Equipment power consumption control method and device based on service awareness
By perceiving and analyzing the device's service transmission data and integrating channel control parameters, and using a decision tree model to dynamically adjust the power consumption mode, the problem of balancing device power consumption and service performance in traditional methods is solved, achieving precise power consumption control and effective adaptation to service needs.
Patent Information
- Application Number
- CN202510744480.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-05
- Publication Date
- 2025-09-19
AI Technical Summary
Existing technologies make it difficult to effectively reduce device power consumption while ensuring business performance. Traditional device power consumption control methods cannot adapt to changes in business needs, resulting in devices remaining in working condition when business demand is low, resulting in unreasonable power consumption.
By performing service perception analysis on the service transmission data of the controlled device, obtaining service characteristic parameters and channel control parameters, constructing a ternary table and fusion feature vector, and using the decision tree model to train the power consumption control model, the power consumption mode of the device can be dynamically adjusted by combining the predictive control scheme and the ternary table.
It achieves precise control of equipment power consumption while ensuring business performance, adapting to changes in business needs and reducing unnecessary power consumption.
Smart Images
Figure CN120676437A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of device control, and in particular to a method and apparatus for device power consumption control based on service perception. Background Art
[0002] In the power grid sector, properly controlling the power consumption of service-related equipment has long been a pressing technical challenge. On the one hand, service-related equipment frequently receives and processes a wide range of information. As the amount of information increases, so does the power consumption of the equipment. On the other hand, as the types and number of services increase, a trade-off becomes necessary between service performance and equipment power consumption. Currently, there is no solution for reducing power consumption while maintaining service performance.
[0003] Traditional device power consumption control methods are typically based on a relatively fixed device sleep strategy. Typically, this involves setting specific sleep periods, forcing the device to sleep during those periods and remaining operational during the remaining periods. While simple and easy to implement, these traditional methods struggle to adapt to changing service requirements, making it difficult to guarantee service performance. Furthermore, this inability to adapt to changing service requirements means that the device may remain operational during periods of low service demand, resulting in inappropriate power consumption. Therefore, reducing device power consumption while ensuring service performance remains a pressing issue in existing technologies. Summary of the Invention
[0004] The present application provides a device power consumption control method and apparatus based on service perception to solve the technical problem in the prior art that it is impossible to simultaneously ensure service performance and control device power consumption.
[0005] According to a first aspect of the embodiments of the present application, a method for controlling device power consumption based on service awareness is provided, comprising:
[0006] Perform business perception analysis on the business transmission data of the controlled device to obtain business characteristic parameters;
[0007] Acquire channel control parameters of the channel where the service transmission data is located, and construct a ternary table according to the channel control parameters;
[0008] According to the timestamp of the data packet containing the service transmission data, an association is established between the service characteristic parameter and the channel control parameter to obtain a fused feature vector;
[0009] Inputting the fused feature vector into a preset power consumption control model to obtain a predictive control scheme; wherein the power consumption control model is obtained based on decision tree model training;
[0010] According to the power consumption mode of the device to be controlled, combined with the predictive control scheme and the ternary table, a power consumption control scheme is obtained, and the device to be controlled is controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled; wherein, the power consumption mode includes a first power consumption mode and a second power consumption mode; the power consumption of the first power consumption mode is not less than that of the second power consumption mode; the power consumption control scheme includes a mode control instruction and a sleep timer.
[0011] This application first performs a service perception analysis on the service transmission data of the device to be controlled to obtain service characteristic parameters, then obtains the channel control parameters of the channel where it is located, and constructs a ternary table, and then constructs the association between the service characteristic parameters and the channel control parameters to obtain a fusion feature vector, which can accurately obtain the service characteristics corresponding to the device to be controlled, and then obtain a predictive control scheme through a power consumption control model trained based on a decision tree model. It is ensured that the obtained predictive control scheme controls the power consumption of the device while combining the service characteristics to ensure service performance; then, according to the power consumption mode of the device to be controlled, the power consumption control scheme is obtained by combining the predictive control scheme and the ternary table, and then the device to be controlled is controlled, and the power consumption control scheme is obtained through the power consumption mode. On the basis of the predictive control scheme, the power consumption of the device is further more accurately controlled, thereby completing accurate control of the power consumption of the device while ensuring service performance.
