CN117236522A - Power energy consumption management method, system, electronic equipment and medium - Google Patents
Power energy consumption management method, system, electronic equipment and medium Download PDFInfo
- Publication number
- CN117236522A CN117236522A CN202311493013.2A CN202311493013A CN117236522A CN 117236522 A CN117236522 A CN 117236522A CN 202311493013 A CN202311493013 A CN 202311493013A CN 117236522 A CN117236522 A CN 117236522A
- Authority
- CN
- China
- Prior art keywords
- characteristic data
- power
- power characteristic
- power consumption
- preprocessed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007726 management method Methods 0.000 title claims abstract description 36
- 238000005265 energy consumption Methods 0.000 title claims description 66
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims description 30
- 238000012216 screening Methods 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 12
- 238000013461 design Methods 0.000 description 6
- 238000005065 mining Methods 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application belongs to the technical field of data processing, and aims to provide a power consumption management method, a system, electronic equipment and a medium. The application can screen the power characteristic data influencing the power consumption, so as to obtain the characteristic data influencing the power consumption of the power equipment in different scenes; in addition, the method and the device also train the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values to obtain the trained power consumption prediction model, so that the real-time prediction of the power consumption of the power equipment can be realized, the limitation of manual power consumption prediction is overcome, the prediction efficiency is higher, and the popularization and application values are realized.
Description
Technical Field
The application belongs to the technical field of data processing, and particularly relates to a power energy consumption management method, a system, electronic equipment and a medium.
Background
The electric power energy is an important support for economic development of China, and the conditions of shortage of electric power resource supply, surge in price and the like occur along with the reasons of policy transition from a traditional power generation mode to a new energy power generation mode, so that the electric power resource consumption of industrial and mining enterprises in the production process is often large, the electric power energy consumption management is carried out, and the electric power energy management method has important significance for reducing the production cost of the industrial and mining enterprises and improving the market competitiveness of the industrial and mining enterprises. The prediction of the power consumption is an important link of the power consumption management work, however, at present, the prediction of the power consumption is usually performed by relying on manual experience and subjective judgment in the field, and is obtained by manually modeling mass data, so that the efficiency of the power consumption prediction is lower, and meanwhile, the prediction of the power consumption of industrial and mining enterprises in different scenes cannot be realized, and the limitation is higher.
Disclosure of Invention
The application aims to solve the technical problems at least to a certain extent, and provides a power energy consumption management method, a system, electronic equipment and a medium.
In order to achieve the above purpose, the present application adopts the following technical scheme:
in a first aspect, the present application provides a power consumption management method, including:
collecting a plurality of groups of initial power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the plurality of groups of initial power characteristic data sets from a preset power data set, and preprocessing the plurality of groups of initial power characteristic data sets to obtain a plurality of groups of preprocessed power characteristic data sets;
according to the multiple groups of preprocessed electric power characteristic data sets and the multiple actual electric power energy consumption values respectively corresponding to the multiple groups of preprocessed electric power characteristic data sets, carrying out initial electric power characteristic data screening on the preprocessed electric power characteristic data sets to obtain multiple groups of screened electric power characteristic data sets;
constructing an initial power consumption prediction model, and training the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values to obtain a trained power consumption prediction model;
acquiring a real-time electric power characteristic data set, and preprocessing the real-time electric power characteristic data set to obtain a preprocessed real-time electric power characteristic data set;
and inputting the preprocessed real-time power characteristic data set into the trained power energy consumption prediction model to obtain a real-time energy consumption prediction result.
The application can screen the power characteristic data influencing the power consumption, so as to obtain the characteristic data influencing the power consumption of the power equipment in different scenes; in addition, the method and the device also train the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values to obtain the trained power consumption prediction model, so that the real-time prediction of the power consumption of the power equipment can be realized, the limitation of manual power consumption prediction is overcome, the prediction efficiency is higher, and the popularization and application values are realized.
In one possible design, each set of pre-processed power signature data sets includes a plurality of different kinds of pre-processed power signature data; according to the power characteristic data sets after the pretreatment and a plurality of actual power consumption values respectively corresponding to the power characteristic data sets after the pretreatment, the power characteristic data sets after the pretreatment are subjected to initial power characteristic data screening to obtain a plurality of power characteristic data sets after the screening, and the method comprises the following steps:
acquiring a plurality of types of power characteristic data point sets corresponding to all the preprocessed power characteristic data in the plurality of groups of preprocessed power characteristic data sets according to the plurality of groups of preprocessed power characteristic data sets;
acquiring an actual power consumption value set according to a plurality of types of actual power consumption values respectively corresponding to the power characteristic data sets after the pretreatment;
acquiring correlation coefficients of all the preprocessed power characteristic data and the actual power consumption value according to a plurality of kinds of power characteristic data point sets corresponding to all the preprocessed power characteristic data and the actual power consumption value set;
and screening the plurality of groups of preprocessed power characteristic data sets to obtain preprocessed power characteristic data with the correlation coefficient with the actual power consumption value larger than a preset correlation coefficient threshold value, and obtaining the plurality of groups of screened power characteristic data sets according to all the preprocessed power characteristic data with the correlation coefficient larger than the preset correlation coefficient threshold value.
