CN116307284A - Energy consumption prediction method, electronic device and storage medium - Google Patents
Energy consumption prediction method, electronic device and storage medium Download PDFInfo
- Publication number
- CN116307284A CN116307284A CN202310565254.7A CN202310565254A CN116307284A CN 116307284 A CN116307284 A CN 116307284A CN 202310565254 A CN202310565254 A CN 202310565254A CN 116307284 A CN116307284 A CN 116307284A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- matrix
- consumption data
- data
- historical
- 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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 283
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 156
- 238000004590 computer program Methods 0.000 description 12
- 238000010606 normalization Methods 0.000 description 11
- 230000001174 ascending effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008094 contradictory effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Water Supply & Treatment (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Algebra (AREA)
- Operations Research (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an energy consumption prediction method, electronic equipment and a storage medium, and relates to the technical field of energy, wherein the method comprises the following steps: generating a first matrix based on the acquired historical energy consumption data, carrying out standardization processing on each historical energy consumption data in a second matrix selected from the first matrix based on preset time to obtain a standardized matrix, calculating the information bearing capacity of each column in the standardized matrix according to a preset value, the standard deviation of each column in the standardized matrix and a correlation coefficient, calculating the initial information weight of each column in the standardized matrix according to the information bearing capacity, adjusting a plurality of initial information weights according to the preset value if any initial information weight meets preset adjustment conditions to obtain a plurality of target information weights, and calculating energy consumption prediction data corresponding to the preset time based on a preset step length and preset time and a plurality of target information weights and selecting a plurality of target energy consumption data from the first matrix. The prediction accuracy of the energy consumption can be improved.
Description
Technical Field
The present disclosure relates to the field of energy technologies, and in particular, to an energy consumption prediction method, an electronic device, and a storage medium.
Background
In the current prediction scheme of energy consumption, the prediction cannot be performed by combining with the energy usage rule in actual situations, so that the accuracy of the predicted energy consumption is low. Because the accuracy of the existing energy prediction is low, the energy scheduling in the industrial production is easy to be influenced.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides an energy consumption prediction method, electronic equipment and a storage medium, which can solve the technical problem of low prediction accuracy of energy consumption.
In order to solve the above technical problems, an embodiment of the present invention provides an energy consumption prediction method, including:
generating a first matrix based on the acquired historical energy consumption data;
selecting a second matrix from the first matrix based on preset time, and performing standardization processing on each historical energy consumption data in the second matrix to obtain a standardization matrix;
calculating standard deviation and correlation coefficient of each column in the standardized matrix, and calculating information bearing capacity of each column in the standardized matrix according to a preset value, the standard deviation and the correlation coefficient;
according to the information bearing capacity, calculating initial information weight of each column in the standardized matrix;
If any initial information weight meets a preset adjustment condition, adjusting a plurality of initial information weights according to the preset value to obtain a plurality of adjusted target information weights;
and selecting a plurality of target energy consumption data corresponding to the plurality of target information weights from the first matrix based on a preset step length and the preset time, and calculating energy consumption prediction data corresponding to the preset time according to the plurality of target information weights and the plurality of target energy consumption data.
Optionally, generating the first matrix based on the acquired historical energy consumption data includes:
acquiring a plurality of preset first dimension times and a plurality of preset second dimension times;
creating a null matrix according to the plurality of first dimension times and the plurality of second dimension times, wherein each first dimension time and each second dimension time correspond to a position in the null matrix;
determining a first historical dimension time and a second historical dimension time of each historical energy consumption data;
and confirming the corresponding positions of each first historical dimension time and each second historical dimension time in the empty matrix according to the plurality of first dimension times and the plurality of second dimension times, and writing the corresponding historical energy consumption data into the determined positions to obtain the first matrix.
Optionally, the normalizing the historical energy consumption data in the second matrix to obtain a normalized matrix includes:
traversing all the historical energy consumption data in the second matrix, and selecting the largest historical energy consumption data and the smallest historical energy consumption data from the second matrix;
comparing each historical energy consumption data in the second matrix with preset energy consumption index data;
if any one of the historical energy consumption data in the second matrix is smaller than the energy consumption index data, calculating a first difference value between the energy consumption index data and any one of the historical energy consumption data;
calculating standardized energy consumption data corresponding to any one of the historical energy consumption data according to the energy consumption index data, the preset value, the first difference value, the maximum historical energy consumption data and the minimum historical energy consumption data; or alternatively
If any one of the historical energy consumption data is larger than the energy consumption index data, calculating a second difference value between any one of the historical energy consumption data and the energy consumption index data;
calculating the standardized energy consumption data according to the energy consumption index data, the preset value, the second difference value, the maximum historical energy consumption data and the minimum historical energy consumption data; or alternatively
If any one of the historical energy consumption data is equal to the energy consumption index data, determining the preset value as the standardized energy consumption data;
and replacing each historical energy consumption data in the second matrix with corresponding standardized energy consumption data to obtain the standardized matrix.
Optionally, the calculating the standardized energy consumption data corresponding to any one of the historical energy consumption data according to the energy consumption index data, the preset value, the first difference value, the maximum historical energy consumption data and the minimum historical energy consumption data includes:
calculating a third difference between the energy consumption index data and the minimum historical energy consumption data, and calculating a fourth difference between the maximum historical energy consumption data and the energy consumption index data;
selecting a larger value between the third difference value and the fourth difference value, and calculating a difference value ratio between the first difference value and the larger value;
and determining a difference value between the preset value and the difference value ratio as the standardized energy consumption data.