[0012] In certain embodiments of the present application, performing service-aware analysis on service transmission data of the device to be controlled to obtain service characteristic parameters specifically includes:
[0013] Performing service perception on the device to be controlled to obtain original service transmission data, and segmenting the original service transmission data according to preset time lengths to obtain multiple groups of time window data;
[0014] Count the fluctuations of business data volume in each time window data group to obtain multiple groups of business fluctuation characteristics;
[0015] Perform correlation feature analysis on the business data volume of each time window data group and the adjacent time window data group to obtain multiple groups of business continuity features;
[0016] The multiple groups of business fluctuation characteristics and the multiple groups of business continuity characteristics are combined and spliced in chronological order to obtain business characteristic parameters.
[0017] This application first performs business perception on the device to be controlled to obtain the original business transmission data, and divides it according to the preset time length to obtain multiple groups of time window data, which is conducive to independent and separate research on each group of data, and then statistically analyzes the fluctuation of the business data volume in each group of data and the correlation characteristics with the adjacent groups of data, to obtain multiple groups of business fluctuation characteristics and multiple groups of business continuity characteristics, and then combine and splice them in chronological order to obtain business characteristic parameters, which can respectively obtain and study the fluctuation characteristics and continuity characteristics of the business transmission data, thereby accurately obtaining the business characteristics of the device to be controlled, and thus improving the accuracy of the obtained predictive control scheme.
[0018] In certain embodiments of the present application, constructing an association between the service characteristic parameter and the channel control parameter according to the timestamp of the data packet containing the service transmission data to obtain a fused feature vector specifically includes:
[0019] Constructing a parameter mapping table between the service characteristic parameters and the channel control parameters in a time dimension according to the timestamp of the data packet containing the service transmission data;
[0020] According to the parameter mapping table, correlation feature analysis is performed on the service feature parameters and the channel control parameters to obtain a fusion feature vector.
[0021] This application first constructs a parameter mapping table of service characteristic parameters and channel control parameters in the time dimension based on the timestamp of the service transmission data, and then performs correlation feature analysis to obtain a fused feature vector. Through the parameters of the device to be controlled in terms of service transmission and channel control, the service characteristics of the device to be controlled can be accurately reflected, thereby improving the accuracy of the obtained prediction control scheme when making predictions based on the fused feature vector.
[0022] In certain embodiments of the present application, the power consumption control scheme is obtained based on the power consumption mode of the device to be controlled, combined with the predictive control scheme and the ternary table, and the device to be controlled is controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled, specifically including:
[0023] When the device to be controlled is in a first power consumption mode, determining an end time of the first power consumption mode according to the ternary table, and correcting a mode control instruction and a sleep timing in the predictive control scheme according to the ternary table and the end time to obtain a power consumption control scheme;
[0024] When the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme, the power consumption mode of the device to be controlled is changed according to the mode control instruction of the power consumption control scheme.
[0025] When the device to be controlled is in the first power consumption mode, the present application determines the end time of the first power consumption mode according to the ternary table, and then corrects the mode control instructions and sleep timing in the predictive control scheme, so as to control the power consumption of the device to be controlled. The predictive control scheme can be corrected in combination with the current mode of the device to be controlled to make it more consistent with the actual power consumption control of the device to be controlled, thereby achieving precise control of the power consumption of the device to be controlled.
[0026] In certain embodiments of the present application, the power consumption control scheme is obtained based on the power consumption mode of the device to be controlled, combined with the predictive control scheme and the ternary table, and the device to be controlled is controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled, specifically including:
[0027] When the device to be controlled is in the second power consumption mode, the mode control instruction in the prediction control scheme is corrected according to the ternary table to obtain a power consumption control scheme;
[0028] When the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme, the power consumption mode of the device to be controlled is set to the first power consumption mode according to the mode control instruction of the power consumption control scheme.
[0029] When the device to be controlled is in the second power consumption mode, the present application corrects the mode control instruction in the predictive control scheme according to the ternary table, thereby controlling the power consumption of the device to be controlled. The predictive control scheme can be corrected in combination with the current mode of the device to be controlled to make it more consistent with the actual power consumption control of the device to be controlled, thereby achieving precise control of the power consumption of the device to be controlled.