In one possible design, the correlation coefficient of any kind of preprocessed power characteristic data and the actual power consumption value is:
；
in the method, in the process of the application,a power characteristic data point set corresponding to the pre-processed power characteristic data of the current type; />The method comprises the steps of setting actual power consumption value sets; />For the current category of the set of power characteristic data points +.>And the actual power consumption value set +.>Covariance between; />For the current category of the set of power characteristic data points +.>Is a variance of (2); />For the set of actual power consumption values +.>Is a variance of (c).
In one possible design, the pre-processed power feature data set is screened for initial power feature data according to a plurality of sets of pre-processed power feature data sets and a plurality of actual power consumption values respectively corresponding to the plurality of sets of pre-processed power feature data sets, and the GBDT feature selection algorithm is adopted when the plurality of sets of screened power feature data sets are obtained.
In one possible design, training the initial power consumption prediction model according to a plurality of sets of the filtered power feature data sets and a corresponding plurality of the actual power consumption values to obtain a trained power consumption prediction model, including:
dividing a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values into a training data set and a verification data set;
training the initial power consumption prediction model according to the training data set to obtain an initial trained power consumption prediction model;
inputting the screened power characteristic data set in the verification data set into the initial trained power energy consumption prediction model to obtain a power energy consumption prediction value;
and acquiring an absolute value of a difference between the power consumption predicted value and an actual power consumption value corresponding to the screened power characteristic data set in the verification data set, judging whether the current absolute value is smaller than a preset power consumption deviation threshold, if so, taking the initial trained power consumption predicted model as a trained power consumption predicted model, and if not, retraining the initial power consumption predicted model until the trained power consumption predicted model is obtained.
In one possible design, the trained power consumption prediction model is:
=/>·/>=（/>,…，/>）·/>；
in the method, in the process of the application,the power consumption predicted value is the power consumption predicted value; />For inputting the power characteristic data set of the trained power consumption prediction model +.>，/>,…,/>Each power characteristic data in the power characteristic data set; />For the power characteristic data set +.>Corresponding weight set, < >>（/>,…，/>），/>,…，/>Respectively is the power characteristic data->,…,/>And (5) corresponding weight.
In one possible design, after obtaining the real-time energy consumption prediction result, the method further includes:
judging whether the real-time energy consumption prediction result is smaller than a preset energy consumption threshold value, if not, obtaining a power characteristic data adjustment scheme according to the preprocessed real-time power characteristic data set and the trained power energy consumption prediction model;
and adjusting the real-time power characteristic data set according to the power characteristic data adjustment scheme to obtain an adjusted power characteristic data set so as to enable an adjusted energy consumption prediction result corresponding to the adjusted power characteristic data set to be smaller than a preset energy consumption threshold.
In a second aspect, the present application provides a power consumption management system for implementing a power consumption management method as described in any one of the above; the power consumption management system includes:
the training data acquisition module is used for acquiring a plurality of groups of initial power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the plurality of groups of initial power characteristic data sets from a preset power data set, preprocessing the plurality of groups of initial power characteristic data sets, and obtaining a plurality of groups of preprocessed power characteristic data sets;
the training data acquisition module is further used for carrying out initial power characteristic data screening on the preprocessed power characteristic data sets according to a plurality of groups of preprocessed power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the preprocessed power characteristic data sets to obtain a plurality of groups of screened power characteristic data sets;
the model construction module is in communication connection with the training data acquisition module and is used for constructing an initial power consumption prediction model, training the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values, and obtaining a trained power consumption prediction model;
the energy consumption prediction module is in communication connection with the model construction module and is used for acquiring a real-time electric power characteristic data set, preprocessing the real-time electric power characteristic data set and obtaining a preprocessed real-time electric power characteristic data set;
the energy consumption prediction module is further used for inputting the preprocessed real-time power characteristic dataset into the trained power energy consumption prediction model to obtain a real-time energy consumption prediction result.
In a third aspect, the present application provides an electronic device, comprising:
a memory for storing computer program instructions; the method comprises the steps of,
a processor for executing the computer program instructions to perform the operations of the power consumption management method as claimed in any one of the preceding claims.
