, elements in the sequence are binary, calculating information entropy according to the length of the time sequence, and selecting a window function from a preloaded function library according to the information entropy;
s13, performing discrete wavelet transformation on the time sequence by taking a window function as a fundamental frequency, wherein the transformation function is as follows:
;
Wherein f (a, b) is a discrete wavelet transform function, a is a scale parameter, b is a time delay parameter, t0 is a sampling interval of a time sequence, delta (k) is a window function, E (k) is a kth element value in the time sequence, N is the number of elements in the time sequence, and k is a sequence index.
Further, step S2 includes:
S21, limiting the scale parameter in a period length range of a window function, calculating the maximum value of a discrete wavelet transformation function, and recording the size of a time delay parameter b when the maximum value is taken as an output function as a time frequency window;
S22, cutting a time sequence by using a time-frequency window, enabling each subsequence to contain m elements, complementing the subsequence with a low-level signal if the subsequence with the length less than m exists, numbering the subsequences according to a time sequence, determining the preamble sequence of each subsequence according to a descending order of the numbering, and taking the last subsequence as the preamble sequence in the initial subsequence;
Carrying out dimensionless polyline transformation on each sub-sequence, and calculating the composition difference, composition ratio and T-type association coefficient of each sub-sequence:
;
Wherein z represents the composition difference between the subsequence and the preamble sequence, z1 (x) represents the difference between the xth element and the xth+1th element in the preamble subsequence, z2 (x) represents the difference between the xth element and the xth+1th element in the current subsequence, s represents the composition ratio of the subsequence and the preamble sequence, min and max represent maximum and minimum functions, respectively, and r represents a T-type correlation coefficient.
Further, step S3 includes:
S31, calculating T-type association coefficients between all subsequences and other sequences, dividing the subsequences into a group, enabling the association coefficients between every two sequences in the group to be smaller than a threshold value, storing all groups into a set, and obtaining a first reference set;
And S32, screening out all the packets with the sequence number smaller than the threshold value in the first reference set to obtain a second reference set.
Further, step S4 includes:
S41, calculating the average value of each bit element in all subsequences in the group for each group in the second reference set, compiling into a high-level signal if the average value is larger than a sampling standard, compiling into a low-level signal if the average value is smaller than the sampling standard, acquiring all compiled signals, and combining the signals into a standardized sequence, wherein an error interval is [ - Σ (x=1,m)|z(x)-z0(x)|,Σ(x=1,m) |z (x) -z0 (x) |], z (x) represents an xth element in the standardized sequence, and z0 (x) represents the average value of xth element in all subsequences in the group;
S42, when the subsequent time sequences are transmitted in the communication node, cutting the subsequent time sequences according to a time-frequency window to obtain subsequences of the subsequent time sequences, calculating T-shaped association coefficients between the subsequences of each subsequent time sequence and the standardized sequence, and if the association degree is within an error interval, replacing the subsequences of the subsequent time sequences with the standardized sequence, and restoring and outputting the result.
Further, step S5 includes:
S51, determining the information processing speed of the communication node according to the proportion of the information quantity of the input subsequence and the output subsequence in the communication node, and marking the speed of each node in a communication network;
S52, calculating information quantity of data to be processed, and distributing flow among nodes by using a scheduling algorithm, wherein the scheduling algorithm comprises dynamic weighted scheduling, hybrid scheduling, neural network scheduling and batch processing scheduling.
Compared with the prior art, the invention has the following beneficial effects:
According to the invention, communication data is expanded in a time sequence, the windowing transformation of a variable window is adopted, the time-frequency window of the time sequence is determined, the dimensionless polyline transformation is carried out on each sequence and the preamble sequence according to the time-frequency window cutting sequence, the T-shaped association coefficient of the technical sequence can identify the long-term trend, the periodic variation and the seasonal pattern in the data, the cyclic pattern of the time sequence can be predicted more accurately, and the integrity and the quality of the data are improved.
According to the method, the relevance is calculated according to the T-shaped relevance coefficient, all sequence sets with relevance smaller than the threshold value are reserved, when the subsequent input is positioned in an error interval of the standardized sequence, the subsequent sequence is subjected to standardized pretreatment and then output, and abnormal noise in data is identified and removed through a smoothing technology, so that the time sequence is clearer and has better interpretability.
