CN117195036A - Intelligent processing method and system for power plant data - Google Patents
Intelligent processing method and system for power plant data Download PDFInfo
- Publication number
- CN117195036A CN117195036A CN202310915988.3A CN202310915988A CN117195036A CN 117195036 A CN117195036 A CN 117195036A CN 202310915988 A CN202310915988 A CN 202310915988A CN 117195036 A CN117195036 A CN 117195036A
- Authority
- CN
- China
- Prior art keywords
- power plant
- plant data
- processed
- strategy
- data processing
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 149
- 238000013468 resource allocation Methods 0.000 claims abstract description 47
- 230000006870 function Effects 0.000 claims abstract description 36
- 238000000034 method Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an intelligent processing method and system for power plant data, which relate to the technical field of electric data processing and comprise the steps of determining the type of power plant data processing resources corresponding to each type of power plant data to be processed according to the multi-type power plant data to be processed; defining utility functions of each type of power plant data to be processed based on importance degrees of the power plant data to be processed in multiple types and the corresponding power plant data processing resource types; constructing a strategy space corresponding to the power plant data to be processed in each category; and the policy space is divided accordingly; and sequentially inputting a plurality of strategy subspaces with different priorities into the game model, determining the optimal solution of the corresponding order according to the utility function until the strategy subspaces are input according with the game requirement, and distributing power plant data processing resources required by the power plant data to be processed. The reliability of the data processing resource game is improved, and the rationality of the processing resource allocation is ensured, so that the utilization rate and the effectiveness of the processing resource are improved.
Description
Technical Field
The application relates to the technical field of electric data processing, in particular to an intelligent processing method and system for power plant data.
Background
With the increasing demand for energy and the development of the energy industry, power plants as the primary energy suppliers produce a large amount of data. Such data includes information on the operating state of the power plant, the power load, the energy consumption, and the like. To operate and manage power plants more efficiently, the power industry is beginning to employ intelligent processing techniques to analyze and apply such data.
In the prior art, the data of the power plant are various and complex in variety, and the corresponding processing data are various and large in quantity, such as computing resources, storage resources and the like, and in the existing power plant, the processing resources cannot be reasonably allocated according to the self-properties of the required processing data, so that the resource waste or the resource effectiveness is poor.
Therefore, how to improve the rationality of processing resource allocation and the resource utilization rate is a technical problem to be solved at present.
Disclosure of Invention
The application provides an intelligent processing method for power plant data, which is used for solving the technical problems of poor resource allocation rationality and low utilization rate in the prior art. The method comprises the following steps:
acquiring to-be-processed power plant data, and classifying the to-be-processed power plant data to obtain multi-category to-be-processed power plant data;
acquiring power plant data processing resources, and determining the types of the power plant data processing resources corresponding to each type of power plant data to be processed according to the multi-type power plant data to be processed;
defining utility functions of each type of power plant data to be processed based on importance degrees of the power plant data to be processed in multiple types and the corresponding power plant data processing resource types;
defining a resource allocation strategy, and constructing a strategy space corresponding to the power plant data to be processed in each category;
determining the adaptability level of a resource allocation strategy, and dividing a strategy space according to the adaptability level to obtain a plurality of strategy subspaces with different priorities;
sequentially inputting a plurality of strategy subspaces with different priorities into a game model, and determining an optimal solution of a corresponding order according to a utility function until the input of the strategy subspaces meets the game requirement;
and reasonably distributing power plant data processing resources required by the power plant data to be processed through the optimal solution obtained through the game.
In some embodiments of the present application, classifying the to-be-processed power plant data to obtain multi-class to-be-processed power plant data includes:
extracting all data characteristics in the power plant data to be processed, and receiving all task demands in the power plant data processing;
calculating the correlation degree of each data feature and each task requirement respectively, and recording the data features with the correlation degree exceeding a first correlation degree threshold as meaning features;
the data features with the correlation degree exceeding the second correlation degree threshold and not exceeding the first correlation degree threshold are recorded as features to be checked;
the difference value between the correlation degree of the feature to be checked and the second correlation degree threshold value is recorded as a first difference value, and the difference value between the correlation degree of the feature to be checked and the first correlation degree threshold value is recorded as a second difference value;
determining an updating coefficient according to the ratio of the first difference value to the second difference value, and updating the correlation degree of the feature to be checked to obtain a new correlation degree;
if the new correlation exceeds a third correlation threshold, taking the feature to be checked as a meaning feature;
and clustering the meaning features by a preset clustering algorithm, and classifying the data by adopting a semi-supervised learning mode to obtain multi-category power plant data to be processed.
