CN113780630A - Method for realizing form code prediction based on historical electricity consumption data of electricity consumption customer - Google Patents
Method for realizing form code prediction based on historical electricity consumption data of electricity consumption customer Download PDFInfo
- Publication number
- CN113780630A CN113780630A CN202110944009.8A CN202110944009A CN113780630A CN 113780630 A CN113780630 A CN 113780630A CN 202110944009 A CN202110944009 A CN 202110944009A CN 113780630 A CN113780630 A CN 113780630A
- Authority
- CN
- China
- Prior art keywords
- data
- code
- historical
- active
- table code
- 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
- 230000005611 electricity Effects 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000000611 regression analysis Methods 0.000 claims abstract description 68
- 230000008859 change Effects 0.000 claims abstract description 30
- 238000012216 screening Methods 0.000 claims abstract description 21
- 238000005192 partition Methods 0.000 claims abstract description 10
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012417 linear regression Methods 0.000 claims description 8
- 238000006467 substitution reaction Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 8
- KRTSDMXIXPKRQR-AATRIKPKSA-N monocrotophos Chemical compound CNC(=O)\C=C(/C)OP(=O)(OC)OC KRTSDMXIXPKRQR-AATRIKPKSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Probability & Statistics with Applications (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Fuzzy Systems (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a method for realizing meter code prediction based on historical electricity consumption data of electricity customers, and belongs to the technical field of analysis and processing of electric energy metering data. The method comprises the steps of obtaining table code missing information, screening historical table code data, calculating active table code change rate and carrying out inter-partition statistics, judging active table code-time curves and corresponding regression analysis equations, solving regression analysis equation parameters, solving table codes corresponding to historical data time, judging deviation degree of predicted data and the like. The method can realize the prediction of the hourly electric quantity data within a period of time and provide effective data support for the production work of the power enterprises.
Description
Technical Field
The invention belongs to the technical field of electric energy metering data analysis and processing, particularly relates to a method for realizing meter code prediction based on historical electricity utilization data of electricity utilization customers, and particularly relates to a method for realizing meter code prediction of electricity utilization customers within a period of time (generally not more than 24 hours) through regression analysis based on historical electricity utilization data of electricity utilization customers.
Background
The electric power enterprise realizes the collection of data such as electric quantity, voltage, current, power and power factor in the multifunctional electronic electric energy meter through the cooperation of the metering automation system and the remote communication technology so as to be used for the work such as the settlement of electric charge and data analysis in the enterprise. However, with the construction of digital smart grids, power enterprises find that the previous data acquisition mode cannot meet the requirements of daily production, business management and the like, and therefore, the data volume and frequency of acquisition are gradually increased to realize data application in deeper business scenes.
The influence of the stability of the electric energy acquisition device and the communication channel often causes data loss such as the meter code and the power of related customers in the metering automation system, so that the normal operation of related work of an electric power enterprise is influenced. Most of the existing meter code/electric quantity data prediction methods predict the daily electric quantity or the monthly electric quantity of electricity customers, and the methods for predicting the meter code data of the electricity customers within a period of time (generally not more than 24 hours) are few, so that the problems that the electricity utilization conditions of most of the electricity customers within 24 hours are obviously changed along with the time, the electricity customers cannot predict the hour meter code/electric quantity of the electricity customers by adopting most of the prediction methods, or the deviation of the prediction result and the actual electricity utilization condition is large often occur, and the prediction data can not well guide the development of the daily production work of an electric power enterprise in the actual use process.
In a certain period of time, the electric equipment of most customers is relatively fixed, and the meter code and the electricity consumption are closely related to the use condition of the electric equipment, so that the invention provides a method for realizing the prediction of the meter code data of the customer by regression analysis based on the historical electricity consumption data of the customer, and the practical problems encountered in the production process of an electric power enterprise are solved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, solve the problems that a method for predicting meter data of a power consumption client within a period of time (generally not more than 24 hours) is less, and part of methods cannot well predict the power consumption condition of the power consumption client within each hour or the predicted electric quantity has larger deviation from the actual value, and provide a method for realizing meter code prediction based on historical power consumption data of the power consumption client.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a method for realizing form code prediction based on historical electricity utilization data of an electricity utilization client comprises the following steps:
step one, acquiring table code missing information: acquiring information of missing data of a power consumption client table in a period of time by a metering automation system;
step two, screening historical table code data: acquiring historical table code data of a power consumption client through a metering automation system, and screening the historical table code data according to the current table code data missing information of the power consumption client;
step three, calculating the change rate of the active codes and carrying out interval statistics: calculating the active table code change rate K value and carrying out interval statistics on the screened historical table code data of the electricity consumption client to obtain the number of the K values in each interval;
step four, judging the active power table code-time curve and the corresponding regression analysis equation: judging the type of the active table code-time curve corresponding to the historical data according to the obtained K value statistical result, and obtaining a regression analysis equation corresponding to the type;
step five, solving regression analysis equation parameters: solving a regression analysis equation to obtain an unknown variable in the regression analysis equation;
step six, solving the predicted active table code corresponding to the historical data time: according to the obtained regression equation, solving a table code corresponding to historical data time to serve as an active prediction table code;
step seven, calculating and judging the deviation degree of the predicted data: calculating the data deviation degree, verifying the obtained linear regression equation according to the data deviation degree, continuing to perform the next step if the conditions are met, and reselecting data from the second step for calculation if the conditions are not met until the conditions are met;
step eight, calculating an active table code: calculating an hourly power increment value according to an active prediction table code corresponding to historical data time, and then calculating active table code data missing from power customers at each moment;
step nine, calculating a reactive table code: calculating the reactive table code value missing from the power utilization customers at each moment according to the average power factor of the power utilization of the users;
step ten, outputting table codes: and marking the obtained active and reactive meter data which are lost by the electricity customers, and outputting the active and reactive meter data to a metering automation system so as to confirm and trace the related data in the later period.