Optionally, the correlation coefficient of each column in the standardized matrix is multiple, and calculating the information bearing capacity of each column in the standardized matrix according to the preset value, the standard deviation and the correlation coefficient includes:
Calculating coefficient difference values between the preset value and each correlation coefficient, and calculating contradiction coefficients of each column in the standardized matrix according to a plurality of coefficient difference values;
and calculating the information bearing capacity of each column in the standardized matrix according to the standard deviation and the contradiction coefficient.
Optionally, the calculating the initial information weight of each column in the standardized matrix according to the information bearing capacity includes:
calculating the sum of information bearing capacities of all columns in the standardized matrix;
the ratio between the information bearing capacity of each column and the sum of the information bearing capacities is determined as the initial information weight of each column of data.
Optionally, if any initial information weight meets a preset adjustment condition, adjusting a plurality of initial information weights according to the preset value, and obtaining a plurality of adjusted target information weights includes:
if any initial information weight is greater than a preset weight, obtaining a parameter adjusting coefficient of each initial information weight;
and calculating the target information weight of each initial information weight according to each initial information weight and the parameter adjusting coefficient corresponding to each initial information weight, and ensuring that all the target information weights are added to be equal to the preset value.
Optionally, the selecting, based on a preset step size and the preset time, a plurality of target energy consumption data corresponding to the plurality of target information weights from the first matrix, and calculating, according to the plurality of target information weights and the plurality of target energy consumption data, energy consumption prediction data corresponding to the preset time includes:
generating a plurality of target positions according to the preset step length and the preset time, and determining historical energy consumption data on the plurality of target positions in the first matrix as the plurality of target energy consumption data;
selecting a target information weight corresponding to a column to which each target energy consumption data belongs;
and calculating the product of each target energy consumption data and the corresponding target information weight, and determining the sum of a plurality of products as the energy consumption prediction data.
In addition, the embodiment of the invention also provides electronic equipment, which comprises:
a memory storing at least one instruction; and
And the processor acquires the instructions stored in the memory to realize the energy consumption prediction method according to any one of the above.
In addition, an embodiment of the present invention further provides a computer readable storage medium, where at least one instruction is stored, where the at least one instruction is acquired by a processor in an electronic device to implement the energy consumption prediction method according to any one of the foregoing.
According to the technical scheme, the types of the historical energy consumption data are not limited, so that the energy consumption prediction method has wide applicability, each historical energy consumption data in the second matrix can be normalized to a uniform range through standardization processing, standard deviation and correlation coefficient of each column in the standardized matrix are more convenient to calculate, the standard deviation can represent fluctuation size in each column of the historical energy consumption data, the correlation coefficient can represent correlation degree of each column and other columns in the standardized matrix, and the information bearing capacity synthesizes the correlation coefficient and data change characteristics reflected by the standard deviation, so that the information bearing capacity of each column can reflect energy consumption change rules corresponding to each column of the historical energy consumption data. Because the initial information weight is the ratio between the information bearing capacity of each column and the sum of the information bearing capacities of all columns, the initial information weight of each column can intuitively represent the importance degree of each column in the standardized matrix, and meanwhile, the initial information weight of each column contains the energy consumption change rule information of the historical energy consumption data of each column. By adjusting the plurality of initial information weights, the adjusted plurality of target information weights can be more accurate. According to the method and the device for predicting the energy consumption corresponding to the preset time, the historical time of the plurality of target energy consumption data is continuous, and the continuous plurality of target energy consumption data have a larger association relationship, so that when the preset time and the historical time of the plurality of target energy consumption data are mutually continuous, the energy consumption prediction data are calculated through the target information weight containing the energy consumption change rule information and the continuous plurality of target energy consumption data, and the accuracy of the energy consumption prediction data can be ensured.
It can be appreciated that the electronic device and the computer-readable storage medium correspond to the above-mentioned energy consumption prediction method, and therefore, the advantages achieved by the method can refer to the advantages of the corresponding method provided above, and will not be described herein.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an energy consumption prediction method according to an embodiment of the present application.
Fig. 2 is a flowchart of a data normalization processing method according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the current prediction scheme of energy consumption, the prediction cannot be performed by combining with the energy usage rule in actual situations, so that the accuracy of the predicted energy consumption is low. Because the accuracy of the existing energy prediction is low, the energy scheduling in the industrial production is easy to be influenced.
In order to solve the above technical problems, embodiments of the present application provide an energy consumption prediction method, which can improve the accuracy of predicting the energy consumption, and will be described in detail below with reference to the corresponding drawings. The method for predicting energy consumption provided in the embodiments of the present application may be applied to one or more electronic devices (for example, the electronic device 1 shown in fig. 3), where the electronic device is a device capable of automatically performing parameter value calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to: microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital signal processors (Digital Signal Processor, DSP), embedded devices, etc.
The electronic device may be any electronic product that can interact with a user in a human-computer manner, such as a personal computer, tablet computer, smart phone, personal digital assistant (Personal Digital Assistant, PDA), game console, interactive internet protocol television (Internet Protocol Television, IPTV), smart wearable device, etc.