In some embodiments of the present application, determining a type of power plant data processing resource corresponding to each type of power plant data to be processed according to the multi-type of power plant data to be processed includes:
acquiring a data processing record of each type of power plant data to be processed, and determining the types of power plant data processing resources related to the power plant data to be processed for multiple times;
if the types of the power plant data processing resources related to the power plant data to be processed in each category are the same, establishing a corresponding relation between the power plant data to be processed in the category and the types of the related power plant data processing resources;
otherwise, establishing a corresponding relation according to the types of power plant data processing resources involved in the power plant data to be processed of each category for a plurality of times;
if the different times in the power plant data processing resource types related to the power plant data to be processed of each category exceeds the times threshold, taking the union of the power plant data processing resource types related to the power plant data to be processed of each category as the corresponding relation of the power plant data to be processed of the category;
otherwise, the power plant data processing resource type with the largest number of times in the power plant data processing resource types related to the power plant data to be processed in each category is used as the corresponding relation of the power plant data to be processed in the category.
In some embodiments of the present application, the method further includes determining a importance level of a type of the data processing resource of the power plant, including:
determining multi-category to-be-processed power plant data corresponding to each power plant data processing resource, and marking the multi-category to-be-processed power plant data as first corresponding to the to-be-processed power plant data;
acquiring a plurality of important factors of the first corresponding power plant data to be processed, and determining the importance degree of the type of the power plant data processing resources;
；
wherein P is the importance degree of the type of the power plant data processing resource, n is the number of important factors,influence weight corresponding to the ith important factor, +.>For the size of the parameter corresponding to the ith important factor, exp is an exponential function, m is the number exceeding the initial value of each important factor, and +.>For the correction weight corresponding to the important factor of the jth item exceeding the respective initial value,/for>For the size of the parameter corresponding to the important factor of the jth item exceeding the respective initial value, < >>And k is a preset constant, wherein the k is the initial value corresponding to the j-th important factor.
In some embodiments of the present application, defining utility functions for each category of plant data to be processed based on importance levels of the plurality of categories of plant data to be processed and their respective corresponding plant data processing resource categories includes:
determining initial preference weights of the power plant data to be processed in each category on different power plant data processing resource categories according to the importance degree of the power plant data processing resource categories;
and correcting the initial preference weight according to the data processing record of the power plant data to be processed in each category so as to obtain the utility function of the power plant data to be processed in each category.
In some embodiments of the present application, defining a resource allocation policy, and constructing a policy space corresponding to each type of to-be-processed power plant data, including:
setting the corresponding number of unit copies for the resources corresponding to different power plant data processing resource types, and setting the resource allocation strategy as the number of copies;
constructing a strategy space corresponding to the power plant data to be processed in each category according to the number of resources in the history record, and recording the strategy space as a first strategy space;
setting corresponding proportion of resources corresponding to different power plant data processing resource types, and setting a resource allocation strategy as proportion size;
constructing a strategy space corresponding to the power plant data to be processed in each category according to the different resource proportion in the history record, and recording the strategy space as a second strategy space;
comparing the first strategy space with the second strategy space, and taking the larger one of the first strategy space and the second strategy space as the strategy space if the space size difference between the first strategy space and the second strategy space exceeds the first space size threshold;
otherwise, determining a first adjustment coefficient and a second adjustment coefficient according to the difference between the first strategy space and the first space size threshold and the difference between the second strategy space and the first space size threshold respectively;
adjusting the first policy space based on the first adjustment coefficient, and adjusting the second policy space based on the second adjustment coefficient;
and taking the adjusted first strategy space and the adjusted second strategy space which are relatively close to the second space size threshold value as strategy spaces.
In some embodiments of the present application, determining an adaptability level of a resource allocation policy, and dividing a policy space accordingly to obtain a plurality of policy subspaces with different priorities, including:
acquiring a plurality of power plant data processing effect indexes, and predicting each power plant data processing effect index corresponding to a resource allocation strategy so as to acquire a comprehensive index;
and determining the adaptability level based on the comprehensive indexes corresponding to the resource allocation strategies, wherein the adaptability levels of different resource allocation strategies are different, so that the strategy space is divided, and a plurality of strategy subspaces with different priorities are obtained.
In some embodiments of the present application, a plurality of policy subspaces with different priorities are sequentially put into a game model, and an optimal solution of a corresponding order is determined according to a utility function until the input of the policy subspaces meets a game requirement, including:
taking multi-category pending power plant data as game participants;
sequentially inputting different strategy subspaces into a preset competition game model based on the priority order;
setting target benefits corresponding to each priority according to the number of the priorities;
after each strategy subspace investment is completed, determining Nash equilibrium solutions;
if the number of Nash equilibrium solutions is unique, calculating whether the difference between the benefits of the Nash equilibrium solutions and the target benefits corresponding to the priorities accords with a preset difference value, taking the Nash equilibrium solutions as optimal solutions, stopping inputting the strategy subspaces, and if not, continuing inputting the strategy subspaces;
if the number of Nash equilibrium solutions is not unique, comparing the benefits of the Nash equilibrium solutions, calculating whether the difference between the Nash equilibrium solution with the highest benefit and the target benefit corresponding to the priority accords with a preset difference value, taking the Nash equilibrium solution as an optimal solution, stopping inputting the strategy subspace, and if not, continuing inputting the strategy subspace.