Further, preferably, the specific method of the first step is as follows: n groups of table code data in the time period are inquired through a metering automation system, wherein n is more than or equal to 24 and is more than or equal to 3 (T)1，W1，Q1)，(T2Without, at the same time，None), … …, (T)n-1None, none), (T)n，Wn，Qn)，TnAt an hour of 24h, when Tn-1＞TnThen TnAdding 24h to the original value of the data, wherein T2To Tn-1No corresponding table data exists in the time period.
Further, preferably, the specific method of step two is: firstly, the active electric quantity delta W in the delta T time period is calculated, and the delta T is equal to Tn-T1，ΔW＝Wn-W1；
Then, querying data information of the historical table of the electricity consumer through a metering automation system, and screening n groups of continuous data, wherein n is more than or equal to 24 and is more than or equal to 3, namely (T)1’，W1’，Q1’)，(T2’，W2’，Q2’)，……，(Tn’，Wn’，Qn’)，Tn' at an hour of 24h, when Tn-1’＞TnWhen it is, then Tn'data is added with 24h on the basis of original values, so that delta T ═ T'n-T1′＝ΔT，ΔW′＝W′n-W1The value of ' satisfies the requirement of 1.05 delta W > delta W ' > 0.95 delta W, and delta W ' is most approximate to delta W.
Further, preferably, the specific method of step three is: will T1’，T2’，……，Tn' moment corresponding active table code value substitution formula
Calculating to obtain active table code change rate values K (1), K (2), … … and K (n-2), and dividing the obtained K value into three sections: k is more than 1.05, K is more than or equal to 1.05 and more than or equal to 0.95, and K is less than 0.95, and the number of the K values in the three sections is counted respectively.
Further, preferably, the specific method of step four is:
(1) when the number of K values in the interval of K < 0.95 is greater than or equal to 80% of the total number, the regression analysis equation is
(2) When the number of K values in the interval of K > 1.05 is greater than or equal to 80% of the total number, the regression analysis equation is
(3) In other cases, the regression analysis equation is
Further, in the seventh step, it is preferable that the regression equation satisfies the condition if all the obtained deviation degrees are equal to or less than 1%, and if not, the data is newly selected from the second step and calculated until a result satisfying the condition is obtained.
The invention also provides a system for realizing form code prediction based on historical electricity consumption data of electricity customers, which comprises the following steps:
the meter code missing information acquisition module is used for acquiring meter code missing information of the electricity consumption client within a period of time through the metering automation system;
the history table code data screening module is used for acquiring history table code data of the electricity consumer through the metering automation system and screening the history table code data according to the current table code data missing information of the electricity consumer;
the active table code change rate calculation and inter-partition statistics module is used for calculating the active table code change rate K value and performing inter-partition statistics on the screened historical table code data of the electricity utilization client to obtain the number of the K values in each partition;
the active table code-time curve and corresponding regression analysis equation judgment module is used for judging the type of the active table code-time curve corresponding to the historical data according to the obtained K value statistical result and obtaining a corresponding regression analysis equation;
the regression analysis equation parameter solving module is used for solving a regression analysis equation to obtain an unknown variable in the regression analysis equation;
the table code module corresponding to the historical data time is used for solving the table code corresponding to the historical data time according to the obtained regression equation to serve as the table code for successful prediction;
the data deviation degree judging and predicting module is used for calculating the data deviation degree; verifying the obtained linear regression equation according to the data deviation degree, continuing to perform the next step if the conditions are met, and reselecting data from the second step for calculation if the conditions are not met until the conditions are met;
the active power meter code calculating module is used for calculating an hourly power increment value according to the active power prediction meter code and then calculating active power meter code data missing from power customers at each moment;
the reactive power meter code calculating module is used for calculating the reactive power meter code value missing from the electricity utilization client at each moment according to the average power factor of the electricity utilization of the user;
and the meter code output module is used for marking the obtained active meter code data and reactive meter code data which are lost by the electricity customers and outputting the marked active meter code data and reactive meter code data to the metering automation system so as to confirm and trace the related data in the later period.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, and is characterized in that the processor executes the program to realize the steps of the method for realizing the table code prediction based on the historical electricity utilization data of the electricity utilization customers.
The present invention additionally provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the steps of the method for performing form prediction based on historical electricity usage data of electricity consumers as described above.
Compared with the prior art, the invention has the beneficial effects that:
in a certain time, electrical equipment of most customers is relatively fixed and has certain randomness, in the existing method, the hour electricity data missing from the customers are mostly predicted by adopting an interval hour electricity average value, and the influence on the table code prediction due to the difference of electricity utilization time and electricity utilization load is not considered, so that the problems that the prediction cannot be performed or the deviation of the prediction result and the actual electricity utilization condition is large are caused. The invention provides a method for realizing form code prediction based on historical electricity utilization data of electricity utilization customers, which comprises the steps of screening and judging the historical electricity utilization data, identifying a group of electric quantity data which are closer to the current electricity utilization condition, predicting hour electric quantity data within a period of time (generally not more than 24 hours) through regression analysis, eliminating influences caused by different electricity utilization time and fluctuation of electricity utilization load as far as possible, improving the accuracy and practicability of the hour form code prediction, and providing effective data support for production work of power enterprises.