In a fourth aspect, the present application provides a computer readable storage medium storing computer program instructions readable by a computer, the computer program instructions being configured to perform operations of the power consumption management method according to any one of the preceding claims when run.
Drawings
FIG. 1 is a flow chart of a method of power consumption management in an embodiment;
FIG. 2 is a block diagram of a power consumption management system in an embodiment;
fig. 3 is a block diagram of an electronic device in an embodiment.
Detailed Description
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the present application will be briefly described below with reference to the accompanying drawings and the description of the embodiments or the prior art, and it is obvious that the following description of the structure of the drawings is only some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art. It should be noted that the description of these examples is for aiding in understanding the present application, but is not intended to limit the present application.
Example 1:
the present embodiment discloses a power consumption management method, which may be performed by, but not limited to, a computer device or a virtual machine with a certain computing resource, for example, an electronic device such as a personal computer, a smart phone, a personal digital assistant, or a wearable device, or a virtual machine.
As shown in fig. 1, a power consumption management method may include, but is not limited to, the following steps:
s1, acquiring a plurality of groups of initial power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the plurality of groups of initial power characteristic data sets from a preset power data set, and preprocessing the plurality of groups of initial power characteristic data sets to obtain a plurality of groups of preprocessed power characteristic data sets; in this embodiment, the initial power characteristic data in each set of initial power characteristic data sets includes, but is not limited to, environmental impact parameters such as temperature, humidity, air pressure, etc., power quality impact parameters such as frequency deviation, harmonic distortion, voltage deviation, three-phase imbalance variation and voltage fluctuation, etc., and power equipment intrinsic parameters such as time, rated power, service life, etc., which are not limited herein.
In this embodiment, the preprocessing of the initial power characteristic data set may include, but is not limited to:
s101, screening abnormal values such as abrupt values and repeated values from the initial power characteristic data set to obtain an abnormal value screened power characteristic data set;
s102, carrying out interpolation processing on the missing data in the electric power characteristic data set after the abnormal value is screened out, and obtaining an electric power characteristic data set after interpolation;
s103, carrying out normalization processing on the interpolated electric power characteristic data set to obtain a preprocessed electric power characteristic data set.
Through the arrangement of the steps S101 to S103, the subsequent data processing efficiency can be conveniently improved, and the situation of overlarge errors in the data processing process is avoided.
S2, performing initial power characteristic data screening on the preprocessed power characteristic data sets according to the preprocessed power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the preprocessed power characteristic data sets, and obtaining a plurality of screened power characteristic data sets.
In this embodiment, each set of preprocessed power feature data sets includes a plurality of different kinds of preprocessed power feature data; according to the power characteristic data sets after the pretreatment and a plurality of actual power consumption values respectively corresponding to the power characteristic data sets after the pretreatment, the power characteristic data sets after the pretreatment are subjected to initial power characteristic data screening to obtain a plurality of power characteristic data sets after the screening, and the method comprises the following steps:
s201, acquiring a plurality of types of power characteristic data point sets corresponding to all the preprocessed power characteristic data in the plurality of groups of preprocessed power characteristic data sets according to the plurality of groups of preprocessed power characteristic data sets;
s202, acquiring an actual power consumption value set according to a plurality of types of actual power consumption values respectively corresponding to a plurality of groups of preprocessed power characteristic data sets;
s203, acquiring correlation coefficients of all the preprocessed power characteristic data and actual power consumption values according to a plurality of kinds of power characteristic data point sets corresponding to all the preprocessed power characteristic data and the actual power consumption value sets;
specifically, in this embodiment, the correlation coefficient between any kind of preprocessed power characteristic data and the actual power consumption value is:
；
in the method, in the process of the application,a power characteristic data point set corresponding to the pre-processed power characteristic data of the current type; />The method comprises the steps of setting actual power consumption value sets; />For the current category of the set of power characteristic data points +.>And the actual power consumption value set +.>Covariance between; />For the current category of the set of power characteristic data points +.>Is a variance of (2); />For the set of actual power consumption values +.>Is a variance of (c).
S204, screening out a plurality of groups of preprocessed electric power characteristic data sets, obtaining preprocessed electric power characteristic data with the correlation coefficient with the actual electric power consumption value larger than a preset correlation coefficient threshold value, and obtaining a plurality of groups of screened electric power characteristic data sets according to all the preprocessed electric power characteristic data with the correlation coefficient larger than the preset correlation coefficient threshold value.
As another implementation manner of the initial power feature data screening, in this embodiment, according to a plurality of sets of preprocessed power feature data sets and a plurality of actual power consumption values corresponding to the plurality of sets of preprocessed power feature data sets, the initial power feature data screening is performed on the preprocessed power feature data sets, and when the plurality of sets of screened power feature data sets are obtained, the GBDT feature selection algorithm is adopted.