Correspondingly, the application also provides an intelligent power plant data processing system, which comprises:
the classification module is used for acquiring the to-be-processed power plant data, classifying the to-be-processed power plant data and obtaining multi-class to-be-processed power plant data;
the corresponding module is used for acquiring power plant data processing resources and determining the types of the power plant data processing resources corresponding to each type of the power plant data to be processed according to the multi-type power plant data to be processed;
the definition module is used for defining utility functions of the power plant data to be processed in each category based on importance degrees of the power plant data to be processed in the categories and the corresponding power plant data processing resource categories;
the construction module is used for defining a resource allocation strategy and constructing a strategy space corresponding to the power plant data to be processed in each category;
the division module is used for determining the adaptability level of the resource allocation strategy and dividing the strategy space according to the adaptability level to obtain a plurality of strategy subspaces with different priorities;
the game module is used for sequentially inputting a plurality of strategy subspaces with different priorities into the game model, and determining the optimal solution of the corresponding order according to the utility function until the input of the strategy subspaces meets the game requirement;
and the processing module is used for reasonably distributing power plant data processing resources required by the power plant data to be processed through the optimal solution obtained through the game.
By applying the technical scheme, the power plant data to be processed is obtained, and the power plant data to be processed is classified to obtain multi-category power plant data to be processed; acquiring power plant data processing resources, and determining the types of the power plant data processing resources corresponding to each type of power plant data to be processed according to the multi-type power plant data to be processed; defining utility functions of each type of power plant data to be processed based on importance degrees of the power plant data to be processed in multiple types and the corresponding power plant data processing resource types; defining a resource allocation strategy, and constructing a strategy space corresponding to the power plant data to be processed in each category; determining the adaptability level of a resource allocation strategy, and dividing a strategy space according to the adaptability level to obtain a plurality of strategy subspaces with different priorities; sequentially inputting a plurality of strategy subspaces with different priorities into a game model, and determining an optimal solution of a corresponding order according to a utility function until the input of the strategy subspaces meets the game requirement; and reasonably distributing power plant data processing resources required by the power plant data to be processed through the optimal solution obtained through the game. According to the method, the utility function of the power plant data to be processed in each category is defined through the importance degree of the power plant data to be processed in the categories and the power plant data processing resource types corresponding to the power plant data to be processed in each category, the strategy space corresponding to the power plant data to be processed in each category is constructed, divided and the like, the reliability of data processing resource game is improved, the rationality of processing resource allocation is guaranteed, and therefore the utilization rate and the effectiveness of processing resources are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a schematic flow chart of a method for intelligently processing power plant data according to an embodiment of the application;
fig. 2 shows a schematic structural diagram of a power plant data intelligent processing system according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides a power plant data intelligent processing method, as shown in fig. 1, which comprises the following steps:
step S101, obtaining the to-be-processed power plant data, and classifying the to-be-processed power plant data to obtain multi-category to-be-processed power plant data.
In this embodiment, the to-be-processed power plant data is classified according to the characteristics to be used as the participants in the subsequent game.
In some embodiments of the present application, classifying the to-be-processed power plant data to obtain multi-class to-be-processed power plant data includes:
extracting all data characteristics in the power plant data to be processed, and receiving all task demands in the power plant data processing;
calculating the correlation degree of each data feature and each task requirement respectively, and recording the data features with the correlation degree exceeding a first correlation degree threshold as meaning features;
the data features with the correlation degree exceeding the second correlation degree threshold and not exceeding the first correlation degree threshold are recorded as features to be checked;
the difference value between the correlation degree of the feature to be checked and the second correlation degree threshold value is recorded as a first difference value, and the difference value between the correlation degree of the feature to be checked and the first correlation degree threshold value is recorded as a second difference value;
determining an updating coefficient according to the ratio of the first difference value to the second difference value, and updating the correlation degree of the feature to be checked to obtain a new correlation degree;
if the new correlation exceeds a third correlation threshold, taking the feature to be checked as a meaning feature;
and clustering the meaning features by a preset clustering algorithm, and classifying the data by adopting a semi-supervised learning mode to obtain multi-category power plant data to be processed.
In this embodiment, after the task demands are quantized, the correlation between each data feature and each task demand is calculated. Thereby screening for meaningful features and removing nonsensical features.
In this embodiment, the update coefficient updates the correlation degree of the feature to be checked to obtain a new correlation degree. New correlation = update coefficient.
In this embodiment, the first difference, the second difference and the update coefficient effectively screen out significant features, so as to improve adaptability and reliability of features and provide a solid foundation for classification.
