Power plant data intelligent processing method and system

Abstract

The application discloses a power plant data intelligent processing method and system, relates to the electric data processing technical field, and comprises the following steps: determining the power plant data processing resource type corresponding to each category of to-be-processed power plant data according to multiple categories of to-be-processed power plant data; defining the utility function of each category of to-be-processed power plant data based on the importance degree of the multiple categories of to-be-processed power plant data and the power plant data processing resource type corresponding to each category of to-be-processed power plant data; constructing the strategy space corresponding to each category of to-be-processed power plant data; dividing the strategy space according to the strategy space; sequentially inputting multiple strategy subspaces with different priorities into a game model, and determining the optimal solution of the corresponding order according to the utility function until the input of the strategy subspaces is stopped in accordance with the game requirements, and the power plant data processing resources required by the to-be-processed power plant data are distributed. The reliability of the data processing resource game is improved, the rationality of the processing resource distribution is ensured, and therefore the utilization rate and effectiveness of the processing resources are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric data processing, and more particularly, to an intelligent power plant data processing method and system. BACKGROUND

[0002] With the increasing demand for energy and the development of the energy industry, power plants, as the main energy suppliers, generate a large amount of data. These data include information such as the operating status of power generation equipment, power load, energy consumption, etc. In order to more efficiently operate and manage power plants, the power industry has begun to use intelligent processing technology to analyze and apply these data.

[0003] In the prior art, the data of power plants is numerous and complex in type, and the corresponding data processing resources are numerous and large in quantity, such as computing resources, storage resources, etc. In existing power plants, the processing resources cannot be reasonably allocated according to the nature of the data to be processed, resulting in waste of resources or poor resource effectiveness.

[0004] Therefore, how to improve the rationality of processing resource allocation and resource utilization is a technical problem to be solved at present. SUMMARY

[0005] The present application provides an intelligent power plant data processing method to solve the technical problems of poor resource allocation rationality and low utilization rate in the prior art. The method comprises:

[0006] Obtaining the to-be-processed power plant data, classifying the to-be-processed power plant data, and obtaining multiple categories of to-be-processed power plant data;

[0007] Obtaining power plant data processing resources, and determining the type of power plant data processing resources corresponding to each category of to-be-processed power plant data according to the multiple categories of to-be-processed power plant data;

[0008] Defining the utility function of each category of to-be-processed power plant data based on the importance of the multiple categories of to-be-processed power plant data and their respective corresponding types of power plant data processing resources;

[0009] Defining a resource allocation strategy and constructing a strategy space corresponding to each category of to-be-processed power plant data;

[0010] Determining the adaptability level of the resource allocation strategy, and dividing the strategy space according to the adaptability level to obtain multiple strategy subspaces with different priorities;

[0011] Putting the multiple strategy subspaces with different priorities into a game model in turn, and determining the optimal solution of the corresponding order according to the utility function, until the input of the strategy subspace is stopped according to the requirements of the game;

[0012] The optimal solution obtained by the game is used to reasonably allocate the power plant data processing resources required by the to-be-processed power plant data.

[0013] In some embodiments of the present application, the to-be-processed power plant data is classified to obtain multi-category to-be-processed power plant data, including:

[0014] All data features in the to-be-processed power plant data are extracted, and all task requirements in the power plant data processing are received;

[0015] The relevance of each data feature and each task requirement is calculated respectively, and the data feature with a relevance exceeding a first relevance threshold is recorded as a significant feature;

[0016] The data feature with a relevance exceeding a second relevance threshold and not exceeding the first relevance threshold is recorded as a to-be-checked feature;

[0017] The difference between the relevance of the to-be-checked feature and the second relevance threshold is recorded as a first difference, and the difference between the relevance of the to-be-checked feature and the first relevance threshold is recorded as a second difference;

[0018] An update coefficient is determined according to the ratio of the first difference to the second difference, and the relevance of the to-be-checked feature is updated to obtain a new relevance;

[0019] If the new relevance exceeds a third relevance threshold, the to-be-checked feature is taken as a significant feature;

[0020] The significant features are clustered by a preset clustering algorithm, and data classification is performed in a semi-supervised learning manner to obtain multi-category to-be-processed power plant data.

