CN116756528B - Method, device, equipment and medium for complementing electricity load data - Google Patents
Method, device, equipment and medium for complementing electricity load data Download PDFInfo
- Publication number
- CN116756528B CN116756528B CN202311042511.5A CN202311042511A CN116756528B CN 116756528 B CN116756528 B CN 116756528B CN 202311042511 A CN202311042511 A CN 202311042511A CN 116756528 B CN116756528 B CN 116756528B
- Authority
- CN
- China
- Prior art keywords
- missing
- power consumption
- electricity
- historical
- load data
- 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.)
- Active
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 237
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002354 daily effect Effects 0.000 claims description 83
- 230000001502 supplementing effect Effects 0.000 claims description 26
- 230000000295 complement effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 230000003203 everyday effect Effects 0.000 claims description 4
- 230000003442 weekly effect Effects 0.000 claims description 4
- 230000006872 improvement Effects 0.000 abstract description 4
- 238000012217 deletion Methods 0.000 description 12
- 230000037430 deletion Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000008439 repair process Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a device, equipment and a medium for complementing electricity load data, which relate to the technical field of electric power data, and comprise the following steps: acquiring electricity load data and determining a missing period of time in the electricity load data; distributing the total consumed electric quantity to each day in the missing time period according to the missing time length proportion to obtain the consumed electric quantity corresponding to each day in the missing time period; determining a power consumption rule of a user, and adjusting the power consumption corresponding to each day of the missing time period to obtain the power consumption; performing feature coding on the electricity consumption of each day of the missing time period to obtain a matched data segment with highest similarity with the missing time period in the historical electricity consumption; and determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the power quantity corresponding to the matched data segment. The invention realizes the completion of the missing value in the power load data and ensures the improvement of the quality of the power load data.
Description
Technical Field
The invention relates to the technical field of power data, in particular to a method, a device, equipment and a medium for complementing power load data.
Background
The electricity load data is the basis of the operation of the intelligent power grid, and can be widely applied to the fields of stability analysis, fault detection, load prediction, load management and the like. The effect of these applications is largely dependent on the quality of the collected electrical load data, but the collected electrical load data may contain a certain proportion of missing values due to limitations and restrictions on data collection accuracy, data transmission and data storage reliability, thereby causing inaccuracy of the data in application.
Therefore, it is necessary to complement the missing value in the electrical load data.
Disclosure of Invention
In view of the above, the embodiments of the present invention provide a method, an apparatus, a device, and a medium for supplementing electrical load data, so as to solve the problem that the electrical load data collected in the prior art may include a certain proportion of missing values, thereby causing inaccuracy of the data in application.
According to a first aspect, an embodiment of the present invention provides a method for complementing electrical load data, which is characterized in that the method includes:
acquiring electricity load data and determining a missing period of time in the electricity load data; the electricity load data comprises two data of electricity consumption and electricity consumption power.
Based on the electricity consumption of the previous period and the next period adjacent to the missing period, determining the total electricity consumption of the missing period, and distributing the total electricity consumption to each day in the missing period according to the missing period proportion to obtain the electricity consumption corresponding to each day in the missing period;
determining a power consumption rule of a user based on historical power consumption load data without missing values, and adjusting the power consumption corresponding to each day of the missing period according to the user rule to obtain the power consumption corresponding to each day of the missing period;
carrying out feature coding on the electricity consumption of each day in the missing period according to the characteristics of the electricity consumption of each day, the characteristics of each week and the characteristics of each year, and matching the coded characteristics with the historical electricity consumption in the historical electricity consumption load data to obtain a matched data segment with highest similarity with the missing period in the historical electricity consumption;
and determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the power quantity corresponding to the matched data segment.
With reference to the first aspect, in a first implementation manner of the first aspect, the determining, based on the power consumption of the previous and the next adjacent missing time periods, the total power consumption of the missing time periods, and distributing the total power consumption to each day of the missing time periods according to the missing time length proportion, to obtain the power consumption corresponding to each day of the missing time periods specifically includes:
Subtracting the electricity consumption of the adjacent previous time period from the electricity consumption of the adjacent next time period in the missing time period to obtain the total electricity consumption of the missing time period;
and equally distributing the total power consumption to each day in the missing period according to the proportion of the missing duration in each day in the missing period, and obtaining the power consumption corresponding to each day in the missing period.
With reference to the first aspect, in a second implementation manner of the first aspect, the determining, based on historical electricity load data that does not include a missing value, an electricity consumption rule of a user, and adjusting, according to the user rule, electricity consumption corresponding to each day of a missing period, to obtain electricity consumption corresponding to each day of the missing period, includes:
determining average power consumption corresponding to each of the historical power consumption monday to sunday in the historical power consumption load data to obtain historical power consumption data;
determining historical daily electricity consumption by using all the historical weekly electricity consumption;
according to the difference value of the historical week electricity consumption and the historical day average electricity consumption, determining deviation average amounts respectively corresponding to monday to sunday;
superposing the deviation average quantity to the consumption electric quantity corresponding to each day of the corresponding missing time period to obtain a superposition value;
and determining the average value of all the overlapped deviation average amounts, and subtracting the average value from the overlapped value to obtain the power consumption corresponding to each day of the time period.
With reference to the first aspect, in a third implementation manner of the first aspect, the feature encoding is performed on the electricity consumption of each day in the missing period according to the electricity consumption feature of each day, the week feature and the year feature, and the encoded feature is used for matching with the historical electricity consumption in the historical electricity load data to obtain a matching data segment with highest similarity with the missing period in the historical electricity consumption, where the matching data segment specifically includes:
performing feature coding on the power consumption corresponding to each day in the missing period according to the daily power consumption features, the week features and the year features, and matching the coded features with the historical power consumption in the historical power consumption load data to obtain a matched data segment with highest similarity with the day in the historical power consumption;
and accumulating the matched data segments corresponding to the missing time period every day to obtain the matched data segments corresponding to the missing time period.