In this embodiment, the clustering and semi-supervised learning methods are conventional techniques in the art, and are not described herein.
Step S102, power plant data processing resources are obtained, and the type of the power plant data processing resources corresponding to each type of the power plant data to be processed is determined according to the multi-type of the power plant data to be processed.
In this embodiment, the power plant data processing resource is a resource required for data processing such as a computing resource, a storage resource, and a bandwidth resource. And determining the resource type corresponding to each category data.
In some embodiments of the present application, determining a type of power plant data processing resource corresponding to each type of power plant data to be processed according to the multi-type of power plant data to be processed includes:
acquiring a data processing record of each type of power plant data to be processed, and determining the types of power plant data processing resources related to the power plant data to be processed for multiple times;
if the types of the power plant data processing resources related to the power plant data to be processed in each category are the same, establishing a corresponding relation between the power plant data to be processed in the category and the types of the related power plant data processing resources;
otherwise, establishing a corresponding relation according to the types of power plant data processing resources involved in the power plant data to be processed of each category for a plurality of times;
if the different times in the power plant data processing resource types related to the power plant data to be processed of each category exceeds the times threshold, taking the union of the power plant data processing resource types related to the power plant data to be processed of each category as the corresponding relation of the power plant data to be processed of the category;
otherwise, the power plant data processing resource type with the largest number of times in the power plant data processing resource types related to the power plant data to be processed in each category is used as the corresponding relation of the power plant data to be processed in the category.
In this embodiment, the competition game of the subsequent game model is facilitated by establishing an accurate correspondence between the data types and the resource types.
Step S103, defining utility functions of the power plant data to be processed in each category based on importance degrees of the power plant data to be processed in the categories and the corresponding power plant data processing resource categories.
In this embodiment, utility functions play a key role in resource gaming and decision making issues, which are used to quantify individual or participant preferences for different resource allocation schemes. The utility function has the significance of measuring the preference of participants, guiding resource allocation, supporting decision-making processes, and the like.
In some embodiments of the present application, the method further includes determining a importance level of a type of the data processing resource of the power plant, including:
determining multi-category to-be-processed power plant data corresponding to each power plant data processing resource, and marking the multi-category to-be-processed power plant data as first corresponding to the to-be-processed power plant data;
acquiring a plurality of important factors of the first corresponding power plant data to be processed, and determining the importance degree of the type of the power plant data processing resources;
；
wherein P is the importance degree of the type of the power plant data processing resource, n is the number of important factors,influence weight corresponding to the ith important factor, +.>For the size of the parameter corresponding to the ith important factor, exp is an exponential function, m is the number exceeding the initial value of each important factor, and +.>For the correction weight corresponding to the important factor of the jth item exceeding the respective initial value,/for>For the size of the parameter corresponding to the important factor of the jth item exceeding the respective initial value, < >>And k is a preset constant, wherein the k is the initial value corresponding to the j-th important factor.
In this embodiment, the importance of the type of the data processing resource in the power plant is understood as the importance of the type of the processing resource.
In this embodiment, the multi-class to-be-processed power plant data corresponding to each power plant data processing resource is determined, and the data corresponding to each power plant data processing resource is the first to-be-processed power plant data.
In this embodiment, the multiple important factors include data size, time-efficiency requirements for data processing, performance requirements for the system, and the like.
In the present embodiment of the present application,indicating the correction of all the influence amounts by factors exceeding the initial value. />When=0,>=1, do not pair->And (5) performing correction.
In some embodiments of the present application, defining utility functions for each category of plant data to be processed based on importance levels of the plurality of categories of plant data to be processed and their respective corresponding plant data processing resource categories includes:
determining initial preference weights of the power plant data to be processed in each category on different power plant data processing resource categories according to the importance degree of the power plant data processing resource categories;
and correcting the initial preference weight according to the data processing record of the power plant data to be processed in each category so as to obtain the utility function of the power plant data to be processed in each category.
In this embodiment, for example, the utility function of some data to be processed is,
indicating that certain data to be processed are in use +.>The requirements or satisfaction of the three processing resources. />、/>、/>Respectively representing the respective initial preference weights. And determining a correction coefficient according to the data processing record of the power plant data to be processed in each category, wherein the correction coefficient is equal to the initial preference weight=the updated weight, so as to obtain a brand new utility function.
Step S104, defining a resource allocation strategy and constructing a strategy space corresponding to each type of power plant data to be processed.
In this embodiment, the resource allocation policy may be understood as a range of variables, that is, a range of intervals for processing the number of resource copies or the ratio. Policy space is the interval range of variables.