[0021] In some embodiments of the present application, the type of power plant data processing resource corresponding to each category of to-be-processed power plant data is determined according to the multi-category to-be-processed power plant data, including:

[0022] The data processing records of each category of to-be-processed power plant data are obtained, and the types of power plant data processing resources involved in each category of to-be-processed power plant data are determined;

[0023] If the types of power plant data processing resources involved in each category of to-be-processed power plant data are all the same, a corresponding relationship is established between the category of to-be-processed power plant data and the type of power plant data processing resource involved;

[0024] Otherwise, the corresponding relationship is established according to the types of power plant data processing resources involved in each category of to-be-processed power plant data;

[0025] If the number of different types of power plant data processing resources involved in each category of to-be-processed power plant data exceeds a number threshold, the union of the types of power plant data processing resources involved in each category of to-be-processed power plant data is taken as the corresponding relationship of the category of to-be-processed power plant data;

[0026] Otherwise, the same number of power plant data processing resource categories involved in the power plant data processing of each category of to-be-processed power plant data is determined as the corresponding relationship of the to-be-processed power plant data of the category.

[0027] In some embodiments of the application, the method further comprises determining the importance of the power plant data processing resource category, comprising:

[0028] Determine the corresponding multi-category to-be-processed power plant data of each power plant data processing resource, denoted as the first corresponding to-be-processed power plant data.

[0029] Obtain the multiple important factors of the first corresponding to-be-processed power plant data, and determine the importance of the power plant data processing resource category.

[0030] ;

[0031] Wherein, P is the importance of the power plant data processing resource category, n is the number of important factors, is the influence weight corresponding to the ith important factor, is the parameter size corresponding to the ith important factor, exp is the exponential function, and m is the number of multiple important factors exceeding the respective initial value, is the correction weight corresponding to the jth important factor exceeding the respective initial value, is the parameter size corresponding to the jth important factor exceeding the respective initial value, is the initial value size corresponding to the jth important factor, and k is a preset constant.

[0032] In some embodiments of the application, the utility function of each category of to-be-processed power plant data is defined based on the multi-category to-be-processed power plant data and the importance of the respective power plant data processing resource category, comprising:

[0033] Determine the initial preference weight of each category of to-be-processed power plant data for different power plant data processing resource categories according to the importance of the power plant data processing resource category;

[0034] And correct the initial preference weight according to the data processing record of each category of to-be-processed power plant data, to obtain the utility function of each category of to-be-processed power plant data.

[0035] In some embodiments of the application, a resource allocation strategy is defined, and a strategy space corresponding to each category of to-be-processed power plant data is constructed, comprising:

[0036] Set the number corresponding to the resource setting unit fraction corresponding to different power plant data processing resource categories, and set the resource allocation strategy to be how many fractions;

[0037] According to the resource shares in the historical records, a strategy space corresponding to each category of to-be-processed power plant data is constructed, denoted as a first strategy space;

[0038] The resource settings corresponding to different power plant data processing resource categories are set to corresponding proportions, and the resource allocation strategy is set to the proportion size;

[0039] According to the proportion sizes of different resources in the historical records, a strategy space corresponding to each category of to-be-processed power plant data is constructed, denoted as a second strategy space;

[0040] By comparing the first strategy space and the second strategy space, if the size difference between the first strategy space and the second strategy space exceeds a first space size threshold, the larger one of the first strategy space and the second strategy space is taken as the strategy space;

[0041] Otherwise, a first adjustment coefficient and a second adjustment coefficient are determined 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;

[0042] The first strategy space is adjusted based on the first adjustment coefficient, and the second strategy space is adjusted based on the second adjustment coefficient;

[0043] The one of the adjusted first strategy space and the adjusted second strategy space that is relatively close to a second space size threshold is taken as the strategy space.

[0044] In some embodiments of the present application, the adaptability level of the resource allocation strategy is determined, and the strategy space is divided accordingly to obtain a plurality of strategy subspaces with different priorities, including:

[0045] A plurality of power plant data processing effect indicators are obtained, and each power plant data processing effect indicator corresponding to the resource allocation strategy is predicted to obtain a comprehensive indicator;

[0046] The adaptability level of the resource allocation strategy is determined based on the comprehensive indicator corresponding to the resource allocation strategy, and the strategy space is divided according to the different adaptability levels of different resource allocation strategies to obtain a plurality of strategy subspaces with different priorities.

[0047] In some embodiments of the present application, the plurality of strategy subspaces with different priorities are sequentially input into a game model, and the optimal solution of the corresponding order is determined according to a utility function until the input of the strategy subspaces is stopped in accordance with the requirements of the game, including:

[0048] The plurality of categories of to-be-processed power plant data are taken as participants in the game;

[0049] The different strategy subspaces are sequentially input into a preset competitive game model based on the priority order;

[0050] The target revenue corresponding to each priority is set according to the number of priorities.