[0030] According to a second aspect of the embodiments of the present application, there is provided a device power consumption control apparatus based on service perception, comprising a service perception analysis module, a channel parameter acquisition module, a parameter association construction module, a control scheme prediction module and a device power consumption control module;
[0031] The service perception analysis module is used to perform service perception analysis on the service transmission data of the control device to obtain service characteristic parameters;
[0032] The channel parameter acquisition module is used to obtain the channel control parameters of the channel where the service transmission data is located, and to construct a ternary table according to the channel control parameters;
[0033] The parameter association building module is used to build an association between the service characteristic parameter and the channel control parameter according to the timestamp of the data packet containing the service transmission data, so as to obtain a fusion feature vector;
[0034] The control scheme prediction module is used to input the fused feature vector into a preset power consumption control model to obtain a predicted control scheme; wherein the power consumption control model is obtained based on decision tree model training;
[0035] The device power consumption control module is used to obtain a power consumption control scheme based on the power consumption mode of the device to be controlled, in combination with the predictive control scheme and the ternary table, and control the device to be controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled; wherein, the power consumption mode includes a first power consumption mode and a second power consumption mode; the power consumption of the first power consumption mode is not less than that of the second power consumption mode; and the power consumption control scheme includes a mode control instruction and a sleep timer.
[0036] In certain embodiments of the present application, the business perception analysis module includes a data perception segmentation unit, a data fluctuation statistics unit, a data association analysis unit, and a feature splicing and combination unit;
[0037] The data sensing and splitting unit is used to perform service sensing on the device to be controlled to obtain original service transmission data, and split the original service transmission data according to preset time lengths to obtain multiple groups of time window data;
[0038] The data fluctuation statistics unit is used to respectively count the fluctuations of the business data volume in each group of time window data to obtain multiple groups of business fluctuation characteristics;
[0039] The data association analysis unit is used to perform association feature analysis on the business data volume of each group of time window data and adjacent time window data to obtain multiple groups of business continuity features;
[0040] The feature splicing and combining unit is used to sequentially combine and splice the multiple groups of business fluctuation features with the multiple groups of business continuity features in chronological order to obtain business feature parameters.
[0041] In certain embodiments of the present application, the parameter association construction module includes a parameter mapping construction unit and a parameter association analysis unit;
[0042] The parameter mapping construction unit is configured to construct a parameter mapping table between the service characteristic parameters and the channel control parameters in a time dimension according to the timestamp of the data packet containing the service transmission data;
[0043] The parameter association analysis unit is used to perform association feature analysis on the service feature parameters and the channel control parameters according to the parameter mapping table to obtain a fusion feature vector.
[0044] In certain embodiments of the present application, the device power consumption control module includes a first solution acquisition unit and a first device control unit;
[0045] The first scheme acquisition unit is configured to, when the device to be controlled is in the first power consumption mode, determine an end time of the first power consumption mode according to the ternary table, and modify a mode control instruction and a sleep timing in the predictive control scheme according to the ternary table and the end time to obtain a power consumption control scheme;
[0046] The first device control unit is configured to change the power consumption mode of the device to be controlled according to the mode control instruction of the power consumption control scheme when the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme.
[0047] In certain embodiments of the present application, the device power consumption control module includes a second solution acquisition unit and a second device control unit;
[0048] The second scheme acquisition unit is configured to, when the device to be controlled is in the second power consumption mode, correct the mode control instruction in the predictive control scheme according to the ternary table to obtain a power consumption control scheme;
[0049] The second device control unit is configured to set the power consumption mode of the device to be controlled to the first power consumption mode according to the mode control instruction of the power consumption control scheme when the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme.
[0050] This application first performs a service perception analysis on the service transmission data of the device to be controlled to obtain service characteristic parameters, then obtains the channel control parameters of the channel where it is located, and constructs a ternary table, and then constructs the association between the service characteristic parameters and the channel control parameters to obtain a fusion feature vector, which can accurately obtain the service characteristics corresponding to the device to be controlled, and then obtain a predictive control scheme through a power consumption control model trained based on a decision tree model. It is ensured that the obtained predictive control scheme controls the power consumption of the device while combining the service characteristics to ensure service performance; then, according to the power consumption mode of the device to be controlled, the power consumption control scheme is obtained by combining the predictive control scheme and the ternary table, and then the device to be controlled is controlled, and the power consumption control scheme is obtained through the power consumption mode. On the basis of the predictive control scheme, the power consumption of the device is further more accurately controlled, thereby completing accurate control of the power consumption of the device while ensuring service performance. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 : A flow chart of a method for controlling device power consumption based on service awareness according to certain embodiments of the present application;
[0052] Figure 2 : This is a module structure diagram of a device power consumption control device based on business awareness shown in certain embodiments of the present application. DETAILED DESCRIPTION
[0053] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below in conjunction with the accompanying drawings are exemplary and are only used to explain some embodiments of the present application and should not be understood as limiting the embodiments of the present application. Based on the embodiments shown in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0054] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly indicate the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of this application, unless otherwise clearly specified, "multiple" and "several" mean two or more.
