CN116882701B - Electric power material intelligent scheduling system and method based on zero-carbon mode - Google Patents
Electric power material intelligent scheduling system and method based on zero-carbon mode Download PDFInfo
- Publication number
- CN116882701B CN116882701B CN202310936240.1A CN202310936240A CN116882701B CN 116882701 B CN116882701 B CN 116882701B CN 202310936240 A CN202310936240 A CN 202310936240A CN 116882701 B CN116882701 B CN 116882701B
- Authority
- CN
- China
- Prior art keywords
- information
- historical
- power material
- data
- clustering
- 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.)
- Active
Links
- 239000000463 material Substances 0.000 title claims abstract description 187
- 238000000034 method Methods 0.000 title claims abstract description 50
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims description 40
- 238000012216 screening Methods 0.000 claims description 31
- 239000011159 matrix material Substances 0.000 claims description 20
- 238000003064 k means clustering Methods 0.000 claims description 17
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims 1
- 238000004891 communication Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Biodiversity & Conservation Biology (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Probability & Statistics with Applications (AREA)
Abstract
The invention relates to the technical field of electric power, and provides an intelligent electric power material dispatching system and a method thereof based on a zero-carbon mode, wherein the method comprises the following steps: acquiring historical power failure information and current power failure information; obtaining a current power material scheduling scheme set based on the historical power equipment fault information and the historical power material scheduling scheme; extracting characteristic information of the historical environment information, carrying out clustering processing on the historical environment information according to the characteristic information, and matching power material scheduling tool information for each clustering result; according to the current environment information and the power material dispatching tool information corresponding to each clustering result, the current power material dispatching tool information is obtained, and the power material dispatching is carried out based on the current power material dispatching tool information and the current power material dispatching scheme set.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to an intelligent electric power material dispatching system and method based on a zero-carbon mode.
Background
At present, after the power equipment breaks down, the power supplies are generally required to be transported to a destination for maintenance, if the power supplies cannot be timely distributed to the destination, the faults can be further expanded, and therefore the timely transportation of the power supplies is very important; at present, after the power equipment fails, the failure cause is generally analyzed manually, then the materials are dispatched and transported according to the analysis result, and the final dispatching scheme may be inaccurate due to excessive human factors involved in the method, and meanwhile, the efficiency of the method is low, so how to efficiently and accurately match the dispatching scheme is very important.
Disclosure of Invention
The invention aims to provide an intelligent power material dispatching system and method based on a zero-carbon mode, so as to solve the problems.
In order to achieve the above object, the embodiment of the present application provides the following technical solutions:
In one aspect, an embodiment of the present application provides an intelligent power material scheduling method based on a zero-carbon mode, where the method includes:
Acquiring historical power failure information and current power failure information, wherein each historical power failure information comprises historical environment information and historical power equipment failure information, acquiring a historical power material scheduling scheme corresponding to each historical power equipment failure information, wherein each historical power material scheduling scheme comprises at least one historical power material scheduling parameter information, and the current power failure information comprises current environment information and current power equipment failure information;
constructing a training sample based on the historical power equipment fault information and the historical power material scheduling scheme, and training a convolutional neural network model by using the training sample to obtain a power material scheduling scheme prediction model; inputting the current power equipment fault information into the power material scheduling scheme prediction model to obtain a current power material scheduling scheme set;
Extracting characteristic information of historical environment information, carrying out clustering processing on the historical environment information by using a K-means clustering method according to the characteristic information, and matching power material scheduling tool information for each clustering result;
And obtaining current power material dispatching tool information according to the current environment information and the power material dispatching tool information corresponding to each clustering result, screening schemes in the current power material dispatching scheme set according to preset screening conditions to obtain a screened current power material dispatching scheme, and carrying out power material dispatching according to the screened current power material dispatching scheme and the current power material dispatching tool information.
In a second aspect, an embodiment of the application provides an intelligent power material scheduling system based on a zero-carbon mode, which comprises an acquisition module, a training module, a clustering module and a screening module.