[0051] After each time the strategy subspace is put in, a Nash equilibrium solution is determined;

[0052] If the number of Nash equilibrium solutions is unique, whether the difference between the income of the Nash equilibrium solution and the target income corresponding to the priority meets the preset difference value is calculated, if yes, the Nash equilibrium solution is taken as the optimal solution, and the input of the strategy subspace is stopped, and if no, the input of the strategy subspace is continued;

[0053] If the number of Nash equilibrium solutions is not unique, whether the difference between the Nash equilibrium solution with the highest income and the target income corresponding to the priority meets the preset difference value is calculated, if yes, the Nash equilibrium solution is taken as the optimal solution, and the input of the strategy subspace is stopped, and if no, the input of the strategy subspace is continued.

[0054] Correspondingly, the application also provides an intelligent power plant data processing system, which comprises:

[0055] A classification module is configured to obtain to-be-processed power plant data, classify the to-be-processed power plant data, and obtain multiple categories of to-be-processed power plant data;

[0056] A corresponding module is configured to obtain power plant data processing resources, and determine the type of power plant data processing resources corresponding to each category of to-be-processed power plant data according to the multiple categories of to-be-processed power plant data;

[0057] A definition module is configured to define the utility function of each category of to-be-processed power plant data based on the multiple categories of to-be-processed power plant data and the importance of the type of power plant data processing resources corresponding to each category of to-be-processed power plant data;

[0058] A construction module is configured to define a resource allocation strategy, and construct the strategy space corresponding to each category of to-be-processed power plant data;

[0059] A division module is configured to determine the adaptability level of the resource allocation strategy, and divide the strategy space according to the adaptability level, to obtain multiple strategy subspaces with different priorities;

[0060] A game module is configured to put the multiple strategy subspaces with different priorities into a game model in sequence, and determine the optimal solution of the corresponding order according to the utility function, until the input of the strategy subspace is stopped when the game requirement is met;

[0061] A processing module is configured to reasonably allocate the power plant data processing resources required by the to-be-processed power plant data by using the optimal solution obtained through the game.

[0062] By applying the above technical scheme, the power plant data to be processed is obtained, the power plant data to be processed is classified to obtain multi-category power plant data to be processed; power plant data processing resources are obtained, and the type of power plant data processing resources corresponding to each category of power plant data to be processed is determined according to the multi-category power plant data to be processed; the utility function of each category of power plant data to be processed is defined based on the multi-category power plant data to be processed and the importance degree of the respective corresponding type of power plant data processing resources; a resource allocation strategy is defined, and a strategy space corresponding to each category of power plant data to be processed is constructed; the adaptability level of the resource allocation strategy is determined, and the strategy space is divided accordingly to obtain multiple strategy subspaces with different priorities; the multiple strategy subspaces with different priorities are sequentially input into a game model, and the optimal solution of the corresponding order is determined according to the utility function, until the input of the strategy subspaces is stopped in accordance with the requirements of the game; and the optimal solution obtained by the game is used to reasonably allocate the power plant data processing resources required by the power plant data to be processed. The utility function of each category of power plant data to be processed is defined by the importance degree of the multi-category power plant data to be processed and the respective corresponding type of power plant data processing resources, and the strategy space corresponding to each category of power plant data to be processed is constructed and divided, which improves the reliability of the data processing resource game, ensures the rationality of the processing resource allocation, and thus improves the utilization rate and effectiveness of the processing resources. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0064] Figure 1 A flowchart of a power plant data intelligent processing method according to an embodiment of the present application is shown;

[0065] Figure 2 A structural diagram of a power plant data intelligent processing system according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0067] An embodiment of the present application provides a power plant data intelligent processing method, as shown in Figure 1 The method comprises the following steps:

[0068] In step S101, the to-be-processed power plant data is obtained, and the to-be-processed power plant data is classified to obtain multi-category to-be-processed power plant data.

[0069] In this embodiment, the to-be-processed power plant data is classified according to features, so as to serve as a participant in subsequent game.

[0070] In some embodiments of the present application, the to-be-processed power plant data is classified to obtain multi-category to-be-processed power plant data, including:

[0071] All data features in the to-be-processed power plant data are extracted, and all task requirements in power plant data processing are received;

[0072] The relevance of each data feature and each task requirement is calculated respectively, and a data feature with a relevance exceeding a first relevance threshold is recorded as a meaningful feature;

[0073] A data feature with a relevance exceeding a second relevance threshold and not exceeding the first relevance threshold is recorded as a to-be-checked feature;

[0074] A difference between the relevance of the to-be-checked feature and the second relevance threshold is recorded as a first difference, and a difference between the relevance of the to-be-checked feature and the first relevance threshold is recorded as a second difference;

[0075] An update coefficient is determined according to a ratio of the first difference and the second difference, and the relevance of the to-be-checked feature is updated to obtain a new relevance;

[0076] If the new relevance exceeds a third relevance threshold, the to-be-checked feature is taken as the meaningful feature;

[0077] The meaningful features are clustered by a preset clustering algorithm, and data classification is performed in a semi-supervised learning manner to obtain multi-category to-be-processed power plant data.