[0055] Traditional device power consumption control methods are typically based on a relatively fixed device sleep strategy. Typically, this involves setting specific sleep periods, forcing the device to sleep during those periods and remaining operational during the remaining periods. While simple and easy to implement, these traditional methods struggle to adapt to changing service requirements, making it difficult to guarantee service performance. Furthermore, this inability to adapt to changing service requirements means that the device may remain operational during periods of low service demand, resulting in inappropriate power consumption. Therefore, reducing device power consumption while ensuring service performance remains a pressing issue in existing technologies.
[0056] Based on the above technical background, please refer to Figure 1 The embodiment of the present application provides a device power consumption control method based on service perception, including steps S101 to S105, each of which is as follows:
[0057] Step S101: performing service perception analysis on service transmission data of the device to be controlled to obtain service characteristic parameters.
[0058] In certain embodiments of the present application, performing service-aware analysis on service transmission data of the device to be controlled to obtain service characteristic parameters specifically includes:
[0059] Performing service perception on the device to be controlled to obtain original service transmission data, and segmenting the original service transmission data according to preset time lengths to obtain multiple groups of time window data;
[0060] Count the fluctuations of business data volume in each time window data group to obtain multiple groups of business fluctuation characteristics;
[0061] Perform correlation feature analysis on the business data volume of each time window data group and the adjacent time window data group to obtain multiple groups of business continuity features;
[0062] The multiple groups of business fluctuation characteristics and the multiple groups of business continuity characteristics are combined and spliced in chronological order to obtain business characteristic parameters.
[0063] In certain embodiments of the present application, service perception is performed on the device to be controlled to obtain original service transmission data. Available implementations include, but are not limited to: obtaining the data transmission log in the service flow of the device to be controlled as the original service transmission data; obtaining the business transaction data log between the service-associated device of the device to be controlled and the device to be controlled as the original service transmission data; monitoring the service flow of the device to be controlled and obtaining the monitoring log as the original service transmission data; and implementations implemented in different combinations of the above implementations. A preferred implementation is to obtain the data transmission log in the service flow of the device to be controlled as the original service transmission data.
[0064] In certain embodiments of the present application, in order to balance the feature significance between the business fluctuation feature and the business continuity feature obtained through analysis, one implementation of the preset time length may be 10 minutes.
[0065] This application first performs business perception on the device to be controlled to obtain the original business transmission data, and divides it according to the preset time length to obtain multiple groups of time window data, which is conducive to independent and separate research on each group of data, and then statistically analyzes the fluctuation of the business data volume in each group of data and the correlation characteristics with the adjacent groups of data, to obtain multiple groups of business fluctuation characteristics and multiple groups of business continuity characteristics, and then combine and splice them in chronological order to obtain business characteristic parameters, which can respectively obtain and study the fluctuation characteristics and continuity characteristics of the business transmission data, thereby accurately obtaining the business characteristics of the device to be controlled, and thus improving the accuracy of the obtained predictive control scheme.
[0066] Step S102: Acquire channel control parameters of the channel where the service transmission data is located, and construct a ternary table according to the channel control parameters.
[0067] Specifically, the channel control parameters include reference frame number, reference time slot number, channel control type, channel offset and channel control time, and the ternary table includes information repetition frame number, information repetition duration, channel control type, device serial number and device control mode.
[0068] Step S103: constructing an association between the service characteristic parameters and the channel control parameters according to the timestamp of the data packet containing the service transmission data, and obtaining a fusion feature vector.
[0069] In certain embodiments of the present application, constructing an association between the service characteristic parameter and the channel control parameter according to the timestamp of the data packet containing the service transmission data to obtain a fused feature vector specifically includes:
[0070] Constructing a parameter mapping table between the service characteristic parameters and the channel control parameters in a time dimension according to the timestamp of the data packet containing the service transmission data;
[0071] According to the parameter mapping table, correlation feature analysis is performed on the service feature parameters and the channel control parameters to obtain a fusion feature vector.