The invention determines the operation speed of the nodes according to the input-output standardized sequence number of each node and the input-output ratio, performs task node management on the communication network, and ensures that the input-output sequence number of each node keeps a uniform ratio so as to stabilize the data processing efficiency of the communication network, better understand the dynamic information processing state of the communication network and improve the overall information processing efficiency of the communication network.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a communication network-based time series data preprocessing system according to the present invention;
fig. 2 is a schematic diagram of steps of a time-series data preprocessing method based on a communication network according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides a time sequence data preprocessing system based on a communication network, which comprises a signal monitoring module, a wave frequency analysis module, a standard fitting module, a sequence processing module and a node scheduling module;
The signal monitoring module is used for loading a monitoring control in a node server of a communication network, acquiring input data and output data of each communication network node, expanding the communication data in a time sequence, setting an information processing device or a signal transmission path at an input/output port of the node so as to store the expanded time sequence, and carrying out operation analysis on the time sequence;
The signal monitoring module comprises a port control unit and a central processing unit;
the port control unit is arranged in an input/output port of the node server and is used for monitoring the time sequence of the input/output signals;
The central processing unit is used for providing calculation force support for time sequence analysis through a terminal data operation chip or a feedback path.
The wave frequency analysis module is used for processing the expanded time sequence by adopting windowing transformation of the variable window, determining a time-frequency window of the time sequence according to the window interval when the correlation coefficient is highest, cutting the sequence according to the time-frequency window to obtain subsequences, carrying out dimensionless broken line transformation on each subsequence and the preamble subsequence, and calculating the composition difference, the composition ratio and the T-shaped correlation coefficient of each subsequence according to the information distribution among the subsequences;
The wave frequency analysis module comprises a windowing conversion unit, a time-frequency cutting unit and a constituent analysis unit;
The windowing transformation unit is used for selecting a window function according to the data information entropy and performing discrete wavelet transformation on the time sequence based on the window function;
The time-frequency cutting unit is used for calculating the time delay of a window function when the discrete wavelet transformation function takes the maximum value, and cutting the sequence by using a time-frequency window to obtain a subsequence;
The composition analysis unit is used for calculating composition differences, composition ratios and T-type correlation coefficient functions of the subsequences according to information distribution among the subsequences.
The standard fitting module is used for calculating the association degree of each subsequence with other subsequences according to the T-shaped association coefficient among the subsequences, reserving all sequence sets with the association degree smaller than a threshold value to obtain a first reference set, discarding the sets with the sequence number smaller than the threshold value in the first reference set to obtain second reference sets, performing differential fitting on all the subsequences in each second reference set, and outputting a standardized sequence and an observation error interval corresponding to each second reference set;
the standard fitting module comprises a correlation grouping unit and a differential fitting unit;
The association grouping unit is used for calculating the association degree of the T-shaped association coefficient among the subsequences and grouping the subsequences according to the calculation result;
the difference fitting unit is used for screening grouping results, removing invalid groupings and non-significant groupings, and obtaining a second reference set.
The sequence processing module is used for acquiring a subsequent input or output sequence, separating a subsequent subsequence according to a time-frequency window cutting sequence, calculating the association degree of the subsequent subsequence and each standardized sequence, carrying out standardized processing on the subsequent sequence when the association degree is positioned in an error interval, enabling the subsequent sequence to be consistent with the standardized fitting sequence and then outputting, otherwise repeating time window cutting, and fusing a cutting result into a first reference set;
The sequence processing module comprises a signal filtering unit and a sequence fusion unit;
The signal filtering unit is used for cutting the subsequent subsequence and filtering the subsequent subsequence according to the corresponding standard sequence information;
The sequence fusion unit is used for fusing the filtered subsequent subsequences, reducing the subsequent subsequences into a time sequence and sending the time sequence to the communication node for processing.
The node scheduling module is used for acquiring the number of the input and output subsequences of each node in the communication network, determining the operation speed of the node according to the ratio of the number of the input and output subsequences, and carrying out tasking node management on the communication network according to the operation speed of the node so as to keep the number of the input and output subsequences of each node in a uniform ratio to stabilize the data processing efficiency of the communication network.
The node scheduling module comprises a node testing unit, a task management unit and an efficiency stabilizing unit;
The node test unit is used for calculating the information processing speed of the communication node according to the proportion of the information quantity of the input subsequence and the output subsequence in the communication node;
the task management unit is used for planning an optimal task allocation mode according to the data volume of the signal to be transmitted and the information processing speed of each node;
The efficiency stabilizing unit is used for calculating the overall efficiency of the communication network in real time and uploading the information quantity of the input and output time sequence of the communication network in real time.