The electronic device may also include a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network server, a server group composed of a plurality of network servers, or a Cloud based Cloud Computing (Cloud Computing) composed of a large number of hosts or network servers.
The network in which the electronic device is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN), and the like.
Fig. 1 is a flowchart of an energy consumption prediction method according to an embodiment of the present application. The sequence of the steps in the flowchart may be adjusted according to actual requirements, and some steps may be omitted. The main execution body of the method is an electronic device, such as the electronic device 1 shown in fig. 3.
S11, generating a first matrix based on the acquired historical energy consumption data.
In at least one embodiment of the present application, the historical energy consumption data is a plurality of historical energy consumption data of the same energy consumption type, including, but not limited to: electrical energy, industrial capacity, natural gas energy, water energy, and the like. The first matrix is a matrix generated after integrating the plurality of historical energy consumption data.
In at least one embodiment of the present application, the generating, by the electronic device, the first matrix based on the acquired historical energy consumption data includes:
the electronic equipment acquires a plurality of preset first dimension time and a plurality of preset second dimension time, creates a null matrix according to the plurality of first dimension time and the plurality of second dimension time, wherein each first dimension time and each second dimension time correspond to one position in the null matrix, determines a first historical dimension time and a second historical dimension time of each historical energy consumption data, and confirms the corresponding position of each first historical dimension time and each second historical dimension time in the null matrix according to the plurality of first dimension time and the plurality of second dimension time, and writes the corresponding historical energy consumption data into the determined position to obtain the first matrix.
Specifically, the electronic device creating a null matrix according to the plurality of first dimension times and the plurality of second dimension times includes:
the electronic device uses the number of the plurality of first dimension times as the number of rows/columns, and uses the number of the plurality of second dimension times as the number of columns/rows to construct the empty matrix.
In this embodiment, the plurality of first dimension times and the plurality of second dimension times may be a plurality of years (such as 2017, 2018, 2019, 2020, 2021, 2022, etc.) in a certain arrangement order, a plurality of months (such as 1 month-12 months, etc.) in a certain arrangement order, a plurality of quarters (such as first quarter, second quarter, third quarter, and fourth quarter) in a certain arrangement order, a plurality of dates (such as 1 day-30 days in an ascending order) in a certain arrangement order, a plurality of times (0 point-24 points in an ascending order) in a certain arrangement order, or the like.
The arrangement order may be ascending order or descending order, and the dimensions of the plurality of first dimension times are different from the dimensions of the plurality of second dimensions. For example, if the plurality of first dimension times is a plurality of years, the plurality of second dimension times may be a plurality of months, a plurality of dates, or a plurality of times, etc.; if the plurality of first dimension times is a plurality of months, the plurality of second dimension times may be a plurality of years, a plurality of dates, or a plurality of moments, etc.; if the plurality of first dimension times is a plurality of dates, the plurality of second dimension times may be a plurality of times, a plurality of years, a plurality of months, or the like.
S12, selecting a second matrix from the first matrix based on preset time, and carrying out standardization processing on each historical energy consumption data in the second matrix to obtain a standardization matrix.
In at least one embodiment of the present application, the second matrix refers to a matrix formed by rows and columns except for the corresponding rows or columns of the preset time in the first matrix.
In at least one embodiment of the present application, the preset time refers to a predicted time of the energy consumption to be predicted, the preset time and the maximum historical time are continuous with each other, but the preset time is greater than the maximum historical time, the historical time refers to occurrence time of all historical energy consumption data in the first matrix, and each historical time includes a first historical dimension time and a second historical dimension time hereinafter. For example, when the maximum history time is 2022 year 11 month, the preset time may be 2022 year 12 month, or when the maximum history time is 2022 year 12 month, the preset time may be 2023 year 1 month.
In at least one embodiment of the present application, the selecting, by the electronic device, the second matrix from the first matrix based on the preset time includes:
The electronic device determines the time with the largest dimension in the preset time, determines the row or column corresponding to the time with the largest dimension in the first matrix as other data, and determines the other rows and columns except the other data in the first matrix as the second matrix.
Wherein the dimension of year > the dimension of quarter > the dimension of month > the dimension of date > the dimension of time. For example, if the preset time includes a preset year, the dimension of the year is the largest, so that a row or a column of the first matrix except for the preset year is determined as the other data, and other rows and columns of the first matrix except for the other data are determined as the second matrix;
in this embodiment, since the plurality of first dimension times and the plurality of second dimension times have a certain arrangement order, when the arrangement order of the plurality of first dimension times and the plurality of second dimension times is an ascending order, the other data generally corresponds to the last row or the last column in the first matrix, so the electronic device determines other rows/columns except for the last row or the last column in the first matrix as the second matrix, or when the arrangement order of the plurality of first dimension times and the plurality of second dimension times is a descending order, the other data generally corresponds to the first row or the first column in the first matrix, so the electronic device determines other rows/columns except for the first row or the first column in the first matrix as the second matrix.
For example, the obtained plurality of historical energy consumption data, the first historical dimension time of each historical energy consumption data, and the second historical dimension time may be as shown in table 1, where the plurality of first historical dimension times in table 1 are 8 months to 12 months, the plurality of first historical dimension times are ordered in ascending order from top to bottom, the plurality of second historical dimension times are 2018 years to 2022, and the plurality of second historical dimension times are ordered in ascending order from left to right.
