CN116258312A - End-to-end scheduling plan generation model training method, plan generation method and device - Google Patents
End-to-end scheduling plan generation model training method, plan generation method and device Download PDFInfo
- Publication number
- CN116258312A CN116258312A CN202211468594.XA CN202211468594A CN116258312A CN 116258312 A CN116258312 A CN 116258312A CN 202211468594 A CN202211468594 A CN 202211468594A CN 116258312 A CN116258312 A CN 116258312A
- Authority
- CN
- China
- Prior art keywords
- data
- weather forecast
- historical
- scheduling plan
- numerical weather
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 111
- 238000012549 training Methods 0.000 title claims abstract description 109
- 238000013528 artificial neural network Methods 0.000 claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims abstract description 28
- 230000015654 memory Effects 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 18
- 238000005070 sampling Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000009825 accumulation Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000006243 chemical reaction Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007792 addition Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
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
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/29—Geographical information databases
-
- 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
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Remote Sensing (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Water Supply & Treatment (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application provides an end-to-end scheduling plan generation model training method, a plan generation method and a device, wherein the training method comprises the following steps: preprocessing various historical numerical weather forecast raw data of the comprehensive energy base to obtain various historical numerical weather forecast data with the same dimension; generating a data set according to various historical numerical weather forecast data and corresponding historical actual output data in the same historical time period; training a preset deep neural network by adopting a data set to obtain an end-to-end scheduling plan generation model for outputting corresponding power scheduling plan data according to the numerical weather forecast data of the comprehensive energy base. According to the method and the device, the training effectiveness and reliability of the end-to-end scheduling plan generation model can be improved, the end-to-end scheduling plan can be generated, the efficiency of the output scheduling plan result output by the model can be improved, information loss and error accumulation can be effectively avoided, and the stability and safety of the operation of the comprehensive energy base can be improved.
Description
Technical Field
The present disclosure relates to the field of energy scheduling technologies, and in particular, to a method and apparatus for training an end-to-end scheduling plan generation model.
Background
The large energy resource can collect wind, light and thermal power and send the collected wind, light and thermal power out through direct current. The operation of the large energy base needs to make a scheduling plan of wind, light and heat power in advance, so that the defects of insufficient standby capacity caused by various reasons or a large amount of waste wind and waste light caused by unreasonable configuration are avoided.
The traditional wind power and photovoltaic power prediction is performed by different data and algorithms, and then the predicted product is used as input for power prediction, and the flow chart is shown in the figure 1. Different weather forecast products are often selected for photovoltaic power forecast and wind power plant weather forecast, respective forecast results are obtained through different forecast models, and the respective forecast results are combined with other constraints such as minimum and maximum output of a thermal power station, direct current output line capacity and the like to obtain a final scheduling plan. However, since the three models in fig. 1 are not considered with each other, each model in the process introduces different errors, and the information utilization efficiency is low, so that the safe and stable operation capability of the comprehensive energy base cannot be improved.
Disclosure of Invention
In view of this, embodiments of the present application provide end-to-end scheduling plan generation model training methods, plan generation methods, and apparatus to obviate or ameliorate one or more of the disadvantages of the prior art.
A first aspect of the present application provides a method for training an end-to-end scheduling plan generation model, comprising:
preprocessing various historical numerical weather forecast raw data of the comprehensive energy base to obtain various historical numerical weather forecast data with the same dimension;
generating a data set according to various historical numerical weather forecast data and corresponding historical actual output data in the same historical time period;
and training a preset deep neural network by adopting the data set to obtain an end-to-end scheduling plan generation model for directly outputting corresponding output scheduling plan data according to various numerical weather forecast data of the comprehensive energy base.
In some embodiments of the present application, preprocessing various kinds of historical numerical weather forecast raw data of the integrated energy base to obtain various kinds of historical numerical weather forecast data with the same dimension includes:
acquiring various historical numerical weather forecast original data of a comprehensive energy base;
Preprocessing various historical value weather forecast original data with different spatial resolutions by adopting an image sampling and interpolation method to obtain various two-dimensional historical value weather forecast data with the same resolution;
and preprocessing various kinds of history numerical weather forecast original data with asynchronous time by adopting a linear interpolation method to obtain various kinds of history numerical weather forecast data with the same time dimension so as to generate corresponding various history numerical weather forecast data samples based on the various kinds of history numerical weather forecast data.
In some embodiments of the present application, the generating a data set according to the historical numerical weather forecast data and the corresponding historical actual output data in the same historical time period includes:
obtaining historical actual output data samples of the comprehensive energy base, which are respectively in the same historical time period with each historical numerical weather forecast data sample, wherein each historical actual output data sample comprises: historical actual photovoltaic output duty ratio, historical actual wind power output duty ratio and historical actual thermal power output duty ratio;
and generating each sample pair according to each historical numerical weather forecast data sample and the corresponding relation with each historical actual output data sample so as to obtain a data set containing a plurality of sample pairs.
In some embodiments of the present application, before the training of the preset deep neural network using the data set, the method further includes:
constructing a loss function for representing a difference value between the output dispatching plan data output by the deep neural network and the historical actual output data;
correspondingly, the training the preset deep neural network by adopting the data set comprises the following steps:
and training a preset deep neural network based on the data set by taking the minimum value of the loss function as a target.