[0078] In this embodiment, after the task requirements are quantitatively processed, the relevance of each data feature and each task requirement is calculated. In this way, meaningful features are screened out, and meaningless features are removed.

[0079] In this embodiment, the update coefficient updates the relevance of the to-be-checked feature to obtain a new relevance. New relevance = update coefficient * relevance.

[0080] In this embodiment, the first difference, the second difference, and the update coefficient effectively screen out meaningful features, improve the adaptability and reliability of the features, and provide a solid foundation for classification.

[0081] In this embodiment, the clustering and semi-supervised learning manner are conventional techniques in the field, and will not be described here.

[0082] In step S102, the power plant data processing resource is obtained, and the power plant data processing resource category corresponding to each category of to-be-processed power plant data is determined according to the to-be-processed power plant data of multiple categories.

[0083] In this embodiment, the power plant data processing resource is a data processing required resource such as a computing resource, a storage resource, and a bandwidth resource. The resource category corresponding to each category of data is determined.

[0084] In some embodiments of the present application, the power plant data processing resource category corresponding to each category of to-be-processed power plant data is determined according to the to-be-processed power plant data of multiple categories, including:

[0085] The data processing record of each category of to-be-processed power plant data is obtained, and the power plant data processing resource category involved in each category of to-be-processed power plant data multiple times is determined;

[0086] If the power plant data processing resource categories involved in each category of to-be-processed power plant data multiple times are all the same, a corresponding relationship is established between the category of to-be-processed power plant data and the power plant data processing resource category involved;

[0087] Otherwise, the corresponding relationship is established according to the power plant data processing resource categories involved in each category of to-be-processed power plant data multiple times;

[0088] If the number of different times of the power plant data processing resource categories involved in each category of to-be-processed power plant data multiple times exceeds a threshold, the union set of the power plant data processing resource categories involved in each category of to-be-processed power plant data multiple times is taken as the corresponding relationship of the category of to-be-processed power plant data;

[0089] Otherwise, the power plant data processing resource category with the largest number of same times in the power plant data processing resource categories involved in each category of to-be-processed power plant data multiple times is taken as the corresponding relationship of the category of to-be-processed power plant data.

[0090] In this embodiment, by establishing the corresponding relationship between the accurate data category and the resource category, the subsequent competitive game of the game model is facilitated.

[0091] In step S103, the utility function of each category of to-be-processed power plant data is defined based on the importance of the to-be-processed power plant data of multiple categories and the power plant data processing resource categories corresponding thereto.

[0092] In this embodiment, the utility function plays a key role in resource game and decision-making problems, and it is used to quantify the preference degree of an individual or a participant to different resource allocation schemes. The significance of the utility function lies in measuring the preferences of participants, guiding resource allocation, supporting decision-making processes, etc.

[0093] In some embodiments of the present application, the method further includes determining the importance of the power plant data processing resource category, including:

[0094] determining the multi-category to-be-processed power plant data corresponding to each power plant data processing resource, denoted as first corresponding to-be-processed power plant data;

[0095] obtaining a plurality of important factors of the first corresponding to-be-processed power plant data, and determining the importance degree of the power plant data processing resource category;

[0096]

[0097] wherein P is the importance degree of the power plant data processing resource category, n is the number of important factors, is the influence weight corresponding to the ith important factor, is the parameter size corresponding to the ith important factor, exp is an exponential function, and m is the number of important factors exceeding the respective initial values, is the correction weight corresponding to the jth important factor exceeding the respective initial values, is the parameter size corresponding to the jth important factor exceeding the respective initial values, is the initial value size corresponding to the jth important factor, and k is a preset constant.

[0098] In this embodiment, the importance degree of the power plant data processing resource category can be understood as the importance degree of the processing resource of this category.

[0099] In this embodiment, the multi-category to-be-processed power plant data corresponding to each power plant data processing resource is determined, and any data having a corresponding relationship with each power plant data processing resource is the first corresponding to-be-processed power plant data.

[0100] In this embodiment, the plurality of important factors include data size, data processing timeliness requirement, system performance requirement, etc.

[0101] In this embodiment, represents the correction of all influence quantities by the factors exceeding the initial values. = 0, = 1, and no correction is performed on .