S3, constructing an initial power consumption prediction model, and training the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values to obtain a trained power consumption prediction model.
In this embodiment, training the initial power consumption prediction model according to a plurality of sets of the filtered power feature data sets and a plurality of corresponding actual power consumption values to obtain a trained power consumption prediction model, including:
s301, dividing a plurality of groups of screened power characteristic data sets and corresponding actual power consumption values into training data sets and verification data sets, wherein the training data sets comprise 70% of screened power characteristic data sets and corresponding actual power consumption values thereof, and the verification data sets comprise 30% of screened power characteristic data sets and corresponding actual power consumption values thereof in the embodiment;
s302, training the initial power consumption prediction model according to the training data set to obtain an initial trained power consumption prediction model;
s303, inputting the screened power characteristic data set in the verification data set into the initial trained power energy consumption prediction model to obtain a power energy consumption prediction value;
s304, obtaining an absolute value of a difference between the power consumption predicted value and an actual power consumption value corresponding to the screened power characteristic data set in the verification data set, judging whether the current absolute value is smaller than a preset energy consumption deviation threshold, if so, taking the initial trained power consumption predicted model as a trained power consumption predicted model, and if not, retraining the initial power consumption predicted model until the trained power consumption predicted model is obtained.
In this embodiment, the standard of obtaining the trained power consumption prediction model after successful training according to the initial power consumption prediction model is as follows: and after any one of the screened power characteristic data sets in the verification data set is input into the trained power energy consumption prediction model, the absolute value of the difference between the power energy consumption predicted value output by the trained power energy consumption prediction model and the actual power energy consumption value corresponding to the current screened power characteristic data set is smaller than a preset power consumption deviation threshold.
Specifically, in this embodiment, the trained power consumption prediction model is:
=/>·/>=（/>,…，/>）·/>；
in the method, in the process of the application,the power consumption predicted value is the power consumption predicted value; />For inputting the power characteristic data set of the trained power consumption prediction model +.>，/>,…,/>Each power characteristic data in the power characteristic data set; />For the power characteristic data set +.>Corresponding weight set, < >>（/>,…，/>），/>,…，/>Respectively is the power characteristic data->,…,/>And (5) corresponding weight.
S4, acquiring a real-time electric power characteristic data set, and preprocessing the real-time electric power characteristic data set to obtain a preprocessed real-time electric power characteristic data set.
S5, inputting the preprocessed real-time power characteristic data set into the trained power energy consumption prediction model to obtain a real-time energy consumption prediction result.
In this embodiment, after obtaining the real-time energy consumption prediction result, the method further includes:
s6, judging whether the real-time energy consumption prediction result is smaller than a preset energy consumption threshold value, if not, obtaining a power characteristic data adjustment scheme according to the preprocessed real-time power characteristic data set and the trained power energy consumption prediction model;
s7, adjusting the real-time power characteristic data set according to the power characteristic data adjustment scheme to obtain an adjusted power characteristic data set so as to enable an adjusted energy consumption prediction result corresponding to the adjusted power characteristic data set to be smaller than a preset energy consumption threshold.
In this embodiment, the power characteristic data adjustment scheme is obtained according to the preprocessed real-time power characteristic data set and the trained power energy consumption prediction model, and includes: obtaining the adjustment quantity of the preprocessed real-time power characteristic data according to all preprocessed real-time power characteristic data in the preprocessed real-time power characteristic data set and the weights corresponding to the preprocessed real-time power characteristic data in the trained power energy consumption prediction model; and the adjustment amounts corresponding to all the preprocessed real-time power characteristic data in the preprocessed real-time power characteristic data set form a power characteristic data adjustment scheme. The sum of all the preprocessed real-time power characteristic data in the preprocessed real-time power characteristic data set and the corresponding adjustment amount in the power characteristic data adjustment scheme forms adjusted power characteristic data in the adjusted power characteristic data set.
In this embodiment, according to the preprocessed real-time power feature data set and the trained power energy consumption prediction model, a power feature data adjustment scheme is obtained, so that a user can conveniently adjust the preprocessed real-time power feature data set based on the power feature data adjustment scheme, and further, it is ensured that a power energy consumption result corresponding to the adjusted power feature data set is smaller than an energy consumption threshold, and therefore, adjustment of power energy consumption is achieved.
The embodiment can screen the power characteristic data influencing the power consumption, so as to obtain the characteristic data influencing the power consumption of the power equipment in different scenes; in addition, the embodiment also trains the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values to obtain a trained power consumption prediction model, so that the real-time prediction of the power consumption of the power equipment can be realized, the limitation of manual power consumption prediction is overcome, the prediction efficiency is higher, and the popularization and application values are realized.
