CN117278074A - Power terminal carrier communication evaluation method and system based on multidimensional index - Google Patents

Power terminal carrier communication evaluation method and system based on multidimensional index Download PDF

Info

Publication number
CN117278074A
CN117278074A CN202311247795.1A CN202311247795A CN117278074A CN 117278074 A CN117278074 A CN 117278074A CN 202311247795 A CN202311247795 A CN 202311247795A CN 117278074 A CN117278074 A CN 117278074A
Authority
CN
China
Prior art keywords
index
weight matrix
carrier communication
indexes
criterion decision
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.)
Pending
Application number
CN202311247795.1A
Other languages
Chinese (zh)
Inventor
施展
刘嘉宁
李星南
张延旭
苏卓
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.)
Guangdong Power Grid Co Ltd
Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd
Original Assignee
Guangdong Power Grid Co Ltd
Electric Power Dispatch Control Center of Guangdong Power Grid 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 Guangdong Power Grid Co Ltd, Electric Power Dispatch Control Center of Guangdong Power Grid Co Ltd filed Critical Guangdong Power Grid Co Ltd
Priority to CN202311247795.1A priority Critical patent/CN117278074A/en
Publication of CN117278074A publication Critical patent/CN117278074A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B3/00—Line transmission systems
    • H04B3/02—Details
    • H04B3/46—Monitoring; Testing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B3/00—Line transmission systems
    • H04B3/54—Systems for transmission via power distribution lines

Landscapes

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

Abstract

The invention discloses a power end carrier communication evaluation method and a system based on multidimensional indexes, wherein the method comprises the following steps: the method comprises the steps of collecting multidimensional indexes for carrying out carrier communication evaluation on the power terminal to be detected, constructing a carrier communication multilevel evaluation system corresponding to the power terminal to be detected and a multi-criterion decision index weight matrix integrating the multi-indexes, carrying out consistency check on the multi-criterion decision index weight matrix, adjusting the multi-criterion decision index weight matrix according to a check result, determining the weight of each index in the multidimensional indexes according to the adjusted multi-criterion decision index weight matrix, and obtaining a carrier communication evaluation result of the power terminal to be detected according to the weight and the power terminal carrier communication multilevel evaluation system, so that the accuracy and the comprehensiveness of the power terminal carrier communication evaluation are improved.