Drawings
FIG. 1 is a flow chart of a method for implementing form code prediction based on historical electricity consumption data of electricity customers according to the present invention;
fig. 2 is a typical graph of the active table code of a power consumer over time.
FIG. 3 is a schematic structural diagram of a system for implementing form code prediction based on historical electricity consumption data of electricity customers according to the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples.
It will be appreciated by those skilled in the art that the following examples are illustrative of the invention only and should not be taken as limiting the scope of the invention. The examples do not specify particular techniques or conditions, and are performed according to the techniques or conditions described in the literature in the art or according to the product specifications. The materials or equipment used are not indicated by manufacturers, and all are conventional products available by purchase.
A method for realizing form code prediction based on historical electricity utilization data of an electricity utilization client comprises the following steps:
step one, acquiring table code missing information: acquiring information of missing data of a power consumption client table in a period of time by a metering automation system;
step two, screening historical table code data: acquiring historical table code data of a power consumption client through a metering automation system, and screening the historical table code data according to the current table code data missing information of the power consumption client;
step three, calculating the change rate of the active codes and carrying out interval statistics: calculating the active table code change rate K value and carrying out interval statistics on the screened historical table code data of the electricity consumption client to obtain the number of the K values in each interval;
step four, judging the active power table code-time curve and the corresponding regression analysis equation: judging the type of the active table code-time curve corresponding to the historical data according to the obtained K value statistical result, and obtaining a regression analysis equation corresponding to the type;
step five, solving regression analysis equation parameters: solving a regression analysis equation to obtain an unknown variable in the regression analysis equation;
step six, solving the predicted active table code corresponding to the historical data time: according to the obtained regression equation, solving a table code corresponding to historical data time to serve as an active prediction table code;
step seven, calculating and judging the deviation degree of the predicted data: calculating the data deviation degree, verifying the obtained linear regression equation according to the data deviation degree, continuing to perform the next step if the conditions are met, and reselecting data from the second step for calculation if the conditions are not met until the conditions are met;
step eight, calculating an active table code: calculating an hourly power increment value according to an active prediction table code corresponding to historical data time, and then calculating active table code data missing from power customers at each moment;
step nine, calculating a reactive table code: calculating the reactive table code value missing from the power utilization customers at each moment according to the average power factor of the power utilization of the users;
step ten, outputting table codes: and marking the obtained active and reactive meter data which are lost by the electricity customers, and outputting the active and reactive meter data to a metering automation system so as to confirm and trace the related data in the later period.
The specific method of the first step comprises the following steps: n groups of table code data in the time period are inquired through a metering automation system, wherein n is more than or equal to 24 and is more than or equal to 3 (T)1，W1，Q1)，(T2None, none), … …, (T)n-1None, none), (T)n，Wn，Qn)，TnAt an hour of 24h, when Tn-1＞TnThen TnAdding 24h to the original value of the data, wherein T2To Tn-1No corresponding table data exists in the time period.
The specific method of the second step is as follows: firstly, the active electric quantity delta W in the delta T time period is calculated, and the delta T is equal to Tn-T1，ΔW＝Wn-W1；
Then, querying data information of the historical table of the electricity consumer through a metering automation system, and screening n groups of continuous data, wherein n is more than or equal to 24 and is more than or equal to 3, namely (T)1’，W1’，Q1’)，(T2’，W2’，Q2’)，……，(Tn’，Wn’，Qn’)，Tn' at an hour of 24h, when Tn-1’＞TnWhen it is, then Tn' data should be added 24h on the basis of original value, so that T is equal to Tn-T1＝ΔT，ΔW＝Wn-W1The value of (A) meets the requirement that the value is more than 1.05 delta W and more than 0.95 delta W, and delta W' is closest to delta W.
The concrete method of the third step is as follows: will T1’，T2’，……，Tn' moment corresponding active table code value substitution formula
Calculating to obtain active table code change rate values K (1), K (2), … … and K (n-2), and dividing the obtained K value into three sections: k is more than 1.05, K is more than or equal to 1.05 and more than or equal to 0.95, and K is less than 0.95, and the number of the K values in the three sections is counted respectively.
The concrete method of the step four is as follows:
(1) when the number of K values in the interval of K < 0.95 is greater than or equal to 80% of the total number, the regression analysis equation is
(2) When the number of K values in the interval of K > 1.05 is greater than or equal to 80% of the total number, the regression analysis equation is
(3) In other cases, the regression analysis equation is
And seventhly, if the obtained deviation degrees are less than or equal to 1%, the regression equation meets the conditions, and if the deviation degrees are not met, the data are selected from the second step again for calculation until the result meeting the conditions is obtained.