[0072] In certain embodiments of the present application, a parameter mapping table of the service characteristic parameters and the channel control parameters in the time dimension is constructed based on the timestamp of the data packet containing the service transmission data, specifically: based on the timestamp of the data packet containing the service transmission data, a parameter relationship between the service characteristic parameters and the channel control parameters in the time dimension is constructed, so as to construct a parameter mapping table based on the parameter relationship; wherein the parameter relationship satisfies a one-to-many relationship or a many-to-one relationship.
[0073] This application first constructs a parameter mapping table of service characteristic parameters and channel control parameters in the time dimension based on the timestamp of the service transmission data, and then performs correlation feature analysis to obtain a fused feature vector. Through the parameters of the device to be controlled in terms of service transmission and channel control, the service characteristics of the device to be controlled can be accurately reflected, thereby improving the accuracy of the obtained prediction control scheme when making predictions based on the fused feature vector.
[0074] Step S104: inputting the fused feature vector into a preset power consumption control model to obtain a predictive control scheme; wherein the power consumption control model is obtained based on decision tree model training.
[0075] In certain embodiments of the present application, the decision tree model is a model constructed based on a decision tree algorithm. The implementation of the decision tree model includes but is not limited to a model constructed based on the ID3 algorithm / C4.5 algorithm / CART algorithm / random forest algorithm / gradient boosting algorithm / XGBoost algorithm. The preferred implementation is a random forest model constructed based on the random forest algorithm.
[0076] Step S105: According to the power consumption mode of the device to be controlled, combined with the predictive control scheme and the ternary table, a power consumption control scheme is obtained, and the device to be controlled is controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled; wherein, the power consumption mode includes a first power consumption mode and a second power consumption mode; the power consumption of the first power consumption mode is not less than that of the second power consumption mode; the power consumption control scheme includes a mode control instruction and a sleep timer.
[0077] In certain embodiments of the present application, the power consumption control scheme is obtained based on the power consumption mode of the device to be controlled, combined with the predictive control scheme and the ternary table, and the device to be controlled is controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled, specifically including:
[0078] When the device to be controlled is in a first power consumption mode, determining an end time of the first power consumption mode according to the ternary table, and correcting a mode control instruction and a sleep timing in the predictive control scheme according to the ternary table and the end time to obtain a power consumption control scheme;
[0079] When the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme, the power consumption mode of the device to be controlled is changed according to the mode control instruction of the power consumption control scheme.
[0080] When the device to be controlled is in the first power consumption mode, the present application determines the end time of the first power consumption mode according to the ternary table, and then corrects the mode control instructions and sleep timing in the predictive control scheme, so as to control the power consumption of the device to be controlled. The predictive control scheme can be corrected in combination with the current mode of the device to be controlled to make it more consistent with the actual power consumption control of the device to be controlled, thereby achieving precise control of the power consumption of the device to be controlled.
[0081] In certain embodiments of the present application, the power consumption control scheme is obtained based on the power consumption mode of the device to be controlled, combined with the predictive control scheme and the ternary table, and the device to be controlled is controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled, specifically including:
[0082] When the device to be controlled is in the second power consumption mode, the mode control instruction in the prediction control scheme is corrected according to the ternary table to obtain a power consumption control scheme;
[0083] When the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme, the power consumption mode of the device to be controlled is set to the first power consumption mode according to the mode control instruction of the power consumption control scheme.
[0084] When the device to be controlled is in the second power consumption mode, the present application corrects the mode control instruction in the predictive control scheme according to the ternary table, thereby controlling the power consumption of the device to be controlled. The predictive control scheme can be corrected in combination with the current mode of the device to be controlled to make it more consistent with the actual power consumption control of the device to be controlled, thereby achieving precise control of the power consumption of the device to be controlled.