The system comprises an acquisition module, a power management module and a power management module, wherein the acquisition module is used for acquiring historical power failure information and current power failure information, each piece of historical power failure information comprises historical environment information and historical power equipment failure information, and acquiring a historical power material scheduling scheme corresponding to each piece of historical power equipment failure information, each historical power material scheduling scheme comprises at least one piece of historical power material scheduling parameter information, and the current power failure information comprises current environment information and current power equipment failure information;
the training module is used for constructing training samples based on the historical power equipment fault information and the historical power material scheduling scheme, and training the convolutional neural network model by using the training samples to obtain a power material scheduling scheme prediction model; inputting the current power equipment fault information into the power material scheduling scheme prediction model to obtain a current power material scheduling scheme set;
The clustering module is used for extracting characteristic information of the historical environment information, carrying out clustering processing on the historical environment information by utilizing a K-means clustering method according to the characteristic information, and matching power material scheduling tool information for each clustering result;
And the screening module is used for obtaining current power material dispatching tool information according to the current environment information and the power material dispatching tool information corresponding to each clustering result, screening schemes in the current power material dispatching scheme set according to preset screening conditions to obtain a screened current power material dispatching scheme, and carrying out power material dispatching according to the screened current power material dispatching scheme and the current power material dispatching tool information.
In a third aspect, an embodiment of the present application provides an intelligent power material scheduling apparatus based on a zero-carbon mode, where the apparatus includes a memory and a processor. The memory is used for storing a computer program; and the processor is used for realizing the intelligent scheduling method of the electric power materials based on the zero-carbon mode when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a readable storage medium, where a computer program is stored, where the computer program, when executed by a processor, implements the steps of the foregoing method for intelligent scheduling of electric power materials based on a zero-carbon mode.
The beneficial effects of the invention are as follows:
In order to quickly acquire the current power material scheduling scheme, the invention trains the model by utilizing the historical power equipment fault information and the historical power material scheduling scheme, and simultaneously considers the influence of noise data when training the model, so that the noise data is screened when training, and the accuracy of the final model is improved by the method; thirdly, cluster analysis is carried out on the historical environment information, corresponding scheduling tools are matched for each piece of historical environment information, and when the scheduling tools are matched, the factors of energy consumption and time are comprehensively considered, so that the method can be closed to a zero-carbon mode; finally, after the current power material scheduling scheme set is obtained, screening conditions are set, the specific screening conditions can be set by a user according to the current material stock, and the screened power material scheduling scheme can be realized in such a way, so that the integrity of the whole scheme is ensured. Therefore, the method can rapidly and accurately read the power material dispatching scheme and the dispatching tool aiming at the current power failure information, and further can timely transport the power material to a destination.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent dispatching method for electric power materials based on a zero-carbon mode in the embodiment of the invention;
FIG. 2 is a schematic diagram of an intelligent power material dispatching system based on a zero-carbon mode according to an embodiment of the invention;
Fig. 3 is a schematic structural diagram of an intelligent power material dispatching device based on a zero-carbon mode in an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
It should be noted that: like reference numerals or letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1
As shown in fig. 1, the embodiment provides an intelligent power material scheduling method based on a zero-carbon mode, which includes steps S1, S2, S3 and S4.
Step S1, acquiring historical power failure information and current power failure information, wherein each piece of historical power failure information comprises historical environment information and historical power equipment failure information, acquiring a historical power material scheduling scheme corresponding to each piece of historical power equipment failure information, wherein each historical power material scheduling scheme comprises at least one piece of historical power material scheduling parameter information, and the current power failure information comprises current environment information and current power equipment failure information;
in this step, the history environmental information may be understood as environmental information in which the power equipment is located, for example, rough mountain roads, spacious roads, and the like; historical power device fault information may be understood as operational parameter information of the power device, such as temperature, output current signals, etc.; the historical power material scheduling parameter information can be understood as any parameter such as the use amount, model number and the like of power materials, for example, the number of scheduling cables, the type of transformers and the like;
S2, constructing a training sample based on the historical power equipment fault information and the historical power material scheduling scheme, and training a convolutional neural network model by using the training sample to obtain a power material scheduling scheme prediction model; inputting the current power equipment fault information into the power material scheduling scheme prediction model to obtain a current power material scheduling scheme set;
in order to quickly acquire the current power material scheduling scheme, the step utilizes the historical power equipment fault information and the historical power material scheduling scheme to train a model, and the specific implementation steps comprise a step S21 and a step S22;
Step S21, randomly selecting any number of historical power material dispatching parameter information from the corresponding historical power material dispatching schemes for each piece of historical power equipment fault information to be combined to obtain a plurality of combination parameter information, taking the combination parameter information as labeling information of the corresponding historical power equipment fault information, marking the labeled historical power equipment fault information as first information, inputting the first information into a VGG network to be subjected to prediction processing, and calculating second information according to a prediction result, wherein the second information comprises cross entropy loss corresponding to the first information;
in the step, a plurality of combination parameter information can be obtained in a combination mode, and the diversity of samples can be enriched in the mode; meanwhile, certain noise is also considered in the sample, so that noise data is screened in the step, the accuracy of the sample can be ensured to the greatest extent by the mode, and the accuracy of model training is improved;
In the step, the VGG network can be replaced by a convolutional neural network, and after the VGG network is input, the VGG network outputs, and the cross entropy loss corresponding to the initial data can be calculated according to the output result;
S22, inputting the first information into a denoising self-encoder to obtain third information, and performing supervised training on the denoising self-encoder by using an absolute value of a difference value between the first information and the third information to obtain a trained denoising self-encoder; and finishing screening the marked historical power failure information according to the trained denoising self-encoder and the cross entropy loss, and training the convolutional neural network model by using the screened marked historical power failure information to obtain a power material scheduling scheme prediction model.