The invention also provides a system for realizing form code prediction based on historical electricity consumption data of electricity customers, as shown in fig. 3, comprising:
the table code missing information acquiring module 101 is used for acquiring the information that the table code data of the electricity consumption client is missing in a period of time through a metering automation system;
the history table code data screening module 102 is used for acquiring history table code data of the electricity consumer through the metering automation system and screening the history table code data according to the current table code data missing information of the electricity consumer;
the active table code change rate calculation and inter-partition statistics module 103 is used for calculating an active table code change rate K value and performing inter-partition statistics on the screened historical table code data of the electricity utilization client to obtain the number of the K values in each partition;
the active table code-time curve and corresponding regression analysis equation judgment module 104 is used for judging the type of the active table code-time curve corresponding to the historical data according to the obtained K value statistical result and obtaining a regression analysis equation corresponding to the type;
a regression analysis equation parameter solving module 105, configured to solve a regression analysis equation to obtain an unknown variable in the regression analysis equation;
the table code module 106 for solving the historical data time correspondence is used for solving the table code corresponding to the historical data time according to the obtained regression equation to serve as the table code for active prediction;
a predicted data deviation degree judging module 107, configured to calculate a data deviation degree; verifying the obtained linear regression equation according to the data deviation degree, continuing to perform the next step if the conditions are met, and reselecting data from the second step for calculation if the conditions are not met until the conditions are met;
the active power table code calculating module 108 is used for calculating an hourly power increment value according to the active power prediction table code and then calculating active power table code data missing by power customers at each moment;
the reactive table code calculating module 109 is used for calculating the reactive table code value missing from the electricity customers at each moment according to the average power factor of the electricity consumed by the users;
and the meter code output module 110 is used for marking the obtained active and reactive meter code data which are lost by the electricity customers and outputting the marked active and reactive meter code data to the metering automation system so as to confirm and trace the related data in the later period.
The system for realizing the form code prediction based on the historical electricity utilization data of the electricity utilization customers can realize the hourly electricity quantity data prediction within a period of time and provide effective data support for the production work of power enterprises.
The system provided by the embodiment of the present invention is used for executing the above method embodiments, and for details of the process and the details, reference is made to the above embodiments, which are not described herein again.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and referring to fig. 4, the electronic device may include: a processor (processor)201, a communication Interface (communication Interface)202, a memory (memory)203 and a communication bus 204, wherein the processor 201, the communication Interface 202 and the memory 203 complete communication with each other through the communication bus 204. The processor 201 may call logic instructions in the memory 203 to perform the following method:
step one, acquiring table code missing information: acquiring information of missing data of a power consumption client table in a period of time by a metering automation system;
step two, screening historical table code data: acquiring historical table code data of a power consumption client through a metering automation system, and screening the historical table code data according to the current table code data missing information of the power consumption client;
step three, calculating the change rate of the active codes and carrying out interval statistics: calculating the active table code change rate K value and carrying out interval statistics on the screened historical table code data of the electricity consumption client to obtain the number of the K values in each interval;
step four, judging the active power table code-time curve and the corresponding regression analysis equation: judging the type of the active table code-time curve corresponding to the historical data according to the obtained K value statistical result, and obtaining a regression analysis equation corresponding to the type;
step five, solving regression analysis equation parameters: solving a regression analysis equation to obtain an unknown variable in the regression analysis equation;
step six, solving the predicted active table code corresponding to the historical data time: according to the obtained regression equation, solving a table code corresponding to historical data time to serve as an active prediction table code;
step seven, calculating and judging the deviation degree of the predicted data: calculating the data deviation degree, verifying the obtained linear regression equation according to the data deviation degree, continuing to perform the next step if the conditions are met, and reselecting data from the second step for calculation if the conditions are not met until the conditions are met;
step eight, calculating an active table code: calculating an hourly power increment value according to an active prediction table code corresponding to historical data time, and then calculating active table code data missing from power customers at each moment;
step nine, calculating a reactive table code: calculating the reactive table code value missing from the power utilization customers at each moment according to the average power factor of the power utilization of the users;
step ten, outputting table codes: and marking the obtained active and reactive meter data which are lost by the electricity customers, and outputting the active and reactive meter data to a metering automation system so as to confirm and trace the related data in the later period.
In addition, the logic instructions in the memory 203 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform a method for implementing table code prediction based on historical electricity consumption data of an electricity consumer according to the embodiments described above, for example, the method includes:
step one, acquiring table code missing information: acquiring information of missing data of a power consumption client table in a period of time by a metering automation system;
step two, screening historical table code data: acquiring historical table code data of a power consumption client through a metering automation system, and screening the historical table code data according to the current table code data missing information of the power consumption client;
step three, calculating the change rate of the active codes and carrying out interval statistics: calculating the active table code change rate K value and carrying out interval statistics on the screened historical table code data of the electricity consumption client to obtain the number of the K values in each interval;
step four, judging the active power table code-time curve and the corresponding regression analysis equation: judging the type of the active table code-time curve corresponding to the historical data according to the obtained K value statistical result, and obtaining a regression analysis equation corresponding to the type;
step five, solving regression analysis equation parameters: solving a regression analysis equation to obtain an unknown variable in the regression analysis equation;
step six, solving the predicted active table code corresponding to the historical data time: according to the obtained regression equation, solving a table code corresponding to historical data time to serve as an active prediction table code;
step seven, calculating and judging the deviation degree of the predicted data: calculating the data deviation degree, verifying the obtained linear regression equation according to the data deviation degree, continuing to perform the next step if the conditions are met, and reselecting data from the second step for calculation if the conditions are not met until the conditions are met;
step eight, calculating an active table code: calculating an hourly power increment value according to an active prediction table code corresponding to historical data time, and then calculating active table code data missing from power customers at each moment;
step nine, calculating a reactive table code: calculating the reactive table code value missing from the power utilization customers at each moment according to the average power factor of the power utilization of the users;
step ten, outputting table codes: and marking the obtained active and reactive meter data which are lost by the electricity customers, and outputting the active and reactive meter data to a metering automation system so as to confirm and trace the related data in the later period.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Examples of the applications
The method comprises the step one of acquiring table code missing information.