[0085] Compared with the existing technology, the present application first performs business perception analysis on the business transmission data of the device to be controlled to obtain business characteristic parameters, then obtains the channel control parameters of the channel where it is located, and constructs a ternary table, and then constructs the association between the business characteristic parameters and the channel control parameters to obtain a fusion feature vector, which can accurately obtain the business characteristics corresponding to the device to be controlled, and then obtain the prediction control scheme through the power consumption control model trained based on the decision tree model. It is ensured that the obtained prediction control scheme controls the power consumption of the device while combining the business characteristics to ensure business performance; then, according to the power consumption mode of the device to be controlled, the power consumption control scheme is obtained by combining the prediction control scheme and the ternary table, and then the device to be controlled is controlled, and the power consumption control scheme is obtained through the power consumption mode. The device is further more accurately controlled in terms of power consumption based on the prediction control scheme, thereby completing accurate control of the device power consumption while ensuring business performance.
[0086] Corresponding to the above method, see Figure 2 , the embodiment of the present application provides a device power consumption control apparatus based on service perception, including a service perception analysis module 210, a channel parameter acquisition module 220, a parameter association construction module 230, a control scheme prediction module 240 and a device power consumption control module 250;
[0087] The service perception analysis module 210 is used to perform service perception analysis on the service transmission data of the controlled device to obtain service characteristic parameters;
[0088] The channel parameter acquisition module 220 is used to obtain the channel control parameters of the channel where the service transmission data is located, and to construct a ternary table according to the channel control parameters;
[0089] The parameter association building module 230 is used to build an association between the service characteristic parameter and the channel control parameter according to the timestamp of the data packet containing the service transmission data, so as to obtain a fusion feature vector;
[0090] The control scheme prediction module 240 is used to input the fused feature vector into a preset power consumption control model to obtain a predicted control scheme; wherein the power consumption control model is obtained based on decision tree model training;
[0091] The device power consumption control module 250 is used to obtain a power consumption control scheme based on the power consumption mode of the device to be controlled, combined with the predictive control scheme and the ternary table, and control the device to be controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled; wherein, the power consumption mode includes a first power consumption mode and a second power consumption mode; the power consumption of the first power consumption mode is not less than that of the second power consumption mode; the power consumption control scheme includes a mode control instruction and a sleep timer.
[0092] In certain embodiments of the present application, the business-aware analysis module 210 includes a data-aware segmentation unit, a data fluctuation statistics unit, a data association analysis unit, and a feature splicing and combination unit;
[0093] The data sensing and splitting unit is used to perform service sensing on the device to be controlled to obtain original service transmission data, and split the original service transmission data according to preset time lengths to obtain multiple groups of time window data;
[0094] The data fluctuation statistics unit is used to respectively count the fluctuations of the business data volume in each group of time window data to obtain multiple groups of business fluctuation characteristics;
[0095] The data association analysis unit is used to perform association feature analysis on the business data volume of each group of time window data and adjacent time window data to obtain multiple groups of business continuity features;
[0096] The feature splicing and combining unit is used to sequentially combine and splice the multiple groups of business fluctuation features with the multiple groups of business continuity features in chronological order to obtain business feature parameters.
[0097] In certain embodiments of the present application, the parameter association construction module 230 includes a parameter mapping construction unit and a parameter association analysis unit;
[0098] The parameter mapping construction unit is configured to construct a parameter mapping table between the service characteristic parameters and the channel control parameters in a time dimension according to the timestamp of the data packet containing the service transmission data;
[0099] The parameter association analysis unit is used to perform association feature analysis on the service feature parameters and the channel control parameters according to the parameter mapping table to obtain a fusion feature vector.
[0100] In certain embodiments of the present application, the device power consumption control module 250 includes a first solution acquisition unit and a first device control unit;
[0101] The first scheme acquisition unit is configured to, when the device to be controlled is in the first power consumption mode, determine an end time of the first power consumption mode according to the ternary table, and modify a mode control instruction and a sleep timing in the predictive control scheme according to the ternary table and the end time to obtain a power consumption control scheme;
[0102] The first device control unit is configured to change the power consumption mode of the device to be controlled according to the mode control instruction of the power consumption control scheme when the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme.
[0103] In certain embodiments of the present application, the device power consumption control module 250 includes a second solution acquisition unit and a second device control unit;
[0104] The second scheme acquisition unit is configured to, when the device to be controlled is in the second power consumption mode, correct the mode control instruction in the predictive control scheme according to the ternary table to obtain a power consumption control scheme;
[0105] The second device control unit is configured to set the power consumption mode of the device to be controlled to the first power consumption mode according to the mode control instruction of the power consumption control scheme when the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme.