With reference to the third embodiment of the first aspect, in a fourth embodiment of the first aspect, the power consumption corresponding to each day in the missing period is encoded according to the daily power consumption characteristics, the week characteristics and the year characteristics, and the encoded characteristics are matched with the historical power consumption in the historical power consumption load data to obtain a matched data segment with the highest similarity with the day in the historical power consumption; the method specifically comprises the following steps:
Determining a daily electricity consumption difference characteristic between the daily of the missing period and the daily of the historical electricity load data based on the electricity consumption corresponding to the daily of the missing period, the electricity consumption corresponding to the daily of the historical electricity load data, the determined maximum electricity consumption and the determined maximum electricity consumption;
determining a week difference characteristic between the daily of the missing period and the daily of the historical electricity load data based on the week number corresponding to the daily of the missing period and the week number corresponding to the daily of the historical electricity load data;
determining an annual difference characteristic between the daily of the missing period and the daily of the historical electricity load data based on the specific number of days in one year corresponding to the daily of the missing period and the specific number of days in one year corresponding to the daily of the historical electricity load data;
and determining the weight corresponding to each characteristic, carrying out weighted summation on the daily electric quantity characteristic difference, the week characteristic difference and the year characteristic difference, determining the difference characteristic between the daily of the missing time period and the daily of the historical electric load data, and determining the date of the historical electric load data with the smallest difference characteristic as the matched data segment corresponding to the daily of the missing time period.
With reference to the first aspect, in a fifth implementation manner of the first aspect, the determining, based on a power consumption of the matching data segment, a power amount corresponding to the matching data segment, and obtaining, based on the power amount corresponding to the matching data segment, the power amount of the missing time segment specifically includes:
Determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment;
and determining the power consumption of the matched data segment, determining the proportion between the power consumption of the missing time segment and the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the proportion and the power quantity of the matched data segment.
With reference to the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect, the determining, based on the power consumption of the matching data segment, the power amount corresponding to the matching data segment specifically includes:
and determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment, the power consumption of the previous time segment adjacent to the matched data segment and the time difference between the two time segments.
According to a second aspect, an embodiment of the present invention further provides a device for supplementing electrical load data, where the device includes:
the loss determination module is used for obtaining the electricity load data and determining a loss time period in the electricity load data; the electricity load data comprises electricity consumption and power consumption;
the power distribution module is used for determining the total power consumption of the missing time period based on the power consumption of the previous time period and the next time period adjacent to the missing time period, and distributing the total power consumption to each day of the missing time period according to the missing time length proportion to obtain the power consumption corresponding to each day of the missing time period;
The first completion module is used for determining the electricity utilization rule of the user based on the historical electricity utilization load data without the missing value, and adjusting the consumed electricity quantity corresponding to each day of the missing period according to the user rule to obtain the consumed electricity quantity corresponding to each day of the missing period;
the characteristic matching module is used for carrying out characteristic coding on the electricity consumption of each day in the missing period according to the characteristics of the electricity consumption of each day, the characteristics of each week and the characteristics of each year, and matching the coded characteristics with the historical electricity consumption in the historical electricity consumption load data to obtain a matching data segment with highest similarity with the missing period in the historical electricity consumption;
the second completion module is used for determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the power quantity corresponding to the matched data segment.
According to a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method for supplementing electrical load data as described in any one of the above when the program is executed.
According to a fourth aspect, embodiments of the present invention also provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of supplementing electrical load data as described in any of the above.
According to the method, the device, the equipment and the medium for complementing the power consumption load data, the power consumption missing value in the power consumption load data is effectively complemented through the power consumption rule in the complete power consumption load data, the complete power consumption data section with the highest similarity is matched for the power consumption in the missing time section in a characteristic matching mode, so that the effective complementation of the power consumption missing value in the power consumption load data is realized, the missing value in the complete power consumption load data is realized, the quality improvement of the power consumption load data is ensured, the complete power consumption load data is provided for the application of downstream stability analysis, fault detection, load prediction, load management and the like, and the accuracy and the robustness of a downstream task model can be effectively improved.
Drawings
The features and advantages of the present invention will be more clearly understood by reference to the accompanying drawings, which are illustrative and should not be construed as limiting the invention in any way, in which:
FIG. 1 shows a schematic flow chart of a method for supplementing electrical load data provided by the invention;
fig. 2 is a schematic flowchart showing a specific step S20 in the method for complementing electric load data according to the present invention;
fig. 3 is a schematic flowchart showing a specific step S30 in the method for complementing electric load data according to the present invention;
Fig. 4 is a schematic flowchart showing a specific step S40 in the method for complementing electric load data according to the present application;
fig. 5 is a schematic flow chart showing a specific step S41 in the method for complementing electric load data provided by the present application;
fig. 6 is a schematic flowchart showing a specific step S50 in the method for complementing electric load data according to the present application;
FIG. 7 shows a repair diagram of the electricity consumption after the electricity consumption is completed in the method for completing the electricity consumption load data;
FIG. 8 shows a repair graph after the power amount is complemented in the method for complementing the power load data provided by the application;
FIG. 9 shows a schematic structural diagram of a complementing device for electrical load data provided by the application;
fig. 10 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Along with the development of smart power grids, the number of smart power meters is increased, and the smart power meters are responsible for recording and transmitting various power load data, such as voltage, reactive power, user power consumption and the like, which are the basis of smart power grid operation and can be widely applied to the fields of stability analysis, fault detection, load prediction, load management and the like. The effect of these applications is largely dependent on the quality of the collected electrical load data, but the collected electrical load data may contain a certain proportion of missing values due to limitations and restrictions on data collection accuracy, data transmission and data storage reliability, thereby causing inaccuracy of the data in application.