In some embodiments of the present application, the historical numerical weather forecast data is time-space sequence data;
correspondingly, the deep neural network comprises: conv-LSTM model.
In some embodiments of the present application, the Conv-LSTM model comprises: conv-LSTM module composed of a plurality of Conv-LSTM layers connected in sequence, CNN and LSTM module composed of a plurality of LSTM layers connected in sequence;
the Conv-LSTM module is used for outputting a corresponding two-dimensional characteristic tensor according to the input historical numerical weather forecast data;
the CNN is used for extracting the two-dimensional characteristic tensor to be a one-dimensional characteristic tensor, and inputting the one-dimensional characteristic tensor as an initial state tensor of the LSTM module.
A second aspect of the present application provides a method for generating an end-to-end scheduling plan of an integrated energy base, including:
acquiring various numerical weather forecast original data of the comprehensive energy base in a target period;
preprocessing various types of the numerical weather forecast raw data to obtain various types of numerical weather forecast data with the same dimension;
inputting various types of the numerical weather forecast data into an end-to-end scheduling plan generating model, so that the end-to-end scheduling plan generating model outputs output scheduling plan data of the comprehensive energy base on the next day of the target period;
the end-to-end scheduling plan generation model is trained and obtained in advance based on the end-to-end scheduling plan generation model training method.
A third aspect of the present application provides an end-to-end scheduling plan generation model training apparatus, comprising:
the data preprocessing module is used for preprocessing various historical numerical weather forecast raw data of the comprehensive energy base to obtain various historical numerical weather forecast data with the same dimension;
the data set generation module is used for generating a data set according to various historical numerical weather forecast data and corresponding historical actual output data in the same historical time period;
And the model training module is used for training a preset deep neural network by adopting the data set so as to obtain an end-to-end scheduling plan generating model for directly outputting corresponding output scheduling plan data according to various numerical weather forecast data of the comprehensive energy base.
A fourth aspect of the present application provides an end-to-end schedule plan generation apparatus for an integrated energy base, comprising:
the data acquisition module is used for acquiring various numerical weather forecast original data of the comprehensive energy base in a target period;
the data processing module is used for preprocessing various types of the numerical weather forecast raw data to obtain various types of numerical weather forecast data with the same dimension;
the model prediction module is used for inputting various numerical weather forecast data into an end-to-end scheduling plan generation model so that the end-to-end scheduling plan generation model outputs output scheduling plan data of the comprehensive energy base on the next day of the target period; the end-to-end scheduling plan generating model is obtained by training the end-to-end scheduling plan generating model training method.
In a fifth aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, where the processor implements the end-to-end scheduling plan generation model training method when executing the computer program, or implements the end-to-end scheduling plan generation method of the integrated energy base.
A sixth aspect of the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the end-to-end scheduling plan generation model training method, or implements the end-to-end scheduling plan generation method for an integrated energy base.
According to the end-to-end scheduling plan generation model training method, various historical numerical weather forecast data with the same dimension are obtained by preprocessing various historical numerical weather forecast raw data of the comprehensive energy base; generating a data set according to various historical numerical weather forecast data and corresponding historical actual output data in the same historical time period; the preset deep neural network is trained by the data set to obtain an end-to-end scheduling plan generation model for directly outputting corresponding output scheduling plan data according to various numerical weather forecast data of the comprehensive energy base, training effectiveness and reliability of the end-to-end scheduling plan generation model can be improved, generation of an end-to-end scheduling plan can be achieved, efficiency of output scheduling plan results output by the model can be improved, information loss and error accumulation can be effectively avoided, rationality and effectiveness of energy configuration of the comprehensive energy base according to the output scheduling plan results can be improved, and stability and safety of operation of the comprehensive energy base can be further improved.
Additional advantages, objects, and features of the application will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and drawings.
It will be appreciated by those skilled in the art that the objects and advantages that can be achieved with the present application are not limited to the above-detailed description, and that the above and other objects that can be achieved with the present application will be more clearly understood from the following detailed description.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is an exemplary schematic diagram of a prior art scheduling plan generation scheme.
Fig. 2 is a schematic diagram of a basic logic architecture of an end-to-end scheduling plan generation scheme provided in the present application.
FIG. 3 is a flow chart of a method of end-to-end scheduling plan generation model training in an embodiment of the present application.
FIG. 4 is another flow diagram of an end-to-end scheduling plan generation model training method in an embodiment of the present application.
Fig. 5 is a flow chart of a method for generating an end-to-end scheduling plan in another embodiment of the present application.
Fig. 6 is a schematic structural diagram of an end-to-end scheduling plan generation model training apparatus in another embodiment of the present application.
Fig. 7 is a schematic structural diagram of an end-to-end scheduling plan generating apparatus in another embodiment of the present application.
Fig. 8 is an exemplary schematic diagram of spatial dimension preprocessing provided in an application example of the present application.
Fig. 9 is an exemplary schematic diagram of time dimension preprocessing provided in an application example of the present application.
Fig. 10 is a schematic diagram illustrating the structure of the Conv-LSTM model provided in the application example of the present application.
Detailed Description
The following description of the embodiments of the present application will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It should be noted here that, in order to avoid obscuring the present application due to unnecessary details, only structures and/or processing steps closely related to the solution according to the present application are shown in the drawings, while other details not greatly related to the present application are omitted.