As shown in fig. 2, the communication network-based time series data preprocessing method includes the following steps:
S1, monitoring input and output signals at a port of a node server, expanding the signals in a time sequence form, calculating information entropy of the time sequence, selecting a window function according to the information entropy, and performing discrete wavelet transform on the time sequence by taking the window function as a fundamental frequency to obtain a discrete wavelet transform function;
the step S1 comprises the following steps:
S11, loading a monitoring control in a node server of a communication network, monitoring input and output signals, and transmitting the input and output signals into a processing chip through a terminal data operation chip or a feedback path;
S12, expanding the monitored input and output signals into a time sequence in a processing chip, wherein the time sequence is a finite length sequence, elements in the sequence are binary, calculating information entropy according to the length of the time sequence, and selecting a window function from a preloaded function library according to the information entropy;
s13, performing discrete wavelet transformation on the time sequence by taking a window function as a fundamental frequency, wherein the transformation function is as follows:
;
Wherein f (a, b) is a discrete wavelet transform function, a is a scale parameter, b is a time delay parameter, t0 is a sampling interval of a time sequence, delta (k) is a window function, E (k) is a kth element value in the time sequence, N is the number of elements in the time sequence, and k is a sequence index.
S2, calculating the time delay of a window function when the discrete wavelet transformation function takes the maximum value, recording the time delay as a time-frequency window, taking the time-frequency window as a cutting time sequence, obtaining subsequences with fixed code element length, carrying out dimensionless broken line transformation on each subsequence, and calculating the composition difference, the composition ratio and the T-shaped association coefficient of each subsequence;
The step S2 comprises the following steps:
S21, limiting the scale parameter in a period length range of a window function, calculating the maximum value of a discrete wavelet transformation function, and recording the size of a time delay parameter b when the maximum value is taken as an output function as a time frequency window;
S22, cutting a time sequence by using a time-frequency window, enabling each subsequence to contain m elements, complementing the subsequence with a low-level signal if the subsequence with the length less than m exists, numbering the subsequences according to a time sequence, determining the preamble sequence of each subsequence according to a descending order of the numbering, and taking the last subsequence as the preamble sequence in the initial subsequence;
Carrying out dimensionless polyline transformation on each sub-sequence, and calculating the composition difference, composition ratio and T-type association coefficient of each sub-sequence:
;
Wherein z represents the composition difference between the subsequence and the preamble sequence, z1 (x) represents the difference between the xth element and the xth+1th element in the preamble subsequence, z2 (x) represents the difference between the xth element and the xth+1th element in the current subsequence, s represents the composition ratio of the subsequence and the preamble sequence, min and max represent maximum and minimum functions, respectively, and r represents a T-type correlation coefficient.
S3, calculating T-type association coefficients between each subsequence and other subsequences, classifying all subsequences with the degree of association smaller than a threshold value into one type to obtain a first reference set, and discarding the set with the number of elements smaller than the threshold value to obtain a second reference set;
the step S3 comprises the following steps:
S31, calculating T-type association coefficients between all subsequences and other sequences, dividing the subsequences into a group, enabling the association coefficients between every two sequences in the group to be smaller than a threshold value, storing all groups into a set, and obtaining a first reference set;
And S32, screening out all the packets with the sequence number smaller than the threshold value in the first reference set to obtain a second reference set.
S4, superposing and sampling sub-sequences in each reference set to obtain a standardized sequence and an error interval, cutting a subsequent time sequence according to a time-frequency window, calculating T-shaped association coefficients of the sub-sequences of the subsequent time sequence and each standardized sequence, and carrying out standardized processing on each subsequent sub-sequence when the association degree is in the error interval;
The step S4 includes:
S41, calculating the average value of each bit element in all subsequences in the group for each group in the second reference set, compiling into a high-level signal if the average value is larger than a sampling standard, compiling into a low-level signal if the average value is smaller than the sampling standard, acquiring all compiled signals, and combining the signals into a standardized sequence, wherein an error interval is [ - Σ (x=1,m)|z(x)-z0(x)|,Σ(x=1,m) |z (x) -z0 (x) |], z (x) represents an xth element in the standardized sequence, and z0 (x) represents the average value of xth element in all subsequences in the group;
S42, when the subsequent time sequences are transmitted in the communication node, cutting the subsequent time sequences according to a time-frequency window to obtain subsequences of the subsequent time sequences, calculating T-shaped association coefficients between the subsequences of each subsequent time sequence and the standardized sequence, and if the association degree is within an error interval, replacing the subsequences of the subsequent time sequences with the standardized sequence, and restoring and outputting the result.
S5, representing the information processing speed of the communication node according to the information quantity ratio of the input subsequence and the output subsequence in the communication node, and performing task allocation according to the data quantity of the signal to be transmitted and the information processing speed of each node so as to maximize the overall efficiency of the communication network.
The step S5 comprises the following steps:
S51, determining the information processing speed of the communication node according to the proportion of the information quantity of the input subsequence and the output subsequence in the communication node, and marking the speed of each node in a communication network;
S52, calculating information quantity of data to be processed, and distributing flow among nodes by using a scheduling algorithm, wherein the scheduling algorithm comprises dynamic weighted scheduling, hybrid scheduling, neural network scheduling and batch processing scheduling.