In order to solve the above-described problems, a method of complementing electrical load data is provided in the present embodiment. The method aims at complementing the missing value in the collected electricity load data. The method for supplementing the electrical load data according to the embodiment of the invention can be used in electronic equipment, including but not limited to computers, mobile terminals and the like, and fig. 1 is a schematic flow chart of the method for supplementing the electrical load data according to the embodiment of the invention, as shown in fig. 1, the method comprises the following steps:
S10, acquiring electricity load data, and determining a missing time period in the electricity load data. In the embodiment of the invention, the power consumption load data comprises two data of power consumption and power consumption.
The power load data can be offline data stored in the electronic equipment in advance, or can be online data acquired by the electronic equipment from the outside in real time. For example, the electronic device obtains from a smart meter, which is responsible for collecting online power load data.
The specific acquisition form of the electricity load data is not limited, and the electronic equipment can acquire the electricity load data.
In the embodiment of the invention, the power consumption load data is a series of time-adjacent and continuous load data sequences, the load data sequences are data sequences formed by a series of time-adjacent and continuous power consumption data, and in order to ensure the accuracy of the subsequent data supplementing process, the electronic equipment continuously acquires the power consumption load data, stores the complete power consumption load data and takes the complete power consumption load data as historical power consumption load data, supplements the power consumption load data with the missing condition, and takes the supplemented power consumption load data as the historical power consumption load data.
As a preferred implementation manner of the embodiment of the present invention, the electrical load data is stored for a preset time period every interval, so as to obtain a plurality of load data sequences, for example, the preset time period is set to be 15 minutes, and then the load data sequence is a data sequence with a complete duration of 15 minutes, that is, the time difference between the end and the beginning of the load data sequence is 15 minutes. It should be noted that, if a certain household electricity meter no longer collects the electricity load data of the user, the part less than the preset time period is also saved.
In step S10, it is determined that at least one missing period, that is, there may be a plurality of independent areas with missing values in the obtained electrical load data, where the missing values in each independent area are continuous, and each independent area may be composed of a plurality of obtained periods (preset periods), so that each independent area is one missing period, and each missing period includes its position in the electrical load data, the missing values contained in each missing period, the number of missing values, the date (which may be specific to a minute unit) to which the missing values specifically correspond, and so on.
And S20, determining the total power consumption of the missing time period based on the power consumption of the previous time period and the next time period adjacent to the missing time period, and distributing the total power consumption to each day of the missing time period according to the missing time length proportion to obtain the power consumption corresponding to each day of the missing time period.
In step S20, the number of missing values in each day in the missing period is counted and determined, the consumed electric quantity is distributed to the corresponding days according to the number proportion of missing values in each day, and the consumed electric quantity in the missing period is completed.
S30, determining a power consumption rule of a user based on historical power consumption load data without missing values, and adjusting the power consumption corresponding to each day of the missing period according to the user rule to obtain the power consumption corresponding to each day of the missing period.
In step S30, firstly, historical electricity consumption data, i.e. all electricity consumption data without missing values, in the historical electricity consumption load data are queried, average values of electricity consumption from monday to sunday in the electricity consumption data are obtained respectively, historical week electricity consumption data are obtained, average electricity consumption per day is obtained by using all week electricity consumption data, after finding out a week electricity consumption rule, the week electricity consumption rule is superimposed on the electricity consumption corresponding to each day of the missing period, in the embodiment of the invention, in order to keep the sum of the electricity consumption in the missing period unchanged, and finally, the average value of all superimposed electricity consumption is uniformly subtracted in each day of the missing period.
And S40, carrying out feature coding on the electricity consumption of each day in the missing period according to the characteristics of the electricity consumption of each day, the characteristics of each week and the characteristics of each year, and utilizing the coded characteristics to match with the historical electricity consumption in the historical electricity consumption load data so as to obtain a matched data segment with highest similarity with the missing period in the historical electricity consumption. It is understood that the data of each time period in the historical electricity load data is complete, i.e. the historical electricity load data is composed of electricity consumption and power amount data of multiple complete time periods.
And searching a section of complete power consumption data with the smallest difference with the missing time section, wherein the similarity between the power consumption data of the complete time section and the power consumption data of the missing time section is highest, taking the complete time section as a matching time section, and then using the power quantity corresponding to the section of data to complement the power data missing value in the missing time section.
S50, determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the power quantity corresponding to the matched data segment.
According to the method for complementing the power consumption load data, provided by the invention, the power consumption missing value in the power consumption load data is effectively complemented by the power consumption rule in the complete power consumption load data, and the power consumption in the missing period is matched with a complete power consumption data segment with highest similarity by using the characteristic matching mode, so that the effective complementation of the power consumption missing value in the power consumption load data is realized, the missing value in the complete power consumption load data is complemented, the improvement of the power consumption load data quality is ensured, the complete power consumption load data is provided for the applications such as downstream stability analysis, fault detection, load prediction, load management and the like, and the accuracy and the robustness of a downstream task model can be effectively improved.
The following describes a method for supplementing electric load data provided by the present invention with reference to fig. 2, and step S20 specifically includes:
s21, subtracting the electricity consumption of the adjacent next time period from the electricity consumption of the adjacent previous time period of the missing time period to obtain the total electricity consumption of the missing time period.
Wherein,indicating the loss period of electrical load data +.>Is used for the power consumption of the battery; />Representing a missing period +.>The number of middle electric quantity missing values; />Representing a missing period +.>A last time period (time acquisition node); />Representing the amount of electricity used.
It should be noted that, here, the unit of "1" is determined according to the preset time period, and the specific value of "1" is the duration of the preset time period.
S22, the total power consumption is distributed to each day in the missing period in an equal proportion according to the proportion of the missing duration in each day in the missing period, and the power consumption corresponding to each day in the missing period is obtained.