Example 2:
the embodiment discloses a power consumption management system for realizing the power consumption management method in the embodiment 1; as shown in fig. 2, the power consumption management system includes:
the training data acquisition module is used for acquiring a plurality of groups of initial power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the plurality of groups of initial power characteristic data sets from a preset power data set, preprocessing the plurality of groups of initial power characteristic data sets, and obtaining a plurality of groups of preprocessed power characteristic data sets;
the training data acquisition module is further used for carrying out initial power characteristic data screening on the preprocessed power characteristic data sets according to a plurality of groups of preprocessed power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the preprocessed power characteristic data sets to obtain a plurality of groups of screened power characteristic data sets;
the model construction module is in communication connection with the training data acquisition module and is used for constructing an initial power consumption prediction model, training the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values, and obtaining a trained power consumption prediction model;
the energy consumption prediction module is in communication connection with the model construction module and is used for acquiring a real-time electric power characteristic data set, preprocessing the real-time electric power characteristic data set and obtaining a preprocessed real-time electric power characteristic data set;
the energy consumption prediction module is further used for inputting the preprocessed real-time power characteristic dataset into the trained power energy consumption prediction model to obtain a real-time energy consumption prediction result.
Example 3:
on the basis of embodiment 1 or 2, this embodiment discloses an electronic device, which may be a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like. An electronic device may be referred to as being used for a terminal, a portable terminal, a desktop terminal, etc., as shown in fig. 3, the electronic device includes:
a memory for storing computer program instructions; the method comprises the steps of,
a processor configured to execute the computer program instructions to perform the operations of the power consumption management method according to any one of embodiment 1.
In particular, processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 301 may also include a main processor, which is a processor for processing data in an awake state, also called a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 301 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen.
Memory 302 may include one or more computer-readable storage media, which may be non-transitory. Memory 302 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in memory 302 is used to store at least one instruction for execution by processor 301 to implement the power consumption management method provided by embodiment 1 of the present application.
In some embodiments, the terminal may further optionally include: a communication interface 303, and at least one peripheral device. The processor 301, the memory 302 and the communication interface 303 may be connected by a bus or signal lines. The respective peripheral devices may be connected to the communication interface 303 through a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 304, a display screen 305, and a power supply 306.
The communication interface 303 may be used to connect at least one peripheral device associated with an I/O (Input/Output) to the processor 301 and the memory 302. In some embodiments, processor 301, memory 302, and communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, either or both of the processor 301, the memory 302, and the communication interface 303 may be implemented on separate chips or circuit boards, which is not limited in this embodiment.
The Radio Frequency circuit 304 is configured to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuitry 304 communicates with a communication network and other communication devices via electromagnetic signals.
The display screen 305 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof.
The power supply 306 is used to power the various components in the electronic device.
Example 4:
on the basis of any one of embodiments 1 to 3, this embodiment discloses a computer-readable storage medium for storing computer-readable computer program instructions configured to perform the operations of the power consumption management method described in embodiment 1 when run.
It will be apparent to those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, or they may alternatively be implemented in program code executable by computing devices, such that they may be stored in a memory device for execution by the computing devices, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps within them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solution of the present application, and not limiting thereof; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced by equivalents. Such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. The power consumption management method is characterized in that: comprising the following steps:
collecting a plurality of groups of initial power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the plurality of groups of initial power characteristic data sets from a preset power data set, and preprocessing the plurality of groups of initial power characteristic data sets to obtain a plurality of groups of preprocessed power characteristic data sets;
according to the multiple groups of preprocessed electric power characteristic data sets and the multiple actual electric power energy consumption values respectively corresponding to the multiple groups of preprocessed electric power characteristic data sets, carrying out initial electric power characteristic data screening on the preprocessed electric power characteristic data sets to obtain multiple groups of screened electric power characteristic data sets;
constructing an initial power consumption prediction model, and training the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values to obtain a trained power consumption prediction model;
acquiring a real-time electric power characteristic data set, and preprocessing the real-time electric power characteristic data set to obtain a preprocessed real-time electric power characteristic data set;
and inputting the preprocessed real-time power characteristic data set into the trained power energy consumption prediction model to obtain a real-time energy consumption prediction result.