In the embodiment, the time sequence of the input communication node is [10110110], the time domain window is 3 after windowing transformation, the sequence is cut into three subsequences of [101], [101] and [100], the [101] and the [101] are divided into one group, the [100] is divided into one group, the grouping of the [100] is screened, and when the subsequent signal input is [111], the subsequent signal is normalized to be the [101] output.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the above-mentioned embodiments are merely preferred embodiments of the present invention, and the present invention is not limited thereto, but may be modified or substituted for some of the technical features thereof by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1.基于通信网络的时间序列数据预处理方法,其特征在于,所述方法包括以下步骤:1. A time series data preprocessing method based on a communication network, characterized in that the method comprises the following steps: 步骤S1.在节点服务器端口监听输入输出信号,将信号以时间序列形式展开,计算时间序列的信息熵,按照信息熵选择窗口函数,以窗口函数为基频对时间序列作离散小波变换,得到离散小波变换函数;Step S1. Listen to input and output signals at the node server port, expand the signals in the form of time series, calculate the information entropy of the time series, select a window function according to the information entropy, perform discrete wavelet transform on the time series with the window function as the base frequency, and obtain a discrete wavelet transform function; 步骤S2.计算离散小波变换函数取最大值时窗口函数的时延,记为时频窗口,以时频窗口为切割时间序列,得到固定码元长度的子序列,对各子序列进行无量纲化折线变换,计算各子序列的构成差、构成比和T型关联系数;Step S2. Calculate the time delay of the window function when the discrete wavelet transform function takes the maximum value, record it as the time-frequency window, use the time-frequency window as the cutting time series, obtain the subsequence of fixed code element length, perform dimensionless broken line transformation on each subsequence, and calculate the composition difference, composition ratio and T-type correlation coefficient of each subsequence; 步骤S3.对各子序列与其他子序列间的T型关联系数进行计算,将所有相互间关联度小于阈值的子序列分为一类,得到第一参考集合,舍弃其中元素数量小于阈值的集合,得到第二参考集合;Step S3. Calculate the T-type correlation coefficient between each subsequence and other subsequences, classify all subsequences whose mutual correlation is less than the threshold into one category, obtain a first reference set, discard the set with the number of elements less than the threshold, and obtain a second reference set; 步骤S4.对各参考集合中的子序列叠加取样,得到标准化序列和误差区间,按时频窗口切割后序时间序列,计算后序时间序列的子序列与各标准化序列的T型关联系数,当关联度位于误差区间内时,将各后序子序列进行标准化处理;Step S4. Superimpose and sample the subsequences in each reference set to obtain a standardized sequence and an error interval, cut the subsequent time series according to the time-frequency window, calculate the T-type correlation coefficient between the subsequences of the subsequent time series and each standardized sequence, and when the correlation is within the error interval, perform standardization on each subsequent subsequence; 步骤S5.以通信节点中输入子序列和输出子序列的信息量比例,表示通信节点的信息处理速度,按照待传输信号的数据量和各节点的信息处理速度进行任务分配,使通信网络的整体效率最高。Step S5. The information processing speed of the communication node is represented by the information volume ratio of the input subsequence and the output subsequence in the communication node. Tasks are allocated according to the data volume of the signal to be transmitted and the information processing speed of each node to maximize the overall efficiency of the communication network. 2.根据权利要求1所述的基于通信网络的时间序列数据预处理方法,其特征在于:步骤S1包括:2. The time series data preprocessing method based on a communication network according to claim 1 is characterized in that: step S1 comprises: 步骤S11.在通信网络的节点服务器中载入监听控件,监听输入输出信号,通过终端数据运算芯片或反馈通路,将输入输出信号传输到处理芯片内;Step S11. Loading a monitoring control in a node server of the communication network, monitoring input and output signals, and transmitting the input and output signals to a processing chip through a terminal data operation chip or a feedback path; 步骤S12.在处理芯片内将监听到的输入输出信号展开为时间序列,所述时间序列为有限长度序列,且序列中的元素均为二进制,根据时间序列的长度计算信息熵,按照信息熵从预载入的函数库中选择窗口函数;Step S12. Expand the monitored input and output signals into a time series in the processing chip. The time series is a finite length sequence, and all elements in the sequence are binary. Calculate the information entropy according to the length of the time series, and select a window function from a preloaded function library according to the information entropy. 步骤S13.