It should be emphasized that the term "comprises/comprising" when used herein is taken to specify the presence of stated features, elements, steps or components, but does not preclude the presence or addition of one or more other features, elements, steps or components.
It is also noted herein that the term "coupled" may refer to not only a direct connection, but also an indirect connection in which an intermediate is present, unless otherwise specified.
Hereinafter, embodiments of the present application will be described with reference to the drawings. In the drawings, the same reference numerals represent the same or similar components, or the same or similar steps.
In the existing scheduling plan generation scheme, the scheduling plan is generated into a plurality of stages, different models are adopted for calculation, as shown in fig. 1, different errors are generated in the different stages in a superposition mode, and finally, the errors are reflected in the generated scheduling plan, so that a gap exists between the generated scheduling plan and the actual demand.
In the prior art, because photovoltaic power prediction, wind power prediction and scheduling plan generation are all carried out by different models (model 1, model 2 and model 3) at different stages, the coupling degree between the photovoltaic power and the wind power is low, the information utilization efficiency is low, and the prediction result and the scheduling plan possibly have a gap from actual demands, in order to overcome the defect, an end-to-end scheduling plan generation model training method and an end-to-end scheduling plan generation method are required to be designed, and intermediate links which possibly generate errors are reduced as much as possible. The numerical weather forecast products P1 to P4 respectively represent different types of numerical weather forecast products.
Based on this, in order to improve the information utilization efficiency and reduce the influence of errors on the scheduling plan, the embodiment of the application proposes an end-to-end scheduling plan model training and end-to-end scheduling plan generating method, wherein the inputs of different stages in the traditional flow are simultaneously input into a deep neural network model, and the scheduling plan is directly generated at the output end, as shown in fig. 2.
The following examples are provided to illustrate the invention in more detail.
The embodiment of the application provides an end-to-end scheduling plan generating model training method which can be realized by an end-to-end scheduling plan generating model training device, and referring to fig. 3, the end-to-end scheduling plan generating model training method specifically comprises the following contents:
Step 100: preprocessing various historical numerical weather forecast raw data of the comprehensive energy base to obtain various historical numerical weather forecast data with the same dimension.
In step 100, the end-to-end dispatch plan generation model training device may receive various types of historical numerical weather forecast raw data collected from a database of the integrated energy base.
It can be understood that the numerical weather forecast refers to the data of the actual data collected from the atmosphere according to the weather detection instruments (satellites, airplanes, ships, weather stations, sounding balloons, etc.) as the initial field of the atmosphere, and under the condition of a certain initial value and a certain boundary value, the numerical calculation is performed by a supercomputer, so as to solve the equation set of the fluid mechanics and the thermodynamics describing the weather evolution process and predict the atmospheric motion state and the weather phenomenon in a certain period of time in the future. The types of the historical numerical weather forecast raw data can be divided according to data sources, collection modes and weather map types, for example: 500HPA weather map, 850HPA weather map, near-surface weather map, and so forth.
Step 200: and generating a data set according to the various historical numerical weather forecast data and the corresponding historical actual output data in the same historical time period.
In step 200, the end-to-end dispatch plan generation model training device may receive historical actual output data from a database of the integrated energy base collected during the same historical time period as the historical numerical weather forecast data.
It can be understood that the data set stores the corresponding relation between the various historical numerical weather forecast data and the historical actual output data, and the corresponding relation refers to the one-to-one relation between the various historical numerical weather forecast data and the historical actual output data as well as the content of the historical actual output data in the data set.
Step 300: and training a preset deep neural network by adopting the data set to obtain an end-to-end scheduling plan generation model for directly outputting corresponding output scheduling plan data according to various numerical weather forecast data of the comprehensive energy base.
In step 300, training a preset deep neural network by using the data set, specifically: the data set can be used as a training set to train the deep neural network; the data set can be divided into a training set, a verification set, a test set and the like, so that after the deep neural network is trained according to the training set, the deep neural network is further optimized according to the verification set and the test set and the like, the reliability and the effectiveness of a model training result are improved, and the model training method can be specifically set according to actual application situations.
In one or more embodiments of the present application, the end-to-end scheduling plan generating model refers to a machine learning model for generating an end-to-end scheduling plan, where the architecture of the model is the same as the infrastructure of the deep neural network, that is, the end-to-end scheduling plan generating model refers to the deep neural network that is currently trained, and then, according to actual application requirements, each type of the latest updated historical numerical weather forecast data and the corresponding historical actual output data may be periodically collected from the database of the integrated energy base, and then, the end-to-end scheduling plan generating model is optimized and iterated by using each type of the updated historical numerical weather forecast data and the corresponding historical actual output data, so as to obtain an updated end-to-end scheduling plan generating model, so as to further improve reliability and effectiveness of model training results, and be more suitable for state change of the integrated energy base.
From the above description, it can be seen that the end-to-end scheduling plan generation model training method provided by the embodiment of the application can improve the training effectiveness and reliability of the end-to-end scheduling plan generation model, can realize the generation of the end-to-end scheduling plan, can improve the efficiency of the output scheduling plan result output by the model, can effectively avoid information loss and error accumulation, can improve the rationality and effectiveness of energy configuration on the comprehensive energy base according to the output scheduling plan result, and can further improve the stability and safety of the operation of the comprehensive energy base.