Description

Power terminal carrier communication evaluation method and system based on multidimensional index
Technical Field
The invention relates to the technical field of power system safety evaluation, in particular to a power terminal carrier communication evaluation method and system based on multidimensional indexes.
Background
The power line carrier communication technology has the advantages of low cost, high utilization rate of infrastructure, high data transmission reliability, wide coverage range of a power line and the like, is an important communication mode for supporting information interaction between the power terminal and the power grid, and can realize remote data transmission and signal control by using the power line as a transmission medium. However, the power line carrier communication technology is susceptible to factors such as load change of a power line, interference of power equipment, electromagnetic interference and the like in a transmission process of a power terminal, so that the real-time performance and reliability of data transmission are not high, and the power line carrier communication technology is particularly remarkable in a complex power network. Meanwhile, potential safety hazards such as data leakage and tampering can exist in the power line carrier communication technology in the power terminal data transmission process.
The comprehensive evaluation of the real-time performance, the reliability and the safety of the power terminal carrier communication technology can be carried out, the operation efficiency and the reliability of a power system can be improved, the safety of carrier communication can be ensured, potential security threats and attacks are prevented, and the stable operation of the power system is ensured.
However, the existing evaluation method does not consider the real-time performance, reliability and overall performance of safety of the power end carrier communication, only one index is often concerned, so that the evaluation result is inaccurate or incomplete, and meanwhile, readjustment in the consistency test process of the multi-criterion decision index weight matrix is ignored, and the situation of relative importance among accurate indexes can not be obtained by correcting when the index weight matrix does not meet consistency, so that the evaluation result of the power end carrier communication technology is inaccurate.
Disclosure of Invention
In order to solve the technical problems, the invention discloses a power end carrier communication evaluation method and a system based on multidimensional indexes, which improve the accuracy and the comprehensiveness of power end carrier communication evaluation.
To achieve the above object, in a first aspect, the present invention discloses a power end carrier communication evaluation method based on a multidimensional index, including:
the method comprises the steps of collecting multidimensional indexes for carrying out carrier communication evaluation on the power terminal to be detected, and constructing a carrier communication multi-level evaluation system corresponding to the power terminal to be detected;
constructing a multi-criterion decision index weight matrix which is corresponding to each level in the carrier communication multi-level evaluation system and is fused with multiple indexes;
consistency verification is carried out on the multi-criterion decision index weight matrix, and the multi-criterion decision index weight matrix is adjusted according to a verification result;
and determining the weight of each index in the multidimensional index according to the adjusted multi-criterion decision index weight matrix, and obtaining the carrier communication evaluation result of the power terminal to be detected according to the weight and the power terminal carrier communication multi-level evaluation system.
The invention discloses a power terminal carrier communication assessment method based on multi-dimensional indexes, which comprises the steps of firstly constructing a carrier communication multi-level assessment system corresponding to a power terminal to be detected according to collected multi-dimensional indexes, specifically, carrying out multi-dimensional assessment according to the collected multi-dimensional indexes, improving the comprehensiveness of carrier communication assessment, further constructing a multi-criterion decision index weight matrix corresponding to each level in the multi-level assessment system after fusion of the multi-criterion decision index weight matrix, so as to better reflect the uncertainty and the variability of each index weight during assessment according to the multi-criterion decision index weight matrix, further objectively evaluate the comprehensive performance of the power terminal carrier communication technology, realize the best result matching of carrier performance quality, improve the accuracy and the comprehensiveness of the power terminal carrier communication technology assessment, simultaneously carry out consistency check on the constructed multi-criterion decision index weight matrix, analyze the rationality of the weight distribution among elements in the multi-criterion decision index weight, and adjust the multi-criterion index weight matrix according to the check result, thereby improving the accuracy of the power terminal carrier communication relative to the power terminal communication assessment.
As a preferable example, the multi-dimensional index includes a real-time index, a reliability index, and a safety index; wherein, the real-time index comprises congestion rate index, transmission rate index, communication delay index, packet loss rate index and signal intensity index; the reliability index comprises a time delay fluctuation index, a retransmission frequency index, a line utilization index, a bit error rate index and a line fault probability index; the safety indexes comprise data encryption and decryption capability indexes, anti-interference capability indexes, security vulnerability protection capability indexes and fault recovery speed indexes.
According to the invention, various index data representing the power terminal to be detected are respectively collected, so that the reliability, the safety and the real-time performance of the power terminal to be detected are respectively evaluated according to the index data, and the comprehensiveness of the carrier communication technology evaluation of the power terminal to be detected is improved.
As a preferred example, the constructing the multi-criterion decision index weight matrix of the fusion multi-index corresponding to each level in the multi-level evaluation system of carrier communication includes:
dividing indexes of each level in each level into a plurality of groups according to a preset grouping mode to obtain a plurality of groups of index data sets;
According to a preset ordering mode, ordering a plurality of indexes in each of the plurality of groups of index data sets;
defining weight sets corresponding to each group of index data sets through the sequencing to obtain a plurality of weight sets corresponding to the plurality of groups of index data sets;
and comparing the plurality of weight sets pairwise according to a preset floating grading evaluation method to obtain the multi-criterion decision index weight matrix.
According to the method, indexes of each level are grouped according to a preset grouping mode, each group comprises a plurality of indexes, then each index in each group is ordered, the subsequent comparison is convenient, the weight corresponding to each index is defined according to the ordering, the weight set corresponding to each index group is further obtained, the importance degree of different weight sets on a certain index is compared in pairs through the floating grading evaluation method, a multi-criterion decision index is further formed, meanwhile, the floating grading evaluation method converts the original fixed score scoring method into a method for scoring any score of an interval, and convenience is provided for readjustment of a weight matrix of the subsequent multi-criterion decision index on the basis of not greatly changing the importance among indexes.
As a preferred example, the performing consistency check on the multi-criterion decision index weight matrix includes:
performing consistency check on the multi-criterion decision index weight matrix according to a preset consistency measurement index; wherein, the consistency measurement index is as follows:
H＝(max[α 1 ,α 2 ,Lα m ]-n)/(n-1)
wherein alpha is m And the m characteristic root of the index multi-criterion decision index weight matrix is represented, n represents the index weight number in the multi-criterion decision index weight matrix, H is a consistency measurement index and is used for measuring the deviation consistency degree of the multi-criterion decision index weight matrix.
The consistency of the multi-criterion decision index weight matrix is measured according to the consistency measurement index, and the rationality of weight distribution among all elements in the multi-criterion decision index weight matrix is analyzed by observing the consistency measurement index of the multi-criterion decision index weight matrix so as to obtain the accurate relative importance condition among index elements.
As a preferred example, the adjusting the multi-criterion decision index weight matrix according to the result of the test includes:
comparing the consistency measurement index with a preset index threshold value, and judging whether the multi-criterion decision index weight matrix meets consistency or not;
When the consistency measurement index is smaller than or equal to the index threshold, judging that the multi-criterion decision index weight matrix meets consistency and not adjusting the multi-criterion decision index weight matrix;
when the consistency measurement index is larger than the index threshold, judging that the multi-criterion decision index weight matrix does not meet consistency, and adjusting the multi-criterion decision index weight matrix through a preset self-adaptive learning multi-layer perceptron.
In the invention, whether the generated multi-criterion decision index weight matrix is reasonable is judged by setting a threshold value, so that the reasonable matrix is utilized to carry out subsequent evaluation, the evaluation accuracy is improved, and in the judging process, if the weight matrix does not meet the consistency, the weight matrix is adjusted by a set self-adaptive learning multi-layer perceptron so as to obtain the optimal consistency of the matrix.
As a preferred example, the adjusting the multi-criterion decision index weight matrix by the preset adaptive learning multi-layer perceptron includes:
adjusting the multi-criterion decision index weight matrix according to multi-layer mapping among an observation layer, a middle layer and a prediction layer in the self-adaptive learning multi-layer perceptron; wherein, the mapping formula between the observation layer and the middle layer is:
C mid (t)＝HardSwish[Q 1 (t),δ mid Logistic(C in (t))]-Gate[M 1 (t),γ mid Logistic(C in (t))]