以窗口函数为基频对时间序列作离散小波变换,离散小波变换函数为:Step S13. Perform discrete wavelet transform on the time series with the window function as the base frequency. The discrete wavelet transform function is: ; 其中,f(a,b)为离散小波变换函数,a为尺度参数,b为时延参数,t0为时间序列的取样间隔,δ(k)为窗口函数,E(k)为时间序列中的第k个元素值,N为时间序列中的元素数量,k为顺序标号。Among them, f(a, b) is the discrete wavelet transform function, a is the scale parameter, b is the delay parameter, t0 is the sampling interval of the time series, δ(k) is the window function, E(k) is the kth element value in the time series, N is the number of elements in the time series, and k is the sequence number. 3.根据权利要求2所述的基于通信网络的时间序列数据预处理方法,其特征在于:步骤S2包括:3. The time series data preprocessing method based on communication network according to claim 2 is characterized in that: step S2 comprises: 步骤S21.将尺度参数限定在窗口函数的一个周期长度范围内,计算离散小波变换函数的最大值,输出函数取最大值时时延参数b的大小,记为时频窗口;Step S21. Limit the scale parameter to a period length range of the window function, calculate the maximum value of the discrete wavelet transform function, and output the size of the delay parameter b when the function takes the maximum value, which is recorded as the time-frequency window; 步骤S22.利用时频窗口切割时间序列,使每个子序列中含有m个元素,若存在长度不足m的序列,则用低电平信号补足,按照时间顺序对子序列编号,按编号降序确定各子序列的前序序列,初始子序列以末尾子序列为前序序列;Step S22. Use the time-frequency window to cut the time series so that each subsequence contains m elements. If there is a sequence whose length is less than m, it is supplemented with a low-level signal. The subsequences are numbered in chronological order, and the preamble sequence of each subsequence is determined in descending order of the number. The initial subsequence uses the last subsequence as the preamble sequence; 对每个子序列进行无量纲化折线变换,计算各子序列的构成差、构成比和T型关联系数:Perform dimensionless broken line transformation on each subsequence and calculate the composition difference, composition ratio and T-type correlation coefficient of each subsequence: ; 其中,z代表子序列与前序序列的构成差,z1(x)代表前序子序列中第x个元素与第x+1个元素的差,z2(x)代表当前子序列中第x个元素与第x+1个元素的差,s代表子序列与前序序列的构成比,min和max分别代表取最大值和取最小值函数,r代表T型关联系数。Among them, z represents the composition difference between the subsequence and the previous sequence, z1(x) represents the difference between the xth element and the x+1th element in the previous subsequence, z2(x) represents the difference between the xth element and the x+1th element in the current subsequence, s represents the composition ratio of the subsequence to the previous sequence, min and max represent the maximum and minimum functions respectively, and r represents the T-type correlation coefficient. 4.根据权利要求3所述的基于通信网络的时间序列数据预处理方法,其特征在于:步骤S3包括:4. The method for preprocessing time series data based on a communication network according to claim 3, characterized in that: step S3 comprises: 步骤S31.计算所有子序列与其他序列间的T型关联系数,将子序列分为一组,使组内每两个序列相互间的关联系数均小于阈值,将所有分组存入集合中,得到第一参考集合;Step S31. Calculate the T-type correlation coefficients between all subsequences and other sequences, divide the subsequences into a group, make the correlation coefficients between every two sequences in the group smaller than a threshold, store all the groups into a set, and obtain a first reference set; 步骤S32.筛除第一参考集合中所有包含序列数量小于阈值的分组,得到第二参考集合;Step S32. All groups in the first reference set containing sequences whose number is less than a threshold are screened out to obtain a second reference set; 步骤S4包括:Step S4 includes: 步骤S41.对于第二参考集合中的每一组,计算组内的所有子序列中每一位元素的平均值,若平均值大于取样标准,则编译为高电平信号,若平均值小于取样标准,则编译为低电平信号,获取所有编译后的信号,组合为标准化序列,误差区间为[-Σ(x=1,m)|z(x)-z0(x)|,Σ(x=1,m)|z(x)-z0(x)|],其中z(x)代表标准化序列中第x个元素,z0(x)代表组内的所有子序列第x位元素的平均值;Step S41. For each group in the second reference set, calculate the average value of each bit element in all subsequences in the group. If the average value is greater than the sampling standard, compile it into a high-level signal. If the average value is less than the sampling standard, compile it into a low-level signal. Obtain all compiled signals and combine them into a standardized sequence. The error interval is [-Σ (x=1,m) |z(x)-z0(x)|,Σ (x=1,m) |z(x)-z0(x)|], where z(x) represents the x-th element in the standardized sequence, and z0(x) represents the average value of the x-th element of all subsequences in the group. 步骤S42.通信节点中传输后序时间序列时,将后序时间序列按照时频窗口切割,得到后序时间序列的子序列,计算各后序时间序列的子序列与标准化序列间的T型关联系数,若关联度位于误差区间内,则用标准化序列替代后序时间序列的子序列,还原后输出。Step S42. When the subsequent time series is transmitted in the communication node, the subsequent time series is cut according to the time-frequency window to obtain the subsequences of the subsequent time series, and the T-type correlation coefficient between each subsequence of the subsequent time series and the standardized sequence is calculated. If the correlation is within the error interval, the subsequence of the subsequent time series is replaced by the standardized sequence, and then restored and output. 