[0102] In some embodiments of the present application, the utility function of each category to-be-processed power plant data is defined based on the multi-category to-be-processed power plant data and the importance degree of the power plant data processing resource category corresponding to each to-be-processed power plant data, including:

[0103] determining the initial preference weight of each category to-be-processed power plant data for different power plant data processing resource categories according to the importance degree of the power plant data processing resource category;

[0104] ​And the initial preference weight is corrected according to the data processing record of each category of to-be-processed power plant data, to obtain the utility function of each category of to-be-processed power plant data.

[0105] In this embodiment, for example, the utility function of a certain to-be-processed data is, , which represents the satisfaction degree of a certain to-be-processed data in using three kinds of processing resources. , , respectively represent the initial preference weight corresponding to each. A correction coefficient is determined according to the data processing record of each category of to-be-processed power plant data, and the correction coefficient * initial preference weight = updated weight, to obtain a brand new utility function.

[0106] Step S104, define the resource allocation strategy, and construct the strategy space corresponding to each category of to-be-processed power plant data.

[0107] In this embodiment, the resource allocation strategy can be understood as the interval of the variable, that is, the interval range of the processing resource share or proportion. The strategy space is the interval range of the variable.

[0108] In some embodiments of the application, defining the resource allocation strategy and constructing the strategy space corresponding to each category of to-be-processed power plant data comprises:

[0109] Setting the number of resource setting units corresponding to each category of to-be-processed power plant data corresponding to different kinds of power plant data processing resources, and setting the resource allocation strategy as the number of shares;

[0110] According to the resource share in the historical record, the strategy space corresponding to each category of to-be-processed power plant data is constructed, which is recorded as the first strategy space;

[0111] Setting the proportion of resource settings corresponding to each category of to-be-processed power plant data corresponding to different kinds of power plant data processing resources, and setting the resource allocation strategy as the proportion size;

[0112] According to the historical record of different resource proportion sizes, the strategy space corresponding to each category of to-be-processed power plant data is constructed, which is recorded as the second strategy space;

[0113] Compare the first strategy space and the second strategy space, if the size difference between the first strategy space and the second strategy space exceeds the first space size threshold, the larger one of the first strategy space and the second strategy space is taken as the strategy space;

[0114] Otherwise, according to the difference between the first strategy space and the first space size threshold, the difference between the second strategy space and the first space size threshold, the first adjustment coefficient and the second adjustment coefficient are determined respectively;

[0115] adjust the first strategy space based on a first adjustment coefficient and adjust the second strategy space based on a second adjustment coefficient;

[0116] The strategy space is determined based on the first adjusted strategy space and the second adjusted strategy space that are close to the second space size threshold.

[0117] In this embodiment, the strategy space or the space size is the interval range size of the variable.

[0118] In this embodiment, the quantity corresponding to the resource setting unit share of different power plant data processing resource categories is different for different processing resources, and therefore the variable needs to be unified to a certain extent, that is, how many quantities of processing resources are set as one share of the resource. The corresponding proportion of the resource setting of different power plant data processing resource categories is used as the variable.

[0119] In this embodiment, the strategy space corresponding to each category of to-be-processed power plant data is constructed according to the resource share in the historical record, which can be understood as constructing the variable range interval of each category of to-be-processed data.

[0120] In step S105, the adaptability level of the resource allocation strategy is determined, and the strategy space is divided based on the adaptability level, to obtain a plurality of strategy subspaces with different priorities.

[0121] In this embodiment, the adaptability level of the resource allocation strategy is determined, which is equivalent to determining the adaptability level corresponding to different variable intervals. The overall variable interval is divided based on this, to obtain a plurality of strategy subspaces with different priorities.

[0122] In some embodiments of the present application, the adaptability level of the resource allocation strategy is determined, and the strategy space is divided based on the adaptability level, to obtain a plurality of strategy subspaces with different priorities, including:

[0123] A plurality of power plant data processing effect indicators are obtained, each power plant data processing effect indicator corresponding to the resource allocation strategy is predicted, and a comprehensive indicator is obtained;

[0124] The adaptability level is determined based on the comprehensive indicator corresponding to the resource allocation strategy, different resource allocation strategies have different adaptability levels, and the strategy space is divided based on this, to obtain a plurality of strategy subspaces with different priorities.

[0125] In this embodiment, the plurality of power plant data processing effect indicators include processing efficiency, processing quality, and the like.

[0126] In this embodiment, the adaptability level is determined based on the comprehensive indicator corresponding to the resource allocation strategy, the higher the comprehensive indicator, the higher the adaptability level, and the corresponding priority is earlier.