Wherein,representation with deletion period->Is>The power consumption is completed in the day; />Indicate->The power consumption is known, especially when +.>The power data of all the nodes at all times of the day are unknown, and the power data of all the nodes at all times of the day are +.>The value is 0; />Indicate->The number of missing values in a day, for a certain day, the total number of data amounts is the length of the day divided by the preset time period.
The following describes a method for supplementing electric load data provided by the present invention with reference to fig. 3, and step S30 specifically includes:
and S31, determining average power consumption corresponding to the historical power consumption monday to the sunday in the historical power consumption load data, and obtaining historical power consumption data.
Wherein,representing the week>（/>Minimum value of 1, maximum value of 7) average power consumption;representing +.>Zhou->The power consumption of the day; />Representing a common->Historical electricity usage data for the week.
S32, determining the historical daily electricity consumption by using all the historical weekly electricity consumption.
Wherein,indicating the historical daily electricity consumption.
S33, determining deviation average amounts respectively corresponding to monday to sunday according to the difference value of the historical power consumption and the historical power consumption.
Wherein,indicating>Average power consumption>Daily electricity consumption->Is offset by an average amount.
S34, superposing the deviation average quantity to the power consumption corresponding to each day of the corresponding missing period to obtain a superposition value, wherein each day of the missing period is the day of the week, and then adding the week corresponding to the day of the weekDeviation average amount +.>For example, wednesday->Average power consumption>Daily electricity consumption->And (3) superposing the deviation average quantity of the obtained values to the consumed electric quantity corresponding to the Monday of the missing time period to obtain the superposition value corresponding to the Monday of the missing time period.
And S35, determining the average value of all the overlapped deviation average amounts, and subtracting the average value from the overlapped value to obtain the power consumption corresponding to each day of the time period.
In particular, in the method, if only a single missing value exists in a determined missing period, the power consumption of the missing period can be directly obtained by using a linear interpolation mode:
wherein,indicating the loss period of electrical load data +.>Is used for supplementing electricity; />Indicating the moment of loss of electrical load data +.>Previous acquisition period +.>Is used for the electricity consumption of the (a); />Indicating the loss period of electrical load data +.>The latter acquisition period->Is used for the power consumption of the battery.
The following describes a method for supplementing electric load data provided by the present invention with reference to fig. 4, and step S40 specifically includes:
and S41, carrying out feature coding on the power consumption corresponding to each day in the missing period according to the daily power consumption features, the week features and the year features, and matching the coded features with the historical power consumption in the historical power consumption load data to obtain a matched data segment with highest daily similarity in the historical power consumption and the missing period. It can be understood that the matching data segment with the highest similarity of daily electricity consumption is the electricity consumption of one day of the historical electricity load data.
S42, accumulating the matched data segments corresponding to the missing time segments every day to obtain the matched data segments corresponding to the missing time segments.
The following describes a method for supplementing electric load data provided by the present invention with reference to fig. 5, and step S41 specifically includes:
s411, determining a daily electricity consumption difference characteristic between the daily of the missing period and the daily of the historical electricity load data based on the electricity consumption corresponding to the daily of the missing period, the electricity consumption corresponding to the daily of the historical electricity load data, the determined maximum electricity consumption and the determined maximum electricity consumption.
Wherein,indicating the +.>A day; />Indicating the +.>A day; />Representation->And (3) withThe difference characteristic of the daily electricity quantity; />Representation->Is used for the electricity consumption of the (a); />Representation->Is used for the electricity consumption of the (a); />Representing a maximum value of the amount of electricity usage data (including currently acquired electricity usage load data and stored historical electricity usage load data);representing the minimum of the amount of electricity usage data, including the currently acquired electricity usage load data and the stored historical electricity usage load data.
And S412, determining the week difference characteristic between the daily of the missing time period and the daily of the historical electricity load data based on the week number corresponding to the daily of the missing time period and the week number corresponding to the daily of the historical electricity load data.
Wherein,representation->And->Zhou Cha therebetweenDifferent characteristics, the day refers to the day of the week, the first day is Monday, and so on.
For example, the number of the cells to be processed,is the first day of the fifth week, +.>Is the first day of the first week, then the week difference for these two days is characterized as 0; />Is the first day of the fifth week, +.>The second day of the first week, both days being workdays, then the week difference for both days is characterized as 0.5; />Is the first day of the fifth week, +.>Is the sixth day of the first week, +.>And->Neither belonging to the same day within a week nor both weekdays/weekends, the week difference for these two days is characterized as 1.
And S413, determining the annual difference characteristic between the daily of the missing time period and the daily of the historical electricity load data based on the specific days in one year corresponding to the daily of the missing time period and the specific days in one year corresponding to the daily of the historical electricity load data. I.e. the first to be in the missing periodDay and +.f. in complete time period>Phase differenceThe fewer the days, the smaller the annual feature difference degree and the higher the similarity; conversely, the +.sup.th in the deletion period>Day and +.f. in complete time period>The more days the days differ, the greater the annual feature difference, the less the similarity.
Wherein,representation->And->The characteristics of the annual differences between them; />Representation->Days in one year; />Representation->Days in one year; />The number of days of one year is represented, and the specific value is 365 or 366.
And S414, determining the weight corresponding to each feature, carrying out weighted summation on the daily electricity consumption feature difference, the week feature difference and the year feature difference, determining the difference feature between the daily of the missing time period and the daily of the historical electricity load data, and determining the date of the historical electricity load data with the smallest difference feature as the matched data segment corresponding to the daily of the missing time period.
Wherein,representation->And->The larger the difference feature is, the smaller the similarity is, and on the contrary, the smaller the difference feature is, the larger the similarity is; />Representation->Weights of (2); />Representation->Weights of (2); />Representation->Is a weight of (2). Preferably, a +>The value is 10 @, @>The value is 2 @, @>The value is 5.
The following describes a method for supplementing electric load data provided by the present invention with reference to fig. 6, and step S50 specifically includes:
s51, determining the power quantity corresponding to the matched data segment based on the power consumption quantity of the matched data segment.