In the step, the first information is processed according to the trained denoising self-encoder, so that a reconstruction error corresponding to each first information can be obtained, and screening of marked historical power failure information can be completed by utilizing the reconstruction error and cross entropy loss corresponding to each first information, wherein the specific implementation steps comprise step S221 and step S222;
Step S221, inputting the first information into a trained denoising self-encoder to obtain fourth information, and carrying out weighted addition on the second information and the fourth information corresponding to the first information to obtain fifth information;
In this step, the weighted addition of the second information and the fourth information may be understood as that the weighted addition of the reconstruction error and the cross entropy loss corresponding to the first information may be performed, and weights may be the same or different.
Step S222, sorting the first information according to the value of the fifth information, where the smaller the value of the fifth information is, the more the corresponding first information is arranged; and after the first information is ordered, selecting according to a preset selection proportion from front to back to obtain the selected first information, and finishing screening the marked historical power failure information.
In this step, the preset selection proportion may be 50%,25%, and the specific selection proportion may be set in a user-defined manner according to the user's requirement;
S3, extracting characteristic information of the historical environment information, carrying out clustering processing on the historical environment information by using a K-means clustering method according to the characteristic information, and matching power material scheduling tool information for each clustering result;
In this step, after the current power material scheduling scheme set is calculated according to the above method, taking into consideration that a scheduling tool is also required to complete scheduling of materials, such as a transport tool and the like, and the transport tool needs to consider factors of traffic roads, so that this step matches different power material scheduling tool information for different historical environment information, in this way, when a new accident is faced, the current environment information is input to obtain the power material scheduling tool information;
When the electric power material dispatching tools are matched in the step, the final electric power material dispatching tools are determined by manually comprehensively considering the energy consumption and time factors, and the electric power material dispatching tools can be closed to a zero-carbon mode by the method, and the specific implementation steps of the step comprise the step S31 and the step S32;
S31, marking characteristic information of historical environment information as first data, carrying out clustering processing on each piece of historical environment information by using a K-means clustering algorithm and the first data, and carrying out mean value calculation on all first data corresponding to each clustering result to obtain second data; analyzing all first data and second data corresponding to each clustering result, wherein the distance between each first data and the second data is calculated respectively, and the first data with the smallest distance is added into a first set;
in the step, the first data can be understood as feature vectors, the historical environment information can be input into the convolutional neural network, and the feature vectors output by the full connection layer of the convolutional neural network are used as the first data; meanwhile, the second data in this step may be understood as an average value of coordinates of all feature vectors as the second data;
And step S32, clustering historical environment information based on the first set and the K-means clustering method, and matching power material scheduling tool information for each clustering result. The specific implementation steps of the step comprise a step S321 and a step S322;
Step S321, after a first set is obtained by calculation, a first step is executed, wherein the first step comprises the steps of calculating a first distance between each first data and each second data in each clustering result, simultaneously calculating a second distance between each first data and each data in the first set, adding the first distance and all second distances to obtain a sum of distances, and adding the first data corresponding to the minimum sum of distances into the first set; repeating the first step until the number of data contained in the first set is four;
in the step, the number of data is four, or the data can be set according to the requirement of a user, for example, 6, 7, 8 and the like;
Step S322, for each clustering result, combining the second data corresponding to the clustering result and the data contained in the first set according to a preset combination mode to obtain a matrix, and calculating a covariance matrix corresponding to the matrix; and finishing clustering processing of the historical environment information according to the covariance matrix.