[0127] In this embodiment, the significance of dividing the strategy space is to obtain the game result more quickly, because power plant data processing often has certain requirements for timeliness.

[0128] In step S106, the plurality of strategy subspaces with different priorities are sequentially input into the game model, and the optimal solution corresponding to the order is determined according to the utility function, until the input of the strategy subspace is stopped in accordance with the game requirements.

[0129] In this embodiment, in order to obtain the game result, that is, the strategy more quickly and accurately, the sequential input into the preset game model is stopped when the optimal solution meeting the requirements is obtained, so as to ensure the timeliness of power plant data processing.

[0130] In some embodiments of the present application, the plurality of strategy subspaces with different priorities are sequentially input into the game model, and the optimal solution corresponding to the order is determined according to the utility function, until the input of the strategy subspace is stopped in accordance with the game requirements, including:

[0131] Taking the plurality of categories of power plant data to be processed as participants in the game;

[0132] The different strategy subspaces are sequentially input into the preset competitive game model based on the priority order;

[0133] According to the number of priorities, the target revenue corresponding to each priority is set;

[0134] After each input of the strategy subspace is completed, the Nash equilibrium solution is determined;

[0135] If the number of Nash equilibrium solutions is unique, whether the difference between the revenue of the Nash equilibrium solution and the target revenue corresponding to the priority meets the preset difference value is calculated, if yes, the Nash equilibrium solution is taken as the optimal solution, and the input of the strategy subspace is stopped, and if no, the input of the strategy subspace is continued;

[0136] If the number of Nash equilibrium solutions is not unique, whether the difference between the Nash equilibrium solution with the highest revenue and the target revenue corresponding to the priority meets the preset difference value is calculated, if yes, the Nash equilibrium solution is taken as the optimal solution, and the input of the strategy subspace is stopped, and if no, the input of the strategy subspace is continued.

[0137] In this embodiment, the specific game model and the calculation method of the revenue are conventional techniques in the field, and will not be described here.

[0138] In step S107, the optimal solution obtained through the game is used to reasonably allocate the power plant data processing resources required by the power plant data to be processed.

[0139] By applying the above technical solutions, the power plant data to be processed is obtained, the power plant data to be processed is classified to obtain multi-category power plant data to be processed, power plant data processing resources are obtained, and the type of power plant data processing resources corresponding to each category of power plant data to be processed is determined according to the multi-category power plant data to be processed. The utility function of each category of power plant data to be processed is defined based on the multi-category power plant data to be processed and the importance of the type of power plant data processing resources corresponding to each category of power plant data to be processed. A resource allocation strategy is defined, and a strategy space corresponding to each category of power plant data to be processed is constructed. The adaptability level of the resource allocation strategy is determined, and the strategy space is divided accordingly to obtain multiple strategy subspaces with different priorities. The multiple strategy subspaces with different priorities are sequentially input into a game model, and the optimal solution of the corresponding order is determined according to the utility function, until the input of the strategy subspaces stops in accordance with the requirements of the game. The optimal solution obtained by the game is used to reasonably allocate the power plant data processing resources required by the power plant data to be processed. The utility function of each category of power plant data to be processed is defined based on the importance of the multi-category power plant data to be processed and the type of power plant data processing resources corresponding to each category of power plant data to be processed, and the strategy space corresponding to each category of power plant data to be processed is constructed and divided, which improves the reliability of the data processing resource game and ensures the rationality of the processing resource allocation, thereby improving the utilization rate and effectiveness of the processing resources.

[0140] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by hardware, or by means of software and necessary general hardware platform. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.), and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present application.

[0141] In order to further illustrate the technical idea of the present application, the technical solutions of the present application will be described in conjunction with specific application scenarios.

[0142] Correspondingly, the present application also provides an intelligent power plant data processing system, as shown in Figure 2 The system comprises:

[0143] The classification module 201 is configured to obtain the power plant data to be processed, classify the power plant data to be processed, and obtain multi-category power plant data to be processed.

[0144] The corresponding module 202 is configured to obtain power plant data processing resources, and determine the type of power plant data processing resources corresponding to each category of power plant data to be processed according to the multi-category power plant data to be processed.

[0145] The definition module 203 is configured to define the utility function of each category of the to-be-processed power plant data based on the to-be-processed power plant data of multiple categories and the importance of the respective corresponding power plant data processing resource category of the to-be-processed power plant data;

[0146] The construction module 204 is configured to define a resource allocation strategy and construct a strategy space corresponding to each category of the to-be-processed power plant data.