In order to further improve the effectiveness and reliability of the data base for training the model, in the end-to-end scheduling plan generating model training method provided in the embodiment of the present application, referring to fig. 4, step 100 of the end-to-end scheduling plan generating model training method specifically includes the following:
step 110: acquiring various historical numerical weather forecast original data of a comprehensive energy base;
step 120: and preprocessing various historical numerical value weather forecast original data with different spatial resolutions by adopting an image sampling and interpolation method to obtain various two-dimensional historical numerical value weather forecast data with the same resolution.
Step 130: and preprocessing various historical numerical weather forecast raw data with asynchronous time by adopting a linear interpolation method to obtain various historical numerical weather forecast data with the same time dimension, so as to generate corresponding various historical numerical weather forecast data samples based on the various historical numerical weather forecast data.
Specifically, the energy base wind-light-fire scheduling plan can be directly generated without output and re-input in an intermediate stage under the condition that the input is various numerical weather forecast products, so that information loss and error accumulation are avoided, and a more efficient and accurate scheduling plan generation method is realized. Since different weather numerical mode products are time-space sequence data with different resolutions (the input data of each time node is in the form of 2-dimensional images of a plurality of channels), and output is one-dimensional time sequence data (the output data of each time node is in the form of 1-dimensional array), in order to achieve the above functions, a specific data preprocessing method and a network structure are required to achieve the conversion from the input data form to the output data form.
In order to further improve the effectiveness and reliability of the data base for training the model, in the end-to-end scheduling plan generating model training method provided in the embodiment of the present application, referring to fig. 4, step 200 of the end-to-end scheduling plan generating model training method specifically includes the following:
step 210: obtaining historical actual output data samples of the comprehensive energy base, which are respectively in the same historical time period with each historical numerical weather forecast data sample, wherein each historical actual output data sample comprises: historical actual photovoltaic output duty cycle, historical actual wind power output duty cycle and historical actual thermal power output duty cycle.
It can be understood that the sum of the historical actual photovoltaic output ratio, the historical actual wind power output ratio and the historical actual thermal power output ratio in the same historical actual output data sample is 1.
Step 220: and generating each sample pair according to each historical numerical weather forecast data sample and the corresponding relation with each historical actual output data sample so as to obtain a data set containing a plurality of sample pairs.
In particular, a training data set may be established that is composed of numerical weather forecast data and schedule data matching the numerical weather forecast data over a fixed length of time Δt. The fixed time period Δt is exemplified by: 24 hours.
In order to further improve the application effectiveness of the training model, in the end-to-end scheduling plan generating model training method provided in the embodiment of the present application, referring to fig. 4, before step 300 of the end-to-end scheduling plan generating model training method, the method specifically further includes the following contents:
step 010: and constructing a loss function for representing a difference value between the output dispatching plan data output by the deep neural network and the historical actual output data.
In step 010, a difference value between the output power dispatching plan data and the historical actual output power data output by the deep neural network may be determined according to an average value of squares of differences between the output power dispatching plan data and the historical actual output power data.
Correspondingly, referring to fig. 4, the step 300 of the end-to-end scheduling plan generation model training method specifically includes the following:
step 310: and training a preset deep neural network based on the data set by taking the minimum value of the loss function as a target to obtain an end-to-end scheduling plan generation model for directly outputting corresponding output scheduling plan data according to various numerical weather forecast data of the comprehensive energy base.
In order to further improve the reliability of model mapping learning, in the end-to-end scheduling plan generation model training method provided by the embodiment of the application, the historical numerical weather forecast data is space-time sequence data;
correspondingly, the deep neural network comprises: conv-LSTM model.
It is understood that the LSTM model refers to a Long short-term memory (Long short-term memory) model; the Conv-LSTM model refers to a convolutional long-short-term memory neural network, and the Conv-LSTM network has a convolutional structure in the state-to-state (input-to-state) conversion and the state-to-state conversion, and can effectively capture space-time correlation between data.
In order to further improve reliability and application effectiveness of model training, in the method for generating model training for end-to-end scheduling plan provided in the embodiment of the present application, the Conv-LSTM model may specifically include: conv-LSTM module composed of a plurality of Conv-LSTM layers connected in sequence, CNN and LSTM module composed of a plurality of LSTM layers connected in sequence;
the Conv-LSTM module is used for outputting a corresponding two-dimensional characteristic tensor according to the input historical numerical weather forecast data;
The CNN is used for extracting the two-dimensional characteristic tensor to be a one-dimensional characteristic tensor, and inputting the one-dimensional characteristic tensor as an initial state tensor of the LSTM module.
It is understood that CNN refers to convolutional neural network (Convolutional Neural Network).
Based on the embodiment of the end-to-end scheduling plan generation model training method, the application also provides an embodiment of an end-to-end scheduling plan generation method of an integrated energy base, and referring to fig. 5, the end-to-end scheduling plan generation method of the integrated energy base specifically includes the following contents:
step 400: and acquiring various numerical weather forecast original data of the comprehensive energy base in a target period.