In some embodiments of the present application, defining a resource allocation policy, and constructing a policy space corresponding to each type of to-be-processed power plant data, including:
setting the corresponding number of unit copies for the resources corresponding to different power plant data processing resource types, and setting the resource allocation strategy as the number of copies;
constructing a strategy space corresponding to the power plant data to be processed in each category according to the number of resources in the history record, and recording the strategy space as a first strategy space;
setting corresponding proportion of resources corresponding to different power plant data processing resource types, and setting a resource allocation strategy as proportion size;
constructing a strategy space corresponding to the power plant data to be processed in each category according to the different resource proportion in the history record, and recording the strategy space as a second strategy space;
comparing the first strategy space with the second strategy space, and taking the larger one of the first strategy space and the second strategy space as the strategy space if the space size difference between the first strategy space and the second strategy space exceeds the first space size threshold;
otherwise, determining a first adjustment coefficient and a second adjustment coefficient according to the difference between the first strategy space and the first space size threshold and the difference between the second strategy space and the first space size threshold respectively;
adjusting the first policy space based on the first adjustment coefficient, and adjusting the second policy space based on the second adjustment coefficient;
and taking the adjusted first strategy space and the adjusted second strategy space which are relatively close to the second space size threshold value as strategy spaces.
In this embodiment, the policy space or space size is the interval range size of the variable.
In this embodiment, the number of units corresponding to the number of units of the resources corresponding to the types of the data processing resources of different power plants is set, and the units of different processing resources are different, so that a variable needs to be unified to a certain extent, that is, how many processing resources are set as one unit of the resources. Setting corresponding proportion of resources corresponding to different power plant data processing resource types, wherein the proportion between different resources can be used as a variable.
In this embodiment, the policy space corresponding to each type of to-be-processed power plant data is constructed according to the number of resource copies in the history record, which can be understood as constructing a variable range interval of each type of to-be-processed data.
Step S105, determining the adaptability level of the resource allocation strategy, and dividing the strategy space according to the adaptability level to obtain a plurality of strategy subspaces with different priorities.
In this embodiment, determining the adaptability level of the resource allocation policy is equivalent to determining the adaptability level corresponding to different variable intervals. And dividing the whole variable interval to obtain a plurality of strategy subspaces with different priorities.
In some embodiments of the present application, determining an adaptability level of a resource allocation policy, and dividing a policy space accordingly to obtain a plurality of policy subspaces with different priorities, including:
acquiring a plurality of power plant data processing effect indexes, and predicting each power plant data processing effect index corresponding to a resource allocation strategy so as to acquire a comprehensive index;
and determining the adaptability level based on the comprehensive indexes corresponding to the resource allocation strategies, wherein the adaptability levels of different resource allocation strategies are different, so that the strategy space is divided, and a plurality of strategy subspaces with different priorities are obtained.
In this embodiment, the multiple power plant data processing effect indexes include processing efficiency, processing quality, and the like.
In this embodiment, the adaptability level is determined based on the comprehensive index corresponding to the resource allocation policy, and the higher the comprehensive index is, the higher the adaptability level is, and the higher the corresponding priority is.
In this embodiment, the policy space is divided in the sense that the game result is obtained more quickly, because the power plant data processing often has a certain requirement on timeliness.
And S106, sequentially inputting a plurality of strategy subspaces with different priorities into the game model, and determining the optimal solution of the corresponding order according to the utility function until the input of the strategy subspaces meets the game requirement.
In this embodiment, in order to obtain the game result, i.e. the strategy, more quickly and more accurately. And sequentially putting the power plant data into a preset game model, stopping putting the power plant data into the game model when the optimal solution meeting the requirements is obtained, and ensuring timeliness of power plant data processing.
In some embodiments of the present application, a plurality of policy subspaces with different priorities are sequentially put into a game model, and an optimal solution of a corresponding order is determined according to a utility function until the input of the policy subspaces meets a game requirement, including:
taking multi-category pending power plant data as game participants;
sequentially inputting different strategy subspaces into a preset competition game model based on the priority order;
setting target benefits corresponding to each priority according to the number of the priorities;
after each strategy subspace investment is completed, determining Nash equilibrium solutions;
if the number of Nash equilibrium solutions is unique, calculating whether the difference between the benefits of the Nash equilibrium solutions and the target benefits corresponding to the priorities accords with a preset difference value, taking the Nash equilibrium solutions as optimal solutions, stopping inputting the strategy subspaces, and if not, continuing inputting the strategy subspaces;
if the number of Nash equilibrium solutions is not unique, comparing the benefits of the Nash equilibrium solutions, calculating whether the difference between the Nash equilibrium solution with the highest benefit and the target benefit corresponding to the priority accords with a preset difference value, taking the Nash equilibrium solution as an optimal solution, stopping inputting the strategy subspace, and if not, continuing inputting the strategy subspace.
In this embodiment, specific game models and methods for calculating benefits are conventional in the art, and will not be described herein.
And step S107, reasonably distributing power plant data processing resources required by the power plant data to be processed through the optimal solution obtained through the game.