TABLE 1 historical energy consumption data for historical time
For example, in connection with the above embodiment, when the obtained historical energy consumption data is as shown in Table 1, the first matrix is
The second preset time may be 2022 months 12, and since the preset time includes a preset year, other data corresponding to the preset time in the first matrix is the last row in the first matrix, and therefore the second matrix is the first matrixAll rows and all columns except the last row, therefore the second matrix is +.>
。
The detailed flow of the normalization process may refer to the flow shown in fig. 2, and fig. 2 is a flowchart of a data normalization processing method according to an embodiment of the present application.
S121, traversing all the historical energy consumption data in the second matrix by the electronic equipment, and selecting the largest historical energy consumption data and the smallest historical energy consumption data from the second matrix.
S122, the electronic equipment compares each historical energy consumption data in the second matrix with preset energy consumption index data.
And S123, if any historical energy consumption data in the second matrix is smaller than the energy consumption index data, the electronic equipment calculates a first difference value between the energy consumption index data and any historical energy consumption data.
S124, calculating standardized energy consumption data corresponding to any one of the historical energy consumption data according to the energy consumption index data, the preset value, the first difference value, the maximum historical energy consumption data and the minimum historical energy consumption data.
S125, if any one of the historical energy consumption data is larger than the energy consumption index data, the electronic equipment calculates a second difference value between any one of the historical energy consumption data and the energy consumption index data.
And S126, calculating the standardized energy consumption data according to the energy consumption index data, the preset value, the second difference value, the maximum historical energy consumption data and the minimum historical energy consumption data.
And S127, if any one of the historical energy consumption data is equal to the energy consumption index data, the electronic equipment determines the preset value as the standardized energy consumption data.
And S128, the electronic equipment replaces each historical energy consumption data in the second matrix with corresponding standardized energy consumption data to obtain the standardized matrix.
In this embodiment, the preset value is 1.
Specifically, the calculating, by the electronic device, the standardized energy consumption data corresponding to any one of the historical energy consumption data according to the energy consumption index data, the preset value, the first difference value, the maximum historical energy consumption data, and the minimum historical energy consumption data includes:
the electronic equipment calculates a third difference value between the energy consumption index data and the minimum historical energy consumption data, calculates a fourth difference value between the maximum historical energy consumption data and the energy consumption index data, then selects a larger value between the third difference value and the fourth difference value, calculates a difference value ratio between the first difference value and the larger value, and determines a difference value between the preset value and the difference value ratio as the standardized energy consumption data.
In this embodiment, the manner in which the electronic device calculates the standardized energy consumption data according to the energy consumption index data, the preset value, the second difference value, the maximum historical energy consumption data, and the minimum historical energy consumption data is substantially the same as the manner in which the electronic device calculates the standardized energy consumption data corresponding to any one of the historical energy consumption data according to the energy consumption index data, the preset value, the first difference value, the maximum historical energy consumption data, and the minimum historical energy consumption data, which is not repeated herein.
In this embodiment, by performing normalization processing on each of the historical energy consumption data in the second matrix, each of the historical energy consumption data can be normalized to a uniform range, so that each of the normalized data can be compared and the standard deviation and the correlation coefficient can be calculated.
S13, calculating standard deviation and correlation coefficient of each column in the standardized matrix, and calculating information bearing capacity of each column in the standardized matrix according to a preset value, the standard deviation and the correlation coefficient.
In at least one embodiment of the present application, the correlation coefficient refers to a coefficient of a degree of correlation between each column in the normalized matrix and any other column in the normalized matrix. The information bearing capacity refers to the information quantity of each column.
In at least one embodiment of the present application, the calculation formula of the standard deviation of each column in the standardized matrix is:
wherein,,
representing the +.sup.th in the normalization matrix>
Standard deviation of column>
Representing the +.sup.th in the normalization matrix>
Column +.>
Historical energy consumption data->
Represents the +.o of the normalization matrix>
Summing the average value of all historical energy consumption data in a column, < >>
Represents the +.o of the normalization matrix >
The number of all historical energy consumption data in a column.
In at least one embodiment of the present application, the correlation coefficient of each column in the normalization matrix is calculated by:
wherein,,
representing +.>
Column and->
Correlation coefficient between columns,/, for>
Representing the->
Column +.>
Historical energy consumption data of rows, +.>
Representing the->
Average value of all historical energy consumption data in column, +.>
First->
Column +.>
Historical energy consumption data of rows, +.>
Representing the->
The number of all historical energy consumption data in a column or said +.>
The number of all historical energy consumption data in a column, +.>
Representing the->
Average of all historical energy consumption data in the column.
In this embodiment, since the correlation coefficient is a coefficient between any two columns in the normalization matrix, each column in the normalization matrix has a plurality of correlation coefficients.
In at least one embodiment of the present application, the calculating, by the electronic device, the information carrying capacity of each column in the standardized matrix according to the preset value, the standard deviation, and the correlation coefficient includes:
the electronic equipment calculates coefficient difference values between the preset values and each correlation coefficient, calculates contradictory coefficients of each column in the standardized matrix according to a plurality of coefficient difference values, and calculates information bearing capacity of each column in the standardized matrix according to the standard deviation and the contradictory coefficients.
Wherein, the contradiction coefficient reflects the degree of correlation between different indexes, and if the obvious positive correlation is presented, the smaller the contradiction coefficient value is; set the first
The contradiction coefficient between the columns is +.>
The following steps are:
In this embodiment, the electronic apparatus determines a product of the standard deviation and the contradictory coefficient as the information bearing amount.