The historical power amount data in the historical power load data may be offline data stored in the electronic device in advance, or may be obtained by the electronic device based on the historical power amount data. The specific acquisition form of the electricity load data is not limited, and the electronic equipment can acquire the electricity load data.
The method for obtaining the historical power quantity data based on the historical power consumption data comprises the following steps:
wherein,representing the amount of power of the matched data segment, in particular +.>Is power sequence data;representing the power consumption of the matched data segment; />Representing the power consumption of the last time period adjacent to the matched data segment; />Representing the time interval of matching data segments.
S52, determining the power consumption of the matched data segment, determining the ratio between the power consumption of the missing time segment and the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the ratio and the power quantity of the matched data segment.
Wherein,represents the amount of power in the absence period, in particular +.>Is power sequence data; />Representing the power consumption of the matching data segment, calculated in a manner corresponding to +.>And consistent.
By the method, the power quantity corresponding to the missing time period daily can be obtained, and then the total power quantity of the missing time period is obtained.
Referring to fig. 7 and 8, fig. 7 is a schematic diagram of a repair of electricity consumption data in a missing period, where an abscissa unit is hours, an ordinate unit is watt hours, and a dotted line portion is the data of the repair; fig. 8 is a schematic diagram of the repair of the power amount data in the missing period, in which the abscissa is in hours, the ordinate is in watts, the broken line portion is the completed data, and the vertical line is used to separate the completed data from the complete data (solid line portion) that does not contain the missing value.
The description of the device for supplementing the electrical load data provided by the embodiment of the invention is provided below, and the device for supplementing the electrical load data described below and the method for supplementing the electrical load data described above can be referred to correspondingly.
In order to solve the above-described problems, a complementing device for electric load data is provided in the present embodiment. The method aims at complementing the missing value in the collected electricity load data. The device for supplementing electricity load data according to the embodiment of the invention can be used in electronic equipment, including but not limited to computers, mobile terminals and the like, and fig. 9 is a schematic flow chart of the device for supplementing electricity load data according to the embodiment of the invention, as shown in fig. 9, the device comprises the following steps:
the loss determination module 10 is configured to obtain the electrical load data and determine a loss period in the electrical load data. In the embodiment of the invention, the power consumption load data comprises two data of power consumption and power consumption.
The power load data can be offline data stored in the electronic equipment in advance, or can be online data acquired by the electronic equipment from the outside in real time. For example, the electronic device obtains from a smart meter, which is responsible for collecting online power load data.
The specific acquisition form of the electricity load data is not limited, and the electronic equipment can acquire the electricity load data.
In the embodiment of the invention, the power consumption load data is a series of time-adjacent and continuous load data sequences, the load data sequences are data sequences formed by a series of time-adjacent and continuous power consumption data, and in order to ensure the accuracy of the subsequent data supplementing process, the electronic equipment continuously acquires the power consumption load data, stores the complete power consumption load data and takes the complete power consumption load data as historical power consumption load data, supplements the power consumption load data with the missing condition, and takes the supplemented power consumption load data as the historical power consumption load data.
As a preferred implementation manner of the embodiment of the present invention, the electrical load data is stored for a preset time period every interval, so as to obtain a plurality of load data sequences, for example, the preset time period is set to be 15 minutes, and then the load data sequence is a data sequence with a complete duration of 15 minutes, that is, the time difference between the end and the beginning of the load data sequence is 15 minutes. It should be noted that, if a certain household electricity meter no longer collects the electricity load data of the user, the part less than the preset time period is also saved.
The deletion determining module 10 determines at least one deletion time period, that is, there may be a plurality of independent areas with deletion values in the obtained electrical load data, where the deletion values in each independent area are continuous, and each independent area may be composed of a plurality of acquisition time periods (preset time periods), so that each independent area is one deletion time period, and each deletion time period includes its position in the electrical load data, the deletion value contained in each deletion time period, the number of deletion values, the date (which may be specific to a minute unit) to which the deletion value specifically corresponds, and so on.
The power distribution module 20 is configured to determine a total power consumption of the missing period based on power consumption of a previous period and a next period adjacent to the missing period, and distribute the total power consumption to each day of the missing period according to a missing period proportion, so as to obtain power consumption corresponding to each day of the missing period.
The power distribution module 20 counts and determines the number of missing values of each day in the missing period, distributes the consumed power to the corresponding days according to the number proportion of missing values of each day, and complements the consumed power in the missing period.
The first completion module 30 is configured to determine a power consumption rule of a user based on historical power consumption load data that does not contain a missing value, and adjust power consumption corresponding to each day of the missing period according to the user rule, so as to obtain power consumption corresponding to each day of the missing period.
The first completion module 30 firstly inquires historical electricity consumption data in the historical electricity consumption load data, namely all electricity consumption data without missing values, averages the electricity consumption from monday to sunday in the electricity consumption data respectively to obtain historical week electricity consumption data, then calculates average electricity consumption per day by using all week electricity consumption data, and adds the week electricity consumption rule to the electricity consumption corresponding to each day of the missing period after finding the week electricity consumption rule.
The feature matching module 40 is configured to perform feature encoding on the power consumption of each day in the missing period according to the daily power consumption feature, the week feature and the year feature, and match the encoded feature with the historical power consumption in the historical power consumption load data to obtain a matched data segment with highest similarity with the missing period in the historical power consumption. It is understood that the data of each time period in the historical electricity load data is complete, i.e. the historical electricity load data is composed of electricity consumption and power amount data of multiple complete time periods.
And searching a section of complete power consumption data with the smallest difference with the missing time section, wherein the similarity between the power consumption data of the complete time section and the power consumption data of the missing time section is highest, taking the complete time section as a matching time section, and then using the power quantity corresponding to the section of data to complement the power data missing value in the missing time section.