Step 500: preprocessing all kinds of the numerical weather forecast raw data to obtain all kinds of numerical weather forecast data with the same dimension.
Step 600: inputting various types of the numerical weather forecast data into an end-to-end scheduling plan generating model, so that the end-to-end scheduling plan generating model outputs output scheduling plan data of the comprehensive energy base on the next day of the target period; the end-to-end scheduling plan generation model is trained and obtained in advance based on the end-to-end scheduling plan generation model training method.
The end-to-end scheduling plan generating model in the end-to-end scheduling plan generating method of the integrated energy base provided by the application may be specifically implemented based on the processing flow of the embodiment of the end-to-end scheduling plan generating model training method in the above embodiment, and the functions thereof are not described herein in detail, and reference may be made to the detailed description of the embodiment of the end-to-end scheduling plan generating model training method.
As can be seen from the above description, the end-to-end scheduling plan generating method provided by the embodiment of the application can improve the training effectiveness and reliability of the end-to-end scheduling plan generating model, can realize the generation of the end-to-end scheduling plan, can improve the efficiency of the output scheduling plan result output by the model, can effectively avoid information loss and error accumulation, can improve the rationality and effectiveness of energy configuration on the comprehensive energy base according to the output scheduling plan result, and can further improve the stability and safety of the operation of the comprehensive energy base.
From the software aspect, the present application further provides an end-to-end scheduling plan generating model training apparatus for executing all or part of the end-to-end scheduling plan generating model training method, referring to fig. 6, where the end-to-end scheduling plan generating model training apparatus is connected to a database of an integrated energy base and the end-to-end scheduling plan generating apparatus, respectively, so as to retrieve historical data from the database, and send a model obtained by training to the end-to-end scheduling plan generating apparatus for on-line application, where the end-to-end scheduling plan generating model training apparatus specifically includes:
The data preprocessing module 10 is used for preprocessing various historical numerical weather forecast raw data of the comprehensive energy base to obtain various historical numerical weather forecast data with the same dimension;
the data set generating module 20 is configured to generate a data set according to the historical numerical weather forecast data and the corresponding actual historical output data in the same historical time period;
the model training module 30 is configured to train a preset deep neural network by using the data set, so as to obtain an end-to-end scheduling plan generating model for directly outputting corresponding output scheduling plan data according to various numerical weather forecast data of the integrated energy base.
The embodiment of the end-to-end scheduling plan generation model training device provided in the present application may be specifically used to execute the processing flow of the embodiment of the end-to-end scheduling plan generation model training method in the above embodiment, and the functions thereof are not described herein, and may refer to the detailed description of the embodiment of the end-to-end scheduling plan generation model training method.
As can be seen from the above description, the end-to-end scheduling plan generation model training device provided by the embodiment of the application can improve the training effectiveness and reliability of the end-to-end scheduling plan generation model, can realize the generation of the end-to-end scheduling plan, can improve the efficiency of the output scheduling plan result output by the model, can effectively avoid information loss and error accumulation, can improve the rationality and effectiveness of energy configuration on the comprehensive energy base according to the output scheduling plan result, and can further improve the stability and safety of the operation of the comprehensive energy base.
In terms of software, the present application further provides an end-to-end scheduling plan generating apparatus for executing all or part of the end-to-end scheduling plan generating method, referring to fig. 7, where the end-to-end scheduling plan generating apparatus is respectively in communication with the end-to-end scheduling plan generating model training apparatus and a client device held by a user, so as to be capable of receiving an end-to-end scheduling plan generating model from the end-to-end scheduling plan model training apparatus, and sending predicted output scheduling plan data to the client device for viewing by the user, where the end-to-end scheduling plan generating apparatus specifically includes:
the data acquisition module 40 is used for acquiring various numerical weather forecast original data of the comprehensive energy base in a target period;
the data processing module 50 is used for preprocessing various types of the numerical weather forecast raw data to obtain various types of numerical weather forecast data with the same dimension;
a model prediction module 60, configured to input each type of the numerical weather forecast data into an end-to-end scheduling plan generation model, so that the end-to-end scheduling plan generation model outputs output scheduling plan data of the comprehensive energy base on the next day of the target period; the end-to-end scheduling plan generating model is obtained by training the end-to-end scheduling plan generating model training method.
The embodiment of the end-to-end scheduling plan generating apparatus provided in the present application may be specifically used to execute the process flow of the embodiment of the end-to-end scheduling plan generating method in the foregoing embodiment, and the functions thereof are not described herein in detail, and reference may be made to the detailed description of the embodiment of the end-to-end scheduling plan generating method.
As can be seen from the foregoing description, the end-to-end scheduling plan generating device provided by the embodiment of the application can improve the training effectiveness and reliability of the end-to-end scheduling plan generating model, can realize the generation of the end-to-end scheduling plan, can improve the efficiency of the output scheduling plan result output by the model, can effectively avoid information loss and error accumulation, can improve the rationality and effectiveness of energy configuration on the comprehensive energy base according to the output scheduling plan result, and can further improve the stability and safety of the operation of the comprehensive energy base.