By applying the technical scheme, the power plant data to be processed is obtained, and the power plant data to be processed is classified to obtain multi-category power plant data to be processed; acquiring power plant data processing resources, and determining the types of the power plant data processing resources corresponding to each type of power plant data to be processed according to the multi-type power plant data to be processed; defining utility functions of each type of power plant data to be processed based on importance degrees of the power plant data to be processed in multiple types and the corresponding power plant data processing resource types; defining a resource allocation strategy, and constructing a strategy space corresponding to the power plant data to be processed in each category; determining the adaptability level of a resource allocation strategy, and dividing a strategy space according to the adaptability level to obtain a plurality of strategy subspaces with different priorities; sequentially inputting a plurality of strategy subspaces with different priorities into a game model, and determining an optimal solution of a corresponding order according to a utility function until the input of the strategy subspaces meets the game requirement; and reasonably distributing power plant data processing resources required by the power plant data to be processed through the optimal solution obtained through the game. According to the method, the utility function of the power plant data to be processed in each category is defined through the importance degree of the power plant data to be processed in the categories and the power plant data processing resource types corresponding to the power plant data to be processed in each category, the strategy space corresponding to the power plant data to be processed in each category is constructed, divided and the like, the reliability of data processing resource game is improved, the rationality of processing resource allocation is guaranteed, and therefore the utilization rate and the effectiveness of processing resources are improved.
From the above description of the embodiments, it will be clear to those skilled in the art that the present application may be implemented in hardware, or may be implemented by means of software plus necessary general hardware platforms. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present application.
In order to further explain the technical idea of the application, the technical scheme of the application is described with specific application scenarios.
Correspondingly, the application also provides an intelligent processing system for the power plant data, as shown in fig. 2, the system comprises:
the classification module 201 is configured to obtain to-be-processed power plant data, classify the to-be-processed power plant data, and obtain multi-class to-be-processed power plant data;
the corresponding module 202 is configured to obtain power plant data processing resources, and determine a power plant data processing resource type corresponding to each type of power plant data to be processed according to the multi-type power plant data to be processed;
the definition module 203 is configured to define a utility function of each type of to-be-processed power plant data based on importance degrees of the multiple types of to-be-processed power plant data and respective corresponding power plant data processing resource types;
the construction module 204 is configured to define a resource allocation policy, and construct a policy space corresponding to each type of to-be-processed power plant data;
the division module 205 is configured to determine an adaptability level of the resource allocation policy, and divide the policy space accordingly to obtain a plurality of policy subspaces with different priorities;
the game module 206 is configured to sequentially input a plurality of policy subspaces with different priorities into the game model, and determine an optimal solution of the corresponding order according to the utility function until the input of the policy subspaces meets the game requirement;
and the processing module 207 is configured to reasonably allocate power plant data processing resources required by the power plant data to be processed through the optimal solution obtained by the game.
Those skilled in the art will appreciate that the modules in the system in the implementation scenario may be distributed in the system in the implementation scenario according to the implementation scenario description, or that corresponding changes may be located in one or more systems different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be appreciated by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not drive the essence of the corresponding technical solutions to depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (9)
1. An intelligent processing method for power plant data is characterized by comprising the following steps:
acquiring to-be-processed power plant data, and classifying the to-be-processed power plant data to obtain multi-category to-be-processed power plant data;
acquiring power plant data processing resources, and determining the types of the power plant data processing resources corresponding to each type of power plant data to be processed according to the multi-type power plant data to be processed;
defining utility functions of each type of power plant data to be processed based on importance degrees of the power plant data to be processed in multiple types and the corresponding power plant data processing resource types;
defining a resource allocation strategy, and constructing a strategy space corresponding to the power plant data to be processed in each category;
determining the adaptability level of a resource allocation strategy, and dividing a strategy space according to the adaptability level to obtain a plurality of strategy subspaces with different priorities;
sequentially inputting a plurality of strategy subspaces with different priorities into a game model, and determining an optimal solution of a corresponding order according to a utility function until the input of the strategy subspaces meets the game requirement;
and reasonably distributing power plant data processing resources required by the power plant data to be processed through the optimal solution obtained through the game.
2. The intelligent processing method for power plant data according to claim 1, wherein classifying the power plant data to be processed to obtain multi-category power plant data to be processed comprises:
extracting all data characteristics in the power plant data to be processed, and receiving all task demands in the power plant data processing;
calculating the correlation degree of each data feature and each task requirement respectively, and recording the data features with the correlation degree exceeding a first correlation degree threshold as meaning features;
the data features with the correlation degree exceeding the second correlation degree threshold and not exceeding the first correlation degree threshold are recorded as features to be checked;
the difference value between the correlation degree of the feature to be checked and the second correlation degree threshold value is recorded as a first difference value, and the difference value between the correlation degree of the feature to be checked and the first correlation degree threshold value is recorded as a second difference value;
determining an updating coefficient according to the ratio of the first difference value to the second difference value, and updating the correlation degree of the feature to be checked to obtain a new correlation degree;
if the new correlation exceeds a third correlation threshold, taking the feature to be checked as a meaning feature;
and clustering the meaning features by a preset clustering algorithm, and classifying the data by adopting a semi-supervised learning mode to obtain multi-category power plant data to be processed.