Active and reactive table code data in a period of time of a power consumption client are lost, and n groups (24 is more than or equal to n is more than or equal to 3) of table code data in the period of time are inquired by a metering automation system to be (T)1，W1，Q1)，(T2None, none), … …, (T)n-1None, none), (T)n，Wn，Qn)(TnAt an hour of 24h, when Tn-1＞TnThen TnThe data needs to be added for 24 hours on the basis of the original value. WnAnd QnAre respectively TnThe corresponding active and passive code values at the moment), wherein T2To Tn-1No corresponding and reactive table code data exist in the time period.
The second step of the invention is to screen the data of the history table.
First, Δ T (i.e., T) is calculatedn-T1) Active electric quantity Δ W (i.e. W) in time periodn-W1) Then, the data information of the historical list code of the electricity consumer is inquired through a metering automation system, and n groups (24 is more than or equal to n and more than or equal to 3) of continuous data are screened outData, i.e. (T)1’，W1’)，(T2’，W2’)，……，(Tn’，Wn’)(Tn' at an hour of 24h, when Tn-1’＞TnWhen it is, then Tn' data is added for 24h on the basis of the original value. WnIs' TnThe value of the active code corresponding to the time instant) so that it satisfies Δ T ═ Tn’-T1'-. DELTA.T, and C (C. -. DELTA.W/DELTA.W') satisfies the requirement of 1.05 DELTA.W > C > 0.95 DELTA.W, with the C value being closest to 1.
And step three, calculating the change rate of the table codes and carrying out interval statistics.
Will T1’，T2’，……，Tn' moment corresponding active table code value substitution formula
(24 is more than or equal to n and more than or equal to 3), calculating to obtain active power table code change rate values K (1), K (2), … … and K (n-2), and dividing the obtained K value into three sections: k is more than 1.05, K is more than or equal to 1.05 and more than or equal to 0.95, and K is less than 0.95, and the number of the K values in the three sections is counted respectively.
And step four, judging an active power table code-time curve and a corresponding regression analysis equation.
According to the correlation between the user active table code (W) and the time (T), a typical curve of the change of the active table code of the electricity utilization user with the time within a period of time is shown in FIG. 2.
(1) When the number of the K values in the interval of K < 0.95 is greater than or equal to 80% of the total number, the change rate of the active table code along with the time can be approximately considered to be gradually reduced, and the change relation of the active table code and the time is shown as a curve 2 in fig. 2, then the regression analysis equation can be assumed to be
(2) When the number of K values in the interval of K > 1.05 is greater than or equal to 80% of the total number, the change rate of the active codes along with the time is approximately considered to be gradually increased, and the active codes and the time areThe variation is shown by curve 3 in FIG. 2, then the regression analysis equation can be assumed to be
(3) In other cases, the change of the active codes and the time can be approximately considered to be linear, and the change relationship of the active codes and the time is shown as curve 1 in fig. 2, then the regression analysis equation can be assumed as
Step five, described herein, solves the regression analysis equation parameters.
(1) When the assumed regression analysis equation is
Then, the difference between the actual table code and the predicted table code can be expressed as:
the difference between all actual table codes and predicted table codes can be expressed as
To solve for the minimum value of Y, then an equation is solved in which the first partial derivatives with respect to the a and b parameters are both equal to 0, i.e.:
to obtain
(wherein
And
are respectively as
)。
(2) When the assumed regression analysis equation is
First, the equation should be transformed. Taking logarithm on both sides simultaneously to obtain
Order to
T *1/T, then
Thus can be composed of (T)1’，W1’)，(T2’，W2’)，……，(Tn’，Wn') obtaining transformed data (T)1 *，W1 *)，(T2 *，W2 *)，……，(Tn *，Wn *) Simultaneously establishing regression analysis equation for the transformed data
Solving a and b according to the method in (1), and obtaining A-e after inverse transformationaAnd B is-B, and finally obtaining a specific regression analysis equation
(3) When the assumed regression analysis equation is
First, the equation should be transformed. Taking logarithm on both sides simultaneously to obtain
Order to
T*When being T, then
Thus can be composed of (T)1’，W1’)，(T2’，W2’)，……，(Tn’，Wn') obtaining transformed data (T)1 *，W1 *)，(T2 *，W2 *)，……，(Tn *，Wn *) Simultaneously establishing regression analysis equation for the transformed data
Solving a and b according to the method in (1), and obtaining A-e after inverse transformationaB ═ B, the concrete regression analysis equation is finally obtained
And step six, solving the prediction table code corresponding to the historical data moment.
And solving the predicted active table code corresponding to the historical data time according to the obtained regression equation. Handle T1’，T2’，……，TnSubstituting the time value into the corresponding regression equation to calculate the table code
And seventhly, judging the deviation degree of the predicted data.
Defining a degree of deviation as
(n is more than or equal to 1), and the active prediction table code obtained in the sixth step
Substituting into a deviation calculation formula, and obtaining DEVI (1), DEVI (2) … … and DEVI (n) after calculation respectively, wherein if the obtained deviation degrees are less than or equal to 1%, the regression equation meets the condition, and if the deviation degrees are not met, the data are selected again from the second step for calculation until a result meeting the condition is obtained;
step eight of the invention, the active table code is calculated.
According to the prediction table code obtained by calculation in the sixth step
According to
(n is more than or equal to 1) formula, calculating the hourly power increment
Then T2To Tn-1The active codes predicted at the moment are respectively as follows:
step nine of the invention, reactive table code is calculated.