Wherein C is mid (t) represents a multi-criterion decision index weight matrix obtained through mapping between an observation layer and an intermediate layer, logistic (g) represents an activation function for converting an input matrix into a nonlinear output, learning capacity of the adaptive learning multi-layer perceptron is increased, hardSwish (g) represents a weight mapping function for realizing mapping of the weight matrix, and Gate [ g ]]Represents a threshold mapping function for determining whether a threshold matrix is reserved, delta mid Represents a weight factor gamma between the observation layer and the intermediate layer preset according to historical experience mid Representative calendarA threshold factor between an observation layer and an intermediate layer preset by history experience;
the mapping formula between the middle layer and the prediction layer is as follows:
C out (t)＝HardSwish[Q 2 (t),δ out Logistic(C mid (t))]Pred[M 2 (t),γ out Logistic(C mid (t))]
wherein C is out (t) represents a multi-criterion decision index weight matrix obtained by mapping an intermediate layer and a predicted layer, pred [ g ]]Representing a threshold mapping function for mapping the prediction matrix M 2 (t) mapping to prediction layer, delta out Represents a weighting factor gamma between the intermediate layer and the predicted layer preset according to historical experience out Representing a threshold factor between the intermediate layer and the predictive layer preset based on historical experience.
The invention inputs the multi-criterion decision index weight matrix which does not meet the consistency requirement into the built self-adaptive learning multi-layer perceptron, carries out iterative mapping on the multi-criterion decision index weight matrix through the mapping functions preset in the observation layer, the middle layer and the prediction layer of the multi-layer perceptron, continuously adjusts each element in the weight matrix, and outputs the optimized multi-criterion decision index weight matrix, thereby acquiring the accurate relative importance situation among index elements according to the adjusted multi-criterion decision index weight matrix which meets the consistency requirement and improving the accuracy of the power terminal carrier communication technology assessment.
As a preferred example, determining the weight of each index in the multidimensional index according to the adjusted multi-criterion decision index weight matrix, and obtaining the carrier communication evaluation result of the power end to be detected according to the weight and the power end carrier communication multi-level evaluation system includes:
determining the weight of each index in the multi-dimensional indexes through a characteristic method according to the multi-criterion decision index weight matrix;
carrying out quantization detection on each index in the multidimensional indexes according to a preset quantization analysis method and an expert scoring method, and carrying out normalization processing on the quantization detection result to obtain index performance values corresponding to each index respectively;
and obtaining a carrier communication evaluation result of the power end to be detected through a preset evaluation value calculation formula according to the index performance value and the weight.
The invention uses a characteristic method to determine the corresponding index weight of the multi-criterion decision index weight matrix meeting the consistency requirement, and then uses a quantization analysis method and an expert scoring method to quantitatively detect or qualitatively evaluate all index performances of an index layer of a multi-dimensional evaluation index system of the power end carrier communication technology, and performs normalization processing to calculate a specific score of the comprehensive performance of the power end carrier communication technology, thereby accurately evaluating the performance of the current carrier communication technology in real time and realizing modeling and quantitative evaluation of the real-time performance, reliability and safety of the carrier communication technology.
In a second aspect, the invention discloses a power end carrier communication evaluation system based on multidimensional indexes, which comprises a data acquisition module, a weight matrix module, a verification adjustment module and a communication evaluation module.
The data acquisition module is used for acquiring multidimensional indexes for carrying out carrier communication evaluation on the power terminal to be detected and constructing a carrier communication multi-level evaluation system corresponding to the power terminal to be detected;
the weight matrix module is used for constructing a multi-criterion decision index weight matrix which is corresponding to each level in the carrier communication multi-level evaluation system and is fused with multiple indexes;
the verification adjustment module is used for carrying out consistency verification on the multi-criterion decision index weight matrix and adjusting the multi-criterion decision index weight matrix according to a verification result;
the communication evaluation module is used for determining the weight of each index in the multidimensional index according to the adjusted multi-criterion decision index weight matrix, and obtaining the carrier communication evaluation result of the power terminal to be detected according to the weight and the power terminal carrier communication multi-level evaluation system.
The invention discloses a power terminal carrier communication evaluation system based on multi-dimensional indexes, which comprises a multi-dimensional evaluation system for multi-dimensional communication of the carrier communication corresponding to the power terminal to be detected, wherein the multi-dimensional evaluation system is constructed according to the acquired multi-dimensional indexes, specifically, the multi-dimensional evaluation is carried out according to the acquired multi-dimensional indexes, the comprehensiveness of the carrier communication evaluation can be improved, further, a multi-criterion decision index weight matrix corresponding to each level in the multi-level evaluation system after multi-index fusion is constructed, the uncertainty and the variability of each index weight are better reflected when the multi-criterion decision index weight matrix is evaluated, further, objective evaluation is carried out on the comprehensive performance of the power terminal carrier communication technology, the best result matching of the carrier performance is realized, the accuracy and the comprehensiveness of the power terminal carrier communication technology evaluation are improved, meanwhile, the consistence of the multi-criterion decision index weight matrix after construction is carried out is checked, the rationality of the weight distribution among elements in the multi-criterion decision index weight is analyzed, the multi-criterion decision weight matrix is adjusted according to the checking result, and the importance of the power terminal communication is further improved.
As a preferable example, the weight matrix module includes a ranking unit and a weight unit;
the sorting unit is used for dividing indexes of each level in each level into a plurality of groups according to a preset grouping mode to obtain a plurality of groups of index data sets; according to a preset ordering mode, ordering a plurality of indexes in each of the plurality of groups of index data sets;
the weight unit is used for defining weight sets corresponding to each group of index data sets through the sorting to obtain a plurality of weight sets corresponding to the plurality of groups of index data sets; and comparing the plurality of weight sets pairwise according to a preset floating grading evaluation method to obtain the multi-criterion decision index weight matrix.
According to the method, indexes of each level are grouped according to a preset grouping mode, each group comprises a plurality of indexes, then each index in each group is ordered, the subsequent comparison is convenient, the weight corresponding to each index is defined according to the ordering, the weight set corresponding to each index group is further obtained, the importance degree of different weight sets on a certain index is compared in pairs through the floating grading evaluation method, a multi-criterion decision index is further formed, meanwhile, the floating grading evaluation method converts the original fixed score scoring method into a method for scoring any score of an interval, and convenience is provided for readjustment of a weight matrix of the subsequent multi-criterion decision index on the basis of not greatly changing the importance among indexes.
In a third aspect, the invention also discloses an electronic device, which comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; a memory for storing a computer program; the processor is configured to implement a power end carrier communication evaluation method based on a multidimensional index according to the first aspect when executing a program stored in the memory.
Drawings
Fig. 1: the flow diagram of the power end carrier communication evaluation method based on the multidimensional index is provided for the embodiment of the invention;
fig. 2: the embodiment of the invention provides a structural schematic diagram of a power end carrier communication evaluation system based on multidimensional indexes;
fig. 3: the flow chart of the power end carrier communication evaluation method based on the multidimensional index is provided for the further embodiment of the 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.
Example 1
In this embodiment, a power end carrier communication evaluation method based on multidimensional indexes is provided, and a specific implementation flow of the evaluation method may refer to fig. 1, including steps 101 to 104, where the steps include:
step 101: and acquiring multidimensional indexes for carrying out carrier communication evaluation on the power terminal to be detected, and constructing a carrier communication multi-level evaluation system corresponding to the power terminal to be detected.
In this embodiment, the steps include: the multidimensional index comprises a real-time index, a reliability index and a safety index; the acquired real-time indexes comprise congestion rate indexes, transmission rate indexes, communication time delay indexes, packet loss rate indexes and signal strength indexes; the reliability index comprises a time delay fluctuation index, a retransmission frequency index, a line utilization index, a bit error rate index and a line fault probability index; the safety indexes comprise data encryption and decryption capability indexes, anti-interference capability indexes, security vulnerability protection capability indexes and fault recovery speed indexes.
In this embodiment, the step collects various index data representing the power end to be detected, so as to evaluate the reliability, safety and real-time performance of the power end to be detected according to the index data, and improve the comprehensiveness of the evaluation of the carrier communication technology of the power end to be detected.