[0106] This application first performs a service perception analysis on the service transmission data of the device to be controlled to obtain service characteristic parameters, then obtains the channel control parameters of the channel where it is located, and constructs a ternary table, and then constructs the association between the service characteristic parameters and the channel control parameters to obtain a fusion feature vector, which can accurately obtain the service characteristics corresponding to the device to be controlled, and then obtain a predictive control scheme through a power consumption control model trained based on a decision tree model. It is ensured that the obtained predictive control scheme controls the power consumption of the device while combining the service characteristics to ensure service performance; then, according to the power consumption mode of the device to be controlled, the power consumption control scheme is obtained by combining the predictive control scheme and the ternary table, and then the device to be controlled is controlled, and the power consumption control scheme is obtained through the power consumption mode. On the basis of the predictive control scheme, the power consumption of the device is further more accurately controlled, thereby completing accurate control of the power consumption of the device while ensuring service performance.
[0107] It should be understood that the device provided in the embodiment of the present application corresponds to the aforementioned method, and the device power consumption control device based on business perception provided in the embodiment of the present application can implement the device power consumption control method based on business perception provided in any embodiment of the present application.
[0108] Adaptively, the embodiments of the present application further provide a computer device and a computer-readable storage medium.
[0109] The computer device comprises: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor;
[0110] When the processor executes the computer program, a device power consumption control method based on service perception of the present application is implemented.
[0111] The computer-readable storage medium stores a plurality of instructions, which are suitable for loading by a processor to execute a device power consumption control method based on service perception of the present application.
[0112] The above description is a partial embodiment of the present application, which further describes the purpose, technical solutions, and beneficial effects of the present application in detail. It should be understood that the above description of the partial embodiment of the present application is not to be construed as limiting the present application. In particular, it is pointed out that for those skilled in the art, any changes, modifications, equivalent substitutions, and variations made within the spirit and principles of the present application should be included within the scope of protection of the present application.
Claims
1. A device power consumption control method based on service perception, characterized in that: include: Perform business perception analysis on the business transmission data of the controlled device to obtain business characteristic parameters; Acquire channel control parameters of the channel where the service transmission data is located, and construct a ternary table according to the channel control parameters; According to the timestamp of the data packet containing the service transmission data, an association is established between the service characteristic parameter and the channel control parameter to obtain a fused feature vector; Inputting the fused feature vector into a preset power consumption control model to obtain a predictive control scheme; wherein the power consumption control model is obtained based on decision tree model training; According to the power consumption mode of the device to be controlled, combined with the predictive control scheme and the ternary table, a power consumption control scheme is obtained, and the device to be controlled is controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled; wherein, the power consumption mode includes a first power consumption mode and a second power consumption mode; the power consumption of the first power consumption mode is not less than that of the second power consumption mode; the power consumption control scheme includes a mode control instruction and a sleep timer.
2. The device power consumption control method based on service perception according to claim 1, characterized in that: The performing of service perception analysis on the service transmission data of the device to be controlled to obtain service characteristic parameters specifically includes: Performing service perception on the device to be controlled to obtain original service transmission data, and segmenting the original service transmission data according to preset time lengths to obtain multiple groups of time window data; Count the fluctuations of business data volume in each time window data group to obtain multiple groups of business fluctuation characteristics; Perform correlation feature analysis on the business data volume of each time window data group and the adjacent time window data group to obtain multiple groups of business continuity features; The multiple groups of business fluctuation characteristics and the multiple groups of business continuity characteristics are combined and spliced in chronological order to obtain business characteristic parameters.
3. The device power consumption control method based on service perception according to claim 1, characterized in that: The constructing, based on the timestamp of the data packet containing the service transmission data, an association between the service characteristic parameter and the channel control parameter to obtain a fused feature vector specifically includes: Constructing a parameter mapping table between the service characteristic parameters and the channel control parameters in a time dimension according to the timestamp of the data packet containing the service transmission data; According to the parameter mapping table, correlation feature analysis is performed on the service feature parameters and the channel control parameters to obtain a fusion feature vector.
4. The device power consumption control method based on service perception according to claim 1, characterized in that: The method of obtaining a power consumption control scheme based on the power consumption mode of the device to be controlled, combining the predictive control scheme and the ternary table, and controlling the device to be controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled specifically includes: When the device to be controlled is in a first power consumption mode, determining an end time of the first power consumption mode according to the ternary table, and correcting a mode control instruction and a sleep timing in the predictive control scheme according to the ternary table and the end time to obtain a power consumption control scheme; When the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme, the power consumption mode of the device to be controlled is changed according to the mode control instruction of the power consumption control scheme.