5.根据权利要求4所述的基于通信网络的时间序列数据预处理方法,其特征在于:步骤S5包括:5. The method for preprocessing time series data based on a communication network according to claim 4, characterized in that: step S5 comprises: 步骤S51.按照通信节点中输入子序列和输出子序列信息量的比例,确定通信节点的信息处理速度,在通信网络中对各节点的速度进行标识;Step S51. Determine the information processing speed of the communication node according to the ratio of the amount of information of the input subsequence and the output subsequence in the communication node, and identify the speed of each node in the communication network; 步骤S52.计算待处理数据的信息量,选用调度算法在节点间分配流量,所述调度算法包括:动态加权调度、混合调度、神经网络调度和批处理调度。Step S52. Calculate the amount of information of the data to be processed, and select a scheduling algorithm to distribute traffic among nodes. The scheduling algorithm includes: dynamic weighted scheduling, hybrid scheduling, neural network scheduling, and batch scheduling. 6.基于通信网络的时间序列数据预处理系统,其特征在于,所述系统包括以下模块:信号监听模块、波频分析模块、标准拟合模块、序列处理模块和节点调度模块;6. A time series data preprocessing system based on a communication network, characterized in that the system comprises the following modules: a signal monitoring module, a wave frequency analysis module, a standard fitting module, a sequence processing module and a node scheduling module; 所述信号监听模块用于在通信网络的节点服务器中载入监听控件,获取各通信网络节点的输入数据和输出数据,并将通信数据以时间序列展开,在节点的输入输出端口处设置信息处理装置或信号传输通路,以存储展开的时间序列,并对时间序列进行运算分析;The signal monitoring module is used to load the monitoring control in the node server of the communication network, obtain the input data and output data of each communication network node, and expand the communication data in a time series, set an information processing device or a signal transmission path at the input and output ports of the node to store the expanded time series, and perform calculation analysis on the time series; 所述波频分析模块用于采用可变窗口的加窗变换处理展开的时间序列,根据相关系数最高时的窗口间隔确定时间序列的时频窗口,按照时频窗口切割序列,得到子序列,对各子序列与前序子序列进行无量纲化折线变换,根据子序列间的信息分布,计算各子序列的构成差、构成比和T型关联系数;The wave frequency analysis module is used to process the expanded time series using a variable window windowing transformation, determine the time frequency window of the time series according to the window interval when the correlation coefficient is the highest, cut the sequence according to the time frequency window to obtain subsequences, perform dimensionless broken line transformation on each subsequence and the previous subsequence, and calculate the composition difference, composition ratio and T-type correlation coefficient of each subsequence according to the information distribution between the subsequences; 所述标准拟合模块用于按照子序列间的T型关联系数计算各子序列与其他子序列的关联度,保留所有关联度小于阈值的序列集合得到第一参考集合,在第一参考集合中,再舍弃序列数量小于阈值的集合,得到第二参考集合,对于每一个第二参考集合中的全部子序列进行差分拟合,输出每个第二参考集合对应的标准化序列和观测误差区间;The standard fitting module is used to calculate the correlation between each subsequence and other subsequences according to the T-type correlation coefficient between the subsequences, retain all sequence sets with correlations less than a threshold to obtain a first reference set, and in the first reference set, discard the set with a sequence number less than the threshold to obtain a second reference set, perform differential fitting on all subsequences in each second reference set, and output a standardized sequence and an observation error interval corresponding to each second reference set; 所述序列处理模块用于获取后序输入或输出序列,按照时频窗口切割序列,分离出后序子序列,计算后序子序列与各标准化序列的关联度,当关联度位于误差区间内时,对后序序列进行标准化处理,使后序序列与标准化拟合序列一致后输出,否则重复时间窗口切割,并将切割结果融合进第一参考集合中;The sequence processing module is used to obtain a post-sequence input or output sequence, cut the sequence according to the time-frequency window, separate the post-sequence subsequence, calculate the correlation between the post-sequence subsequence and each standardized sequence, and when the correlation is within the error interval, perform standardization on the post-sequence to make the post-sequence consistent with the standardized fitting sequence before outputting it, otherwise repeat the time window cutting, and merge the cutting result into the first reference set; 所述节点调度模块用于获取通信网络中各节点的输入及输出的子序列数量,根据输入输出子序列数量的比例确定节点的运算速度,按照节点的运算速度对通信网络进行任务化节点管理,使各节点的输入输出序列数保持统一比例,以稳定通信网络的数据处理效率。