Step 102: constructing a multi-criterion decision index weight matrix which is corresponding to each level in the carrier communication multi-level evaluation system and is fused with multiple indexes.
In this embodiment, the steps include: dividing indexes of each level in each level into a plurality of groups according to a preset grouping mode to obtain a plurality of groups of index data sets; according to a preset ordering mode, ordering a plurality of indexes in each of the plurality of groups of index data sets; defining weight sets corresponding to each group of index data sets through the sequencing to obtain a plurality of weight sets corresponding to the plurality of groups of index data sets; and comparing the plurality of weight sets pairwise according to a preset floating grading evaluation method to obtain the multi-criterion decision index weight matrix.
In this embodiment, the step groups the indexes of each level according to a preset grouping mode, wherein each group comprises a plurality of indexes, then each index in each group is ordered, the subsequent comparison is convenient, the weight corresponding to each index is defined according to the ordering, the weight set corresponding to each index group is further obtained, the importance degree of different weight sets to a certain index is compared in pairs by the floating grading evaluation method, a multi-criterion decision index is further formed, and meanwhile, the floating grading evaluation method converts the original fixed score scoring method into a method for scoring any score of an interval, so that convenience is provided for readjusting the weight matrix of the subsequent multi-criterion decision index on the basis of not greatly changing the importance among indexes.
Step 103: and carrying out consistency check on the multi-criterion decision index weight matrix, and adjusting the multi-criterion decision index weight matrix according to a check result.
In this embodiment, the steps include: performing consistency check on the multi-criterion decision index weight matrix according to a preset consistency measurement index; wherein, the consistency measurement index is as follows:
H＝(max[α 1 ,α 2 ,Lα m ]-n)/(n-1)
wherein alpha is m And the m characteristic root of the index multi-criterion decision index weight matrix is represented, n represents the index weight number in the multi-criterion decision index weight matrix, H is a consistency measurement index and is used for measuring the deviation consistency degree of the multi-criterion decision index weight matrix.
Comparing the consistency measurement index with a preset index threshold value, and judging whether the multi-criterion decision index weight matrix meets consistency or not; when the consistency measurement index is smaller than or equal to the index threshold, judging that the multi-criterion decision index weight matrix meets consistency and not adjusting the multi-criterion decision index weight matrix; when the consistency measurement index is larger than the index threshold, judging that the multi-criterion decision index weight matrix does not meet consistency, and adjusting the multi-criterion decision index weight matrix through a preset self-adaptive learning multi-layer perceptron.
Further, the multi-criterion decision index weight matrix is adjusted according to multi-layer mapping among an observation layer, a middle layer and a prediction layer in the self-adaptive learning multi-layer perceptron; wherein, the mapping formula between the observation layer and the middle layer is:
C mid (t)＝HardSwish[Q 1 (t),δ mid Logistic(C in (t))]-Gate[M 1 (t),γ mid Logistic(C in (t))]
wherein C is mid (t) represents a multi-criterion decision index weight matrix obtained through mapping between an observation layer and an intermediate layer, logistic (g) represents an activation function for converting an input matrix into a nonlinear output, learning capacity of the adaptive learning multi-layer perceptron is increased, hardSwish (g) represents a weight mapping function for realizing mapping of the weight matrix, and Gate [ g ]]Represents a threshold mapping function for determining whether a threshold matrix is reserved, delta mid Represents a weight factor gamma between the observation layer and the intermediate layer preset according to historical experience mid Representing a threshold factor between an observation layer and an intermediate layer preset according to historical experience;
the mapping formula between the middle layer and the prediction layer is as follows:
C out (t)＝HardSwish[Q 2 (t),δ out Logistic(C mid (t))]Pred[M 2 (t),γ out Logistic(C mid (t))]
wherein C is out (t) represents a multi-criterion decision index weight matrix obtained by mapping an intermediate layer and a predicted layer, pred [ g ]]Representing a threshold mapping function for mapping the prediction matrix M 2 (t) mapping to prediction layer, delta out Represents a weighting factor gamma between the intermediate layer and the predicted layer preset according to historical experience out Representing a threshold factor between the intermediate layer and the predictive layer preset based on historical experience.
In this embodiment, the step measures the consistency of the multi-criterion decision index weight matrix according to the consistency metric index, analyzes the rationality of weight distribution among the elements in the multi-criterion decision index weight matrix by observing the consistency metric index of the multi-criterion decision index weight matrix, so as to obtain the accurate relative importance situation among index elements, determines whether the generated multi-criterion decision index weight matrix is reasonable by setting a threshold value, so that the reasonable matrix is utilized to perform subsequent evaluation, the accuracy of the evaluation is improved, and in the determination process, if the weight matrix does not meet the consistency, the weight matrix is adjusted by the set adaptive learning multi-layer perceptron so as to obtain the optimal consistency of the matrix.
Step 104: and determining the weight of each index in the multidimensional index according to the adjusted multi-criterion decision index weight matrix, and obtaining the carrier communication evaluation result of the power terminal to be detected according to the weight and the power terminal carrier communication multi-level evaluation system.
In this embodiment, the steps include: determining the weight of each index in the multi-dimensional indexes through a characteristic method according to the multi-criterion decision index weight matrix; carrying out quantization detection on each index in the multidimensional indexes according to a preset quantization analysis method and an expert scoring method, and carrying out normalization processing on the quantization detection result to obtain index performance values corresponding to each index respectively; and obtaining a carrier communication evaluation result of the power end to be detected through a preset evaluation value calculation formula according to the index performance value and the weight.
In this embodiment, the step uses a feature method to determine the corresponding index weight of the multi-criterion decision index weight matrix meeting the consistency requirement, and then uses a quantization analysis method and an expert scoring method to perform quantitative performance detection or qualitative evaluation on all index performances of an index layer of a multi-dimensional evaluation index system of the power end carrier communication technology, and performs normalization processing to calculate a specific score of the comprehensive performance of the power end carrier communication technology, so that the current carrier communication technology performance can be accurately evaluated in real time, and modeling and quantitative evaluation on the real-time performance, reliability and safety of the carrier communication technology can be realized.
On the other hand, the embodiment of the invention also discloses a power end carrier communication evaluation system based on multidimensional indexes, the specific structure composition of the evaluation system can be referred to fig. 2, and the system comprises a data acquisition module 201, a weight matrix module 202, a verification adjustment module 203 and a communication evaluation module 204.
The data acquisition module 201 is configured to acquire multidimensional indexes for performing carrier communication evaluation on a power terminal to be detected, and construct a carrier communication multi-level evaluation system corresponding to the power terminal to be detected.
The weight matrix module 202 is configured to construct a multi-criterion decision index weight matrix with multiple fused indexes corresponding to each level in the multi-level evaluation system of carrier communication.
The verification adjustment module 203 is configured to perform consistency verification on the multi-criterion decision index weight matrix, and adjust the multi-criterion decision index weight matrix according to a verification result.
The communication evaluation module 204 is configured to determine a weight of each index of the multidimensional indexes according to the adjusted multi-criterion decision index weight matrix, and obtain a carrier communication evaluation result of the power end to be detected according to the weight and the power end carrier communication multi-level evaluation system.
In this embodiment, the weight matrix module 202 further includes a sorting unit and a weight unit.
The sorting unit is used for dividing indexes of each level in each level into a plurality of groups according to a preset grouping mode to obtain a plurality of groups of index data sets; and ordering the indexes in each of the plurality of sets of index data according to a preset ordering mode.
The weight unit is used for defining weight sets corresponding to each group of index data sets through the sorting to obtain a plurality of weight sets corresponding to the plurality of groups of index data sets; and comparing the plurality of weight sets pairwise according to a preset floating grading evaluation method to obtain the multi-criterion decision index weight matrix.
In addition to the above method and system, the present embodiment further provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus; a memory for storing a computer program; and the processor is used for realizing the power end carrier communication evaluation method based on the multidimensional index when executing the program stored in the memory.