According to electricity consumption client TnThe value W of the active and inactive codes at the momentn，QnThe tangent tan phi of the average power factor angle phi of the client is obtainedn/WnAnd then W obtained in the step eight2、W3、……、Wn-1Substituting reactive table code calculation formula
T is obtained by calculation2To Tn-1The reactive table codes at the moment are respectively as follows: q1、Q2、……、Qn. Finally obtain T2To Tn-1The data of the time is (T)2，W2，Q2)，(T3，W3，Q3)，……，(Tn-1，Wn-1，Qn-1)。
Step ten of the invention, marking and outputting the result.
And outputting the result of the lack of electric quantity and marking the result so as to facilitate the confirmation and tracing of the related data at the later stage.
Specific examples are as follows:
(1) the missing table code information of the electricity consumer is as follows, (8, 906.38, 297.91), (9, none), … … (15, none), (16, 910.13, 299.15), and Δ T is T ═ Tn-T1＝8h，ΔW＝Wn-W1＝3.75kWh。
(2) Querying historical data of the electricity customer to obtain the result that the power customer is delta T ═ Tn’-T1’＝8h，ΔW’＝Wn’-W1' -3.67 kWh, C ═ Δ W/Δ W ═ 3.75/3.67 ═ 1.0218, the filtered customer history table data meet the requirements Δ T ═ Δ T, and 1.05 Δ W > C > 0.95, the specific data are shown in table 1 below.
TABLE 1 Power consumption customer historical data
| Time (h) | Watch code (kWh) | Time (h) | Watch code (kWh) | Time (h) | Watch code (kWh) |
| 6 | 113.04 | 9 | 113.84 | 12 | 115.69 |
| 7 | 113.28 | 10 | 114.33 | 13 | 116.25 |
| 8 | 113.59 | 11 | 114.87 | 14 | 116.71 |
(3) Calculating the change rate of the table code, and carrying out interval statistics on the table code, wherein the specific result is shown in the following table 2:
TABLE 2 TABLE code Rate of Change statistical table
| Interval(s) | K＞1.05 | 1.05≥K≥0.95 | K＜0.95 |
| Number of | 4 | 0 | 3 |
(4) According to the obtained statistical result, the result satisfies the judgment requirement of the condition (3), so the table code-time curve can be assumed as
(5) Solving to obtain
0.4803 and 109.8189, and calculating the regression analysis equation as
(6) According to the obtained regression analysis equation, the prediction table code corresponding to the time when the historical data is solved is shown in table 3 below:
TABLE 3 historical data time-corresponding prediction table code
(7) The deviation degree of the prediction table code corresponding to each historical data moment is calculated according to a deviation degree calculation formula and is shown in the following table 4, and the value of the deviation degree meets the requirement that the deviation degree is less than or equal to 1%.
TABLE 4 prediction table code deviation statistical table
| Time (h) | Prediction table code (kWh) | Actual watch code (kWh) | Degree of departure (%) |
| 6 | 112.70 | 113.04 | 0.30 |
| 7 | 113.18 | 113.28 | 0.09 |
| 8 | 113.66 | 113.59 | 0.06 |
| 9 | 114.14 | 113.84 | 0.27 |
| 10 | 114.62 | 114.33 | 0.26 |
| 11 | 115.10 | 114.87 | 0.20 |
| 12 | 115.58 | 115.69 | 0.09 |
| 13 | 116.06 | 116.25 | 0.16 |
| 14 | 116.54 | 116.71 | 0.14 |
(8) Calculating the current missing table code information, and counting as shown in the following table 5:
TABLE 5 currently missing Table code
| Time (h) | Watch code (kWh) | Time (h) | Watch code (kWh) |
| 9 | 906.87 | 13 | 908.83 |
| 10 | 907.36 | 14 | 909.32 |
| 11 | 907.85 | 15 | 909.82 |
| 12 | 908.34 | / | / |
(9) From the current table code of the user, the user average power factor tan phi ═ Qn/WnTable 6 shows the reactive table codes corresponding to the respective times calculated as 299.15/910.13:
table 6 reactive power table code at each time
(8) The data is marked and output, and is finally as shown in table 7 below:
table 7 reactive table code at each time
| Time (h) | Active watch code (kWh) | Reactive power meter code (kvarh) | Marker bit |
| 8 | 906.38 | 297.91 | 0 |
| 9 | 906.87 | 298.08 | 1 |
| 10 | 907.36 | 298.24 | 1 |
| 11 | 907.85 | 298.40 | 1 |
| 12 | 908.34 | 298.56 | 1 |
| 13 | 908.83 | 298.72 | 1 |
| 14 | 909.33 | 298.88 | 1 |
| 15 | 909.81 | 299.05 | 1 |
| 16 | 910.13 | 299.15 | 0 |
The method for predicting the hour electric quantity data missing from the customer by adopting the average value of the interval hour electric quantity comprises the following steps:
ΔW＝Wn-W13.75kWh, so that the average value of the electricity quantity in the customer hour is Δ W/(n-1) ═ 3.75/8 ═ 0.47 Δ Q/(n-1) ═ 1.24/8 ═ 0.15, and the customer has the reactive table codes at each moment as shown in the following table 8; the flag bit indicates that the data is flagged in the metering automation system, 1 indicates that the data is not from terminal collection but from system prediction (i.e. prediction by the method of the present invention), and 0 indicates that the data is from terminal collection.