The node scheduling module is used to obtain the number of input and output subsequences of each node in the communication network, determine the node's computing speed according to the ratio of the number of input and output subsequences, and perform task-based node management on the communication network according to the node's computing speed, so that the number of input and output sequences of each node maintains a uniform ratio, thereby stabilizing the data processing efficiency of the communication network. 7.根据权利要求6所述的基于通信网络的时间序列数据预处理系统,其特征在于:所述信号监听模块包括:端口控件单元和中央处理单元;7. The time series data preprocessing system based on communication network according to claim 6, characterized in that: the signal monitoring module comprises: a port control unit and a central processing unit; 所述端口控件单元设置在节点服务器的输入输出端口中,用于监听输入输出信号的时间序列;The port control unit is arranged in the input and output ports of the node server and is used to monitor the time series of the input and output signals; 所述中央处理单元用于通过终端数据运算芯片或反馈通路,为时间序列分析提供算力支持。The central processing unit is used to provide computing power support for time series analysis through a terminal data computing chip or a feedback path. 8.根据权利要求7所述的基于通信网络的时间序列数据预处理系统,其特征在于:所述波频分析模块包括:加窗变换单元、时频切割单元和构成分析单元;8. The time series data preprocessing system based on communication network according to claim 7 is characterized in that: the wave frequency analysis module includes: a windowing transformation unit, a time-frequency cutting unit and a composition analysis unit; 所述加窗变换单元用于按照数据信息熵选用窗口函数,以窗口函数为基础对时间序列作离散小波变换;The windowing transformation unit is used to select a window function according to the data information entropy, and perform discrete wavelet transformation on the time series based on the window function; 所述时频切割单元用于计算离散小波变换函数取最大值时窗口函数的时延,以时频窗口切割序列,得到子序列;The time-frequency cutting unit is used to calculate the time delay of the window function when the discrete wavelet transform function takes the maximum value, and cut the sequence with the time-frequency window to obtain a subsequence; 所述构成分析单元用于根据子序列间的信息分布,计算各子序列的构成差、构成比和T型关联系数函数。The composition analysis unit is used to calculate the composition difference, composition ratio and T-type correlation coefficient function of each subsequence according to the information distribution between the subsequences. 9.根据权利要求8所述的基于通信网络的时间序列数据预处理系统,其特征在于:所述标准拟合模块包括:关联分组单元和差分拟合单元;9. The time series data preprocessing system based on communication network according to claim 8, characterized in that: the standard fitting module comprises: an association grouping unit and a differential fitting unit; 所述关联分组单元用于对各子序列间的T型关联系数进行关联度计算,按照计算结果对子序列进行分组;The association grouping unit is used to calculate the association degree of the T-type association coefficients between the subsequences, and group the subsequences according to the calculation results; 所述差分拟合单元用于对分组结果进行筛选,去除无效分组和非显著分组,得到第二参考集合;The differential fitting unit is used to screen the grouping results, remove invalid groups and non-significant groups, and obtain a second reference set; 所述序列处理模块包括:信号过滤单元和序列融合单元;The sequence processing module includes: a signal filtering unit and a sequence fusion unit; 所述信号过滤单元用于切割后序子序列,将后序子序列按照对应的标准序列信息进行过滤;The signal filtering unit is used to cut the post-sequence and filter the post-sequence according to the corresponding standard sequence information; 所述序列融合单元用于融合过滤后的后序子序列,还原为时间序列后送入通信节点进行处理。The sequence fusion unit is used to fuse the filtered post-order subsequences, restore them to time series, and then send them to the communication node for processing. 10.根据权利要求9所述的基于通信网络的时间序列数据预处理系统,其特征在于:所述节点调度模块包括:节点测试单元、任务管理单元和效率稳定单元;10. The time series data preprocessing system based on communication network according to claim 9, characterized in that: the node scheduling module comprises: a node testing unit, a task management unit and an efficiency stabilization unit; 所述节点测试单元用于按照通信节点中输入子序列和输出子序列信息量的比例,计算通信节点的信息处理速度;The node testing unit is used to calculate the information processing speed of the communication node according to the ratio of the information amount of the input subsequence and the output subsequence in the communication node; 所述任务管理单元用于按照待传输信号的数据量和各节点的信息处理速度规划最佳任务分配方式;The task management unit is used to plan the best task allocation method according to the data volume of the signal to be transmitted and the information processing speed of each node; 所述效率稳定单元用于实时计算通信网络的整体效率,实时上传通信网络输入输出时间序列的信息量。The efficiency stabilization unit is used to calculate the overall efficiency of the communication network in real time and upload the information volume of the communication network input and output time series in real time.