2. A power consumption management method according to claim 1, characterized in that: each group of preprocessed power characteristic data sets comprises a plurality of different types of preprocessed power characteristic data; according to the power characteristic data sets after the pretreatment and a plurality of actual power consumption values respectively corresponding to the power characteristic data sets after the pretreatment, the power characteristic data sets after the pretreatment are subjected to initial power characteristic data screening to obtain a plurality of power characteristic data sets after the screening, and the method comprises the following steps:
acquiring a plurality of types of power characteristic data point sets corresponding to all the preprocessed power characteristic data in the plurality of groups of preprocessed power characteristic data sets according to the plurality of groups of preprocessed power characteristic data sets;
acquiring an actual power consumption value set according to a plurality of types of actual power consumption values respectively corresponding to the power characteristic data sets after the pretreatment;
acquiring correlation coefficients of all the preprocessed power characteristic data and the actual power consumption value according to a plurality of kinds of power characteristic data point sets corresponding to all the preprocessed power characteristic data and the actual power consumption value set;
and screening the plurality of groups of preprocessed power characteristic data sets to obtain preprocessed power characteristic data with the correlation coefficient with the actual power consumption value larger than a preset correlation coefficient threshold value, and obtaining the plurality of groups of screened power characteristic data sets according to all the preprocessed power characteristic data with the correlation coefficient larger than the preset correlation coefficient threshold value.
3. A power consumption management method according to claim 2, characterized in that: the correlation coefficient between the preprocessed power characteristic data of any kind and the actual power consumption value is as follows:
；
in the method, in the process of the application,a power characteristic data point set corresponding to the pre-processed power characteristic data of the current type; />The method comprises the steps of setting actual power consumption value sets; />Is of the current kindClass power feature data point set->And the actual power consumption value set +.>Covariance between; />For the current category of the set of power characteristic data points +.>Is a variance of (2); />For the set of actual power consumption values +.>Is a variance of (c).
4. A power consumption management method according to claim 1, characterized in that: and (3) according to the plurality of groups of preprocessed electric power characteristic data sets and a plurality of actual electric power consumption values respectively corresponding to the plurality of groups of preprocessed electric power characteristic data sets, carrying out initial electric power characteristic data screening on the preprocessed electric power characteristic data sets, and when the plurality of groups of screened electric power characteristic data sets are obtained, adopting a GBDT characteristic selection algorithm to realize.
5. A power consumption management method according to claim 1, characterized in that: training the initial power energy consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power energy consumption values to obtain a trained power energy consumption prediction model, wherein the training comprises the following steps:
dividing a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values into a training data set and a verification data set;
training the initial power consumption prediction model according to the training data set to obtain an initial trained power consumption prediction model;
inputting the screened power characteristic data set in the verification data set into the initial trained power energy consumption prediction model to obtain a power energy consumption prediction value;
and acquiring an absolute value of a difference between the power consumption predicted value and an actual power consumption value corresponding to the screened power characteristic data set in the verification data set, judging whether the current absolute value is smaller than a preset power consumption deviation threshold, if so, taking the initial trained power consumption predicted model as a trained power consumption predicted model, and if not, retraining the initial power consumption predicted model until the trained power consumption predicted model is obtained.
6. A power consumption management method according to claim 1, characterized in that: the trained power consumption prediction model is as follows:
=/>·/>=（/>,…，/>）·/>；
in the method, in the process of the application,the power consumption predicted value is the power consumption predicted value; />To input the power characteristic data set of the trained power consumption prediction model,，/>,…,/>each power characteristic data in the power characteristic data set; />For the power characteristic data set +.>Corresponding weight set, < >>（/>,…，/>），/>,…，/>Respectively is the power characteristic data->,…,/>And (5) corresponding weight.
7. A power consumption management method according to claim 1, characterized in that: after obtaining the real-time energy consumption prediction result, the method further comprises the following steps:
judging whether the real-time energy consumption prediction result is smaller than a preset energy consumption threshold value, if not, obtaining a power characteristic data adjustment scheme according to the preprocessed real-time power characteristic data set and the trained power energy consumption prediction model;
and adjusting the real-time power characteristic data set according to the power characteristic data adjustment scheme to obtain an adjusted power characteristic data set so as to enable an adjusted energy consumption prediction result corresponding to the adjusted power characteristic data set to be smaller than a preset energy consumption threshold.
8. An electric power energy consumption management system, characterized in that: for implementing the power consumption management method according to any one of claims 1 to 7; the power consumption management system includes:
the training data acquisition module is used for acquiring a plurality of groups of initial power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the plurality of groups of initial power characteristic data sets from a preset power data set, preprocessing the plurality of groups of initial power characteristic data sets, and obtaining a plurality of groups of preprocessed power characteristic data sets;
the training data acquisition module is further used for carrying out initial power characteristic data screening on the preprocessed power characteristic data sets according to a plurality of groups of preprocessed power characteristic data sets and a plurality of actual power consumption values respectively corresponding to the preprocessed power characteristic data sets to obtain a plurality of groups of screened power characteristic data sets;
the model construction module is in communication connection with the training data acquisition module and is used for constructing an initial power consumption prediction model, training the initial power consumption prediction model according to a plurality of groups of screened power characteristic data sets and a plurality of corresponding actual power consumption values, and obtaining a trained power consumption prediction model;
the energy consumption prediction module is in communication connection with the model construction module and is used for acquiring a real-time electric power characteristic data set, preprocessing the real-time electric power characteristic data set and obtaining a preprocessed real-time electric power characteristic data set;
the energy consumption prediction module is further used for inputting the preprocessed real-time power characteristic dataset into the trained power energy consumption prediction model to obtain a real-time energy consumption prediction result.