3. The intelligent processing method for power plant data according to claim 1, wherein determining the kind of the power plant data processing resource corresponding to each kind of the power plant data to be processed according to the plural kinds of the power plant data to be processed comprises:
acquiring a data processing record of each type of power plant data to be processed, and determining the types of power plant data processing resources related to the power plant data to be processed for multiple times;
if the types of the power plant data processing resources related to the power plant data to be processed in each category are the same, establishing a corresponding relation between the power plant data to be processed in the category and the types of the related power plant data processing resources;
otherwise, establishing a corresponding relation according to the types of power plant data processing resources involved in the power plant data to be processed of each category for a plurality of times;
if the different times in the power plant data processing resource types related to the power plant data to be processed of each category exceeds the times threshold, taking the union of the power plant data processing resource types related to the power plant data to be processed of each category as the corresponding relation of the power plant data to be processed of the category;
otherwise, the power plant data processing resource type with the largest number of times in the power plant data processing resource types related to the power plant data to be processed in each category is used as the corresponding relation of the power plant data to be processed in the category.
4. The intelligent processing method of power plant data according to claim 1, wherein the method further comprises determining a degree of importance of the type of power plant data processing resource, comprising:
determining multi-category to-be-processed power plant data corresponding to each power plant data processing resource, and marking the multi-category to-be-processed power plant data as first corresponding to the to-be-processed power plant data;
acquiring a plurality of important factors of the first corresponding power plant data to be processed, and determining the importance degree of the type of the power plant data processing resources;
；
wherein P is the importance degree of the type of the power plant data processing resource, n is the number of important factors,influence weight corresponding to the ith important factor, +.>For the size of the parameter corresponding to the ith important factor, exp is an exponential function, m is the number exceeding the initial value of each important factor, and +.>For the correction weight corresponding to the important factor of the jth item exceeding the respective initial value,/for>For the size of the parameter corresponding to the important factor of the jth item exceeding the respective initial value, < >>And k is a preset constant, wherein the k is the initial value corresponding to the j-th important factor.
5. The intelligent processing method for power plant data according to claim 4, wherein defining the utility function of each category of the power plant data to be processed based on the importance of the categories of the power plant data to be processed and their respective corresponding power plant data processing resource categories comprises:
determining initial preference weights of the power plant data to be processed in each category on different power plant data processing resource categories according to the importance degree of the power plant data processing resource categories;
and correcting the initial preference weight according to the data processing record of the power plant data to be processed in each category so as to obtain the utility function of the power plant data to be processed in each category.
6. The intelligent processing method for power plant data according to claim 1, wherein defining a resource allocation strategy and constructing a strategy space corresponding to each type of power plant data to be processed comprises:
setting the corresponding number of unit copies for the resources corresponding to different power plant data processing resource types, and setting the resource allocation strategy as the number of copies;
constructing a strategy space corresponding to the power plant data to be processed in each category according to the number of resources in the history record, and recording the strategy space as a first strategy space;
setting corresponding proportion of resources corresponding to different power plant data processing resource types, and setting a resource allocation strategy as proportion size;
constructing a strategy space corresponding to the power plant data to be processed in each category according to the different resource proportion in the history record, and recording the strategy space as a second strategy space;
comparing the first strategy space with the second strategy space, and taking the larger one of the first strategy space and the second strategy space as the strategy space if the space size difference between the first strategy space and the second strategy space exceeds the first space size threshold;
otherwise, determining a first adjustment coefficient and a second adjustment coefficient according to the difference between the first strategy space and the first space size threshold and the difference between the second strategy space and the first space size threshold respectively;
adjusting the first policy space based on the first adjustment coefficient, and adjusting the second policy space based on the second adjustment coefficient;
and taking the adjusted first strategy space and the adjusted second strategy space which are relatively close to the second space size threshold value as strategy spaces.
7. The intelligent processing method for power plant data according to claim 1, wherein determining the adaptability level of the resource allocation strategy and dividing the strategy space accordingly to obtain a plurality of strategy subspaces with different priorities comprises:
acquiring a plurality of power plant data processing effect indexes, and predicting each power plant data processing effect index corresponding to a resource allocation strategy so as to acquire a comprehensive index;
and determining the adaptability level based on the comprehensive indexes corresponding to the resource allocation strategies, wherein the adaptability levels of different resource allocation strategies are different, so that the strategy space is divided, and a plurality of strategy subspaces with different priorities are obtained.