According to the power terminal carrier communication assessment method and system based on the multidimensional index, firstly, a multi-criterion decision index weight matrix which is used for carrier communication assessment and corresponds to the power terminal to be detected is constructed according to the collected multidimensional index, specifically, the collected multidimensional index comprises a real-time index, a reliability index and a safety index, the real-time property, the reliability and the safety of the carrier communication technology of the power terminal to be detected can be comprehensively considered according to the multidimensional index, the comprehensiveness of carrier communication assessment is improved, further, a multi-criterion decision index weight matrix which is corresponding to each level and is fused with the multi-criterion decision index is constructed, uncertainty and variability of weights of the indexes during assessment are better reflected according to the multi-criterion decision index weight matrix, objective assessment is further carried out on the comprehensive performance of the power terminal carrier communication technology, optimal result matching of carrier performance is achieved, accuracy and comprehensiveness of the power terminal carrier communication technology assessment are improved, meanwhile, the constructed multi-criterion decision index weight matrix is consistent, the multi-criterion decision index weight matrix is analyzed according to the fact that the multi-criterion decision index weight matrix is fused, and the accuracy of the power terminal element is reasonably assessed, and the importance of the power terminal element is reasonably assessed according to the fact that the multi-criterion decision index weight matrix is reasonably is distributed.
Example two
The embodiment of the invention provides another power end carrier communication evaluation method based on multidimensional indexes, and the specific implementation process of the evaluation method can refer to fig. 3, and mainly comprises steps 301 to 305, wherein the steps comprise:
step 301: and acquiring multidimensional indexes for carrying out carrier communication evaluation on the power terminal to be detected, and constructing a multidimensional evaluation index system of the power terminal carrier communication technology.
In this embodiment, the steps specifically include: collecting multidimensional indexes for carrying out carrier communication evaluation on the power terminal to be detected, wherein the multidimensional indexes comprise real-time indexes, reliability indexes and safety indexes, and further, the real-time indexes mainly consider indexes such as congestion rate, transmission rate, communication delay, packet loss rate, signal strength and the like, wherein the congestion rate is used for measuring the load condition of a carrier communication transmission link of the power terminal; the transmission rate and the communication time delay are used for measuring the speed of the power end carrier communication to transmit data; the packet loss rate is used for measuring the proportion of lost data packets in the data transmission process; signal strength refers to the strength of a signal received in carrier communication; the reliability index mainly considers indexes such as time delay volatility, retransmission times, line utilization rate, error rate, line fault probability and the like, wherein the time delay volatility indicates the change range of transmission time delay; the retransmission times refer to the times of retransmission in the data transmission process; the line utilization rate is used for measuring the load degree of the power end carrier communication link; the error rate refers to the proportion of transmission errors in the data transmission process, the line fault probability refers to the probability of faults of a power terminal carrier communication link, and the high line fault probability can cause interruption or delay of data transmission; the safety index is as follows: the method mainly considers indexes such as data encryption and decryption capability, anti-interference capability, security vulnerability protection capability, fault recovery speed and the like. The data encryption and decryption capability is used for measuring confidentiality and integrity of a data transmission process; the anti-interference capability is used for measuring the capability of the power end carrier communication to keep normal operation when facing external interference; the security hole protection capability is used for measuring the detection, protection and repair capability of the power line carrier communication technology on the security holes; the fault recovery speed is used for measuring the time for the power end carrier communication link to recover to normal operation after the fault occurs.
Further, after the multi-dimensional indexes are acquired, a multi-dimensional evaluation index system of the power end carrier communication technology is constructed, and the evaluation system comprises an evaluation layer, a criterion layer, an index layer and a result matching layer. The criterion layer comprises real-time indexes, reliability indexes and safety indexes, and is responsible for distributing weights of sub-index items under jurisdiction and comprehensively scoring the indexes; the index layer is the alignment layer index further decomposition, and is responsible for calculating and scoring the magnitude of the sub-index under the jurisdiction of each evaluation index of the criterion layer; the evaluation layer realizes the weight distribution of the indexes of each criterion layer, and finally gives out the comprehensive performance evaluation result of the power terminal carrier communication technology in a percentile mode; the result matching layer carries out grading evaluation on the comprehensive performance in five levels of excellent [100-90], good [89-70], qualified [69-50], poor [59-40] and invalid [39-0], so that the comprehensive performance degree of the power terminal carrier communication technology is easy to intuitively distinguish.
Step 302: constructing a multi-criterion decision index weight matrix of each level fusing multiple indexes.
In this embodiment, this step is mainly: firstly, grouping indexes of each level in the multi-level evaluation system is equivalent to grouping the indexes of each level in each level into a plurality of groups according to a preset grouping mode to obtain a plurality of groups of index data sets, specifically, taking the construction of a multi-criterion decision index weight matrix of the index layers in the multi-level evaluation system as an example, the index layers can be divided into real-time indexes, reliability indexes and safety indexes into 3 groups through expert experience or an automatic distribution program, after grouping is finished, a plurality of indexes in each group of index data sets are ordered according to a preset ordering mode, specifically, the indexes of each group are ordered in the groups according to importance, then the weight set corresponding to each group of index data sets is defined through the ordering, namely, a certain group of index weight set of the index layer is defined as C= [ C ] 1 ,c 2 ,L,c n ]Then compare c two by two i And c j The importance degree of a certain index of the criterion layer is c ij ＝c i /c j Representation, specific assignment criterion reference pre-A floating grading evaluation method is provided. Finally, a weight matrix C= [ C ] is formed ij ] n×n 。
In this embodiment, the assignment table of the floating classification evaluation method is as follows:
assignment interval Meaning of
[0，2) Indicating that the importance of the two indexes is equal
[2，4) Indicating that the front index is slightly more important than the rear index
[4，6) Representing the front index to be significantly more important than the rear index
[6，8) It is very important to represent the front index than the rear index
[8，10) Representing that the front index is extremely important than the rear index
In this embodiment, the floating classification evaluation method is adopted to convert the original fixed score scoring method into the interval arbitrary score scoring method, and on the basis of not greatly changing the importance among indexes, convenience is provided for readjustment of the subsequent multi-criterion decision index weight matrix.
Step 303: and carrying out consistency check on the multi-criterion decision index weight matrix.
In this embodiment, the steps specifically include: traditional consistency test methods, such as weight comparison analysis, are subjective and unilateral processes and have a certain ambiguity. When the degree of deviation of the index weight from the consistency is larger, namely the degree of change of the index element weight is larger, the index weight distribution of some importance indexes may be unreasonable, the accuracy of the adjacent two index weight comparison results of each group of indexes is difficult to ensure, and the comprehensive performance score of the power end carrier communication technology is inaccurate, the consistency metric index is defined for the embodiment to measure the consistency of the multi-criterion decision index weight matrix, the rationality of the weight distribution among each element in the multi-criterion decision index weight matrix is analyzed by observing the consistency metric index of the multi-criterion decision index weight matrix, so that the accurate relative importance condition among index elements is obtained, and the consistency metric index is expressed as:
H＝(max[α 1 ,α 2 ,Lα m ]-n)/(n-1)
Wherein alpha is m The m-th feature root of the index multi-criterion decision index weight matrix C is represented, n represents the index weight number in the multi-criterion decision index weight matrix, H is a consistency measurement index and is used for measuring the deviation consistency degree of the multi-criterion decision index weight matrix. The smaller H is, the better the consistency of the multi-criterion decision index weight matrix is. When H is less than 0.02, the consistency of the obtained multi-criterion decision index weight matrix is strong. When the multi-criterion decision index weight matrix does not meet the consistency, a method based on self-adaptive learning multi-layer perceptron can be adopted to adjust the matrix, so that the matrix obtains the optimal consistency.
Step 304: and adjusting the multi-criterion decision index weight matrix based on a self-adaptive learning multi-layer perceptron method.
In this embodiment, the steps include: adjusting the multi-criterion decision index weight matrix according to multi-layer mapping among an observation layer, a middle layer and a prediction layer in the self-adaptive learning multi-layer perceptron; wherein, the mapping formula between the observation layer and the middle layer is:
C mid (t)＝HardSwish[Q 1 (t),δ mid Logistic(C in (t))]-Gate[M 1 (t),γ mid Logistic(C in (t))]
wherein C is mid (t) represents a multi-criterion decision index weight matrix obtained through mapping between an observation layer and an intermediate layer, logistic (g) represents an activation function for converting an input matrix into a nonlinear output, learning capacity of the adaptive learning multi-layer perceptron is increased, hardSwish (g) represents a weight mapping function for realizing mapping of the weight matrix, and Gate [ g ] ]Represents a threshold mapping function for determining whether a threshold matrix is reserved, delta mid Represents a weight factor gamma between the observation layer and the intermediate layer preset according to historical experience mid Representing a threshold factor between an observation layer and an intermediate layer preset according to historical experience; the mapping formula between the middle layer and the prediction layer is as follows:
C out (t)＝HardSwish[Q 2 (t),δ out Logistic(C mid (t))]Pred[M 2 (t),γ out Logistic(C mid (t))]