CN202510368692.3A 2025-03-27 2025-03-27 Time sequence data preprocessing system and method based on communication network Active CN119906533B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202510368692.3A CN119906533B (en) 2025-03-27 2025-03-27 Time sequence data preprocessing system and method based on communication network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202510368692.3A CN119906533B (en) 2025-03-27 2025-03-27 Time sequence data preprocessing system and method based on communication network

Publications (2)

Publication Number Publication Date
CN119906533A true CN119906533A (en) 2025-04-29
CN119906533B CN119906533B (en) 2025-07-22

Family

ID=95474143

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202510368692.3A Active CN119906533B (en) 2025-03-27 2025-03-27 Time sequence data preprocessing system and method based on communication network

Country Status (1)

Country Link
CN (1) CN119906533B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116975760A (en) * 2023-06-27 2023-10-31 安徽农业大学 Time sequence anomaly detection method combining wavelet transformation and Markov model
CN117851920A (en) * 2024-03-07 2024-04-09 国网山东省电力公司信息通信公司 Power Internet of Things data anomaly detection method and system
CN117950862A (en) * 2024-01-12 2024-04-30 北京邮电大学 Dynamic capacity expansion and contraction method and related equipment
CN119030799A (en) * 2024-10-28 2024-11-26 南京中新赛克科技有限责任公司 Method for mining and analyzing abnormal behaviors in industrial Internet security
CN119538119A (en) * 2025-01-22 2025-02-28 吉林大学 Method and system for detecting abnormal breathing in children based on physiological signals
CN119651605A (en) * 2024-12-24 2025-03-18 南京新联电子股份有限公司 A method for adding control branches in multiple scenarios during demand response execution

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116975760A (en) * 2023-06-27 2023-10-31 安徽农业大学 Time sequence anomaly detection method combining wavelet transformation and Markov model
CN117950862A (en) * 2024-01-12 2024-04-30 北京邮电大学 Dynamic capacity expansion and contraction method and related equipment
CN117851920A (en) * 2024-03-07 2024-04-09 国网山东省电力公司信息通信公司 Power Internet of Things data anomaly detection method and system
CN119030799A (en) * 2024-10-28 2024-11-26 南京中新赛克科技有限责任公司 Method for mining and analyzing abnormal behaviors in industrial Internet security
CN119651605A (en) * 2024-12-24 2025-03-18 南京新联电子股份有限公司 A method for adding control branches in multiple scenarios during demand response execution
CN119538119A (en) * 2025-01-22 2025-02-28 吉林大学 Method and system for detecting abnormal breathing in children based on physiological signals

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王可等: "一种面向工作负载预测的基于小波变换的特征提取方法", 计算机与现代化, no. 05, 15 May 2020 (2020-05-15) *

Also Published As

Publication number Publication date
CN119906533B (en) 2025-07-22

Similar Documents

Publication Publication Date Title
US7451210B2 (en) Hybrid method for event prediction and system control
CN112115024A (en) Training method and device for fault prediction neural network model
CN111242171A (en) Model training, diagnosis and prediction method and device for network fault and electronic equipment
CN113220534B (en) Cluster multidimensional anomaly monitoring method, device, equipment and storage medium
JP3902606B2 (en) Self-similar traffic generation
CN118737252A (en) Flash memory particle classification method, device, electronic device and storage medium
CN113485792B (en) Pod scheduling method in kubernetes cluster, terminal equipment and storage medium
CN113391973B (en) Internet of things cloud container log collection method and device
CN116132553A (en) Big data transmission optimization method and system
CN119906533B (en) Time sequence data preprocessing system and method based on communication network
CN119561872A (en) An intelligent analysis and optimization method based on network traffic
CN112737799B (en) Data processing method, device and storage medium
CN110362387A (en) Processing method, device, system and the storage medium of distributed task scheduling
CN115374019B (en) Method and system for testing distributed UI test cases and computer storage medium
US20180343171A1 (en) Autonomic method for managing a computing system
CN115296930B (en) Periodic behavior detection method, system and terminal
CN114496299B (en) Epidemic prevention information processing method based on deep learning and epidemic prevention service system
US11703835B2 (en) Methods, systems and data structures for optimizing parameter data retrieval from devices in a control system
EP3825873A1 (en) System with big data analysis device for cloud platforms and the operation method thereof
US6721719B1 (en) System and method for classification using time sequences
CN119576888B (en) Analysis method of log data with large data volume and storage medium
CN118312912B (en) Optical fiber temperature monitoring method, device, equipment, storage medium and product
CN117075684B (en) Self-adaptive clock gridding calibration method for Chiplet chip
US20060221860A1 (en) Nodal pattern configuration
JPH0934721A (en) Data analyzer

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载