It will be appreciated that the portion of the end-to-end schedule plan generation model training means that performs end-to-end schedule plan generation model training and the portion of the end-to-end schedule plan generation means that performs end-to-end schedule plan generation may be accomplished in the client device. Specifically, the selection may be made according to the processing capability of the client device, and restrictions of the use scenario of the user. The present application is not limited in this regard. If all operations are done in the client device, the client device may further comprise a processor for specific processing of end-to-end schedule plan generation model training and end-to-end schedule plan generation.
The client device may have a communication module (i.e. a communication unit) and may be connected to a remote server in a communication manner, so as to implement data transmission with the server. The server may include a server on the side of the task scheduling center, and in other implementations may include a server of an intermediate platform, such as a server of a third party server platform having a communication link with the task scheduling center server. The server may include a single computer device, a server cluster formed by a plurality of servers, or a server structure of a distributed device.
Any suitable network protocol may be used for communication between the server and the client device, including those not yet developed at the filing date of this application. The network protocols may include, for example, TCP/IP protocol, UDP/IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol ), REST protocol (Representational State Transfer, representational state transfer protocol), etc. used above the above-described protocol.
In order to further explain the scheme, the application also provides a specific application example of the end-to-end scheduling plan generation model training and end-to-end scheduling plan generation method, and the energy base wind-light-fire scheduling plan can be directly generated without output and re-input in an intermediate stage under the condition that the input is various numerical weather forecast products, so that information loss and error accumulation are avoided, and a more efficient and accurate scheduling plan generation method is realized. Since different weather numerical mode products are time-space sequence data with different resolutions (the input data of each time node is in the form of 2-dimensional images of a plurality of channels), and output is one-dimensional time sequence data (the output data of each time node is in the form of 1-dimensional array), in order to achieve the above functions, a specific data preprocessing method and a network structure are required to achieve the conversion from the input data form to the output data form.
The end-to-end scheduling plan generation model training and end-to-end scheduling plan generation method provided by the application example specifically comprises the following contents:
s1, performing space-time interpolation and sampling on various historical numerical weather forecast data to obtain various types of data with the same data format.
For data with different spatial resolutions, an image sampling and interpolation method, such as nearest point interpolation and sampling method, can be adopted to preprocess the data so as to change the data into two-dimensional data with the same resolution, as shown in fig. 8. And respectively interpolating and sampling the numerical value weather products P1 and the numerical value weather products P2 with different spatial resolutions by adopting an image sampling and interpolation method to obtain an interpolated weather product P1 'and an interpolated weather product P2' with the same resolution.
For data with asynchronous time, a linear interpolation method can also be used to interpolate the data in the time dimension, as shown in fig. 9. Raw data P of time-unsynchronized numerical weather by linear interpolation method T1 Raw data P T2 And original data P T3 Interpolation of time dimension is carried out, and interpolation is obtained based on interpolation time t1 and interpolation time t2Data P t1 And P t2 Etc.
Through the two steps, the numerical weather forecast product data with different types and the same dimension can be obtained.
S2, establishing a training data set consisting of numerical weather forecast data and scheduling data matched with the numerical weather forecast data within a fixed time length delta t. Taking the day-ahead scheduling as an example, Δt is 24h, if the sampling time interval is 15min, the dimension of the numerical weather forecast data is 96×n×h×w, where n is the number of data types, 96 is the total number of sampling points, and h×w is the dimension of the data, which can be understood as the image resolution. The dimension of the scheduling data is 96 multiplied by 3, namely the output duty ratio of the wind, light and fire every 15 minutes.
S3, a deep neural network model is built, and the model needs to have the capability of processing a spatial sequence because the data form is the spatial sequence data, wherein a Conv-LSTM model is adopted to build the network, and the specific structure is shown in figure 10.
In FIG. 10, the CNN component extracts the two-dimensional feature tensor output by Conv-LSTM as the one-dimensional feature tensor, as the initial state tensor input for the subsequent LSTM module, which completes the conversion from 2D meteorological data to data form of 1D dispatch plan data.
S4, setting a loss function to evaluate the training progress of the network:
in the above-mentioned method, the step of,planned photovoltaic output duty cycle for model output, +.>Planned wind power output duty ratio for model output, +. >Planned thermal power output duty ratio for model output, R Pij As the waySolar actual photovoltaic output ratio, R Wij R is the actual wind power output duty ratio of the same day Tij Is the actual thermal power output duty ratio of the day. N is the total number of single sample sampling points and M is the total number of samples.
S5, training the model in S3 by using the data set in S2 and the loss function set in S4.
S6, inputting the numerical mode product after the pretreatment of S1 into the trained model in S5 to obtain a dispatching plan output.
In summary, according to the end-to-end scheduling plan generation model training and end-to-end scheduling plan generation method provided by the application example, the numerical meteorological data is used for an end-to-end flow of a day-ahead scheduling plan; the space-time interpolation method for synthesizing the data sets with the same dimension and sampling rate by using the numerical weather forecast data of different types is provided; the method comprises the steps of realizing the input of multi-channel time-space sequence data for digital weather forecast and outputting the network structure of scheduling plan time sequence data; the method reduces intermediate links such as power prediction from weather forecast data to the day-ahead scheduling plan, and the like, and realizes the end-to-end generation method from the weather data to the scheduling plan, thereby more fully utilizing the data, reducing information loss and obtaining a more accurate day-ahead scheduling plan.