Table 8 reactive power table code at each time
| Time (h) | Active watch code (kWh) | Reactive power meter code (kvarh) | Marker bit |
| 8 | 906.38 | 297.91 | 0 |
| 9 | 906.85 | 298.06 | 1 |
| 10 | 907.32 | 298.21 | 1 |
| 11 | 907.79 | 298.36 | 1 |
| 12 | 908.26 | 298.51 | 1 |
| 13 | 908.73 | 298.66 | 1 |
| 14 | 909.20 | 298.81 | 1 |
| 15 | 909.67 | 298.96 | 1 |
| 16 | 910.13 | 299.15 | 0 |
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A method for realizing form code prediction based on historical electricity consumption data of an electricity consumption client is characterized by comprising the following steps:
step one, acquiring table code missing information: acquiring information of missing data of a power consumption client table in a period of time by a metering automation system;
step two, screening historical table code data: acquiring historical table code data of a power consumption client through a metering automation system, and screening the historical table code data according to the current table code data missing information of the power consumption client;
step three, calculating the change rate of the active codes and carrying out interval statistics: calculating the active table code change rate K value and carrying out interval statistics on the screened historical table code data of the electricity consumption client to obtain the number of the K values in each interval;
step four, judging the active power table code-time curve and the corresponding regression analysis equation: judging the type of the active table code-time curve corresponding to the historical data according to the obtained K value statistical result, and obtaining a regression analysis equation corresponding to the type;
step five, solving regression analysis equation parameters: solving a regression analysis equation to obtain an unknown variable in the regression analysis equation;
step six, solving the predicted active table code corresponding to the historical data time: according to the obtained regression equation, solving a table code corresponding to historical data time to serve as an active prediction table code;
step seven, calculating and judging the deviation degree of the predicted data: calculating the data deviation degree, verifying the obtained linear regression equation according to the data deviation degree, continuing to perform the next step if the conditions are met, and reselecting data from the second step for calculation if the conditions are not met until the conditions are met;
step eight, calculating an active table code: calculating an hourly power increment value according to an active prediction table code corresponding to historical data time, and then calculating active table code data missing from power customers at each moment;
step nine, calculating a reactive table code: calculating the reactive table code value missing from the power utilization customers at each moment according to the average power factor of the power utilization of the users;
step ten, outputting table codes: and marking the obtained active and reactive meter data which are lost by the electricity customers, and outputting the active and reactive meter data to a metering automation system so as to confirm and trace the related data in the later period.
2. The method for realizing form code prediction based on historical electricity utilization data of electricity utilization customers according to claim 1, wherein the specific method in the first step is as follows: n groups of table code data in the time period are inquired through a metering automation system, wherein n is more than or equal to 24 and is more than or equal to 3 (T)1，W1，Q1)，(T2None, none), … …, (T)n-1None, none), (T)n，Wn，Qn)，TnAt an hour of 24h, when Tn-1＞TnThen TnAdding 24h to the original value of the data, wherein T2To Tn-1No corresponding table data exists in the time period.
3. The method for realizing form code prediction based on historical electricity utilization data of electricity utilization customers according to claim 2, wherein the specific method in the second step is as follows: firstly, the active electric quantity delta W in the delta T time period is calculated, and the delta T is equal to Tn-T1，ΔW＝Wn-W1；
Then, querying data information of the historical table of the electricity consumer through a metering automation system, and screening n groups of continuous data, wherein n is more than or equal to 24 and is more than or equal to 3, namely (T)1’，W1’，Q1’)，(T2’，W2’，Q2’)，……，(Tn’，Wn’，Qn’)，Tn' at an hour of 24h, when Tn-1’＞TnWhen it is, then Tn' data should be added 24h on the basis of original value, so that T is equal to Tn-T1＝ΔT，ΔW＝Wn-W1The value of (A) meets the requirement that the value is more than 1.05 delta W and more than 0.95 delta W, and delta W' is closest to delta W.
4. The method for realizing form code prediction based on historical electricity consumption data of electricity customers according to claim 3, wherein the specific method in the third step is as follows: will T1’，T2’，……，Tn' moment corresponding active table code value substitution formula
Calculating to obtain active table code change rate values K (1), K (2), … … and K (n-2), and dividing the obtained K value into three sections: k is more than 1.05, K is more than or equal to 1.05 and more than or equal to 0.95, and K is less than 0.95, and the number of the K values in the three sections is counted respectively.
5. The method for realizing form code prediction based on historical electricity utilization data of an electricity utilization client according to claim 4, wherein the specific method in the fourth step is as follows:
(1) when the number of K values in the interval of K < 0.95 is greater than or equal to 80% of the total number, the regression analysis equation is
(2) When the number of K values in the interval of K > 1.05 is greater than or equal to 80% of the total number, the regression analysis equation is
(3) In other cases, the regression analysis equation is
6. The method for realizing form code prediction based on historical electricity utilization data of electricity utilization customers according to claim 1, wherein in the seventh step, if the obtained deviation degrees are all less than or equal to 1%, the regression equation meets the condition, and if the deviation degrees are not met, the data are selected again from the second step for calculation until a result meeting the condition is obtained.