The predetermined combination in this step may be a combination along the matrix column direction, the row direction, or the like; the specific implementation steps of completing the clustering processing of the historical environment information according to the covariance matrix comprise a step S3221 and a step S3222;
Step S3221, inputting covariance matrixes corresponding to each clustering result into a pre-trained judgment model to obtain an accuracy result corresponding to each clustering result, wherein the judgment model is used for judging the accuracy corresponding to each covariance matrix;
In the step, when the judgment model is trained, the covariance matrix can be used as input, the accuracy result can be used as output for training, and a large number of samples can be used for training the neural network model to obtain the judgment model; wherein, the accurate result comprises accurate, generally accurate and inaccurate results;
S3222, analyzing all the accuracy results, and when the clustering requirement is met, taking the current clustering result as a final clustering result, wherein the clustering requirement comprises that N accuracy results in all the accuracy results are accurate, and N is a positive integer greater than zero; otherwise, updating the K value in the K-means clustering method, and re-clustering until the clustering requirement is met.
And S4, obtaining current power material dispatching tool information according to the current environment information and the power material dispatching tool information corresponding to each clustering result, screening schemes in the current power material dispatching scheme set according to preset screening conditions to obtain a screened current power material dispatching scheme, and carrying out power material dispatching according to the screened current power material dispatching scheme and the current power material dispatching tool information.
In the step, after the current power material scheduling scheme set is obtained, the step considers that a certain power material is absent or a certain model of power material is absent, so that a screening condition is set, a specific screening condition can be set by a user according to the current material stock, and the screened power material scheduling scheme can be ensured to be realized in the mode; for example, in the current power material scheduling scheme set, one scheduling scheme includes power equipment a, one scheduling scheme includes power equipment B, and the current power equipment a lacks, then the screening condition may be set to not include a;
Meanwhile, in the step, current power material dispatching tool information is obtained according to the current environment information and the power material dispatching tool information corresponding to each clustering result, and the specific implementation steps comprise step S41;
Step S41, judging whether all the historical environment information has the historical environment information which is completely the same as the current environment information, if so, recording the historical environment information as sixth information, taking a clustering result of the sixth information as a clustering result of the current environment information, and taking power material scheduling tool information corresponding to the clustering result as the current power material scheduling tool information; and if the current environment information is not similar to each piece of historical environment information, recording historical environment information corresponding to the maximum similarity as seventh information, and taking the power material scheduling tool information corresponding to the seventh information as the current power material scheduling tool information.
By the method, the power material scheduling tool information can be quickly and accurately matched for the current environment information.
Example 2
As shown in fig. 2, the present embodiment provides an intelligent power material scheduling system based on a zero-carbon mode, which includes an acquisition module 701, a training module 702, a clustering module 703 and a screening module 704.
An obtaining module 701, configured to obtain historical power failure information and current power failure information, where each historical power failure information includes historical environment information and historical power equipment failure information, and obtain a historical power material scheduling scheme corresponding to each historical power equipment failure information, where each historical power material scheduling scheme includes at least one historical power material scheduling parameter information, and the current power failure information includes current environment information and current power equipment failure information;
The training module 702 is configured to construct a training sample based on the historical power equipment fault information and the historical power material scheduling scheme, and train the convolutional neural network model by using the training sample to obtain a power material scheduling scheme prediction model; inputting the current power equipment fault information into the power material scheduling scheme prediction model to obtain a current power material scheduling scheme set;
The clustering module 703 is used for extracting characteristic information of the historical environment information, performing clustering processing on the historical environment information by using a K-means clustering method according to the characteristic information, and matching power material scheduling tool information for each clustering result;
And a screening module 704, configured to obtain current power material scheduling tool information according to the current environment information and the power material scheduling tool information corresponding to each clustering result, screen the schemes in the current power material scheduling scheme set according to a preset screening condition, obtain a screened current power material scheduling scheme, and perform power material scheduling according to the screened current power material scheduling scheme and the current power material scheduling tool information.
In one embodiment of the present disclosure, the training module 702 further includes a prediction unit 7021 and a first calculation unit 7022.
The prediction unit 7021 is configured to randomly select, for each piece of historical power equipment fault information, any number of historical power material scheduling parameter information in the corresponding historical power material scheduling scheme to perform combination to obtain a plurality of combination parameter information, use the combination parameter information as labeling information of the corresponding historical power equipment fault information, record the labeled historical power equipment fault information as first information, input the first information into a VGG network to perform prediction processing, and calculate second information according to a prediction result, where the second information includes cross entropy loss corresponding to the first information;
A first calculating unit 7022, configured to input the first information into a denoising self-encoder to obtain third information, and perform supervised training on the denoising self-encoder by using an absolute value of a difference value between the first information and the third information to obtain a trained denoising self-encoder; and finishing screening the marked historical power failure information according to the trained denoising self-encoder and the cross entropy loss, and training the convolutional neural network model by using the screened marked historical power failure information to obtain a power material scheduling scheme prediction model.
In a specific embodiment of the disclosure, the first calculating unit 7022 further includes an input unit 70221 and a sorting unit 70222.