In this embodiment, because the standard deviation can represent the fluctuation of the historical energy consumption data in each column, the correlation coefficient can represent the correlation degree between each column and the rest columns in the standardized matrix, and the information bearing capacity integrates the correlation coefficient and the data change characteristic reflected by the standard deviation, so that the information bearing capacity of each column can reflect the energy consumption change rule corresponding to the historical energy consumption data in each column.
S14, according to the information bearing capacity, calculating the initial information weight of each column in the standardized matrix.
In at least one embodiment of the present application, the initial information weight refers to a proportion of the information bearing capacity of each column in the sum of the information bearing capacities corresponding to all columns.
In at least one embodiment of the present application, the calculating, by the electronic device, the initial information weight of each column in the standardized matrix according to the information bearing capacity includes:
the electronic device calculates the sum of the information bearing capacity of all columns in the standardized matrix, and determines the ratio between the information bearing capacity of each column and the sum of the information bearing capacity as the initial information weight of each column of data.
In this embodiment, since the initial information weight is a ratio between the information bearing capacity of each column and the sum of the information bearing capacities of all columns, the initial information weight of each column can intuitively characterize the importance degree of each column in the standardized matrix.
And S15, if any initial information weight meets a preset adjustment condition, adjusting a plurality of initial information weights according to the preset value to obtain a plurality of adjusted target information weights.
In at least one embodiment of the present application, each target information weight refers to a weight obtained by adjusting a corresponding initial information weight.
In at least one embodiment of the present application, if any one of the initial information weights satisfies a preset adjustment condition, the electronic device adjusts a plurality of the initial information weights according to the preset value, and obtaining a plurality of adjusted target information weights includes:
If any initial information weight is greater than the preset weight corresponding to the initial information weight, the electronic equipment acquires the parameter adjusting coefficient of each initial information weight, calculates the target information weight of each initial information weight according to each initial information weight and the parameter adjusting coefficient corresponding to each initial information weight, and ensures that all target information weights are added to be equal to the preset value.
The preset weights may be set by themselves, but in general, when the weights corresponding to each initial information weight are preset, the preset weights of the columns corresponding to the preset time will be larger as they are closer to each other. The preset value is 1.
In this embodiment, if any initial information weight is greater than a preset weight, the electronic device generates a prompt message to prompt a user for a parameter adjustment coefficient corresponding to each initial information weight, and then the electronic device may receive the input parameter adjustment coefficient corresponding to each initial information weight, and determine a product of each parameter adjustment coefficient and the corresponding initial information weight as a target information weight of each initial information weight.
Wherein, the prompt message can be set by oneself, which is not limited in this application. For example, the prompt information may be: when the initial information weight is abnormal, please input parameter adjusting coefficients corresponding to each initial information weight, and the like; the preset value is 1.
In this embodiment, when the weight of any initial information is greater than the preset weight, it is indicated that the prediction of the weight of any initial information is abnormal, so that on the premise of ensuring that the addition of all the target information weights is equal to 1, the parameter adjustment coefficient is used to adjust each initial information weight, so that the accuracy of the multiple target information weights can be improved.
If any initial information weight does not meet the preset adjustment condition, the initial information weight is not required to be adjusted, and the initial information weight is directly used as a plurality of target information weights.
S16, selecting a plurality of target energy consumption data corresponding to the plurality of target information weights from the first matrix based on a preset step length and the preset time, and calculating energy consumption prediction data corresponding to the preset time according to the plurality of target information weights and the plurality of target energy consumption data.
In at least one embodiment of the present application, the target energy consumption data refers to data selected from other data corresponding to the preset time.
In at least one embodiment of the present application, the selecting, by the electronic device, a plurality of target energy consumption data corresponding to the plurality of target information weights from the first matrix based on a preset step size and the preset time, and calculating, according to the plurality of target information weights and the plurality of target energy consumption data, energy consumption prediction data corresponding to the preset time includes:
The electronic equipment generates a plurality of target positions according to the preset step length and the preset time, and determines historical energy consumption data on the plurality of target positions in the first matrix as the plurality of target energy consumption data, the electronic equipment selects target information weights corresponding to columns to which each target energy consumption data belongs, calculates products of each target energy consumption data and the corresponding target information weights, and determines the sum of the products as the energy consumption prediction data.
The preset step length can be set by itself, which is not limited in the application. For example, the preset step size may be 3, 4, or 5, etc.
In this embodiment, the weighted average operation is performed on the plurality of target energy consumption data and the corresponding target information weight, so that the predicted energy consumption data is integrated, and therefore it can be ensured that the target energy consumption number is closer to the actual energy consumption situation.
In this embodiment, the target location includes a target row or a target column, and the generating, by the electronic device, a plurality of target locations according to the preset step size and the preset time includes:
the electronic equipment takes the row/column corresponding to the preset time in the first matrix as a target row/target column, selects a plurality of continuous target rows/target columns according to the preset step length, and determines historical energy consumption data in the plurality of continuous target rows/target columns as the target energy consumption data.
In this embodiment, the target row/column may be selected according to the actual situation of the preset time.