9. An electronic device, characterized in that: comprising the following steps:
a memory for storing computer program instructions; the method comprises the steps of,
a processor for executing the computer program instructions to perform the operations of the power energy consumption management method of any one of claims 1 to 7.
10. A computer readable storage medium storing computer program instructions readable by a computer, characterized by: the computer program instructions are configured to perform the operations of the power energy consumption management method of any of claims 1 to 7 when run.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311493013.2A CN117236522B (en) | 2023-11-10 | 2023-11-10 | Power energy consumption management method, system, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311493013.2A CN117236522B (en) | 2023-11-10 | 2023-11-10 | Power energy consumption management method, system, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117236522A true CN117236522A (en) | 2023-12-15 |
| CN117236522B CN117236522B (en) | 2024-02-13 |
Family
ID=89088343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311493013.2A Active CN117236522B (en) | 2023-11-10 | 2023-11-10 | Power energy consumption management method, system, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117236522B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103680093A (en) * | 2012-09-25 | 2014-03-26 | 山东金软科技有限公司 | Wireless sensing communication system and wireless sensing communication method for monitoring energy consumption |
| CN107133660A (en) * | 2017-05-23 | 2017-09-05 | 国网辽宁省电力有限公司电力科学研究院 | A kind of electric automobile charging station energetic interaction management system |
| CN107301617A (en) * | 2017-06-09 | 2017-10-27 | 江苏梦兰神彩科技股份有限公司 | A kind of method and apparatus for assessing the waste gas monitoring quality of data |
| US20180026447A1 (en) * | 2015-02-04 | 2018-01-25 | Weidong Gu | Efficient and energy-saving power grid operation method |
| AU2020100630A4 (en) * | 2020-04-24 | 2020-06-04 | Kaplan, Umit Emrah MR | System and method for grade estimation using gradient boosted decesion tree based machine learning algorithims |
| CN112001439A (en) * | 2020-08-19 | 2020-11-27 | 西安建筑科技大学 | GBDT-based shopping mall building air conditioner cold load prediction method, storage medium and equipment |
| CN112421775A (en) * | 2020-10-29 | 2021-02-26 | 国网天津市电力公司 | Local energy consumption control system based on power Internet of things and control method thereof |
| CN113723684A (en) * | 2021-08-30 | 2021-11-30 | 兰州陇能电力科技有限公司 | Device and method for load prediction and energy management of enterprise power users |
| CN114066071A (en) * | 2021-11-19 | 2022-02-18 | 厦门大学 | Power parameter optimization method based on energy consumption, terminal equipment and storage medium |
| CN114065653A (en) * | 2022-01-17 | 2022-02-18 | 南方电网数字电网研究院有限公司 | Construction method of power load prediction model and power load prediction method |
| CN114970928A (en) * | 2021-02-26 | 2022-08-30 | 江苏大学 | Electric power data energy consumption analysis and prediction method |
| CN115091963A (en) * | 2022-07-01 | 2022-09-23 | 北理新源(佛山)信息科技有限公司 | Hydrogen fuel cell automobile energy consumption estimation method based on energy consumption characteristics and working condition segmentation |
| CN115936291A (en) * | 2022-02-24 | 2023-04-07 | 国网山东省电力公司泰安供电公司 | Method for constructing dynamic standard library based on multi-energy collaborative enterprise energy consumption under mass data |
| CN116776937A (en) * | 2023-07-11 | 2023-09-19 | 贵州电网有限责任公司信息中心 | Data processing method and device based on neural network |
| CN116796141A (en) * | 2022-03-14 | 2023-09-22 | 水发能源集团有限公司 | GBDT regression model-based office building energy consumption prediction method |
| CN116887569A (en) * | 2023-07-06 | 2023-10-13 | 广州至为信息科技有限公司 | Data center energy consumption prediction and energy saving adjustment method, system and storage medium |
-
2023
- 2023-11-10 CN CN202311493013.2A patent/CN117236522B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103680093A (en) * | 2012-09-25 | 2014-03-26 | 山东金软科技有限公司 | Wireless sensing communication system and wireless sensing communication method for monitoring energy consumption |
| US20180026447A1 (en) * | 2015-02-04 | 2018-01-25 | Weidong Gu | Efficient and energy-saving power grid operation method |
| CN107133660A (en) * | 2017-05-23 | 2017-09-05 | 国网辽宁省电力有限公司电力科学研究院 | A kind of electric automobile charging station energetic interaction management system |