An input unit 70221, configured to input the first information into a trained denoising self-encoder to obtain fourth information, and perform weighted addition on the second information and the fourth information corresponding to the first information to obtain fifth information;
A sorting unit 70222, configured to sort the first information according to the value of the fifth information, where the smaller the value of the fifth information, the more front the corresponding first information is arranged; and after the first information is ordered, selecting according to a preset selection proportion from front to back to obtain the selected first information, and finishing screening the marked historical power failure information.
In a specific embodiment of the disclosure, the clustering module 703 further includes a second calculating unit 7031 and a clustering unit 7032.
The second computing unit 7031 is configured to record feature information of the historical environmental information as first data, perform clustering processing on each historical environmental information by using a K-means clustering algorithm and the first data, and perform mean value computation on all first data corresponding to each clustering result to obtain second data; analyzing all first data and second data corresponding to each clustering result, wherein the distance between each first data and the second data is calculated respectively, and the first data with the smallest distance is added into a first set;
and a clustering unit 7032, configured to perform clustering processing on the historical environmental information based on the first set and the K-means clustering method, and match power material scheduling tool information for each clustering result.
In a specific embodiment of the disclosure, the clustering unit 7032 further includes a third computing unit 70321 and a fourth computing unit 70322.
A third calculation unit 70321, configured to perform a first step after calculating a first set, where the first step includes calculating a first distance between each first data and each second data in each clustering result, and simultaneously calculating a second distance between each first data and each data in the first set, adding the first distance to all the second distances to obtain a sum of distances, and adding the first data corresponding to a minimum sum of distances to the first set; repeating the first step until the number of data contained in the first set is four;
And a fourth calculating unit 70322, configured to combine, for each clustering result, the second data corresponding to the clustering result and the data included in the first set according to a predetermined combination manner, to obtain a matrix, calculate a covariance matrix corresponding to the matrix, and complete clustering processing on the historical environmental information according to the covariance matrix.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
Example 3
Corresponding to the above method embodiment, the embodiment of the disclosure further provides an electric power material intelligent dispatching device based on the zero-carbon mode, and the electric power material intelligent dispatching device based on the zero-carbon mode described below and the electric power material intelligent dispatching method based on the zero-carbon mode described above can be referred to correspondingly.
Fig. 3 is a block diagram illustrating a zero-carbon mode based power asset intelligent scheduling apparatus 800, according to an exemplary embodiment. As shown in fig. 3, the power supply intelligent scheduling apparatus 800 based on the zero-carbon mode may include: a processor 801, a memory 802. The zero-carbon mode based power asset intelligent scheduling apparatus 800 may also include one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the power material intelligent scheduling apparatus 800 based on the zero-carbon mode, so as to complete all or part of the steps in the power material intelligent scheduling method based on the zero-carbon mode. The memory 802 is used to store various types of data to support operation on the zero-carbon mode based power asset intelligent scheduling apparatus 800, which may include, for example, instructions for any application or method operating on the zero-carbon mode based power asset intelligent scheduling apparatus 800, as well as application-related data, such as contact data, messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the smart power material scheduling device 800 and other devices based on the zero-carbon mode. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G, or 4G, or a combination of one or more thereof, the corresponding communication component 805 may therefore include: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the zero-carbon mode-based power material intelligent scheduling apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASIC), digital signal processors (DIGITALSIGNAL PROCESSOR DSP), digital signal processing devices (DIGITAL SIGNAL Processing Device DSPD), programmable logic devices (Programmable Logic Device PLD), field programmable gate arrays (Field Programmable GATE ARRAY FPGA), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described zero-carbon mode-based power material intelligent scheduling method.
In another exemplary embodiment, a computer readable storage medium is also provided that includes program instructions that, when executed by a processor, implement the steps of the zero-carbon mode-based power asset intelligent scheduling method described above. For example, the computer readable storage medium may be the memory 802 including program instructions described above, which are executable by the processor 801 of the zero-carbon mode based power material intelligent scheduling apparatus 800 to perform the zero-carbon mode based power material intelligent scheduling method described above.
Example 4
Corresponding to the above method embodiments, the present disclosure further provides a readable storage medium, where the readable storage medium described below and the above power material intelligent scheduling method based on the zero-carbon mode may be referred to correspondingly.
A readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the power material intelligent scheduling method based on the zero-carbon mode in the above method embodiment.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, which may store various program codes.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention 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. An intelligent power material scheduling method based on a zero-carbon mode is characterized by comprising the following steps of:
Acquiring historical power failure information and current power failure information, wherein each historical power failure information comprises historical environment information and historical power equipment failure information, acquiring a historical power material scheduling scheme corresponding to each historical power equipment failure information, wherein each historical power material scheduling scheme comprises at least one historical power material scheduling parameter information, and the current power failure information comprises current environment information and current power equipment failure information;
constructing a training sample based on the historical power equipment fault information and the historical power material scheduling scheme, and training a convolutional neural network model by using the training sample to obtain a power material scheduling scheme prediction model; inputting the current power equipment fault information into the power material scheduling scheme prediction model to obtain a current power material scheduling scheme set;
Extracting characteristic information of historical environment information, carrying out clustering processing on the historical environment information by using a K-means clustering method according to the characteristic information, and matching power material scheduling tool information for each clustering result;
And obtaining current power material dispatching tool information according to the current environment information and the power material dispatching tool information corresponding to each clustering result, screening schemes in the current power material dispatching scheme set according to preset screening conditions to obtain a screened current power material dispatching scheme, and carrying out power material dispatching according to the screened current power material dispatching scheme and the current power material dispatching tool information.
2. The zero-carbon mode-based power material intelligent scheduling method of claim 1, wherein constructing training samples based on the historical power equipment fault information and the historical power material scheduling scheme, training a convolutional neural network model by using the training samples, and obtaining a power material scheduling scheme prediction model comprises the following steps:
For each piece of historical power equipment fault information, randomly selecting any number of historical power material scheduling parameter information from the corresponding historical power material scheduling schemes to be combined to obtain a plurality of combination parameter information, taking the combination parameter information as labeling information of the corresponding historical power equipment fault information, marking the labeled historical power equipment fault information as first information, inputting the first information into a VGG network to perform prediction processing, and calculating second information according to a prediction result, wherein the second information comprises cross entropy loss corresponding to the first information;
Inputting the first information into a denoising self-encoder to obtain third information, and performing supervised training on the denoising self-encoder by using the absolute value of the difference value between the first information and the third information to obtain a trained denoising self-encoder; and finishing screening the marked historical power failure information according to the trained denoising self-encoder and the cross entropy loss, and training the convolutional neural network model by using the screened marked historical power failure information to obtain a power material scheduling scheme prediction model.
3. The zero-carbon mode-based power material intelligent scheduling method according to claim 2, wherein the screening of the noted historical power failure information is completed according to the trained denoising self-encoder and the cross entropy loss, comprising:
Inputting the first information into a trained denoising self-encoder to obtain fourth information, and carrying out weighted addition on the second information and the fourth information corresponding to the first information to obtain fifth information;
Sorting the first information according to the value of the fifth information, wherein the smaller the value of the fifth information is, the earlier the corresponding first information is arranged; and after the first information is ordered, selecting according to a preset selection proportion from front to back to obtain the selected first information, and finishing screening the marked historical power failure information.
4. The zero-carbon mode-based power material intelligent scheduling method of claim 1, wherein clustering historical environment information by using a K-means clustering method according to the characteristic information, matching power material scheduling tool information for each clustering result, comprises:
Characteristic information of historical environment information is recorded as first data, clustering processing is carried out on each piece of historical environment information by using a K-means clustering algorithm and the first data, and average value calculation is carried out on all first data corresponding to each clustering result to obtain second data; analyzing all first data and second data corresponding to each clustering result, wherein the distance between each first data and the second data is calculated respectively, and the first data with the smallest distance is added into a first set;
and clustering historical environment information based on the first set and the K-means clustering method, and matching power material scheduling tool information for each clustering result.
5. The zero-carbon mode-based power material intelligent scheduling method according to claim 4, wherein clustering historical environment information based on the first set and the K-means clustering method, matching power material scheduling tool information for each clustering result, comprises:
After a first set is obtained through calculation, a first step is executed, wherein the first step comprises the steps of calculating a first distance between each first data and each second data in each clustering result, simultaneously calculating a second distance between each first data and each data in the first set, adding the first distance and all second distances to obtain a sum of distances, and adding the first data with the smallest sum of distances into the first set; repeating the first step until the number of data contained in the first set is four;
and combining the second data corresponding to the clustering result and the data contained in the first set according to a preset combination mode aiming at each clustering result to obtain a matrix, calculating a covariance matrix corresponding to the matrix, and completing clustering processing of the historical environment information according to the covariance matrix.