The present application further provides an electronic device (i.e., an electronic device), where the electronic device may include a processor, a memory, a receiver, and a transmitter, where the processor is configured to perform the end-to-end scheduling plan generation model training method or the end-to-end scheduling plan generation method mentioned in the foregoing embodiments, and the processor and the memory may be connected by a bus or other manners, for example, by a bus connection. The receiver may be connected to the processor, memory, by wire or wirelessly.
The processor may be a central processing unit (Central Processing Unit, CPU). The processor may also be any other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof.
The memory, as a non-transitory computer readable storage medium, may be used to store a non-transitory software program, a non-transitory computer executable program, and a module, such as program instructions/modules corresponding to an end-to-end scheduling plan generation model training method or an end-to-end scheduling plan generation method in embodiments of the present application. The processor executes the various functional applications of the processor and data processing by running the non-transitory software programs, instructions, and modules stored in the memory, i.e., implementing the end-to-end schedule generation model training method or end-to-end schedule generation method in the above-described method embodiments.
The memory may include a memory program area and a memory data area, wherein the memory program area may store an operating system, at least one application program required for a function; the storage data area may store data created by the processor, etc. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory may optionally include memory located remotely from the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory that, when executed by the processor, perform the end-to-end schedule plan generation model training method or the end-to-end schedule plan generation method of the embodiments.
In some embodiments of the present application, the user equipment may include a processor, a memory, and a transceiver unit, where the transceiver unit may include a receiver and a transmitter, and the processor, the memory, the receiver, and the transmitter may be connected by a bus system, the memory storing computer instructions, and the processor executing the computer instructions stored in the memory to control the transceiver unit to transmit and receive signals.
As an implementation manner, the functions of the receiver and the transmitter in the present application may be considered to be implemented by a transceiver circuit or a dedicated chip for transceiver, and the processor may be considered to be implemented by a dedicated processing chip, a processing circuit or a general-purpose chip.
As another implementation manner, a manner of using a general-purpose computer may be considered to implement the server provided in the embodiments of the present application. I.e. program code for implementing the functions of the processor, the receiver and the transmitter are stored in the memory, and the general purpose processor implements the functions of the processor, the receiver and the transmitter by executing the code in the memory.
Embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the aforementioned end-to-end scheduling plan generation model training method or end-to-end scheduling plan generation method. The computer readable storage medium may be a tangible storage medium such as Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, floppy disks, hard disk, a removable memory disk, a CD-ROM, or any other form of storage medium known in the art.
Those of ordinary skill in the art will appreciate that the various illustrative components, systems, and methods described in connection with the embodiments disclosed herein can be implemented as hardware, software, or a combination of both. The particular implementation is hardware or software dependent on the specific application of the solution and the design constraints. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave.
It should be clear that the present application is not limited to the particular arrangements and processes described above and illustrated in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps, after appreciating the spirit of the present application.
The features described and/or illustrated in this application for one embodiment may be used in the same way or in a similar way in one or more other embodiments and/or in combination with or instead of the features of the other embodiments.
The foregoing description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and variations may be made to the embodiment of the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (10)
1. An end-to-end scheduling plan generation model training method, comprising:
preprocessing various historical numerical weather forecast raw data of the comprehensive energy base to obtain various historical numerical weather forecast data with the same dimension;
generating a data set according to various historical numerical weather forecast data and corresponding historical actual output data in the same historical time period;
and training a preset deep neural network by adopting the data set to obtain an end-to-end scheduling plan generation model for directly outputting corresponding output scheduling plan data according to various numerical weather forecast data of the comprehensive energy base.
2. The method for training an end-to-end scheduling plan generation model according to claim 1, wherein preprocessing the raw data of various historical numerical weather forecast of the integrated energy base to obtain the data of various historical numerical weather forecast with the same dimension comprises:
acquiring various historical numerical weather forecast original data of a comprehensive energy base;
preprocessing various historical value weather forecast original data with different spatial resolutions by adopting an image sampling and interpolation method to obtain various two-dimensional historical value weather forecast data with the same resolution;
and preprocessing various kinds of history numerical weather forecast original data with asynchronous time by adopting a linear interpolation method to obtain various kinds of history numerical weather forecast data with the same time dimension so as to generate corresponding various history numerical weather forecast data samples based on the various kinds of history numerical weather forecast data.
3. The end-to-end dispatch plan generation model training method of claim 2, wherein the generating a data set from the historical numerical weather forecast data and the corresponding historical actual output data for each of the types within the same historical time period comprises:
Obtaining historical actual output data samples of the comprehensive energy base, which are respectively in the same historical time period with each historical numerical weather forecast data sample, wherein each historical actual output data sample comprises: historical actual photovoltaic output duty ratio, historical actual wind power output duty ratio and historical actual thermal power output duty ratio;
and generating each sample pair according to each historical numerical weather forecast data sample and the corresponding relation with each historical actual output data sample so as to obtain a data set containing a plurality of sample pairs.
4. The end-to-end dispatch plan generation model training method of claim 1, further comprising, prior to the training of the preset deep neural network with the data set:
constructing a loss function for representing a difference value between the output dispatching plan data output by the deep neural network and the historical actual output data;
correspondingly, the training the preset deep neural network by adopting the data set comprises the following steps:
and training a preset deep neural network based on the data set by taking the minimum value of the loss function as a target.