[0147] The division module 205 is configured to determine the adaptability level of the resource allocation strategy and divide the strategy space according to the adaptability level to obtain multiple strategy subspaces with different priorities.

[0148] The game module 206 is configured to sequentially input the multiple strategy subspaces with different priorities into a game model and determine the optimal solution of the corresponding order according to the utility function until the input of the strategy subspaces is stopped in accordance with the game requirement.

[0149] The processing module 207 is configured to reasonably allocate the power plant data processing resources required by the to-be-processed power plant data through the optimal solution obtained by the game.

[0150] Those skilled in the art can understand that the modules in the system in the implementation scenario can be distributed in the system in the implementation scenario according to the description of the implementation scenario, or can be changed to be located in one or more systems different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0151] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art can understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not drive the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A power plant data intelligent processing method, characterized in that, The method comprises: acquiring power plant data to be processed, classifying the power plant data to be processed to obtain multi-category power plant data to be processed; acquiring power plant data processing resources, and determining the type of power plant data processing resources corresponding to each category of power plant data to be processed according to the multi-category power plant data to be processed; defining the utility function of each category of power plant data to be processed based on the multi-category power plant data to be processed and the importance of the type of power plant data processing resources corresponding to each category of power plant data to be processed; defining a resource allocation strategy and constructing a strategy space corresponding to each category of power plant data to be processed; determining the adaptability level of the resource allocation strategy, and dividing the strategy space according to the adaptability level to obtain multiple strategy subspaces with different priorities; sequentially inputting the multiple strategy subspaces with different priorities into a game model, and determining the optimal solution of the corresponding order according to the utility function until the input of the strategy subspaces is stopped in accordance with the requirements of the game; allocating the power plant data processing resources required by the power plant data to be processed through the optimal solution obtained by the game; classifying the power plant data to be processed to obtain multi-category power plant data to be processed, comprising: extracting all data features in the power plant data to be processed, and receiving all task requirements in the power plant data processing; calculating the correlation of each data feature with each task requirement respectively, and recording the data features with a correlation exceeding a first correlation threshold as significant features; recording the data features with a correlation exceeding a second correlation threshold and not exceeding the first correlation threshold as to-be-checked features; recording the difference between the correlation of the to-be-checked feature and the second correlation threshold as a first difference, and recording the difference between the correlation of the to-be-checked feature and the first correlation threshold as a second difference; determining an update coefficient according to the ratio of the first difference to the second difference, and updating the correlation of the to-be-checked feature to obtain a new correlation; if the new correlation exceeds a third correlation threshold, the to-be-checked feature is regarded as a significant feature; performing clustering on the significant features through a preset clustering algorithm, and performing data classification in a semi-supervised learning manner to obtain multi-category power plant data to be processed.

2. The power plant data intelligent processing method of claim 1, wherein, and determining the type of power plant data processing resources corresponding to each category of power plant data to be processed according to the multi-category power plant data to be processed, comprising: acquiring the data processing records of each category of power plant data to be processed, and determining the types of power plant data processing resources involved in each category of power plant data to be processed multiple times; if the types of power plant data processing resources involved in each category of power plant data to be processed multiple times are all the same, a corresponding relationship is established between the category of power plant data to be processed and the types of power plant data processing resources involved; otherwise, the corresponding relationship is established according to the types of power plant data processing resources involved in each category of power plant data to be processed multiple times; if the number of different types of power plant data processing resources involved in each category of power plant data to be processed multiple times exceeds a threshold, the union of the types of power plant data processing resources involved in each category of power plant data to be processed multiple times is taken as the corresponding relationship of the category of power plant data to be processed; otherwise, the type of power plant data processing resources with the largest number of times in the types of power plant data processing resources involved in each category of power plant data to be processed multiple times is taken as the corresponding relationship of the category of power plant data to be processed.

3. The power plant data intelligent processing method of claim 1, wherein, The method further comprises determining the importance of the power plant data processing resource category, comprising: determining the corresponding multi-category to-be-processed power plant data of each power plant data processing resource, denoted as the first corresponding to-be-processed power plant data; obtaining a plurality of important factors of the first corresponding to-be-processed power plant data, and determining the importance of the power plant data processing resource category; ； Wherein, P is the importance of power plant data processing resource category, n is the number of important factors, is the influence weight corresponding to the i th important factor, is the parameter size corresponding to the i th important factor, exp is an exponential function, and m is the number of important factors that exceed the respective initial values, is the correction weight corresponding to the j th important factor that exceeds the respective initial value, is the parameter size corresponding to the j th important factor that exceeds the respective initial value, is the initial value size corresponding to the j th important factor, and k is a preset constant.