5. The device power consumption control method based on service perception according to claim 1, characterized in that: The method of obtaining a power consumption control scheme based on the power consumption mode of the device to be controlled, combining the predictive control scheme and the ternary table, and controlling the device to be controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled specifically includes: When the device to be controlled is in the second power consumption mode, the mode control instruction in the prediction control scheme is corrected according to the ternary table to obtain a power consumption control scheme; When the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme, the power consumption mode of the device to be controlled is set to the first power consumption mode according to the mode control instruction of the power consumption control scheme.
6. A device power consumption control device based on service perception, characterized in that: It includes a service perception analysis module, a channel parameter acquisition module, a parameter association construction module, a control scheme prediction module and a device power consumption control module; The service perception analysis module is used to perform service perception analysis on the service transmission data of the control device to obtain service characteristic parameters; The channel parameter acquisition module is used to obtain the channel control parameters of the channel where the service transmission data is located, and to construct a ternary table according to the channel control parameters; The parameter association building module is used to build an association between the service characteristic parameter and the channel control parameter according to the timestamp of the data packet containing the service transmission data, so as to obtain a fusion feature vector; The control scheme prediction module is used to input the fused feature vector into a preset power consumption control model to obtain a predicted control scheme; wherein the power consumption control model is obtained based on decision tree model training; The device power consumption control module is used to obtain a power consumption control scheme based on the power consumption mode of the device to be controlled, in combination with the predictive control scheme and the ternary table, and control the device to be controlled according to the power consumption control scheme to adjust the power consumption of the device to be controlled; wherein, the power consumption mode includes a first power consumption mode and a second power consumption mode; the power consumption of the first power consumption mode is not less than that of the second power consumption mode; and the power consumption control scheme includes a mode control instruction and a sleep timer.
7. The device power consumption control device based on service perception according to claim 6, characterized in that: The business perception analysis module includes a data perception segmentation unit, a data fluctuation statistics unit, a data association analysis unit and a feature splicing and combination unit; The data sensing and splitting unit is used to perform service sensing on the device to be controlled to obtain original service transmission data, and split the original service transmission data according to preset time lengths to obtain multiple groups of time window data; The data fluctuation statistics unit is used to respectively count the fluctuations of the business data volume in each group of time window data to obtain multiple groups of business fluctuation characteristics; The data association analysis unit is used to perform association feature analysis on the business data volume of each group of time window data and adjacent time window data to obtain multiple groups of business continuity features; The feature splicing and combining unit is used to sequentially combine and splice the multiple groups of business fluctuation features with the multiple groups of business continuity features in chronological order to obtain business feature parameters.
8. The device power consumption control device based on service perception according to claim 6, characterized in that: The parameter association construction module includes a parameter mapping construction unit and a parameter association analysis unit; The parameter mapping construction unit is configured to construct a parameter mapping table between the service characteristic parameters and the channel control parameters in a time dimension according to the timestamp of the data packet containing the service transmission data; The parameter association analysis unit is used to perform association feature analysis on the service feature parameters and the channel control parameters according to the parameter mapping table to obtain a fusion feature vector.
9. The device power consumption control device based on service perception according to claim 6, characterized in that: The device power consumption control module includes a first solution acquisition unit and a first device control unit; The first scheme acquisition unit is configured to, when the device to be controlled is in the first power consumption mode, determine an end time of the first power consumption mode according to the ternary table, and modify a mode control instruction and a sleep timing in the predictive control scheme according to the ternary table and the end time to obtain a power consumption control scheme; The first device control unit is configured to change the power consumption mode of the device to be controlled according to the mode control instruction of the power consumption control scheme when the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme.
10. The device power consumption control device based on service perception according to claim 6, characterized in that: The device power consumption control module includes a second solution acquisition unit and a second device control unit; The second scheme acquisition unit is configured to, when the device to be controlled is in the second power consumption mode, correct the mode control instruction in the predictive control scheme according to the ternary table to obtain a power consumption control scheme; The second device control unit is configured to set the power consumption mode of the device to be controlled to the first power consumption mode according to the mode control instruction of the power consumption control scheme when the sleep duration of the device to be controlled meets the sleep timing of the power consumption control scheme.