wherein C is out (t) represents a multi-criterion decision index weight matrix obtained by mapping an intermediate layer and a predicted layer, pred [ g ]]Representing a threshold mapping function for mapping the prediction matrix M 2 (t) mapping to prediction layer, delta out Represents a weighting factor gamma between the intermediate layer and the predicted layer preset according to historical experience out Representing a threshold factor between the intermediate layer and the predictive layer preset based on historical experience.
Specifically, in this embodiment, when the adaptive learning multi-layer perceptron is adjusted, the training process of the adaptive learning multi-layer perceptron includes:
(1) And constructing a self-adaptive learning multi-layer perceptron model suitable for consistency optimization of the multi-criterion decision index weight matrix. The self-adaptive learning multi-layer perceptron comprises an observation layer, an intermediate layer and a prediction layer. Defining the weight matrix and the threshold matrix between the observation layer and the middle layer as Q respectively 1 (t) and M 1 (t); weight moment between middle layer and prediction layerThe matrix and the prediction matrix are Q respectively 2 (t) and M 2 (t)。
(2) And training the self-adaptive learning multi-layer perceptron model by taking the multi-criterion decision index weight matrix meeting the consistency requirement as a sample, and obtaining an adjusted multi-criterion decision index weight matrix through multi-layer mapping among the observation layer, the middle layer and the prediction layer. Defining the input multi-criterion decision index weight matrix as C in (t) the adjusted multi-criterion decision index weight matrix is C out (t), the mapping formula between the observation layer and the middle layer at the t-th iteration is as follows:
C mid (t)＝HardSwish[Q 1 (t),δ mid Logistic(C in (t))]-Gate[M 1 (t),γ mid Logistic(C in (t))]
wherein C is mid (t) is a multi-criterion decision index weight matrix obtained by mapping an observation layer and an intermediate layer, logistic (g) is an activation function and is used for converting an input matrix into nonlinear output, the learning capacity of the self-adaptive learning multi-layer perceptron is increased, hardSwish (g) is a weight mapping function and is used for realizing the mapping of the weight matrix, and Gate [ g ]]Is a threshold mapping function and is used for judging whether the threshold matrix is reserved or not. Delta mid For weighting factors between the observation layer and the intermediate layer preset according to historical experience, gamma mid The adjustment of the output of the middle layer can be realized by utilizing the weight factors and the threshold factors for the threshold factors between the observation layer and the middle layer preset according to historical experience.
Meanwhile, the mapping formula between the t-th iteration middle layer and the prediction layer is as follows:
C out (t)＝HardSwish[Q 2 (t),δ out Logistic(C mid (t))]Pred[M 2 (t),γ out Logistic(C mid (t))]
wherein C is out (t) is a multi-criterion decision index weight matrix obtained by mapping an intermediate layer and a predicted layer, pred [ g ]]As a threshold mapping function for mapping the prediction matrix M 2 (t) mapping to a prediction layer. Delta out For the weighting factor between the intermediate layer and the prediction layer preset according to the history experience,γ out the adjustment of the output of the prediction layer can be realized by utilizing the weight factors and the threshold factors for the threshold factors between the middle layer and the prediction layer preset according to the historical experience.
(3) Based on the adjusted multi-criterion decision index weight matrix C obtained according to the mapping formula between the middle layer and the prediction layer out (t) a desired multi-criterion decision index weight matrix C obtained according to a conventional consistency adjustment method * And updating the self-adaptive learning multi-layer perceptron parameter by the consistency deviation degree dev (t), wherein the updating is as follows:
dev(t)＝e H(t)/0.02
wherein, kappa mid (t) adaptively learning the intermediate layer weight matrix learning rate parameter of the multi-layer perceptron for the t iteration adaptation; kappa (kappa) out (t) adaptively learning a multi-layer perceptron prediction layer weight matrix learning rate parameter for the t iteration adaptation; v (v) mid (t) adaptively learning a multi-layer perceptron intermediate layer threshold matrix learning rate parameter for the t iteration adaptation; kappa (kappa) out (t) adaptively learning a multi-layer perceptron prediction layer prediction matrix learning rate parameter for the t iteration adaptation; weup (g) is a weight matrix update function, gaup (g) is a threshold matrix update function, prup (g) is a prediction matrix update function, and the update functions are all related to a multi-criterion decision index weight matrix and expected multi-criterionThe decision index weight matrix error is related, the update is carried out along the error gradient, dev (t) is the consistency deviation degree of the t iteration self-adaptive learning multi-layer perceptron, the ratio of the consistency measurement index H (t) of the t iteration actually output multi-criterion decision index weight matrix and the consistency measurement index maximum limit value 0.02 is utilized to describe the consistency deviation degree of the actually output multi-criterion decision index weight matrix, the consistency deviation degree is reflected by the ratio, the closer the value of the dev (t) is to 1, the smaller the deviation degree is, and otherwise, the larger the deviation degree is. The invention improves the learning rate by using the consistency deviation degree dev (t), so that the learning rate is inversely proportional to the consistency deviation degree, and the learning rate is lower when the consistency deviation degree is larger, thereby realizing the self-adaptive updating of the learning rate and improving the prediction precision of the self-adaptive learning multi-layer perceptron.
(4) And (3) finishing training when the consistency measurement index H is lower than the preset maximum limit value, otherwise, turning to the step (2), and at the moment, continuously training the original input multi-criterion decision index weight matrix again according to the updated self-adaptive learning multi-layer perceptron parameters until the consistency measurement index H is lower than the preset maximum limit value.
(5) And readjusting the multi-criterion decision index weight matrix by using the trained self-adaptive learning multi-layer perceptron to obtain a multi-criterion decision index weight matrix C' meeting the consistency requirement.
Step 305: and obtaining the comprehensive performance evaluation result of the power terminal carrier communication technology based on the adjusted multi-criterion decision index weight matrix and the carrier communication multi-level evaluation system.
In this embodiment, the steps specifically include: firstly, a feature method is used to determine the corresponding index weight of a multi-criterion decision index weight matrix C' meeting the consistency requirement, in this embodiment, each dimension index in the multi-dimension index is evaluated, taking an index layer as an example, and each index weight is expressed as w (C 1 )～w(c 14 ) Secondly, for all index performances of an index layer of a multidimensional evaluation index system of the power end carrier communication technology, a quantization analysis method and an expert scoring method are used for performance Quantitative detection or qualitative assessment, and normalization, denoted χ (c) 1 )～χ(c 14 ). At this time, the evaluation value score of the carrier communication technology real-time index B1 B1 The calculation formula is that
Reliability index B of similarly available carrier communication technology 2 And safety index B 3 And (5) grading the indexes. On the basis, the evaluation layer index is further scored to obtain a comprehensive performance evaluation score all The formula is
Score according to the above evaluation value all The calculation formula calculates the specific score of the comprehensive performance of the power terminal carrier communication technology, can accurately evaluate the performance of the current carrier communication technology in real time, and realizes modeling and quantitative evaluation of the real-time performance, reliability and safety of the carrier communication technology.
The embodiment of the invention provides a power terminal carrier communication evaluation method based on multi-dimensional indexes, which constructs a power terminal carrier communication technology multi-dimensional evaluation index system, comprising an evaluation layer, a criterion layer, an index layer and a result matching layer, by comprehensively considering the real-time performance, reliability and safety indexes of the power terminal carrier communication technology, constructs a multi-criterion decision index weight matrix of each level fusing multi-indexes, puts forward a floating grading evaluation method in the weight comparison process of the multi-criterion decision index weight matrix to better reflect the uncertainty and variability of index weights, further objectively evaluates the comprehensive performance of the power terminal carrier communication technology, realizes the best result matching of carrier performance quality, improves the evaluation accuracy and comprehensiveness of the power terminal carrier communication technology, and simultaneously adopts a multi-criterion decision index weight matrix readjustment method based on a self-adaptive learning multi-layer perceptron, analyzing rationality of weight distribution among elements in the multi-criterion decision index weight matrix by observing consistency metric indexes of the multi-criterion decision index weight matrix, when the multi-criterion decision index weight matrix does not meet consistency, ensuring accuracy of importance conditions of index elements, constructing an adaptive learning multi-layer perceptron model suitable for consistency optimization of the multi-criterion decision index weight matrix, inputting the multi-criterion decision index weight matrix which does not meet consistency requirements into the constructed adaptive learning multi-layer perceptron model to output optimized multi-criterion decision index weight matrix elements, updating parameters of the adaptive learning multi-layer perceptron by utilizing an adaptive updating method based on consistency deviation degree to optimize the training model, thereby acquiring accurate relative importance conditions among index elements, and the accuracy of the power end carrier communication technology evaluation is improved.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention, and are not to be construed as limiting the scope of the invention. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art without departing from the spirit and principles of the present invention are intended to be included in the scope of the present invention.