The second completion module 50 is configured to determine an amount of power corresponding to the matching data segment based on the amount of power used for the matching data segment, and obtain an amount of power of the missing time segment based on the amount of power corresponding to the matching data segment.
According to the device for complementing the power consumption load data, provided by the invention, the power consumption missing value in the power consumption load data is effectively complemented by the power consumption rule in the complete power consumption load data, and the complete power consumption data with highest similarity is matched for the power consumption in the missing time period by using the characteristic matching mode, so that the effective complementation of the power consumption missing value in the power consumption load data is realized, the missing value in the complete power consumption load data is complemented, the improvement of the power consumption load data quality is ensured, the complete power consumption load data is provided for the applications such as downstream stability analysis, fault detection, load prediction, load management and the like, and the accuracy and the robustness of a downstream task model can be effectively improved.
Fig. 10 illustrates a physical structure diagram of an electronic device, as shown in fig. 10, which may include: processor 510, communication interface (Communications Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. Processor 510 may invoke logic commands in memory 530 to perform a method of supplementing electrical load data, the method comprising:
acquiring electricity load data and determining a missing period of time in the electricity load data; the electricity load data comprises two data of electricity consumption and electricity consumption power.
Based on the electricity consumption of the previous period and the next period adjacent to the missing period, determining the total electricity consumption of the missing period, and distributing the total electricity consumption to each day in the missing period according to the missing period proportion to obtain the electricity consumption corresponding to each day in the missing period;
determining a power consumption rule of a user based on historical power consumption load data without missing values, and adjusting the power consumption corresponding to each day of the missing period according to the user rule to obtain the power consumption corresponding to each day of the missing period;
Carrying out feature coding on the electricity consumption of each day in the missing period according to the characteristics of the electricity consumption of each day, the characteristics of each week and the characteristics of each year, and matching the coded characteristics with the historical electricity consumption in the historical electricity consumption load data to obtain a matched data segment with highest similarity with the missing period in the historical electricity consumption;
and determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the power quantity corresponding to the matched data segment.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in some part contributing to the prior art in the form of a software medium, which may be stored in a computer readable storage medium such as ROM/RAM, a magnetic disk, an optical disk, etc., including several commands for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the various embodiments or methods of some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (7)
1. A method of supplementing electrical load data, the method comprising:
acquiring electricity load data and determining a missing period of time in the electricity load data; the electricity load data comprises electricity consumption and power consumption;
based on the electricity consumption of the previous period and the next period adjacent to the missing period, determining the total electricity consumption of the missing period, and distributing the total electricity consumption to each day in the missing period according to the missing period proportion to obtain the electricity consumption corresponding to each day in the missing period;
determining a power consumption rule of a user based on historical power consumption load data without missing values, and adjusting the power consumption corresponding to each day of the missing period according to the user rule to obtain the power consumption corresponding to each day of the missing period;
Carrying out feature coding on the electricity consumption of each day in the missing period according to the characteristics of the electricity consumption of each day, the characteristics of each week and the characteristics of each year, and matching the coded characteristics with the historical electricity consumption in the historical electricity consumption load data to obtain a matched data segment with highest similarity with the missing period in the historical electricity consumption;
determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the power quantity corresponding to the matched data segment;
the method for determining the electricity consumption rule of the user based on the historical electricity consumption load data without the missing value comprises the steps of:
determining average power consumption corresponding to each of the historical power consumption monday to sunday in the historical power consumption load data to obtain historical power consumption data;
determining historical daily electricity consumption by using all the historical weekly electricity consumption;
according to the difference value of the historical week electricity consumption and the historical day average electricity consumption, determining deviation average amounts respectively corresponding to monday to sunday;
superposing the deviation average quantity to the consumption electric quantity corresponding to each day of the corresponding missing time period to obtain a superposition value;
Determining the average value of all superimposed deviation average amounts, and subtracting the average value from the superimposed value to obtain the power consumption corresponding to each day in the time period;
the method for obtaining the matching data segment with highest similarity with the missing time segment in the historical electricity consumption comprises the following steps:
performing feature coding on the power consumption corresponding to each day in the missing period according to the daily power consumption features, the week features and the year features, and matching the coded features with the historical power consumption in the historical power consumption load data to obtain a matched data segment with highest daily similarity with the missing period in the historical power consumption;
accumulating the matched data segments corresponding to the missing time periods every day to obtain the matched data segments corresponding to the missing time periods;
the power consumption corresponding to each day in the missing period is subjected to feature coding according to the daily power consumption features, the week features and the year features, and the coded features are matched with the historical power consumption in the historical power consumption load data to obtain a matched data segment with highest similarity with the day in the historical power consumption; the method specifically comprises the following steps:
Determining a daily electricity consumption difference characteristic between the daily of the missing period and the daily of the historical electricity load data based on the electricity consumption corresponding to the daily of the missing period, the electricity consumption corresponding to the daily of the historical electricity load data, the determined maximum electricity consumption and the determined minimum electricity consumption;
determining a week difference characteristic between the daily of the missing period and the daily of the historical electricity load data based on the week number corresponding to the daily of the missing period and the week number corresponding to the daily of the historical electricity load data;
determining an annual difference characteristic between the daily of the missing period and the daily of the historical electricity load data based on the specific number of days in one year corresponding to the daily of the missing period and the specific number of days in one year corresponding to the daily of the historical electricity load data;
and determining the weight corresponding to each characteristic, carrying out weighted summation on the daily electric quantity characteristic difference, the week characteristic difference and the year characteristic difference, determining the difference characteristic between the daily of the missing time period and the daily of the historical electric load data, and determining the date of the historical electric load data with the smallest difference characteristic as the matched data segment corresponding to the daily of the missing time period.