For example, when the first matrix is
When the preset time is 2022 month 12 and the preset step length is 4, because the preset time includes year 2022 year, the preset time corresponds to the last row in the first matrix, and because the preset step length is 4, 4 months that are mutually continuous with 12 months are selected, so that a column corresponding to 8-11 months that are mutually continuous with 12 months in the last row can be used as the target row/target column, 300, 400 and 200 in a column corresponding to 8-11 months in the last row are used as the target energy consumption data, and when the target information weights respectively corresponding to columns corresponding to 9-11 months are 0.2, 0.4 and 0.2, the energy consumption prediction data is 320=300×0.2+300×0.2+400×0.4+200×0.2.
In this embodiment, since the target energy consumption data is historical energy consumption data in a plurality of continuous target rows/a plurality of target columns, the continuous plurality of target energy consumption data has a larger association relationship, and therefore, when the preset time and the historical time of the plurality of target energy consumption data are mutually continuous times, the accuracy of the energy consumption prediction data can be ensured.
According to the technical scheme, the types of the historical energy consumption data are not limited, so that the energy consumption prediction method has wide applicability, each historical energy consumption data in the second matrix can be normalized to a uniform range through standardization processing, standard deviation and correlation coefficient of each column in the standardized matrix are more convenient to calculate, the standard deviation can represent fluctuation size in each column of the historical energy consumption data, the correlation coefficient can represent correlation degree of each column and other columns in the standardized matrix, and the information bearing capacity synthesizes the correlation coefficient and data change characteristics reflected by the standard deviation, so that the information bearing capacity of each column can reflect energy consumption change rules corresponding to each column of the historical energy consumption data. Because the initial information weight is the ratio between the information bearing capacity of each column and the sum of the information bearing capacities of all columns, the initial information weight of each column can intuitively represent the importance degree of each column in the standardized matrix, and meanwhile, the initial information weight of each column contains the energy consumption change rule information of the historical energy consumption data of each column. By adjusting the plurality of initial information weights, the adjusted plurality of target information weights can be more accurate. According to the method and the device for predicting the energy consumption corresponding to the preset time, the historical time of the plurality of target energy consumption data is continuous, and the continuous plurality of target energy consumption data have a larger association relationship, so that when the preset time and the historical time of the plurality of target energy consumption data are mutually continuous, the energy consumption prediction data are calculated through the target information weight containing the energy consumption change rule information and the continuous plurality of target energy consumption data, and the accuracy of the energy consumption prediction data can be ensured.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
In one embodiment of the present application, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and a computer program, such as an energy consumption prediction program, stored in the memory 12 and executable on the processor 13.
It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and may include more or less components than illustrated, or may combine certain components, or different components, e.g. the electronic device 1 may further include input-output devices, network access devices, buses, etc.
The processor 13 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor 13 is an operation core and a control center of the electronic device 1, connects various parts of the entire electronic device 1 by using various interfaces and lines, and obtains an operating system of the electronic device 1 and various installed application programs, program codes, etc.
The processor 13 obtains an operating system of the electronic device 1 and various applications installed. The processor 13 obtains the application program to implement the steps in the above-described embodiments of the energy consumption prediction method, for example, fig. 1 and 2.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory 12 and retrieved by the processor 13 to complete the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing a specific function for describing the acquisition procedure of the computer program in the electronic device 1.
The memory 12 may be used to store the computer program and/or module, and the processor 13 may implement various functions of the electronic device 1 by running or retrieving the computer program and/or module stored in the memory 12 and invoking data stored in the memory 12. The memory 12 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. In addition, the memory 12 may include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other non-volatile solid state storage device.
The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a physical memory, such as a memory bank, a TF Card (Trans-flash Card), or the like.
The integrated modules/units of the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by instructing related hardware by a computer program, where the computer program may be stored on a computer readable storage medium, and the computer program may implement the steps of each of the method embodiments described above when being acquired by a processor.
Wherein the computer program comprises computer program code which may be in the form of source code, object code, an available file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
In connection with fig. 1, the memory 12 in the electronic device 1 stores a plurality of instructions to implement a method of energy consumption prediction, the processor 13 may obtain the plurality of instructions to implement: generating a first matrix based on the acquired historical energy consumption data; selecting a second matrix from the first matrix based on preset time, and performing standardization processing on each historical energy consumption data in the second matrix to obtain a standardization matrix; calculating standard deviation and correlation coefficient of each column in the standardized matrix, and calculating information bearing capacity of each column in the standardized matrix according to a preset value, the standard deviation and the correlation coefficient; according to the information bearing capacity, calculating initial information weight of each column in the standardized matrix; if any initial information weight meets a preset adjustment condition, adjusting a plurality of initial information weights according to the preset value to obtain a plurality of adjusted target information weights; and selecting a plurality of target energy consumption data corresponding to the plurality of target information weights from the first matrix based on a preset step length and the preset time, and calculating energy consumption prediction data corresponding to the preset time according to the plurality of target information weights and the plurality of target energy consumption data.