7. A system for realizing form code prediction based on historical electricity utilization data of electricity utilization customers is characterized by comprising the following steps:
the meter code missing information acquisition module is used for acquiring meter code missing information of the electricity consumption client within a period of time through the metering automation system;
the history table code data screening module is used for acquiring history table code data of the electricity consumer through the metering automation system and screening the history table code data according to the current table code data missing information of the electricity consumer;
the active table code change rate calculation and inter-partition statistics module is used for calculating the active table code change rate K value and performing inter-partition statistics on the screened historical table code data of the electricity utilization client to obtain the number of the K values in each partition;
the active table code-time curve and corresponding regression analysis equation judgment module is used for judging the type of the active table code-time curve corresponding to the historical data according to the obtained K value statistical result and obtaining a corresponding regression analysis equation;
the regression analysis equation parameter solving module is used for solving a regression analysis equation to obtain an unknown variable in the regression analysis equation;
the table code module corresponding to the historical data time is used for solving the table code corresponding to the historical data time according to the obtained regression equation to serve as the table code for successful prediction;
the data deviation degree judging and predicting module is used for calculating the data deviation degree; verifying the obtained linear regression equation according to the data deviation degree, continuing to perform the next step if the conditions are met, and reselecting data from the second step for calculation if the conditions are not met until the conditions are met;
the active power meter code calculating module is used for calculating an hourly power increment value according to the active power prediction meter code and then calculating active power meter code data missing from power customers at each moment;
the reactive power meter code calculating module is used for calculating the reactive power meter code value missing from the electricity utilization client at each moment according to the average power factor of the electricity utilization of the user;
and the meter code output module is used for marking the obtained active meter code data and reactive meter code data which are lost by the electricity customers and outputting the marked active meter code data and reactive meter code data to the metering automation system so as to confirm and trace the related data in the later period.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method of performing form code prediction based on historical electricity usage data of electricity consumers according to any one of claims 1 to 6.
9. A non-transitory computer readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method for implementing form prediction based on historical electricity usage data of electricity customers according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110944009.8A CN113780630B (en) | 2021-08-17 | 2021-08-17 | Method for realizing form code prediction based on historical electricity consumption data of electricity consumption customer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110944009.8A CN113780630B (en) | 2021-08-17 | 2021-08-17 | Method for realizing form code prediction based on historical electricity consumption data of electricity consumption customer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113780630A true CN113780630A (en) | 2021-12-10 |
| CN113780630B CN113780630B (en) | 2022-11-15 |
Family
ID=78838133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110944009.8A Active CN113780630B (en) | 2021-08-17 | 2021-08-17 | Method for realizing form code prediction based on historical electricity consumption data of electricity consumption customer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113780630B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111141950A (en) * | 2019-12-03 | 2020-05-12 | 深圳供电局有限公司 | Method for judging and repairing time-sharing code abnormality of electric meter of metering automation system |
| CN111177651A (en) * | 2019-12-03 | 2020-05-19 | 深圳供电局有限公司 | Time-sharing missing code fitting method for electric meter of metering automation system |
-
2021
- 2021-08-17 CN CN202110944009.8A patent/CN113780630B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111141950A (en) * | 2019-12-03 | 2020-05-12 | 深圳供电局有限公司 | Method for judging and repairing time-sharing code abnormality of electric meter of metering automation system |
| CN111177651A (en) * | 2019-12-03 | 2020-05-19 | 深圳供电局有限公司 | Time-sharing missing code fitting method for electric meter of metering automation system |
Non-Patent Citations (2)
| Title |
|---|
| 王松等: "电能量数据智能研判处理关键技术研究与应用", 《自动化应用》 * |
| 王绍槐等: "智能电能表日冻结表码停走原因分析及监测方法", 《大众用电》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113780630B (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Aghelinejad et al. | Production scheduling optimisation with machine state and time-dependent energy costs | |
| Zhang et al. | Conditional value at risk‐based stochastic unit commitment considering the uncertainty of wind power generation | |
| US7765123B2 (en) | Indicating which of forecasting models at different aggregation levels has a better forecast quality | |
| CN112070301B (en) | User electricity consumption adjustment method, system and equipment | |
| CN111612275A (en) | Method and device for predicting load of regional user | |
| CN104504479A (en) | Temperature/ economic growth factor considered monthly total electricity consumption predication method | |
| CN112508260B (en) | Medium-and-long-term load prediction method and device of distribution transformer based on comparative learning | |
| CN108830663B (en) | Electric power customer value evaluation method and system and terminal equipment | |
| CN113780630B (en) | Method for realizing form code prediction based on historical electricity consumption data of electricity consumption customer | |
| CN111160614B (en) | Training method and device of resource transfer prediction model and computing equipment | |
| CN113450142B (en) | Clustering analysis method and device for power consumption behaviors of power customers | |
| US20140288861A1 (en) | Sampling methodology for measuring power consumption for a population of power-consuming devices | |
| CN113033870B (en) | Flexible load scheduling method for power special transformer customer and terminal equipment | |
| CN108363789B (en) | Short-term missing repairing method and device for electricity consumption meter data of industrial and commercial users | |
| CN108346080B (en) | Flow package combination optimization method and device | |
| CN113705957A (en) | User cluster baseline load estimation method and device and terminal equipment | |
| CN112351105B (en) | Cloud service evaluation method and device | |
| CN116070781B (en) | Electric energy metering equipment demand prediction method and device and computer equipment | |
| Lee | Predicting key features of a substation without monitoring | |
| CN115085195B (en) | Distribution transformer annual maximum load rate prediction method and related device thereof | |
| CN117909706A (en) | Method and device for ordering cost influence factors and nonvolatile storage medium | |
| CN114399096A (en) | Transaction electric quantity optimization method based on reinforcement learning algorithm | |
| CN115660729A (en) | Distribution network engineering cost prediction method and device, terminal and storage medium | |
| CN115660436A (en) | Data processing method and device, computer readable storage medium and computer equipment | |
| CN117010653A (en) | Rights and interests distribution method, device, equipment and storage medium |
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 |