6. Electric power material intelligent scheduling system based on zero carbon mode, characterized by comprising:
the system comprises an acquisition module, a power management module and a power management module, wherein the acquisition module is used for acquiring historical power failure information and current power failure information, each piece of historical power failure information comprises historical environment information and historical power equipment failure information, and acquiring a historical power material scheduling scheme corresponding to each piece of historical power equipment failure information, each historical power material scheduling scheme comprises at least one piece of historical power material scheduling parameter information, and the current power failure information comprises current environment information and current power equipment failure information;
the training module is used for constructing training samples based on the historical power equipment fault information and the historical power material scheduling scheme, and training the convolutional neural network model by using the training samples to obtain a power material scheduling scheme prediction model; inputting the current power equipment fault information into the power material scheduling scheme prediction model to obtain a current power material scheduling scheme set;
The clustering module is used for extracting characteristic information of the historical environment information, carrying out clustering processing on the historical environment information by utilizing a K-means clustering method according to the characteristic information, and matching power material scheduling tool information for each clustering result;
And the screening module is used for obtaining current power material dispatching tool information according to the current environment information and the power material dispatching tool information corresponding to each clustering result, screening schemes in the current power material dispatching scheme set according to preset screening conditions to obtain a screened current power material dispatching scheme, and carrying out power material dispatching according to the screened current power material dispatching scheme and the current power material dispatching tool information.
7. The zero-carbon mode-based power material intelligent scheduling system of claim 6, wherein the training module comprises:
The prediction unit is used for randomly selecting any number of historical power material scheduling parameter information from the corresponding historical power material scheduling schemes for each piece of historical power equipment fault information to be combined to obtain a plurality of combination parameter information, taking the combination parameter information as labeling information of the corresponding historical power equipment fault information, marking the labeled historical power equipment fault information as first information, inputting the first information into a VGG network to perform prediction processing, and calculating second information according to a prediction result, wherein the second information comprises cross entropy loss corresponding to the first information;
The first calculation unit is used for inputting the first information into a denoising self-encoder to obtain third information, and performing supervised training on the denoising self-encoder by using the absolute value of the difference between the first information and the third information to obtain a trained denoising self-encoder; and finishing screening the marked historical power failure information according to the trained denoising self-encoder and the cross entropy loss, and training the convolutional neural network model by using the screened marked historical power failure information to obtain a power material scheduling scheme prediction model.
8. The zero-carbon mode-based power material intelligent scheduling system of claim 7, wherein the first computing unit comprises:
the input unit is used for inputting the first information into the trained denoising self-encoder to obtain fourth information, and carrying out weighted addition on the second information corresponding to the first information and the fourth information to obtain fifth information;
The sorting unit is used for sorting the first information according to the value of the fifth information, wherein the smaller the value of the fifth information is, the more the corresponding first information is arranged; and after the first information is ordered, selecting according to a preset selection proportion from front to back to obtain the selected first information, and finishing screening the marked historical power failure information.
9. The zero-carbon mode-based power material intelligent scheduling system of claim 6, wherein the clustering module comprises:
the second calculation unit is used for recording characteristic information of the historical environment information as first data, carrying out clustering processing on each piece of historical environment information by using a K-means clustering algorithm and the first data, and carrying out mean value calculation on all pieces of first data corresponding to each clustering result to obtain second data; analyzing all first data and second data corresponding to each clustering result, wherein the distance between each first data and the second data is calculated respectively, and the first data with the smallest distance is added into a first set;
and the clustering unit is used for carrying out clustering processing on the historical environment information based on the first set and the K-means clustering method, and matching power material scheduling tool information for each clustering result.