5. The end-to-end dispatch plan generation model training method of claim 1, wherein the historical numerical weather forecast data is space-time sequence data;
correspondingly, the deep neural network comprises: conv-LSTM model.
6. The end-to-end scheduling plan generation model training method of claim 5, wherein the Conv-LSTM model comprises: conv-LSTM module composed of a plurality of Conv-LSTM layers connected in sequence, CNN and LSTM module composed of a plurality of LSTM layers connected in sequence;
the Conv-LSTM module is used for outputting a corresponding two-dimensional characteristic tensor according to the input historical numerical weather forecast data;
the CNN is used for extracting the two-dimensional characteristic tensor to be a one-dimensional characteristic tensor, and inputting the one-dimensional characteristic tensor as an initial state tensor of the LSTM module.
7. A method of generating an end-to-end dispatch plan for an integrated energy base, comprising:
acquiring various numerical weather forecast original data of the comprehensive energy base in a target period;
preprocessing various types of the numerical weather forecast raw data to obtain various types of numerical weather forecast data with the same dimension;
Inputting various types of the numerical weather forecast data into an end-to-end scheduling plan generating model, so that the end-to-end scheduling plan generating model outputs output scheduling plan data of the comprehensive energy base on the next day of the target period;
wherein the end-to-end scheduling plan generation model is trained in advance based on the end-to-end scheduling plan generation model training method of any one of claims 1 to 6.
8. An end-to-end scheduling plan generation model training apparatus, comprising:
the data preprocessing module is used for preprocessing various historical numerical weather forecast raw data of the comprehensive energy base to obtain various historical numerical weather forecast data with the same dimension;
the data set generation module is used for generating a data set according to various historical numerical weather forecast data and corresponding historical actual output data in the same historical time period;
and the model training module is used for training a preset deep neural network by adopting the data set so as to obtain an end-to-end scheduling plan generating model for directly outputting corresponding output scheduling plan data according to various numerical weather forecast data of the comprehensive energy base.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the end-to-end dispatch plan generation model training method of any one of claims 1 to 6 or the comprehensive energy base end-to-end dispatch plan generation method of claim 7.
10. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the end-to-end scheduling plan generation model training method of any one of claims 1 to 6 or the end-to-end scheduling plan generation method of the integrated energy base of claim 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211468594.XA CN116258312A (en) | 2022-11-22 | 2022-11-22 | End-to-end scheduling plan generation model training method, plan generation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211468594.XA CN116258312A (en) | 2022-11-22 | 2022-11-22 | End-to-end scheduling plan generation model training method, plan generation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116258312A true CN116258312A (en) | 2023-06-13 |
Family
ID=86679943
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211468594.XA Pending CN116258312A (en) | 2022-11-22 | 2022-11-22 | End-to-end scheduling plan generation model training method, plan generation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116258312A (en) |
-
2022
- 2022-11-22 CN CN202211468594.XA patent/CN116258312A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114362367B (en) | Cloud-edge-cooperation-oriented power transmission line monitoring system and method, and cloud-edge-cooperation-oriented power transmission line identification system and method | |
US10951500B2 (en) | Method and apparatus for warning | |
CN110991775B (en) | Deep learning-based rail transit passenger flow demand prediction method and device | |
CN109922427B (en) | Intelligent wireless positioning system and method using large-scale array antenna | |
Nahri et al. | IoV distributed architecture for real-time traffic data analytics | |
CN111928888A (en) | Intelligent monitoring and analyzing method and system for water pollution | |
CN111126618B (en) | Federal learning method and device based on multi-source heterogeneous system | |
CN202058215U (en) | On-line safety inspection system | |
CN111431986A (en) | Industrial intelligent quality inspection system based on 5G and AI cloud edge cooperation | |
CN103595568A (en) | Internet real-time signal transmission method based on LS-SVM | |
CN111103609B (en) | Navigation signal monitoring system with distributed acquisition and centralized processing | |
CN112163668A (en) | Method for reducing time series data transmission based on prediction and cloud edge cooperation | |
CN116258192A (en) | Day-ahead scheduling plan generation model training method, plan generation method and device | |
CN116258312A (en) | End-to-end scheduling plan generation model training method, plan generation method and device | |
CN115860153B (en) | Wireless flow prediction method and system based on personalized packet federal learning | |
CN116961805A (en) | Short wave prediction method based on space-time diagram neural network | |
CN116318365A (en) | Space-time service big data platform with multiple elements | |
CN110022541A (en) | A kind of sparse acquisition of WSN crop growth environment information and transmission method based on NB-IoT and FPGA | |
CN115561790A (en) | Satellite-ground cloud edge collaborative ground target identification method and device based on deep network | |
CN109831421A (en) | Data managing method, system and computer readable storage medium | |
CN112308318B (en) | Queuing time prediction method, queuing time prediction device, queuing time prediction equipment and storage medium | |
CN112486667A (en) | Method and device for accurately processing data based on edge calculation | |
CN116258233A (en) | Day-ahead scheduling plan deviation degree estimation model training method, estimation method and device | |
CN116029562A (en) | New energy consumption proportion contribution evaluation model training method, evaluation method and device | |
CN101404816A (en) | Apparatus and method for monitoring objective |
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 |