Claims (10)

1. The power end carrier communication evaluation method based on the multidimensional index is characterized by comprising the following steps of:
the method comprises the steps of collecting multidimensional indexes for carrying out carrier communication evaluation on the power terminal to be detected, and constructing a carrier communication multi-level evaluation system corresponding to the power terminal to be detected;
constructing a multi-criterion decision index weight matrix which is corresponding to each level in the carrier communication multi-level evaluation system and is fused with multiple indexes;
consistency verification is carried out on the multi-criterion decision index weight matrix, and the multi-criterion decision index weight matrix is adjusted according to a verification result;
and determining the weight of each index in the multidimensional index according to the adjusted multi-criterion decision index weight matrix, and obtaining the carrier communication evaluation result of the power terminal to be detected according to the weight and the power terminal carrier communication multi-level evaluation system.
2. The power end carrier communication evaluation method based on a multi-dimensional index as claimed in claim 1, wherein the multi-dimensional index includes a real-time index, a reliability index and a safety index; wherein, the real-time index comprises congestion rate index, transmission rate index, communication delay index, packet loss rate index and signal intensity index; the reliability index comprises a time delay fluctuation index, a retransmission frequency index, a line utilization index, a bit error rate index and a line fault probability index; the safety indexes comprise data encryption and decryption capability indexes, anti-interference capability indexes, security vulnerability protection capability indexes and fault recovery speed indexes.
3. The power end carrier communication evaluation method based on multidimensional indexes as claimed in claim 1, wherein the constructing the multi-criterion decision index weight matrix of the fusion multi-index corresponding to each level in the carrier communication multi-level evaluation system comprises:
dividing indexes of each level in each level into a plurality of groups according to a preset grouping mode to obtain a plurality of groups of index data sets;
according to a preset ordering mode, ordering a plurality of indexes in each of the plurality of groups of index data sets;
Defining weight sets corresponding to each group of index data sets through the sequencing to obtain a plurality of weight sets corresponding to the plurality of groups of index data sets;
and comparing the plurality of weight sets pairwise according to a preset floating grading evaluation method to obtain the multi-criterion decision index weight matrix.
4. The power end carrier communication evaluation method based on multi-dimensional indexes of claim 1, wherein the performing consistency check on the multi-criterion decision index weight matrix comprises:
performing consistency check on the multi-criterion decision index weight matrix according to a preset consistency measurement index; wherein, the consistency measurement index is as follows:
H＝(max[α 1 ,α 2 ,Lα m ]-n)/(n-1)
wherein alpha is m And the m characteristic root of the multi-criterion decision index weight matrix is represented, n represents the number of index weights in the multi-criterion decision index weight matrix, and H is a consistency measurement index used for measuring the degree of deviation consistency of the multi-criterion decision index weight matrix.
5. The power end carrier communication evaluation method based on multi-dimensional indexes of claim 4, wherein the adjusting the multi-criterion decision index weight matrix according to the result of the inspection comprises:
Comparing the consistency measurement index with a preset index threshold value, and judging whether the multi-criterion decision index weight matrix meets consistency or not;
when the consistency measurement index is smaller than or equal to the index threshold, judging that the multi-criterion decision index weight matrix meets consistency and not adjusting the multi-criterion decision index weight matrix;
when the consistency measurement index is larger than the index threshold, judging that the multi-criterion decision index weight matrix does not meet consistency, and adjusting the multi-criterion decision index weight matrix through a preset self-adaptive learning multi-layer perceptron.
6. The power end carrier communication evaluation method based on multidimensional index according to claim 5, wherein the adjusting the multi-criterion decision index weight matrix by a preset adaptive learning multi-layer perceptron comprises:
adjusting the multi-criterion decision index weight matrix according to multi-layer mapping among an observation layer, a middle layer and a prediction layer in the self-adaptive learning multi-layer perceptron; wherein, the mapping formula between the observation layer and the middle layer is:
C mid (t)＝HardSwish[Q 1 (t),δ mid Logistic(C in (t))]-Gate[M 1 (t),γ mid Logistic(C in (t))]
wherein C is mid (t) represents a multi-criterion decision index weight matrix obtained through mapping between an observation layer and an intermediate layer, logistic (g) represents an activation function for converting an input matrix into a nonlinear output, learning capacity of the adaptive learning multi-layer perceptron is increased, hardSwish (g) represents a weight mapping function for realizing mapping of the weight matrix, and Gate [ g ]]Represents a threshold mapping function for determining whether a threshold matrix is reserved, delta mid Represents a weight factor gamma between the observation layer and the intermediate layer preset according to historical experience mid Representing a threshold factor between an observation layer and an intermediate layer preset according to historical experience;
the mapping formula between the middle layer and the prediction layer is as follows:
C out (t)＝HardSwish[Q 2 (t),δ out Logistic(C mid (t))]Pred[M 2 (t),γ out Logistic(C mid (t))]
wherein C is out (t) represents a multi-criterion decision index weight matrix obtained by mapping an intermediate layer and a predicted layer, pred [ g ]]Representing a threshold mapping function for mapping the prediction matrix M 2 (t) mapping to prediction layer, delta out Represents a weighting factor gamma between the intermediate layer and the predicted layer preset according to historical experience out Representing a threshold factor between the intermediate layer and the predictive layer preset based on historical experience.
7. The power end carrier communication evaluation method based on multi-dimensional indexes as claimed in claim 1, wherein the determining the weight of each index in the multi-dimensional indexes according to the adjusted multi-criterion decision index weight matrix, and obtaining the carrier communication evaluation result of the power end to be detected according to the weight and the power end carrier communication multi-level evaluation system comprises:
Determining the weight of each index in the multi-dimensional indexes through a characteristic method according to the multi-criterion decision index weight matrix;
carrying out quantization detection on each index in the multidimensional indexes according to a preset quantization analysis method and an expert scoring method, and carrying out normalization processing on the quantization detection result to obtain index performance values corresponding to each index respectively;
and obtaining a carrier communication evaluation result of the power end to be detected through a preset evaluation value calculation formula according to the index performance value and the weight.
8. The power end carrier communication evaluation system based on the multidimensional index is characterized by comprising a data acquisition module, a weight matrix module, a verification adjustment module and a communication evaluation module;
the data acquisition module is used for acquiring multidimensional indexes for carrying out carrier communication evaluation on the power terminal to be detected and constructing a carrier communication multi-level evaluation system corresponding to the power terminal to be detected;
the weight matrix module is used for constructing a multi-criterion decision index weight matrix which is corresponding to each level in the carrier communication multi-level evaluation system and is fused with multiple indexes;
The verification adjustment module is used for carrying out consistency verification on the multi-criterion decision index weight matrix and adjusting the multi-criterion decision index weight matrix according to a verification result;
the communication evaluation module is used for determining the weight of each index in the multidimensional index according to the adjusted multi-criterion decision index weight matrix, and obtaining the carrier communication evaluation result of the power terminal to be detected according to the weight and the power terminal carrier communication multi-level evaluation system.
9. The power end carrier communication evaluation system based on the multidimensional index as claimed in claim 8, wherein the weight matrix module includes a ranking unit and a weight unit;
the sorting unit is used for dividing indexes of each level in each level into a plurality of groups according to a preset grouping mode to obtain a plurality of groups of index data sets; according to a preset ordering mode, ordering a plurality of indexes in each of the plurality of groups of index data sets;
the weight unit is used for defining weight sets corresponding to each group of index data sets through the sorting to obtain a plurality of weight sets corresponding to the plurality of groups of index data sets; and comparing the plurality of weight sets pairwise according to a preset floating grading evaluation method to obtain the multi-criterion decision index weight matrix.
10. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
the processor is configured to implement the power end carrier communication evaluation method based on the multidimensional index according to any one of claims 1 to 7 when executing the program stored in the memory.
CN202311247795.1A 2023-09-25 2023-09-25 Power terminal carrier communication evaluation method and system based on multidimensional index Pending CN117278074A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311247795.1A CN117278074A (en) 2023-09-25 2023-09-25 Power terminal carrier communication evaluation method and system based on multidimensional index