2. The method for supplementing electricity load data according to claim 1, wherein the determining the total electricity consumption of the missing period based on the electricity consumption of the previous and the next adjacent missing periods, and distributing the total electricity consumption to each day of the missing period according to the missing period proportion, to obtain the electricity consumption corresponding to each day of the missing period, specifically comprises:
Subtracting the electricity consumption of the adjacent previous time period from the electricity consumption of the adjacent next time period in the missing time period to obtain the total electricity consumption of the missing time period;
and equally distributing the total power consumption to each day in the missing period according to the proportion of the missing duration in each day in the missing period, and obtaining the power consumption corresponding to each day in the missing period.
3. The method for complementing electricity load data according to claim 1, wherein the determining the power amount corresponding to the matching data segment based on the electricity consumption of the matching data segment, and obtaining the power amount of the missing time segment based on the power amount corresponding to the matching data segment, specifically comprises:
determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment;
and determining the power consumption of the matched data segment, determining the proportion between the power consumption of the missing time segment and the power consumption of the matched data segment, and obtaining the power quantity of the missing time segment based on the proportion and the power quantity of the matched data segment.
4. A method for supplementing electrical load data according to claim 3, wherein the determining the amount of power corresponding to the matched data segment based on the amount of power used by the matched data segment specifically comprises:
And determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment, the power consumption of the previous time segment adjacent to the matched data segment and the time difference between the two time segments.
5. A device for supplementing electrical load data, the device comprising:
the loss determination module is used for obtaining the electricity load data and determining a loss time period in the electricity load data; the electricity load data comprises electricity consumption and power consumption;
the power distribution module is used for determining the total power consumption of the missing time period based on the power consumption of the previous time period and the next time period adjacent to the missing time period, and distributing the total power consumption to each day of the missing time period according to the missing time length proportion to obtain the power consumption corresponding to each day of the missing time period;
the first completion module is used for determining the electricity utilization rule of the user based on the historical electricity utilization load data without the missing value, and adjusting the consumed electricity quantity corresponding to each day of the missing period according to the user rule to obtain the consumed electricity quantity corresponding to each day of the missing period;
the characteristic matching module is used for carrying out characteristic coding on the electricity consumption of each day in the missing period according to the characteristics of the electricity consumption of each day, the characteristics of each week and the characteristics of each year, and matching the coded characteristics with the historical electricity consumption in the historical electricity consumption load data to obtain a matching data segment with highest similarity with the missing period in the historical electricity consumption;
The second completion module is used for determining the power quantity corresponding to the matched data segment based on the power consumption of the matched data segment and obtaining the power quantity of the missing time segment based on the power quantity corresponding to the matched data segment;
the first complement module specifically includes:
the first completion unit is used for determining average power consumption corresponding to each of the historical power consumption monday to the sunday in the historical power consumption load data to obtain historical power consumption data;
the second completion unit is used for determining the daily electricity consumption of the history by utilizing all the historical weekly electricity consumption;
the third completion unit is used for determining deviation average amounts respectively corresponding to monday to sunday according to the difference value of the historical power consumption and the historical power consumption;
the fourth completion unit is used for superposing the deviation average quantity to the consumption electric quantity corresponding to the corresponding daily loss time period to obtain a superposition value;
a fifth completion unit, configured to determine an average value of all the superimposed offset average amounts, and subtract the average value from the superimposed value to obtain an electricity consumption amount corresponding to each day in the time period;
the feature matching module specifically comprises:
the first matching unit is used for carrying out feature coding on the power consumption corresponding to each day in the missing period according to the daily power consumption features, the week features and the year features, and matching the coded features with the historical power consumption in the historical power consumption load data to obtain a matched data segment with highest daily similarity with the missing period in the historical power consumption;
The second matching unit is used for accumulating the matching data segments corresponding to the missing time segments every day to obtain the matching data segments corresponding to the missing time segments;
the first matching unit specifically includes:
the third matching unit is used for determining a daily electricity consumption difference characteristic between the daily of the missing time period and the daily of the historical electricity load data based on the electricity consumption corresponding to the daily of the missing time period, the electricity consumption corresponding to the daily of the historical electricity load data, the determined maximum electricity consumption and the determined minimum electricity consumption;
a fourth matching unit for determining a week difference characteristic between the missing period of time and the history electricity load data of time based on the week number of the missing period of time corresponding to each day and the week number of the history electricity load data corresponding to each day;
a fifth matching unit for determining an annual difference feature between the missing period of time and the daily of the historical electricity load data based on the specific number of days in one year corresponding to the missing period of time and the specific number of days in one year corresponding to the daily of the historical electricity load data;
and the sixth matching unit is used for determining the weight corresponding to each characteristic, carrying out weighted summation on the daily electric quantity characteristic difference, the week characteristic difference and the year characteristic difference, determining the difference characteristic between the daily of the missing time period and the daily of the historical electric load data, and determining the date of the historical electric load data with the smallest difference characteristic as the matching data segment corresponding to the daily of the missing time period.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method for supplementing electrical load data according to any one of claims 1 to 4 when the program is executed.
7. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the electrical load data complementing method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311042511.5A CN116756528B (en) | 2023-08-18 | 2023-08-18 | Method, device, equipment and medium for complementing electricity load data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311042511.5A CN116756528B (en) | 2023-08-18 | 2023-08-18 | Method, device, equipment and medium for complementing electricity load data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116756528A CN116756528A (en) | 2023-09-15 |
| CN116756528B true CN116756528B (en) | 2023-11-28 |
Family
ID=87950043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311042511.5A Active CN116756528B (en) | 2023-08-18 | 2023-08-18 | Method, device, equipment and medium for complementing electricity load data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116756528B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651651A (en) * | 2016-12-12 | 2017-05-10 | 全球能源互联网研究院 | Data filling method and device for utilization power curve of grid user |
| CN108345954A (en) * | 2017-11-16 | 2018-07-31 | 北京四方继保自动化股份有限公司 | Distribution network line short-term load forecasting method and device |
| CN111680074A (en) * | 2019-12-31 | 2020-09-18 | 国网浙江省电力有限公司 | Clustering algorithm-based electric power collection load leakage point feature mining method |
| WO2022017606A1 (en) * | 2020-07-23 | 2022-01-27 | Siemens Aktiengesellschaft | Method and device for predicting an energy service offering and software program product |
| CN114358485A (en) * | 2021-11-30 | 2022-04-15 | 国网山东省电力公司日照供电公司 | Source-load matching evaluation method, system, medium and electronic equipment |
| CN114611856A (en) * | 2020-12-03 | 2022-06-10 | 国家电网有限公司大数据中心 | Intelligent electricity consumption complementing method and system |
| CN115329907A (en) * | 2022-10-14 | 2022-11-11 | 杭州致成电子科技有限公司 | Electric load completion method and system based on DBSCAN clustering |
| CN115965125A (en) * | 2022-12-12 | 2023-04-14 | 西北工业大学 | Power load prediction method based on deep learning |
| CN116050866A (en) * | 2023-01-12 | 2023-05-02 | 国网山东省电力公司济南供电公司 | Combined user missing electric quantity fitting method and system based on typical load curve |
| CN116050592A (en) * | 2022-12-27 | 2023-05-02 | 国网冀北电力有限公司唐山供电公司 | Multi-dimensional photovoltaic power prediction method and system |
-
2023
- 2023-08-18 CN CN202311042511.5A patent/CN116756528B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106651651A (en) * | 2016-12-12 | 2017-05-10 | 全球能源互联网研究院 | Data filling method and device for utilization power curve of grid user |
| CN108345954A (en) * | 2017-11-16 | 2018-07-31 | 北京四方继保自动化股份有限公司 | Distribution network line short-term load forecasting method and device |
| CN111680074A (en) * | 2019-12-31 | 2020-09-18 | 国网浙江省电力有限公司 | Clustering algorithm-based electric power collection load leakage point feature mining method |
| WO2022017606A1 (en) * | 2020-07-23 | 2022-01-27 | Siemens Aktiengesellschaft | Method and device for predicting an energy service offering and software program product |
| CN114611856A (en) * | 2020-12-03 | 2022-06-10 | 国家电网有限公司大数据中心 | Intelligent electricity consumption complementing method and system |
| CN114358485A (en) * | 2021-11-30 | 2022-04-15 | 国网山东省电力公司日照供电公司 | Source-load matching evaluation method, system, medium and electronic equipment |
| CN115329907A (en) * | 2022-10-14 | 2022-11-11 | 杭州致成电子科技有限公司 | Electric load completion method and system based on DBSCAN clustering |
| CN115965125A (en) * | 2022-12-12 | 2023-04-14 | 西北工业大学 | Power load prediction method based on deep learning |
| CN116050592A (en) * | 2022-12-27 | 2023-05-02 | 国网冀北电力有限公司唐山供电公司 | Multi-dimensional photovoltaic power prediction method and system |
| CN116050866A (en) * | 2023-01-12 | 2023-05-02 | 国网山东省电力公司济南供电公司 | Combined user missing electric quantity fitting method and system based on typical load curve |
Non-Patent Citations (3)
| Title |
|---|
| Hongshan Zhao,et al.A Method of Complementing Missing Power Data in Low-Voltage Stations Based on Improved Deep Convolutional Self-Encoding Network.《IEEE Access》.2021,57565-57573页. * |
| 基于曲线相似与低秩矩阵的缺失电量数据补全方法;乔文俞;李野;刘浩宇;李扬;杨挺;;电力建设(第01期);32-38页 * |
| 基于用电信息采集数据的电能质量评估方法;张召召;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;第2022年卷(第01期);C042-1853 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116756528A (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Coordination of hydro units with wind power generation using interval optimization | |
| AU2023219861A1 (en) | System and method for optimal control of energy storage system | |
| US20130325195A1 (en) | Pre-Processing of Data For Automatic Generation Control | |
| CN112070301A (en) | Method, system and equipment for adjusting power consumption of user | |
| CN114447964A (en) | Method, device and equipment for determining energy storage charging and discharging scheme and storage medium | |
| Ding et al. | Next-day MV/LV substation load forecaster using time series method | |
| Huang et al. | E-sketch: Gathering large-scale energy consumption data based on consumption patterns | |
| CN112366708A (en) | Charging management method, device, equipment and storage medium | |
| Donadee | Optimal operation of energy storage for arbitrage and ancillary service capacity: The infinite horizon approach | |
| CN116756528B (en) | Method, device, equipment and medium for complementing electricity load data | |
| CN108596416B (en) | Method and system for acquiring electric load reference quantity | |
| CN111798070B (en) | Configuration method and device of user side light storage system | |
| CN116488149A (en) | Method and device for determining micro-grid power generation strategy and micro-grid | |
| CN111160601A (en) | Electric appliance demand response potential prediction method aiming at user power consumption data | |
| CN116128117A (en) | Distribution line loss prediction method and device based on digital twinning | |
| CN115600831A (en) | User theoretical response potential evaluation method, device, terminal and storage medium | |
| CN111915451B (en) | Method for calculating daily power curve of platform area | |
| CN113205259A (en) | Power grid scheduling decision evaluation method and device and terminal equipment | |
| CN111369108A (en) | Power grid real-time pricing method and device | |
| Almeida et al. | Evolutionary Algorithms applied to the Intraday Energy Resource Scheduling in the Context of Multiple Aggregators | |
| CN115225244B (en) | Clock time setting method and device for low-voltage meter reading, main equipment and medium | |
| CN115310811B (en) | Micro-grid electric power energy fair scheduling method | |
| CN113780630B (en) | Method for realizing form code prediction based on historical electricity consumption data of electricity consumption customer | |
| CN117411190B (en) | Power distribution network topology identification method, equipment, system and medium based on multi-source information | |
| CN117595247A (en) | Method and device for reminding power consumption risk of user side |
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 |