Specifically, the specific implementation method of the above instructions by the processor 13 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
In addition, the energy consumption prediction method, the electronic device and the storage medium provided by the embodiments of the present invention are described in detail, and specific examples should be adopted to illustrate the principles and the embodiments of the present invention, where the descriptions of the above embodiments are only used to help understand the method and the core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A method of energy consumption prediction, the method comprising:
generating a first matrix based on the acquired historical energy consumption data;
selecting a second matrix from the first matrix based on preset time, and performing standardization processing on each historical energy consumption data in the second matrix to obtain a standardization matrix;
calculating standard deviation and correlation coefficient of each column in the standardized matrix, and calculating information bearing capacity of each column in the standardized matrix according to a preset value, the standard deviation and the correlation coefficient;
according to the information bearing capacity, calculating initial information weight of each column in the standardized matrix;
If any initial information weight meets a preset adjustment condition, adjusting a plurality of initial information weights according to the preset value to obtain a plurality of adjusted target information weights;
and selecting a plurality of target energy consumption data corresponding to the plurality of target information weights from the first matrix based on a preset step length and the preset time, and calculating energy consumption prediction data corresponding to the preset time according to the plurality of target information weights and the plurality of target energy consumption data.
2. The energy consumption prediction method according to claim 1, wherein generating the first matrix based on the acquired historical energy consumption data comprises:
acquiring a plurality of preset first dimension times and a plurality of preset second dimension times;
creating a null matrix according to the plurality of first dimension times and the plurality of second dimension times, wherein each first dimension time and each second dimension time correspond to a position in the null matrix;
determining a first historical dimension time and a second historical dimension time of each historical energy consumption data;
and confirming the corresponding positions of each first historical dimension time and each second historical dimension time in the empty matrix according to the plurality of first dimension times and the plurality of second dimension times, and writing the corresponding historical energy consumption data into the determined positions to obtain the first matrix.
3. The energy consumption prediction method according to claim 1, wherein the normalizing each historical energy consumption data in the second matrix to obtain a normalized matrix includes:
traversing all the historical energy consumption data in the second matrix, and selecting the largest historical energy consumption data and the smallest historical energy consumption data from the second matrix;
comparing each historical energy consumption data in the second matrix with preset energy consumption index data;
if any one of the historical energy consumption data in the second matrix is smaller than the energy consumption index data, calculating a first difference value between the energy consumption index data and any one of the historical energy consumption data;
calculating standardized energy consumption data corresponding to any one of the historical energy consumption data according to the energy consumption index data, the preset value, the first difference value, the maximum historical energy consumption data and the minimum historical energy consumption data; or alternatively
If any one of the historical energy consumption data is larger than the energy consumption index data, calculating a second difference value between any one of the historical energy consumption data and the energy consumption index data;
calculating the standardized energy consumption data according to the energy consumption index data, the preset value, the second difference value, the maximum historical energy consumption data and the minimum historical energy consumption data; or alternatively
If any one of the historical energy consumption data is equal to the energy consumption index data, determining the preset value as the standardized energy consumption data;
and replacing each historical energy consumption data in the second matrix with corresponding standardized energy consumption data to obtain the standardized matrix.
4. The energy consumption prediction method according to claim 3, wherein the calculating the normalized energy consumption data corresponding to the arbitrary historical energy consumption data according to the energy consumption index data, the preset value, the first difference value, the maximum historical energy consumption data, and the minimum historical energy consumption data includes:
calculating a third difference between the energy consumption index data and the minimum historical energy consumption data, and calculating a fourth difference between the maximum historical energy consumption data and the energy consumption index data;
selecting a larger value between the third difference value and the fourth difference value, and calculating a difference value ratio between the first difference value and the larger value;
and determining a difference value between the preset value and the difference value ratio as the standardized energy consumption data.
5. The energy consumption prediction method according to claim 1, wherein the correlation coefficient of each column in the standardized matrix is plural, and the calculating the information bearing capacity of each column in the standardized matrix according to the preset value, the standard deviation, and the correlation coefficient includes:
Calculating coefficient difference values between the preset value and each correlation coefficient, and calculating contradiction coefficients of each column in the standardized matrix according to a plurality of coefficient difference values;
and calculating the information bearing capacity of each column in the standardized matrix according to the standard deviation and the contradiction coefficient.
6. The energy consumption prediction method according to claim 1, wherein calculating the initial information weight of each column in the standardized matrix according to the information bearing capacity comprises:
calculating the sum of information bearing capacities of all columns in the standardized matrix;
the ratio between the information bearing capacity of each column and the sum of the information bearing capacities is determined as the initial information weight of each column of data.
7. The method for predicting energy consumption according to claim 1 or 6, wherein if any one of the initial information weights satisfies a preset adjustment condition, adjusting a plurality of the initial information weights according to the preset value, and obtaining a plurality of adjusted target information weights includes:
if any initial information weight is greater than the preset weight corresponding to the initial information weight, obtaining a parameter adjusting coefficient of each initial information weight;
and calculating the target information weight of each initial information weight according to each initial information weight and the parameter adjusting coefficient corresponding to each initial information weight, and ensuring that all the target information weights are added to be equal to the preset value.
8. The energy consumption prediction method according to claim 1, wherein selecting a plurality of target energy consumption data corresponding to the plurality of target information weights from the first matrix based on a preset step size and the preset time, and calculating the energy consumption prediction data corresponding to the preset time according to the plurality of target information weights and the plurality of target energy consumption data includes:
generating a plurality of target positions according to the preset step length and the preset time, and determining historical energy consumption data on the plurality of target positions in the first matrix as the plurality of target energy consumption data;
selecting a target information weight corresponding to a column to which each target energy consumption data belongs;
and calculating the product of each target energy consumption data and the corresponding target information weight, and determining the sum of a plurality of products as the energy consumption prediction data.