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311247795.1A CN117278074A (en) 2023-09-25 2023-09-25 Power terminal carrier communication evaluation method and system based on multidimensional index

Publications (1)

Publication Number Publication Date
CN117278074A true CN117278074A (en) 2023-12-22

Family

ID=89205726

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311247795.1A Pending CN117278074A (en) 2023-09-25 2023-09-25 Power terminal carrier communication evaluation method and system based on multidimensional index

Country Status (1)

Country Link
CN (1) CN117278074A (en)

Similar Documents

Publication Publication Date Title
CN109359385B (en) Training method and device for service quality assessment model
CN108038300A (en) Optical fiber state evaluating method based on improved membership function combination neutral net
CN102496069B (en) Cable multimode safe operation evaluation method based on fuzzy analytic hierarchy process (FAHP)
CN106549813A (en) A kind of appraisal procedure and system of network performance
CN111222776B (en) Satellite network coordination situation assessment method and system based on convolutional neural network
CN112699553B (en) Intelligent prediction system method for rock burst intensity level
CN106656357B (en) Power frequency communication channel state evaluation system and method
CN111163487B (en) Communication waveform comprehensive transmission performance evaluation method and system
CN113988441A (en) Power wireless network link quality prediction and model training method and device
CN112668476B (en) Data processing method and device, electronic equipment and storage medium
CN107295537A (en) A kind of method and system for wireless sensor network reliability of testing and assessing
CN110581783A (en) Communication scheme decision method based on AHP and TOPSIS
CN114528721A (en) Cable intermediate joint insulation state assessment method and system
CN111179576A (en) Power utilization information acquisition fault diagnosis method and system with inductive learning function
CN112817842B (en) Imperfect debug SRGM decision method, system, medium, equipment and application
CN104616209B (en) A kind of power cable connector information fusion evaluation method based on on-line monitoring
CN107644285A (en) The screening of power sales profitability evaluation index and Weight Determination and system
CN117278074A (en) Power terminal carrier communication evaluation method and system based on multidimensional index
CN115186013B (en) Data acquisition and analysis method based on aviation equipment
CN115860526A (en) Comprehensive performance evaluation method of communication network based on comprehensive fuzzy evaluation
CN110851784A (en) Early warning method for field operation of electric energy meter
CN115409317A (en) Transformer area line loss detection method and device based on feature selection and machine learning
CN112150008B (en) System structure evaluation method and system based on design data and experimental data
CN114205247A (en) Access method and device of power distribution Internet of things, computer equipment and storage medium
CN112307648A (en) Method for evaluating reliability model of satellite communication system

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