8. The intelligent processing method of power plant data according to claim 7, wherein sequentially inputting a plurality of policy subspaces with different priorities into a game model, and determining an optimal solution of the corresponding order according to a utility function until the input of the policy subspaces meets game requirements, comprises:
taking multi-category pending power plant data as game participants;
sequentially inputting different strategy subspaces into a preset competition game model based on the priority order;
setting target benefits corresponding to each priority according to the number of the priorities;
after each strategy subspace investment is completed, determining Nash equilibrium solutions;
if the number of Nash equilibrium solutions is unique, calculating whether the difference between the benefits of the Nash equilibrium solutions and the target benefits corresponding to the priorities accords with a preset difference value, taking the Nash equilibrium solutions as optimal solutions, stopping inputting the strategy subspaces, and if not, continuing inputting the strategy subspaces;
if the number of Nash equilibrium solutions is not unique, comparing the benefits of the Nash equilibrium solutions, calculating whether the difference between the Nash equilibrium solution with the highest benefit and the target benefit corresponding to the priority accords with a preset difference value, taking the Nash equilibrium solution as an optimal solution, stopping inputting the strategy subspace, and if not, continuing inputting the strategy subspace.
9. A power plant data intelligent processing system, the system comprising:
the classification module is used for acquiring the to-be-processed power plant data, classifying the to-be-processed power plant data and obtaining multi-class to-be-processed power plant data;
the corresponding module is used for acquiring power plant data processing resources and determining the types of the power plant data processing resources corresponding to each type of the power plant data to be processed according to the multi-type power plant data to be processed;
the definition module is used for defining utility functions of the power plant data to be processed in each category based on importance degrees of the power plant data to be processed in the categories and the corresponding power plant data processing resource categories;
the construction module is used for defining a resource allocation strategy and constructing a strategy space corresponding to the power plant data to be processed in each category;
the division module is used for determining the adaptability level of the resource allocation strategy and dividing the strategy space according to the adaptability level to obtain a plurality of strategy subspaces with different priorities;
the game module is used for sequentially inputting a plurality of strategy subspaces with different priorities into the game model, and determining the optimal solution of the corresponding order according to the utility function until the input of the strategy subspaces meets the game requirement;
and the processing module is used for reasonably distributing power plant data processing resources required by the power plant data to be processed through the optimal solution obtained through the game.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310915988.3A CN117195036A (en) | 2023-07-25 | 2023-07-25 | Intelligent processing method and system for power plant data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310915988.3A CN117195036A (en) | 2023-07-25 | 2023-07-25 | Intelligent processing method and system for power plant data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117195036A true CN117195036A (en) | 2023-12-08 |
Family
ID=89000534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310915988.3A Pending CN117195036A (en) | 2023-07-25 | 2023-07-25 | Intelligent processing method and system for power plant data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117195036A (en) |
-
2023
- 2023-07-25 CN CN202310915988.3A patent/CN117195036A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019114421A1 (en) | Model integration method and device | |
| JP2020507135A (en) | Exclusive agent pool distribution method, electronic device, and computer-readable storage medium | |
| CN105718490A (en) | Method and device for updating classifying model | |
| CN111178639A (en) | Method and device for realizing prediction based on multi-model fusion | |
| CN108320089A (en) | It attends a banquet distribution method, electronic device and computer readable storage medium | |
| CN106202092A (en) | The method and system that data process | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN110796485A (en) | Method and device for improving prediction precision of prediction model | |
| CN112200665A (en) | Method and device for determining credit limit | |
| CN114595970A (en) | Resource scheduling intelligent decision method and device, electronic equipment and storage medium | |
| CN113962800A (en) | Model training and overdue risk prediction method, device, equipment and medium | |
| CN117290090A (en) | Node cooperative resource allocation method, device, equipment and storage medium | |
| CN117056018A (en) | Resource scheduling method, apparatus, device, program product and storage medium | |
| CN109145207B (en) | Information personalized recommendation method and device based on classification index prediction | |
| CN115600818A (en) | Multi-dimensional scoring method and device, electronic equipment and storage medium | |
| CN117195036A (en) | Intelligent processing method and system for power plant data | |
| CN113723593B (en) | Cut load prediction method and system based on neural network | |
| CN115222101A (en) | Flow data processing method and device | |
| CN114841490A (en) | Ecological protection priority area identification method, system, device and storage medium | |
| CN113379533A (en) | Method, device, equipment and storage medium for improving circulating loan quota | |
| CN113296951A (en) | Resource allocation scheme determination method and equipment | |
| CN110807599A (en) | Method, device, server and storage medium for deciding electrochemical energy storage scheme | |
| CN115511253B (en) | Method, device, equipment and medium for evaluating land development capacity | |
| CN117726434A (en) | Credit scoring card model training method, application method and related products | |
| CN115658283A (en) | Resource allocation method, device, equipment, medium and program product |
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 |