4. The power plant data intelligent processing method of claim 3, wherein, defining the utility function of each category of to-be-processed power plant data based on the multi-category to-be-processed power plant data and the importance of the corresponding power plant data processing resource category of each to-be-processed power plant data, comprising: determining the initial preference weight of each category of to-be-processed power plant data for different power plant data processing resource categories according to the importance of the power plant data processing resource category; and correcting the initial preference weight according to the data processing record of each category of to-be-processed power plant data to obtain the utility function of each category of to-be-processed power plant data.

5. The power plant data intelligent processing method of claim 1, wherein, defining a resource allocation strategy and constructing a strategy space corresponding to each category of to-be-processed power plant data, comprising: setting the number of resource setting units corresponding to different power plant data processing resource categories to a certain number, and setting the resource allocation strategy to a certain number; constructing the strategy space corresponding to each category of to-be-processed power plant data according to the resource number in the historical record, denoted as the first strategy space; setting the corresponding proportion of resource settings corresponding to different power plant data processing resource categories, and setting the resource allocation strategy to a certain proportion; constructing the strategy space corresponding to each category of to-be-processed power plant data according to the different resource proportion in the historical record, denoted as the second strategy space; comparing the first strategy space and the second strategy space, if the size difference between the first strategy space and the second strategy space exceeds the first space size threshold, the larger one of the first strategy space and the second strategy space is taken as the strategy space; otherwise, 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, the first adjustment coefficient and the second adjustment coefficient are determined respectively; adjusting the first strategy space based on the first adjustment coefficient, and adjusting the second strategy space based on the second adjustment coefficient; taking the one closer to the second space size threshold from the adjusted first strategy space and the adjusted second strategy space as the strategy space.

6. The power plant data intelligent processing method of claim 1, wherein, 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 priority levels, comprising: obtaining a plurality of power plant data processing effect indicators, predicting each power plant data processing effect indicator corresponding to the resource allocation strategy, and thus obtaining a comprehensive indicator; determining the adaptability level based on the comprehensive indicator corresponding to the resource allocation strategy, and different resource allocation strategies have different adaptability levels, thereby dividing the strategy space to obtain a plurality of strategy subspaces with different priority levels.

7. The power plant data intelligent processing method of claim 6 wherein, putting the plurality of strategy subspaces with different priority levels into the game model in turn, and determining the optimal solution of the corresponding order according to the utility function, until the input of the strategy subspace is stopped in accordance with the requirements of the game, comprising: taking the multi-category to-be-processed power plant data as the participants of the game; putting different strategy subspaces into the preset competitive game model in turn based on the priority order; setting the target income corresponding to each priority level according to the number of priority levels; After each strategy subspace investment is completed, a Nash equilibrium solution is determined; If the number of Nash equilibrium solutions is unique, whether the difference between the income of the Nash equilibrium solution and the target income corresponding to the priority meets the preset difference value is calculated, if yes, the Nash equilibrium solution is taken as the optimal solution, and the investment of the strategy subspace is stopped, if no, the investment of the strategy subspace is continued; If the number of Nash equilibrium solutions is not unique, whether the difference between the Nash equilibrium solution with the highest income and the target income corresponding to the priority meets the preset difference value is calculated, if yes, the Nash equilibrium solution is taken as the optimal solution, and the investment of the strategy subspace is stopped, if no, the investment of the strategy subspace is continued.

8. A power plant data intelligent processing system, characterized by, The system uses the power plant data intelligent processing method in any one of claims 1-7, and the system comprises: A classification module is configured to obtain to-be-processed power plant data, classify the to-be-processed power plant data, and obtain multi-category to-be-processed power plant data; A corresponding module is configured to obtain power plant data processing resources and determine the type of power plant data processing resources corresponding to each category of to-be-processed power plant data according to the multi-category to-be-processed power plant data; A definition module is configured to define the utility function of each category of to-be-processed power plant data based on the importance of the multi-category to-be-processed power plant data and the type of power plant data processing resources corresponding to each category of to-be-processed power plant data; A construction module is configured to define a resource allocation strategy and construct a strategy space corresponding to each category of to-be-processed power plant data; A division module is configured to determine the adaptability level of the resource allocation strategy and divide the strategy space according to the adaptability level to obtain multiple strategy subspaces with different priorities; A game module is configured to sequentially input the multiple strategy subspaces with different priorities into a game model and determine the optimal solution in the corresponding order according to the utility function until the investment of the strategy subspace is stopped when the game requirement is met; A processing module is configured to reasonably allocate the power plant data processing resources required by the to-be-processed power plant data through the optimal solution obtained by the game.

Images