9. An electronic device, the electronic device comprising:
a memory storing at least one instruction; and
A processor to fetch instructions stored in the memory to implement the energy consumption prediction method of any one of claims 1 to 8.
10. A computer-readable storage medium, characterized by: the computer-readable storage medium having stored therein at least one instruction that is fetched by a processor in an electronic device to implement the energy consumption prediction method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310565254.7A CN116307284B (en) | 2023-05-19 | 2023-05-19 | Energy consumption prediction method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310565254.7A CN116307284B (en) | 2023-05-19 | 2023-05-19 | Energy consumption prediction method, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116307284A true CN116307284A (en) | 2023-06-23 |
| CN116307284B CN116307284B (en) | 2023-08-08 |
Family
ID=86785302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310565254.7A Active CN116307284B (en) | 2023-05-19 | 2023-05-19 | Energy consumption prediction method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116307284B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118115007A (en) * | 2024-03-28 | 2024-05-31 | 佛山市奥博环保技术有限公司 | Regional water environment comprehensive bearing capacity assessment method, system, equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818380A (en) * | 2017-09-29 | 2018-03-20 | 深圳和而泰智能控制股份有限公司 | Information processing method and server |
| US20210326696A1 (en) * | 2020-04-08 | 2021-10-21 | Sangmyung University Industry-Academy Cooperation Foundation | Method and apparatus for forecasting power demand |
| CN113553755A (en) * | 2021-06-07 | 2021-10-26 | 国网河北省电力有限公司馆陶县供电分公司 | Power system state estimation method, device and equipment |
| CN114186132A (en) * | 2021-12-13 | 2022-03-15 | 中国平安财产保险股份有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN114881344A (en) * | 2022-05-20 | 2022-08-09 | 山东大卫国际建筑设计有限公司 | Training method, device and medium for building energy consumption prediction model |
| WO2023005120A1 (en) * | 2021-07-27 | 2023-02-02 | 上海上实龙创智能科技股份有限公司 | Energy consumption prediction method and apparatus for building, and computer device and storage medium |
-
2023
- 2023-05-19 CN CN202310565254.7A patent/CN116307284B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107818380A (en) * | 2017-09-29 | 2018-03-20 | 深圳和而泰智能控制股份有限公司 | Information processing method and server |
| US20210326696A1 (en) * | 2020-04-08 | 2021-10-21 | Sangmyung University Industry-Academy Cooperation Foundation | Method and apparatus for forecasting power demand |
| CN113553755A (en) * | 2021-06-07 | 2021-10-26 | 国网河北省电力有限公司馆陶县供电分公司 | Power system state estimation method, device and equipment |
| WO2023005120A1 (en) * | 2021-07-27 | 2023-02-02 | 上海上实龙创智能科技股份有限公司 | Energy consumption prediction method and apparatus for building, and computer device and storage medium |
| CN114186132A (en) * | 2021-12-13 | 2022-03-15 | 中国平安财产保险股份有限公司 | Information recommendation method and device, electronic equipment and storage medium |
| CN114881344A (en) * | 2022-05-20 | 2022-08-09 | 山东大卫国际建筑设计有限公司 | Training method, device and medium for building energy consumption prediction model |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118115007A (en) * | 2024-03-28 | 2024-05-31 | 佛山市奥博环保技术有限公司 | Regional water environment comprehensive bearing capacity assessment method, system, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116307284B (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020119051A1 (en) | Cloud platform resource usage prediction method and terminal device | |
| US20240005030A1 (en) | Differentially Private Query Budget Refunding | |
| CN110443618B (en) | Method and device for generating wind control strategy | |
| CN116307284B (en) | Energy consumption prediction method, electronic device and storage medium | |
| CN110083475B (en) | Abnormal data detection method and device | |
| US9210219B2 (en) | Systems and methods for consistent hashing using multiple hash rings | |
| CA3080576A1 (en) | Differentially private budget tracking using renyi divergence | |
| CN109565452A (en) | System and method for determining optimal policy | |
| CN109032511B (en) | Data storage method, server and storage medium | |
| CN112488297B (en) | Neural network pruning method, model generation method and device | |
| CN114168318A (en) | Training method of storage release model, storage release method and equipment | |
| CN107067276A (en) | Determine the method and device of object influences power | |
| CN112632052B (en) | Heterogeneous data sharing method and intelligent sharing system | |
| CN113934920B (en) | Target information pushing method, device and storage medium | |
| Barletta et al. | Orthogonal expansions for VIX options under affine jump diffusions | |
| CN116452242A (en) | Game profit prediction method, device and equipment based on fitting regression | |
| US9092472B1 (en) | Data merge based on logical segregation | |
| CN113643140B (en) | Method, apparatus, device and medium for determining medical insurance expenditure influencing factors | |
| CN113392130B (en) | Data processing method, device and equipment | |
| CN114491699A (en) | Three-dimensional CAD software usability quantification method and device based on expansion interval number | |
| CN114238044A (en) | Method and device for calculating activity of open source project and computer equipment | |
| CN113780675A (en) | Consumption prediction method and device, storage medium and electronic equipment | |
| CN112667721A (en) | Data analysis method, device, equipment and storage medium | |
| CN110189234B (en) | Hotel information adjusting method and device for OTA platform | |
| CN108805692B (en) | Variable selection method and device and server |
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 |