10. The zero-carbon mode-based power material intelligent scheduling system of claim 9, wherein the clustering unit comprises:
The third calculation unit is used for executing a first step after the first set is obtained by calculation, wherein the first step comprises the steps of calculating a first distance between each first data and each second data in each clustering result, simultaneously calculating a second distance between each first data and each data in the first set, adding the first distance and all second distances to obtain a sum of distances, and adding the first data with the smallest sum of distances into the first set; repeating the first step until the number of data contained in the first set is four;
And a fourth calculation unit, configured to combine, for each clustering result, the second data corresponding to the clustering result and the data included in the first set according to a predetermined combination manner, to obtain a matrix, calculate a covariance matrix corresponding to the matrix, and complete clustering processing on the historical environmental information according to the covariance matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310936240.1A CN116882701B (en) | 2023-07-27 | 2023-07-27 | Electric power material intelligent scheduling system and method based on zero-carbon mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310936240.1A CN116882701B (en) | 2023-07-27 | 2023-07-27 | Electric power material intelligent scheduling system and method based on zero-carbon mode |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116882701A CN116882701A (en) | 2023-10-13 |
| CN116882701B true CN116882701B (en) | 2024-05-31 |
Family
ID=88262928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310936240.1A Active CN116882701B (en) | 2023-07-27 | 2023-07-27 | Electric power material intelligent scheduling system and method based on zero-carbon mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116882701B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117649095A (en) * | 2024-01-26 | 2024-03-05 | 北京中能亿信软件有限公司 | Electric power operation and maintenance management method based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113918341A (en) * | 2021-10-20 | 2022-01-11 | 中国平安人寿保险股份有限公司 | Equipment scheduling method, device, equipment and storage medium |
| CN114692758A (en) * | 2022-03-31 | 2022-07-01 | 广东电网有限责任公司 | Power communication fault analysis method and device, terminal equipment and medium |
| CN115796399A (en) * | 2023-02-06 | 2023-03-14 | 佰聆数据股份有限公司 | Intelligent scheduling method, device and equipment based on electric power materials and storage medium |
| CN115884213A (en) * | 2021-09-28 | 2023-03-31 | 中国移动通信集团贵州有限公司 | Resource scheduling method and device and electronic equipment |
| WO2023109251A1 (en) * | 2021-12-17 | 2023-06-22 | 浪潮电子信息产业股份有限公司 | System fault detection method and apparatus, device, and medium |
| CN116433045A (en) * | 2023-03-23 | 2023-07-14 | 国网四川省电力公司物资公司 | Accurate supply management method and system for electric power emergency materials |
-
2023
- 2023-07-27 CN CN202310936240.1A patent/CN116882701B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115884213A (en) * | 2021-09-28 | 2023-03-31 | 中国移动通信集团贵州有限公司 | Resource scheduling method and device and electronic equipment |
| CN113918341A (en) * | 2021-10-20 | 2022-01-11 | 中国平安人寿保险股份有限公司 | Equipment scheduling method, device, equipment and storage medium |
| WO2023109251A1 (en) * | 2021-12-17 | 2023-06-22 | 浪潮电子信息产业股份有限公司 | System fault detection method and apparatus, device, and medium |
| CN114692758A (en) * | 2022-03-31 | 2022-07-01 | 广东电网有限责任公司 | Power communication fault analysis method and device, terminal equipment and medium |
| CN115796399A (en) * | 2023-02-06 | 2023-03-14 | 佰聆数据股份有限公司 | Intelligent scheduling method, device and equipment based on electric power materials and storage medium |
| CN116433045A (en) * | 2023-03-23 | 2023-07-14 | 国网四川省电力公司物资公司 | Accurate supply management method and system for electric power emergency materials |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116882701A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109657805B (en) | Hyper-parameter determination method, device, electronic equipment and computer readable medium | |
| WO2021252734A1 (en) | Systems and methods for managing machine learning models | |
| CN109271627B (en) | Text analysis method, apparatus, computer device and storage medium | |
| CN116882701B (en) | Electric power material intelligent scheduling system and method based on zero-carbon mode | |
| JP5480755B2 (en) | Demand forecasting system and demand forecasting method | |
| CN110276382B (en) | Crowd classification method, device and medium based on spectral clustering | |
| CN110046356B (en) | Label-embedded microblog text emotion multi-label classification method | |
| Casalino et al. | Incremental adaptive semi-supervised fuzzy clustering for data stream classification | |
| CN111815432A (en) | Financial service risk prediction method and device | |
| CN113033861A (en) | Water quality prediction method and system based on time series model | |
| CN112883990A (en) | Data classification method and device, computer storage medium and electronic equipment | |
| CN111783873A (en) | Incremental naive Bayes model-based user portrait method and device | |
| CN115618269A (en) | Big data analysis method and system based on industrial sensor production | |
| CN116150367A (en) | Emotion analysis method and system based on aspects | |
| CN113703773B (en) | NLP-based binary code similarity comparison method | |
| Ashoori et al. | Compare failure prediction models based on feature selection technique: empirical case from Iran | |
| CN113177644A (en) | Automatic modeling system based on word embedding and depth time sequence model | |
| CN111860554B (en) | Risk monitoring method and device, storage medium and electronic equipment | |
| CN114741976B (en) | Displacement prediction method, device and equipment and readable storage medium | |
| CN115374711B (en) | Service life prediction method of rotating multi-component system and related device | |
| CN111582313A (en) | Sample data generation method and device and electronic equipment | |
| CN116029760A (en) | Message pushing method, device, computer equipment and storage medium | |
| CN113850314A (en) | Customer value grade prediction model establishing method, device, medium and equipment | |
| CN112418652B (en) | Risk identification method and related device | |
| CN115063143A (en) | Account data processing method and device, computer equipment and storage medium |
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 |