| CN107301617A (en) * | 2017-06-09 | 2017-10-27 | 江苏梦兰神彩科技股份有限公司 | A kind of method and apparatus for assessing the waste gas monitoring quality of data |
| AU2020100630A4 (en) * | 2020-04-24 | 2020-06-04 | Kaplan, Umit Emrah MR | System and method for grade estimation using gradient boosted decesion tree based machine learning algorithims |
| CN112001439A (en) * | 2020-08-19 | 2020-11-27 | 西安建筑科技大学 | GBDT-based shopping mall building air conditioner cold load prediction method, storage medium and equipment |
| CN112421775A (en) * | 2020-10-29 | 2021-02-26 | 国网天津市电力公司 | Local energy consumption control system based on power Internet of things and control method thereof |
| CN114970928A (en) * | 2021-02-26 | 2022-08-30 | 江苏大学 | Electric power data energy consumption analysis and prediction method |
| CN113723684A (en) * | 2021-08-30 | 2021-11-30 | 兰州陇能电力科技有限公司 | Device and method for load prediction and energy management of enterprise power users |
| CN114066071A (en) * | 2021-11-19 | 2022-02-18 | 厦门大学 | Power parameter optimization method based on energy consumption, terminal equipment and storage medium |
| CN114065653A (en) * | 2022-01-17 | 2022-02-18 | 南方电网数字电网研究院有限公司 | Construction method of power load prediction model and power load prediction method |
| CN115936291A (en) * | 2022-02-24 | 2023-04-07 | 国网山东省电力公司泰安供电公司 | Method for constructing dynamic standard library based on multi-energy collaborative enterprise energy consumption under mass data |
| CN116796141A (en) * | 2022-03-14 | 2023-09-22 | 水发能源集团有限公司 | GBDT regression model-based office building energy consumption prediction method |
| CN115091963A (en) * | 2022-07-01 | 2022-09-23 | 北理新源(佛山)信息科技有限公司 | Hydrogen fuel cell automobile energy consumption estimation method based on energy consumption characteristics and working condition segmentation |
| CN116887569A (en) * | 2023-07-06 | 2023-10-13 | 广州至为信息科技有限公司 | Data center energy consumption prediction and energy saving adjustment method, system and storage medium |
| CN116776937A (en) * | 2023-07-11 | 2023-09-19 | 贵州电网有限责任公司信息中心 | Data processing method and device based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117236522B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105359057A (en) | Setting computer parameters to operate the power supply within a range based on a peak power efficiency of the power supply | |
| CN114881379B (en) | Method, device and equipment for estimating power generation capacity of wind power plant and storage medium | |
| CN118152106A (en) | Resource scheduling method and terminal equipment | |
| CN109740630A (en) | Method for processing abnormal data and device | |
| CN102597912A (en) | Coordinating device and application break events for platform power saving | |
| CN102566954A (en) | Portable electronic device and control method thereof | |
| CN112713650B (en) | Electric power monitoring data processing system | |
| CN114461382A (en) | Flexibly configurable computing power scheduling implementation method and device and storage medium | |
| WO2022135440A1 (en) | Llc resonant circuit control method and control apparatus, and terminal device | |
| CN111697556A (en) | Operation control method of electrical equipment and terminal equipment | |
| US20130297953A1 (en) | Control system | |
| CN117236522B (en) | Power energy consumption management method, system, electronic equipment and medium | |
| CN103942103A (en) | Method and device for generating processor scheduling policy in multi-core system and scheduling system | |
| CN104699224A (en) | Power-saving control method | |
| CN111523654A (en) | Processing apparatus and method | |
| CN117234744B (en) | Multi-chip system performance optimization method, system, electronic equipment and medium | |
| CN116243978A (en) | Data protocol method, device, medium and training system in distributed training | |
| CN102750126B (en) | Pronunciation inputting method and terminal | |
| CN104699223A (en) | Terminal | |
| CN105828421A (en) | Terminal and terminal power saving method | |
| CN104391564A (en) | Power consumption control method and device | |
| CN115269145A (en) | High-energy-efficiency heterogeneous multi-core scheduling method and device for offshore unmanned equipment | |
| CN111862894A (en) | Backlight brightness adjusting method, device, terminal and readable storage medium | |
| CN116610204B (en) | Power management method, system, electronic equipment and medium for electric equipment | |
| CN116302500B (en) | CPIE resource sharing scheduling method and system based on X86 platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |